Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 97. Отображено 97.
13-04-2021 дата публикации

Cognitive visual and ontological mapping of tabular data based on a distribution of a measure of interest

Номер: US0010977294B2
Автор: Raphael Arar, Hovey R. Strong, Jr., Guangjie Ren, Pawan Chowdhary, ARAR RAPHAEL, STRONG JR HOVEY R, REN GUANGJIE, CHOWDHARY PAWAN, Arar, Raphael, Strong, Jr., Hovey R., Ren, Guangjie, Chowdhary, Pawan
Принадлежит: International Business Machines Corporation, IBM

One embodiment provides a computer program product for cognitive visual and ontological mapping of tabular data. The computer program product comprises a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to receive a data query and ontology information relating to the data query, receive context information relating to a display device, determine a measure of interest for the data query and one or more constraints for the measure of interest, determine saliency features based on the context information, and generate a user interface comprising query results corresponding to the data query arranged in a dynamic tabular format for display on the display device. The dynamic tabular format is based on the ontology information, the measure of interest, the one or more constraints for the measure of interest, and the saliency features.

Подробнее
Номер записи: 1
21-05-2020 дата публикации

METHOD AND SYSTEM FOR CORRECTING SPEECH-TO-TEXT AUTO-TRANSCRIPTION USING LOCAL CONTEXT OF TALK

Номер: US20200160866A1
Автор: Margaret H. Szymanski, Robert J. Moore, Sunhwan Lee, Pawan Chowdhary, Shun Jiang, Guangjie Ren, Raphael Arar, SZYMANSKI MARGARET H, MOORE ROBERT J, LEE SUNHWAN, CHOWDHARY PAWAN, JIANG SHUN, REN GUANGJIE, ARAR RAPHAEL, Szymanski, Margaret H., Moore, Robert J., Lee, Sunhwan, Chowdhary, Pawan, Jiang, Shun, Ren, Guangjie, Arar, Raphael
Принадлежит: International Business Machines Corp

One embodiment provides a computer program product for improving accuracy of a transcript of a spoken interaction. The computer program product comprises a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to identify a plurality of patterns in the transcript. The plurality of patterns are indicative of a group of acoustically similar words in the transcript and a corresponding local, sequential context of the group of acoustically similar words. The program instructions are further executable by the processor to cause the processor to predict conditional probabilities for the group of acoustically similar words based on a predictive model and the plurality of patterns, detect one or more transcription errors in the transcript based on the conditional probabilities, and correct the one or more transcription errors by applying a multi-pass correction on the one or more transcription errors.

Подробнее
Номер записи: 2
14-06-2022 дата публикации

Dynamic management of a customer life-cycle value

Номер: US0011361325B2
Автор: Pawan Chowdhary, Markus Ettl, Donald Keefer, Gabriel Toma, Zhengliang Xue
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Systems, methods, and computer-readable media are disclosed for identifying customers having associated opportunities for improved growth and/or profitability with respect to product or service offerings and determining investment solutions that enhance the probability that the customers transition to the higher growth/profitability opportunities. Prior customer transactions are segmented based on segmentation criteria and used to generate a transaction graph. The nodes of the transaction graph represent the segmented transactions and client transaction paths between the nodes represent potential customer life-cycle trajectories. The transaction graph can be used to identify high-value penetration opportunities.

Подробнее
Номер записи: 3
18-06-2020 дата публикации

COGNITIVE VISUAL AND ONTOLOGICAL MAPPING OF TABULAR DATA BASED ON A DISTRIBUTION OF A MEASURE OF INTEREST

Номер: US20200192928A1
Автор: Raphael Arar, Hovey R. Strong, JR., Guangjie Ren, Pawan Chowdhary, ARAR RAPHAEL, STRONG JR HOVEY R, REN GUANGJIE, CHOWDHARY PAWAN, Arar, Raphael, Strong, JR., Hovey R., Ren, Guangjie, Chowdhary, Pawan
Принадлежит: International Business Machines Corp

One embodiment provides a computer program product for cognitive visual and ontological mapping of tabular data. The computer program product comprises a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to receive a data query and ontology information relating to the data query, receive context information relating to a display device, determine a measure of interest for the data query and one or more constraints for the measure of interest, determine saliency features based on the context information, and generate a user interface comprising query results corresponding to the data query arranged in a dynamic tabular format for display on the display device. The dynamic tabular format is based on the ontology information, the measure of interest, the one or more constraints for the measure of interest, and the saliency features.

Подробнее
Номер записи: 4
03-01-2019 дата публикации

DYNAMIC MANAGEMENT OF A CUSTOMER LIFE-CYCLE VALUE

Номер: US20190005514A1
Автор: Pawan Chowdhary, Markus Ettl, Donald Keefer, Gabriel Toma, Zhengliang Xue, CHOWDHARY PAWAN, ETTL MARKUS, KEEFER DONALD, TOMA GABRIEL, XUE ZHENGLIANG, Chowdhary, Pawan, Ettl, Markus, Keefer, Donald, Toma, Gabriel, Xue, Zhengliang
Принадлежит: International Business Machines Corp

Systems, methods, and computer-readable media are disclosed for identifying customers having associated opportunities for improved growth and/or profitability with respect to product or service offerings and determining investment solutions that enhance the probability that the customers transition to the higher growth/profitability opportunities. Prior customer transactions are segmented based on segmentation criteria and used to generate a transaction graph. The nodes of the transaction graph represent the segmented transactions and client transaction paths between the nodes represent potential customer life-cycle trajectories. The transaction graph can be used to identify high-value penetration opportunities associated

Подробнее
Номер записи: 5
26-11-2020 дата публикации

Minimizing Risk Using Machine Learning Techniques

Номер: US20200372397A1
Автор: Sunhwan Lee, Pawan Chowdhary, Guangjie Ren, Raphael I. Arar, LEE SUNHWAN, CHOWDHARY PAWAN, REN GUANGJIE, ARAR RAPHAEL I, Lee, Sunhwan, Chowdhary, Pawan, Ren, Guangjie, Arar, Raphael I.
Принадлежит: International Business Machines Corporation

Embodiments relate to an intelligent computer platform to utilize machine learning techniques to minimize compliance risk. Features are extracted from one or more data sources across two or more domains and activity data is identified. Features are identified within the activity data which are used to create one or more models. Domain activity impact is measured and a risk probability is calculated. A policy is generated based on the calculated risk probability and one or more compliance activities are orchestrated. One or more encoded actions are executed in compliance with the orchestration. 1. A system comprising:a processing unit operatively coupled to memory; a data manager to extract features from one or more primary data sources across two or more domains, and to identify activity data within the extracted features;', 'a machine learning (ML) manager to dynamically identify features within the activity data, create one or more models with the identified features, and measure domain activity impact, including calculate risk probability based on the measured impact;', 'a recommendation engine to generate a policy from the calculated risk probability, and to orchestrate one or more compliance activities based on the generated policy; and, 'an artificial intelligence platform in communication with the processing unit, the platform to monitor and evaluate data and minimize risk across two or more domains, includingthe processing unit to selectively execute one or more encoded actions in compliance with the orchestration.2. The system of claim 1 , further comprising the recommendation engine to employ reinforcement learning to calculate a reward based on the calculated risk probability.3. The system of claim 2 , further comprising the recommendation engine to generate a policy to leverage the calculation to minimize risk and maximize reward across two or more domains.4. The system of claim 1 , further comprising the data manager to detect thread activity and ...

Подробнее
Номер записи: 6
18-10-2007 дата публикации

System and method for applying predictive metric analysis for a business monitoring subsystem

Номер: US20070244738A1
Автор: Pawan Chowdhary, Shubir Kapoor
Принадлежит:

Predictive metric analysis for business management is divided into build time, corresponding to the business owner view of the enterprise, and run time, corresponding to the information technology view of the enterprise. The build time consists of a predictive model and a monitoring model. These models go through transformation processes to the components of the run time. The run time components are a Metric Value Prediction Service (MVPS), which receives as input predictive model transformation and outputs predicted metric values, and a monitoring engine, which receives as input monitoring model transformation, the predicted metric values and business events from the business process. Various analytical engines can be plugged in to provide the predictive capabilities. Input is provided to a framework from various business systems which results in predicting the value of the metrics across the future time horizons.

Подробнее
Номер записи: 7
05-03-2020 дата публикации

Interactive Exercise Experience

Номер: US20200070033A1
Автор: Pawan Chowdhary, Kumar R. Virwani, Charles Thomas Rettner, Bulent N. Kurdi, CHOWDHARY PAWAN, VIRWANI KUMAR R, RETTNER CHARLES THOMAS, KURDI BULENT N, Chowdhary, Pawan, Virwani, Kumar R., Rettner, Charles Thomas, Kurdi, Bulent N.
Принадлежит: International Business Machines Corporation

Embodiments relate to a system, program product, and method for use and an artificial intelligence (AI) platform to identify and analyze physical forces related to sensory input. A sensor operatively coupled to an inertial measurement unit (IMU) is activated. An initial position of the IMU responsive to the sensor activation is captured and movement of the IMU from the initial position is recognized. A comparison is preformed, where the captured initial position is compared to a second position which is correlated with the recognized movement. A score based on the performed comparison is determined and a diagnostic assessment based on the performed comparison and determined score is created. The diagnostic assessment is converted to feedback, where the conversion utilizes real-time communication of an instruction of a second movement position of the IMU. Receipt of the feedback physically conveys a manifestation of the feedback to the apparatus.

Подробнее
Номер записи: 8
28-12-2021 дата публикации

Program dialog by example

Номер: US0011211049B2
Автор: Robert J. Moore, Pawan Chowdhary, Divyesh Jadav, Lei Huang, Sunhwan Lee, Eric Young Liu, Saurabh Mishra
Принадлежит: International Business Machines Corporation

One embodiment provides a method including receiving authoring conversational training data. A machine learning based conversational agent is trained with the conversational training data. The training includes: creating and storing example transcripts of user utterances, creating and storing example transcripts of agent utterances, sequencing utterance transcripts using the example transcripts of user utterances and the example transcripts of agent utterances, forming a corpus from the sequenced utterance transcripts, marking speech patterns that represent social actions from tagging the sequenced utterance transcripts, and forming a patterned corpus from the marked speech patterns.

Подробнее
Номер записи: 9
28-01-2021 дата публикации

Topic Mining based on Interactionally Defined Activity Sequences

Номер: US20210027783A1
Автор: Margaret Helen Szymanski, Lei Huang, Robert John Moore, Raphael Arar, Shun Jiang, Guangjie Ren, Eric Liu, Pawan Chowdhary, Chung-hao Tan, Sunhwan Lee, SZYMANSKI MARGARET HELEN, HUANG LEI, MOORE ROBERT JOHN, ARAR RAPHAEL, JIANG SHUN, REN GUANGJIE, LIU ERIC, CHOWDHARY PAWAN, TAN CHUNG-HAO, LEE SUNHWAN, Szymanski, Margaret Helen, Huang, Lei, Moore, Robert John, Arar, Raphael, Jiang, Shun, Ren, Guangjie, Liu, Eric, Chowdhary, Pawan, Tan, Chung-hao, Lee, Sunhwan
Принадлежит:

A method and system of automatically identifying topics of a conversation are provided. An electronic data package comprising a sequence of utterances between conversation entities is received by a computing device. Each utterance is classified to a corresponding social action. One or more utterances in the sequence are grouped into a segment based on a deep learning model. A similarity of topics between adjacent segments is determined. Upon determining that the similarity is above a predetermined threshold, the adjacent segments are grouped together. A transcript of the conversation including the grouping of the adjacent segments is stored in a memory. 1. A computing device comprising:a processor;a network interface coupled to the processor to enable communication over a network;an interaction engine configured to perform acts comprising:receiving an electronic data package comprising a sequence of utterances between conversation entities, over the network;classifying each utterance to a corresponding social action;identifying transition boundaries based on the social actions;grouping one or more utterances between transition boundaries in the sequence to a segment based on a deep learning model;determining a similarity between adjacent segments; andupon determining that the similarity is above a predetermined threshold, grouping the adjacent segments together; andstoring a transcript of the conversation including the grouping of the adjacent segments in the memory.2. The computing device of claim 1 , wherein the electronic data package comprises raw audio data.3. The computing device of claim 2 , wherein the interaction engine is further configured to perform acts claim 2 , comprising: converting a speech of the raw audio data to text by way of natural language processing (NLP).4. The computing device of claim 2 , wherein the interaction engine is further configured to perform acts claim 2 , comprising:identifying a duration of silences between the utterances; ...

Подробнее
Номер записи: 10
21-12-2021 дата публикации

Contextual disambiguation of an entity in a conversation management system

Номер: US0011205048B2
Автор: Sunhwan Lee, Shun Jiang, Chung-hao Tan, Lei Huang, Pawan Chowdhary
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Systems, computer-implemented methods, and computer program products that can facilitate word entity disambiguation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a language model component that employs an artificial intelligence model to generate a profile vector of an entity based on one or more binary values representing profile data of the entity and a word vector of a word entity in a dialogue based on one or more second word entities adjacent to the word entity in the dialogue. The computer executable components can further comprise a dialogue management component that disambiguates the word entity based on the profile vector and the word vector.

Подробнее
Номер записи: 11
05-05-2022 дата публикации

REDUCING COMPUTATIONAL OVERHEAD INVOLVED WITH PROCESSING RECEIVED SERVICE REQUESTS

Номер: US20220138598A1
Автор: Sunhwan Lee, Pawan Chowdhary
Принадлежит:

A computer-implemented method, according to one approach, is for reducing the computational overhead involved with processing received service requests. The computer-implemented method includes: collecting datasets, each dataset including: a previously submitted service request, and a team that satisfied the respective previously submitted service request. Features are also extracted from the datasets, and a model is trained using the features that are extracted from the datasets. Moreover, a newly submitted service request is received, and features are extracted from the newly submitted service request. A dataset that most closely matches the newly submitted service request is further determined by applying the model to the features extracted from the newly submitted service request.

Подробнее
Номер записи: 12
28-06-2012 дата публикации

METHOD AND APPARATUS OF ON DEMAND BUSINESS ACTIVITY MANAGEMENT USING BUSINESS PERFORMANCE MANAGEMENT LOOPS

Номер: US20120166254A1
Автор: Hung-yang Chang, Shyh-Kwei Chen, Pawan Chowdhary, Jun-Jang Jeng, Liangzhao Zeng, CHANG HUNG-YANG, CHEN SHYH-KWEI, CHOWDHARY PAWAN, JENG JUN-JANG, ZENG LIANGZHAO
Принадлежит: International Business Machines Corporation

An architecture, system, and method are provided for a commitment loop solution for on demand business activity management. A Business Performance Management (BPM) loop includes nodes each relating to different tasks for processing performance management trigger data generated by a business entity in real time. The beginning or sensing element of the loop is triggered by a token (representing a business event from a business process). The ending or executing element provides a business action to be implemented by the business entity. The token is passed from node to node sequentially in a particular order around the loop. Processing of the data represented by the token is governed by policies, which can be changed dynamically and follow a life cycle.

Подробнее
Номер записи: 13
05-10-2021 дата публикации

Topic mining based on interactionally defined activity sequences

Номер: US0011138978B2
Автор: Margaret Helen Szymanski, Lei Huang, Robert John Moore, Raphael Arar, Shun Jiang, Guangjie Ren, Eric Liu, Pawan Chowdhary, Chung-hao Tan, Sunhwan Lee, SZYMANSKI MARGARET HELEN, HUANG LEI, MOORE ROBERT JOHN, ARAR RAPHAEL, JIANG SHUN, REN GUANGJIE, LIU ERIC, CHOWDHARY PAWAN, TAN CHUNG-HAO, LEE SUNHWAN, Szymanski, Margaret Helen, Huang, Lei, Moore, Robert John, Arar, Raphael, Jiang, Shun, Ren, Guangjie, Liu, Eric, Chowdhary, Pawan, Tan, Chung-hao, Lee, Sunhwan
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION, IBM

A method and system of automatically identifying topics of a conversation are provided. An electronic data package comprising a sequence of utterances between conversation entities is received by a computing device. Each utterance is classified to a corresponding social action. One or more utterances in the sequence are grouped into a segment based on a deep learning model. A similarity of topics between adjacent segments is determined. Upon determining that the similarity is above a predetermined threshold, the adjacent segments are grouped together. A transcript of the conversation including the grouping of the adjacent segments is stored in a memory.

Подробнее
Номер записи: 14
05-04-2022 дата публикации

Dynamic management of a customer life-cycle value

Номер: US0011295320B2
Автор: Pawan Chowdhary, Markus Ettl, Donald Keefer, Gabriel Toma, Zhengliang Xue
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Systems, methods, and computer-readable media are disclosed for identifying customers having associated opportunities for improved growth and/or profitability with respect to product or service offerings and determining investment solutions that enhance the probability that the customers transition to the higher growth/profitability opportunities. Prior customer transactions are segmented based on segmentation criteria and used to generate a transaction graph. The nodes of the transaction graph represent the segmented transactions and client transaction paths between the nodes represent potential customer life-cycle trajectories. The transaction graph can be used to identify high-value penetration opportunities.

Подробнее
Номер записи: 15
25-05-2006 дата публикации

Method and apparatus of on demand business activity management using business performance management loops

Номер: US20060111921A1
Автор: Hung-yang Chang, Shyh-Kwei Chen, Pawan Chowdhary, Jun-Jang Jeng, Liangzhao Zeng
Принадлежит:

An architecture, system, and method are provided for a commitment loop solution for on demand business activity management. A Business Performance Management (BPM) loop is defined as a set of nodes each relating to different tasks for processing performance management trigger data generated by a business entity in real time, where the beginning or sensing element of the loop is triggered by a token (representing a business event from a business process) and the ending or executing element provides a business action to be implemented by the business entity. The token is passed from node to node sequentially in a particular order around the loop. Processing of the data represented by the token is governed by policies, which can be changed dynamically and follow a life cycle. On demand business activity management of larger aggregates of business entities (i.e. enterprises and value chains) is achieved by extending this architecture by building upon the BPM loops of the component entities ...

Подробнее
Номер записи: 16
04-01-2007 дата публикации

Method for evaluating dynamic expressions

Номер: US20070006128A1
Автор: Pawan Chowdhary, Haifeng Xi
Принадлежит:

Development and use of a computer program, particularly for simulation or modeling, in an arbitrary language are facilitated by representing expressions to be dynamically evaluated in a simple syntax compatible with a standard language and providing a pattern or template in a form containing the form and syntax required for an embedded standard language query in the arbitrary language. The representation of the expression in the simple syntax is detected and the expression, variables contained in the expression and the name of the result of an evaluation of the expression are extracted and placed in the template or pattern to derive an intermediate form of the expression. Quantitative data developed by the computer program when it is run is substituted for the variables in the intermediate form of the expression to form a standard language query embedded in the arbitrary language program which is ten evaluated by a standard language evaluation engine. Standard query language (SQL) is preferred ...

Подробнее
Номер записи: 17
10-11-2020 дата публикации

Method and system for correcting speech-to-text auto-transcription using local context of talk

Номер: US0010832679B2
Автор: Margaret H. Szymanski, Robert J. Moore, Sunhwan Lee, Pawan Chowdhary, Shun Jiang, Guangjie Ren, Raphael Arar, SZYMANSKI MARGARET H, MOORE ROBERT J, LEE SUNHWAN, CHOWDHARY PAWAN, JIANG SHUN, REN GUANGJIE, ARAR RAPHAEL, Szymanski, Margaret H., Moore, Robert J., Lee, Sunhwan, Chowdhary, Pawan, Jiang, Shun, Ren, Guangjie, Arar, Raphael
Принадлежит: International Business Machines Corporation, IBM

One embodiment provides a computer program product for improving accuracy of a transcript of a spoken interaction. The computer program product comprises a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to identify a plurality of patterns in the transcript. The plurality of patterns are indicative of a group of acoustically similar words in the transcript and a corresponding local, sequential context of the group of acoustically similar words. The program instructions are further executable by the processor to cause the processor to predict conditional probabilities for the group of acoustically similar words based on a predictive model and the plurality of patterns, detect one or more transcription errors in the transcript based on the conditional probabilities, and correct the one or more transcription errors by applying a multi-pass correction on the one or more transcription ...

Подробнее
Номер записи: 18
25-05-2006 дата публикации

Adaptive data warehouse meta model

Номер: US20060112109A1
Автор: Pawan Chowdhary, Jun-Jang Jeng, Shubir Kapoor, Juhnyoung Lee, Josef Schiefer
Принадлежит:

A hybrid approach for capturing meta data about Business Processing Monitoring (BPM) artifacts is based on a combination of a relational meta data model and a semantic net. Meta data about metrics and situations and their dimensional context are first captured. Then, relational meta data are used to describe a generic data schema for metrics, situations and their dimensional context. The meta data from semantic nets are used to extend the meta data definitions. Data from a data warehouse are searched and managed with the schema described and managed with the relational and semantic net meta data.

Подробнее
Номер записи: 19
04-04-2023 дата публикации

Sensor tuning—sensor specific selection for IoT—electronic nose application using gradient boosting decision trees

Номер: US0011619618B2
Автор: Mohammed Abdi, Aminat Adebiyi, Alberto Mannari, Andrea Fasoli, Ronald Robert Labby, Luisa Bozano, Pawan Chowdhary, Abubeker Abdullahi
Принадлежит: International Business Machines Corporation

Provided is a system and method for tuning an array of sensors to enable selection of the most suitable sensors for a target application. After extracting features from sensor raw data, the extracted features are ranked with gradient boosting decision trees to assign an importance value to each extracted feature. A threshold value for the entire set of extracted features is calculated and an importance score is calculated for the individual sensors of the array. Individual sensors with an importance score on or above the threshold value are selected for the target application.

Подробнее
Номер записи: 20
24-08-2021 дата публикации

Product configuration recommendation and optimization

Номер: US0011100570B2
Автор: Pawan Chowdhary, Markus R. Ettl, Somnath Mukherjee, Zhengliang Xue, CHOWDHARY PAWAN, ETTL MARKUS R, MUKHERJEE SOMNATH, XUE ZHENGLIANG, Chowdhary, Pawan, Ettl, Markus R., Mukherjee, Somnath, Xue, Zhengliang
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION, IBM

Systems, methods, and computer-readable media are disclosed for identifying product configurations that are alternatives to a requested product configuration, ranking the alternative product configurations based on one or more pricing metrics, and presenting the alternative product configurations to a prospective customer, thereby providing the customer with the option of selecting an alternative product configuration in lieu of the initially requested product configuration.

Подробнее
Номер записи: 21
02-04-2020 дата публикации

ENTITY MATCHING USING VISUAL INFORMATION

Номер: US20200104410A1
Автор: Sunhwan Lee, Pawan Chowdhary, Guangjie Ren, LEE SUNHWAN, CHOWDHARY PAWAN, REN GUANGJIE, Lee, Sunhwan, Chowdhary, Pawan, Ren, Guangjie
Принадлежит:

One embodiment provides a method comprising receiving a first set of information corresponding to a first entity and receiving a second set of information corresponding to a second entity. Each set of information received corresponding to each entity comprises visual information relating to the entity. The method further comprises encoding each set of information, and classifying the first entity and the second entity as either matching entities or non-matching entities based on the encoding. 1. A method comprising:receiving a first set of information corresponding to a first entity, wherein the first set of information comprises visual information relating to the first entity;receiving a second set of information corresponding to a second entity, wherein the second set of information comprises visual information relating to the second entity;encoding each set of information; andclassifying the first entity and the second entity as either matching entities or non-matching entities based on the encoding.2. The method of claim 1 , wherein encoding each set of information comprises:generating a first set of visual embeddings by embedding the visual information relating to the first entity using a convolutional neural network (CNN);generating a second set of visual embeddings by embedding the visual information relating to the second entity using the CNN; andencoding the first set of visual embeddings and the second set of visual embeddings to a set of pairwise features.3. The method of claim 2 , wherein each set of information corresponding to each entity includes one of a plurality of images of the entity or a single image of the entity claim 2 , and each set of visual embeddings comprises a set of embedded images.4. The method of claim 2 , wherein the set of pairwise features comprise one of the following statistics: a maximum cosine similarity between the first set of visual embeddings and the second set of visual embeddings claim 2 , a top n cosine similarity ...

Подробнее
Номер записи: 22
31-05-2007 дата публикации

METHOD AND SYSTEM FOR ESTIMATING SUPPLY IMPACT ON A FIRM UNDER A GLOBAL CRISIS

Номер: US20070124190A1
Автор: Ching-Hua Chen-Ritzo, Pawan Chowdhary, Thomas Ervolina, Dharmashankar Subramanian
Принадлежит:

The availability of relevant business resources, or supply, during a global crisis or disruption are estimated by using a forecast of a baseline supply of human resources and various forms of infrastructure and raw materials for a firm as input. That forecast is corrected to account for the impact of a crisis or other disruption, and a corrected forecast as output is provided. The corrected forecast reflects changes in the availability of business resources due to the crisis or disruption, dependencies between resources, as well as any mitigating effects resulting from the implementation of mitigation policies.

Подробнее
Номер записи: 23
07-01-2021 дата публикации

PROGRAM DIALOG BY EXAMPLE

Номер: US20210005178A1
Автор: Robert J. Moore, Pawan Chowdhary, Divyesh Jadav, Lei Huang, Sunhwan Lee, Eric Young Liu, Saurabh Mishra, MOORE ROBERT J, CHOWDHARY PAWAN, JADAV DIVYESH, HUANG LEI, LEE SUNHWAN, LIU ERIC YOUNG, MISHRA SAURABH, Moore, Robert J., Chowdhary, Pawan, Jadav, Divyesh, Huang, Lei, Lee, Sunhwan, Liu, Eric Young, Mishra, Saurabh
Принадлежит:

One embodiment provides a method including receiving authoring conversational training data. A machine learning based conversational agent is trained with the conversational training data. The training includes: creating and storing example transcripts of user utterances, creating and storing example transcripts of agent utterances, sequencing utterance transcripts using the example transcripts of user utterances and the example transcripts of agent utterances, forming a corpus from the sequenced utterance transcripts, marking speech patterns that represent social actions from tagging the sequenced utterance transcripts, and forming a patterned corpus from the marked speech patterns. 1. A method comprising:receiving authoring conversational training data; and creating and storing example transcripts of user utterances;', 'creating and storing example transcripts of agent utterances;', 'sequencing utterance transcripts using the example transcripts of user utterances and the example transcripts of agent utterances;', 'forming a corpus from the sequenced utterance transcripts;', 'marking speech patterns that represent social actions from tagging the sequenced utterance transcripts; and', 'forming a patterned corpus from the marked speech patterns., 'training a fully machine learning based conversational agent with the conversational training data comprising2. The method of claim 1 , further comprising:analyzing the patterned corpus to determine annotation entry positions.3. The method of claim 2 , further comprising:annotating user and agent utterance transcripts based on the determined annotation entry positions.4. The method of claim 2 , further comprising:receiving marked variable entries in the example transcripts of user utterances and the example transcripts of agent utterances.5. The method of claim 4 , further comprising:receiving edits for the example transcripts of user utterances to correct behavior of the machine learning based conversational agent.6. The ...

Подробнее
Номер записи: 24
20-03-2008 дата публикации

METHOD AND APPARATUS OF ON DEMAND BUSINESS ACTIVITY MANAGEMENT USING BUSINESS PERFORMANCE MANAGEMENT LOOPS

Номер: US20080071595A1
Автор: Hung-yang Chang, Shyh-Kwei Chen, Pawan Chowdhary, Jun-Jang Jeng, Liangzhao Zeng
Принадлежит:

An architecture, system, and method are provided for a commitment loop solution for on demand business activity management. A Business Performance Management (BPM) loop is defined as a set of nodes each relating to different tasks for processing performance management trigger data generated by a business entity in real time, where the beginning or sensing element of the loop is triggered by a token (representing a business event from a business process) and the ending or executing element provides a business action to be implemented by the business entity. The token is passed from node to node sequentially in a particular order around the loop. Processing of the data represented by the token is governed by policies, which can be changed dynamically and follow a life cycle. On demand business activity management of larger aggregates of business entities (i.e. enterprises and value chains) is achieved by extending this architecture by building upon the BPM loops of the component entities ...

Подробнее
Номер записи: 25
15-03-2022 дата публикации

Interactive exercise experience

Номер: US0011273357B2
Автор: Pawan Chowdhary, Kumar R. Virwani, Charles Thomas Rettner, Bulent N. Kurdi
Принадлежит: International Business Machines Corporation

Embodiments relate to a system, program product, and method for use and an artificial intelligence (AI) platform to identify and analyze physical forces related to sensory input. A sensor operatively coupled to an inertial measurement unit (IMU) is activated. An initial position of the IMU responsive to the sensor activation is captured and movement of the IMU from the initial position is recognized. A comparison is preformed, where the captured initial position is compared to a second position which is correlated with the recognized movement. A score based on the performed comparison is determined and a diagnostic assessment based on the performed comparison and determined score is created. The diagnostic assessment is converted to feedback, where the conversion utilizes real-time communication of an instruction of a second movement position of the IMU. Receipt of the feedback physically conveys a manifestation of the feedback to the apparatus.

Подробнее
Номер записи: 26
29-08-2023 дата публикации

Ticket-agent matching and agent skillset development

Номер: US0011741405B2
Автор: Rohit Avinash Mujumdar, Shubhi Asthana, Pawan Chowdhary, Aly Megahed, Bing Zhang
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION, International Business Machines Corporation

Embodiments are provided for ticket-agent matching and agent skillset development. In some embodiments, a system includes a processor that executes computer-executable components stored in memory. The computer-executable components can include a matching component that determines, using a ticket profile and a space of agent profiles, a ticket-agent pair including a ticket identifier of a service request and an agent identifier of a particular agent within a pool of agents. The computer-executable components also can include a rematching component that assigns a second agent identifier to the service request to develop a skillset of a second particular agent within the pool of agents, the second agent identifier being associated with an unsatisfactory skill score for a defined skill to resolve the service request.

Подробнее
Номер записи: 27
02-07-2013 дата публикации

Method and apparatus of on demand business activity management using business performance management loops

Номер: US0008478633B2
Автор: Hung-yang Chang, Shyh-Kwei Chen, Pawan Chowdhary, Jun-Jang Jeng, Liangzhao Zeng, CHANG HUNG-YANG, CHEN SHYH-KWEI, CHOWDHARY PAWAN, JENG JUN-JANG, ZENG LIANGZHAO
Принадлежит: International Business Machines Corporation, CHANG HUNG-YANG, CHEN SHYH-KWEI, CHOWDHARY PAWAN, JENG JUN-JANG, ZENG LIANGZHAO, IBM, INTERNATIONAL BUSINESS MACHINES CORPORATION

An architecture, system, and method are provided for a commitment loop solution for on demand business activity management. A Business Performance Management (BPM) loop is defined as a set of nodes each relating to different tasks for processing performance management trigger data generated by a business entity in real time, where the beginning or sensing element of the loop is triggered by a token (representing a business event from a business process) and the ending or executing element provides a business action to be implemented by the business entity. The token is passed from node to node sequentially in a particular order around the loop. Processing of the data represented by the token is governed by policies, which can be changed dynamically and follow a life cycle. On demand business activity management of larger aggregates of business entities (i.e. enterprises and value chains) is achieved by extending this architecture by building upon the BPM loops of the component entities ...

Подробнее
Номер записи: 28
26-11-2020 дата публикации

OPTIMIZED TRANSPORTATION SELECTION

Номер: US20200372590A1
Автор: Pawan Chowdhary, Sunhwan Lee, Guangjie Ren, Raphael I. Arar, CHOWDHARY PAWAN, LEE SUNHWAN, REN GUANGJIE, ARAR RAPHAEL I, Chowdhary, Pawan, Lee, Sunhwan, Ren, Guangjie, Arar, Raphael I.
Принадлежит: International Business Machines Corp

Facilitation of optimized transportation selection relative to user travel objectives and user context is provided. A system can include a memory and a processor that executes computer executable components. The computer executable components can include: an objective component that determines travel objectives of a user; a context component that determines context of the user; an analyzer component that analyzes transportation related data relevant to the travel objectives of the user, wherein the analyzer component performs a utility-based analysis that weighs costs versus benefits associated with respective transportation options relative to the travel objectives of the user; and an optimization component that outputs a travel itinerary to the user that includes an optimized transportation selection relative to the user travel objectives and user context.

Подробнее
Номер записи: 29
26-05-2022 дата публикации

DEMAND FORECASTING OF SERVICE REQUESTS VOLUME

Номер: US20220164744A1
Автор: Bing Zhang, Shubhi Asthana, Pawan Chowdhary, Aly Megahed, Rohit Avinash Mujumdar, Taiga Nakamura
Принадлежит: International Business Machines Corp

A method for predicting service requests volume includes generating a machine learning model predicting a number of service requests in time series data, based upon a plurality of actually received service requests in the time series data. The method recommends service request features for use in predicting the service requests volume. The method receives a determination from an human-in-the-loop indicating whether the generated machine learning model correctly predicts the number of service requests in time series data, based on the plurality of actually received service requests in the time series data and the recommended service request features. The method selectively updates the machine learning model predicting the number of service requests in times series data, based upon the determination from the human-in-the-loop. The method predicts, using the updated machine learning model, a number of service requests in time series data incoming during a future time period.

Подробнее
Номер записи: 30
24-12-2020 дата публикации

CONTEXTUAL DISAMBIGUATION OF AN ENTITY IN A CONVERSATION MANAGEMENT SYSTEM

Номер: US20200401659A1
Автор: Sunhwan Lee, Shun Jiang, Chung-hao Tan, Lei Huang, Pawan Chowdhary, LEE SUNHWAN, JIANG SHUN, TAN CHUNG-HAO, HUANG LEI, CHOWDHARY PAWAN, Lee, Sunhwan, Jiang, Shun, Tan, Chung-hao, Huang, Lei, Chowdhary, Pawan
Принадлежит: International Business Machines Corp

Systems, computer-implemented methods, and computer program products that can facilitate word entity disambiguation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a language model component that employs an artificial intelligence model to generate a profile vector of an entity based on one or more binary values representing profile data of the entity and a word vector of a word entity in a dialogue based on one or more second word entities adjacent to the word entity in the dialogue. The computer executable components can further comprise a dialogue management component that disambiguates the word entity based on the profile vector and the word vector.

Подробнее
Номер записи: 31
03-01-2019 дата публикации

DYNAMIC MANAGEMENT OF A CUSTOMER LIFE-CYCLE VALUE

Номер: US20190005512A1
Автор: Pawan Chowdhary, Markus Ettl, Donald Keefer, Gabriel Toma, Zhengliang Xue, CHOWDHARY PAWAN, ETTL MARKUS, KEEFER DONALD, TOMA GABRIEL, XUE ZHENGLIANG, Chowdhary, Pawan, Ettl, Markus, Keefer, Donald, Toma, Gabriel, Xue, Zhengliang
Принадлежит: International Business Machines Corp

Systems, methods, and computer-readable media are disclosed for identifying customers having associated opportunities for improved growth and/or profitability with respect to product or service offerings and determining investment solutions that enhance the probability that the customers transition to the higher growth/profitability opportunities. Prior customer transactions are segmented based on segmentation criteria and used to generate a transaction graph. The nodes of the transaction graph represent the segmented transactions and client transaction paths between the nodes represent potential customer life-cycle trajectories. The transaction graph can be used to identify high-value penetration opportunities associated

Подробнее
Номер записи: 32
19-11-2020 дата публикации

HYBRID PRICE PRESENTATION STRATEGY USING A PROBABILISTIC HOTEL DEMAND FORECAST MODEL

Номер: US20200364809A1
Автор: Sunhwan Lee, Yue Guan, Pawan Chowdhary, Guangjie Ren, LEE SUNHWAN, GUAN YUE, CHOWDHARY PAWAN, REN GUANGJIE, Lee, Sunhwan, Guan, Yue, Chowdhary, Pawan, Ren, Guangjie
Принадлежит: International Business Machines Corp

A computer implemented method includes receiving a first set of data comprising financial data of a company and at least one of holiday data, industrial event data, or weather data. A probabilistic hotel demand forecast is computed for a hotel in a location based on a statistical analysis of prior hotel stays at the hotel in the location with an adjustment based on at least the financial data of the first set of data. The adjustment can be computed by the computer based on a prior effect of at least the financial data on a number of prior hotel stays. The resulting probabilistic hotel demand forecast can be displayed on a user terminal device. This forecast may be used to generate a future pricing strategy.

Подробнее
Номер записи: 33
10-06-2021 дата публикации

SENSOR TUNING - SENSOR SPECIFIC SELECTION FOR IoT-ELECTRONIC NOSE APPLICATION USING GRADIENT BOOSTING DECISION TREES

Номер: US20210172918A1
Автор: Mohammed Abdi, Aminat Adebiyi, Alberto Mannari, Andrea Fasoli, Ronald Robert Labby, Luisa Bozano, Pawan Chowdhary, Abubeker Abdullahi, ABDI MOHAMMED, ADEBIYI AMINAT, MANNARI ALBERTO, FASOLI ANDREA, LABBY RONALD ROBERT, BOZANO LUISA, CHOWDHARY PAWAN, ABDULLAHI ABUBEKER, Abdi, Mohammed, Adebiyi, Aminat, Mannari, Alberto, Fasoli, Andrea, Labby, Ronald Robert, Bozano, Luisa, Chowdhary, Pawan, Abdullahi, Abubeker
Принадлежит:

Provided is a system and method for tuning an array of sensors to enable selection of the most suitable sensors for a target application. After extracting features from sensor raw data, the extracted features are ranked with gradient boosting decision trees to assign an importance value to each extracted feature. A threshold value for the entire set of extracted features is calculated and an importance score is calculated for the individual sensors of the array. Individual sensors with an importance score on or above the threshold value are selected for the target application. 1. A system comprising:a sensor array; anda processor with at least one algorithm stored therein,wherein,raw data obtained from the sensor array are input into the processor to form an input set of extracted features,the at least one algorithm ranks the extracted features from the input set, wherein each extracted feature is given an importance value, andan importance score for each sensor of the sensor array is determined based upon the ranking of the extracted features for each sensor.2. The system of claim 1 , wherein a threshold value refines the input set claim 1 , and individual sensors having an importance score on or above the threshold value are selected for a target application.5. The system of claim 1 , wherein the at least one algorithm comprises gradient boosting decision trees.6. The system of claim 1 , wherein the sensor array is comprised of a plurality of gas sensors and the gas sensors measure volatile organic compounds (VOCs).7. The system of claim 2 , wherein the target application is selected from the group consisting of air quality analyses claim 2 , air pollution analyses claim 2 , water pollution analyses claim 2 , soil analyses claim 2 , lab test claim 2 , medical tests claim 2 , tests for allergens claim 2 , breathalyzer tests claim 2 , food and beverage expiration date analyses claim 2 , food and beverage spoilage analyses claim 2 , alcohol content analyses claim 2 , ...

Подробнее
Номер записи: 34
01-03-2007 дата публикации

Method and apparatus of supporting business performance management with active shared data spaces

Номер: US20070047439A1
Автор: Lianjun An, Hung-Yang Chang, Shyh-Kwei Chen, Pawan Chowdhary, Michael Dikun, Jun-Jang Jeng, Josef Schiefer
Принадлежит:

A managed policy driven virtual data space for managing artifacts relationships and sharing artifacts among services. A policy model is used to represent business artifacts, sharing of the artifacts, and subscription of other artifacts that is of interest to current artifact and, to represent the various state of the artifact. An active shared space provides support functionality for the policy model, such as artifact lifecycle management. The active shared space also provides the support of sharing of such artifact with external/internal services and other artifacts. The active shared space also controls the artifacts storage in the relational database for archiving purposes. Active shared space also provides the mechanism of subscribing to various artifacts and publishing the availability of artifact for services and other artifacts itself. Active shared space also makes the artifact aware of the context within which the said artifact operates and allows subscribing to appropriate artifacts ...

Подробнее
Номер записи: 35
10-12-2013 дата публикации

Business performance management (BPM) system and method having a physical star architecture, data processing rings and BPM loops

Номер: US0008606622B2
Автор: Hung-yang Chang, Shyh-Kwei Chen, Pawan Chowdhary, Jun-Jang Jeng, Liangzhao Zeng, CHANG HUNG-YANG, CHEN SHYH-KWEI, CHOWDHARY PAWAN, JENG JUN-JANG, ZENG LIANGZHAO
Принадлежит: International Business Machines Corporation, CHANG HUNG-YANG, CHEN SHYH-KWEI, CHOWDHARY PAWAN, JENG JUN-JANG, ZENG LIANGZHAO, IBM, INTERNATIONAL BUSINESS MACHINES CORPORATION

An architecture, system, and method are provided for a commitment loop solution for on demand business activity management. A Business Performance Management (BPM) loop includes nodes each relating to different tasks for processing performance management trigger data generated by a business entity in real time. The beginning or sensing element of the loop is triggered by a token (representing a business event from a business process). The ending or executing element provides a business action to be implemented by the business entity. The token is passed from node to node sequentially in a particular order around the loop. Processing of the data represented by the token is governed by policies, which can be changed dynamically and follow a life cycle.

Подробнее
Номер записи: 36
03-05-2022 дата публикации

Minimizing risk using machine learning techniques

Номер: US0011321634B2
Автор: Sunhwan Lee, Pawan Chowdhary, Guangjie Ren, Raphael I. Arar
Принадлежит: International Business Machines Corporation

Embodiments relate to an intelligent computer platform to utilize machine learning techniques to minimize compliance risk. Features are extracted from one or more data sources across two or more domains and activity data is identified. Features are identified within the activity data which are used to create one or more models. Domain activity impact is measured and a risk probability is calculated. A policy is generated based on the calculated risk probability and one or more compliance activities are orchestrated. One or more encoded actions are executed in compliance with the orchestration.

Подробнее
Номер записи: 37
23-07-2009 дата публикации

System and Methods for Generating Data Analysis Queries from Modeling Constructs

Номер: US20090187552A1
Автор: Florian Pinel, Pawan Chowdhary, Frederick Y. Wu
Принадлежит: INTERNATIONAL BUSINESS MACHINE CORPORATION

A method for automatically generating data analysis queries from at least one modeling construct includes selecting a preconfigured template identifying at least one metric or dimension; retrieving dashboard model data comprising the preconfigured template; filtering to the dashboard model data using at least one user-specific access control; and automatically generating a query for at least one database.

Подробнее
Номер записи: 38
08-12-2022 дата публикации

DYNAMIC PRESENTATION ADJUSTMENT

Номер: US20220391044A1
Автор: Lei Huang, Guangjie Ren, Robert John Moore, Shun Jiang, Pawan Chowdhary, Eric Young Liu, Chung-hao Tan
Принадлежит:

A tool for providing dynamic context-based presentation adjustments across one or more computer devices. The tool receives a presentation from at least one of a plurality of user devices. The tool collects real-time contextual data associated with the presentation from at least one of the plurality of user devices. The tool analyzes the real-time contextual data utilizing a training model. The tool determines one or more adjustment actions based, at least in part, on the analysis of the real-time contextual data. The tool modifies the presentation in real-time using the one or more adjustment actions.

Подробнее
Номер записи: 39
19-04-2022 дата публикации

Entity matching using visual information

Номер: US0011308133B2
Автор: Sunhwan Lee, Pawan Chowdhary, Guangjie Ren
Принадлежит: International Business Machines Corporation

One embodiment provides a method comprising receiving a first set of information corresponding to a first entity and receiving a second set of information corresponding to a second entity. Each set of information received corresponding to each entity comprises visual information relating to the entity. The method further comprises encoding each set of information, and classifying the first entity and the second entity as either matching entities or non-matching entities based on the encoding.

Подробнее
Номер записи: 40
11-04-2019 дата публикации

PRODUCT CONFIGURATION RECOMMENDATION AND OPTIMIZATION

Номер: US20190108579A1
Автор: Pawan Chowdhary, Markus R. Ettl, Somnath Mukherjee, Zhengliang Xue, CHOWDHARY PAWAN, ETTL MARKUS R, MUKHERJEE SOMNATH, XUE ZHENGLIANG, Chowdhary, Pawan, Ettl, Markus R., Mukherjee, Somnath, Xue, Zhengliang
Принадлежит:

Systems, methods, and computer-readable media are disclosed for identifying product configurations that are alternatives to a requested product configuration, ranking the alternative product configurations based on one or more pricing metrics, and presenting the alternative product configurations to a prospective customer, thereby providing the customer with the option of selecting an alternative product configuration in lieu of the initially requested product configuration. 1. A computer-implemented method for identifying an alternative product configuration , the method comprising:receiving, by a computer processor from a client device, a request containing an identification of a product configuration and a requested price for the product configuration;identifying, by the computer processor, the alternative product configuration;determining, by the computer processor, pricing metric data for the alternative product configuration, wherein the pricing metric data comprises an optimized price for the alternative product configuration;sending, by the computer processor, the pricing metric data for the alternative product configuration to the client device; andreceiving, by the computer processor from the client device, an indication of selection or rejection of the alternative product configuration.2. The computer-implemented method of claim 1 , further comprising:determining, by the computer processor, an optimized price for the product configuration; anddetermining, by the computer processor, that a deviation between the optimized price for the product configuration and the requested price for the product configuration satisfies a threshold value,wherein the alternative product configuration is identified responsive to determining that the deviation satisfies the threshold value.3. The computer-implemented method of claim 2 , wherein the optimized price of the alternative product configuration is greater or equal to the requested price for the product configuration ...

Подробнее
Номер записи: 41
14-06-2012 дата публикации

METHOD AND SYSTEM FOR EVALUATING PRODUCT SUBSTITUTIONS ALONG MULTIPLE CRITERIA IN RESPONSE TO A SALES OPPORTUNITY

Номер: US20120150682A1
Автор: Chowdhary Pawan R., Ervolina Thomas Robert, Ettl Markus, LEE Young Min, Peters Daniel John, Sheopuri Anshul, Sourirajan Karthik
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A system and method evaluate product substitutions along multiple criteria in response to a sales opportunity, for instance, providing sales recommendations of configurable products in response to a customer request based on propensity functions. A customer propensity is determined to estimate attractiveness of a substitute product to a customer based on one or more attributes. A seller propensity is determined to estimate attractiveness to a seller of selling the substitute product based on one or more attributes. The customer propensity and the seller propensity are combined to find a plurality of substitute products. 1. A computer-implemented method for evaluating product substitutions along multiple criteria in response to a sales opportunity , comprising:determining a customer propensity to estimate attractiveness of a substitute product to a customer based on one or more first attributes;determining a seller propensity to estimate attractiveness to a seller of selling the substitute product based on one or more second attributes; andcombining, by a processor, the customer propensity and the seller propensity to find a plurality of substitute products,the customer propensity determined as a combination of at least: a value representing a price difference between an initial customer choice and a substitute product, a penalty value that penalizes a choice of a component that has a lower quality than that chosen by the customer in a same commodity group, and a penalty value that penalizes choosing a component in the substitute product that is not in the customer's initial choice and that penalizes a component in the customer's initial choice that is absent in the substitute.2. The method of claim 1 , wherein said steps of determining a customer propensity and determining a seller propensity are performed for each of a plurality of candidate substitute products.3. The method of claim 2 , wherein said step of combining includes finding the a list of a plurality of ...

Подробнее
Номер записи: 42
20-12-2012 дата публикации

SUPPLY CHAIN MANAGEMENT SOLUTION

Номер: US20120323633A1
Автор: Chowdhary Pawan R., Drissi Youssef, Helander Mary E., Katircioglu Kaan K., Li Lin, Qiu Min Min, Sourirajan Karthik, Subbian Karthik, Yonezawa Takashi
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A method, system and computer program product are disclosed for providing an integrated solution to a set of supply chain optimization problems. In one embodiment, the method comprises defining a distribution network, vehicle routing, inventory positioning, and environmental sustainability for a supply chain; and combining an optimization of the distribution network, the vehicle routing, the inventory positioning, and the environmental sustainability into a single problem. In an embodiment, the optimization of the distribution network, the vehicle routing, the inventory positioning, and the environmental sustainability are combined into a single problem by using analytical engines. In one embodiment, these analytical engines include an inventory positioning engine to identify an inventory policy, a network analysis engine to identify a network structure, a vehicle routing engine to identify routes for delivering products, and a sustainability engine to quantify energy use and carbon emissions of defined actions. 1. A method of providing an integrated solution to a set of supply chain optimization problems , the method comprising:defining a distribution network, vehicle routing, inventory positioning, and environmental sustainability for a supply chain;combining an optimization of the distribution network, the vehicle routing, the inventory positioning, and the environmental sustainability into a single problem;storing data in a series of tables including a first table including customer information, a second table including vehicle information, a third table including vehicle routing information, a fourth table including supply product information, and a fifth table including supply location information; andusing a series of analytical engines to take data from and to store data in the series of tables, and to process and to use the data from the series of tables to determine a solution for said single problem.2. The method according to claim 1 , wherein:the ...

Подробнее
Номер записи: 43
04-07-2013 дата публикации

Optimizing procurement spend compliance

Номер: US20130173493A1
Автор: Amit Dhurandhar, Bruce C. Graves, Karthik Sourirajan, Markus R. Ettl, Pawan R. Chowdhary, Soumyadip Ghosh, William S. Schaefer, Yu Tang
Принадлежит: International Business Machines Corp

Managing spend compliance may include receiving a set of spend transaction records containing one or more spend attributes, one or more compliance business rules and one or more investment scenarios that increase spend compliance. The compliance business rules may be applied to the transaction records and segments of transactions with predetermined high savings opportunities may be determined. A prioritized investment plan over one or more time periods that yield optimized return on investment may be generated based on applying the segments of transactions and the investment scenarios.

Подробнее
Номер записи: 44
02-01-2020 дата публикации

MANAGING CONSUMER ENERGY DEMAND

Номер: US20200006943A1
Автор: Arar Raphael I., Asthana Shubhi, Butler Eric K., Chowdhary Pawan R., Gopisetty Sandeep, Hernandez Manuel, JR. Hovey R., Kieliszewski Cheryl A., Roche Kevin P., Strong
Принадлежит:

A computer-implemented method, according to one embodiment, includes: receiving an energy consumption profile which spans multiple intervals in a period of time, and predicting a net energy demand of a consumer system over the period of time. Moreover, a first multiple is determined which, when applied to the received energy consumption profile, produces an updated energy consumption profile which corresponds to an amount of energy that is capable of satisfying the predicted net energy demand of the consumer system. A greatest amount of underprediction is estimated. A greatest amount of overprediction is also estimated. Furthermore, an initial state of an energy storage device electrically coupled to the consumer system is computed according to the updated energy consumption profile. The initial state of the energy storage device is also based on a second multiple applied to each of the greatest amount of underprediction, and the greatest amount of overprediction. 1. A computer-implemented method , comprising:receiving an energy consumption profile which spans multiple intervals in a period of time;predicting a net energy demand of a consumer system over the period of time;determining a first multiple which, when applied to the received energy consumption profile, produces an updated energy consumption profile which corresponds to an amount of energy that is capable of satisfying the predicted net energy demand of the consumer system;estimating a greatest amount of underprediction by which the predicted net energy demand of the consumer system underpredicts an actual net energy demand of the consumer system over the period of time;estimating a greatest amount of overprediction by which the predicted net energy demand of the consumer system overpredicts the actual net energy demand of the consumer system over the period of time; andcomputing an initial state of an energy storage device electrically coupled to the consumer system which is able to satisfy the actual ...

Подробнее
Номер записи: 45
25-01-2018 дата публикации

Dynamic Payment Mechanism Recommendation Generator

Номер: US20180025341A1
Автор: Chandra Anca A., Chowdhary Pawan R., Glissmann-Hochstein Susanne M., Griffin Thomas D., Jadav Divyesh, JR. Hovey Raymond, Lee Sunhwan, Ren Guangjie, Strong
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Embodiments of the invention relate to a system, computer program product, and method for generating a recommendation for using a payment instrument or combination of payment instruments to tender payment. Payment instrument data is stored in a database. Upon receiving a request for a payment recommendation, payment instrument data is retrieved from the database and a payment instrument score is assessed across two or more payment instruments. The assessment comprises the application of a function to a payment instrument, the function taking into account payment instrument variables, category, and location. A recommendation of an apportionment of the payment is generated, including an allocation of an associated cost and the recommended payment is transmitted to a network server. The payment may then be tendered in accordance with the recommendation and recorded, or alternatively, the recommendation may be overridden and the payment tendered with the overriding data, the data then being recorded and the function adjusted accordingly. 1. A computer system comprising:a processing unit operatively coupled to memory; save one or more payment instruments onto a database;', 'receive a request for payment recommendation;', 'upon receiving a request, determine availability of a network connection;', 'determine a payment category for the payment recommendation;', 'apply a function to each payment instrument, wherein the function takes into account payment instrument variables within at least one payment category;', 'select one or more payment instruments in accordance with the functions; and', 'conduct an expense apportionment and payment tendering action with the selected payment instruments., 'the processing unit to generate an apportionment of expenses across one or more payment instruments, comprising the processing unit to2. The computer system of claim 1 , wherein the expense apportionment and payment tendering action comprises the processing unit to:generate a ...

Подробнее
Номер записи: 46
24-01-2019 дата публикации

INTERMEDIATE BLOCKCHAIN SYSTEM FOR MANAGING TRANSACTIONS

Номер: US20190026821A1
Автор: Bathen Luis Angel D., Chowdhary Pawan R., Garagiola Andres, Jiang Shun, Masini Diego A., Ponceleon Dulce B., Ren Guangjie, Tan Chung-hao
Принадлежит:

An example operation may include one or more of identifying a first conferred asset exchange request from a first user account and a second conferred asset exchange request from a second user account which are capable of being used to settle each other, requesting an intermediary blockchain to perform a conferred asset settlement transaction for the first and second conferred asset exchange requests, determining that first conferred assets of the first user account and second conferred assets of the second user account have been transferred to temporary intermediary trading addresses, respectively, and releasing the first conferred assets to the second user account and the second loyalty assets to the first user account, in response to the determining. 1. A method , comprising:identifying a first conferred asset exchange request from a first user account and a second conferred asset exchange request from a second user account which are capable of being used to settle each other;requesting an intermediary blockchain to perform a conferred asset settlement transaction for the first and second conferred asset exchange requests;determining that first conferred assets of the first user account and second conferred assets of the second user account have been transferred to temporary intermediary trading addresses, respectively; andreleasing the first conferred assets to the second user account and the second loyalty assets to the first user account, in response to the determining.2. The method of claim 1 , wherein the identifying further comprises identifying at least one additional conferred asset exchange request from at least one additional user account which is capable of being settled together with a group including the first conferred asset exchange request and the second conferred asset exchange request claim 1 , and requesting the intermediary blockchain to perform the conferred settlement transaction for the first claim 1 , second claim 1 , and at least one ...

Подробнее
Номер записи: 47
30-01-2020 дата публикации

BOT-BASED DATA COLLECTION FOR DETECTING PHONE SOLICITATIONS

Номер: US20200034743A1
Автор: Baracaldo Angel Nathalie, Chowdhary Pawan R., Ludwig Heiko H., Moore Robert J., Nakamura Taiga
Принадлежит:

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data. 1. A method comprising: collecting training data;', classifying each portion of the training data as one of poison data or truthful training data based on content of the portion and one or more learned detection models for detecting poisoned data; and', 'filtering the training data to remove any portion of the training data that is classified as poison data; and, 'protecting the training data against an adversary attempting to poison the training data by, 'training the machine learning model based on the filtered training data., 'decreasing a likelihood of a misclassification from a machine learning model by2. The method of claim 1 , wherein collecting training data comprises:answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot configured to engage in one or more conversations with one or more callers who initiate the one or more incoming phone calls; andrecording the one or more conversations;wherein the training data comprises the one or more recorded conversations.3. The method of claim 2 , wherein the bot is configured to utilize a voice recording that impersonates an individual belonging to a type of demographic targeted by the one or more callers.4. The method of claim 2 , wherein the bot is configured to dynamically converse with the one or more callers based on a conversation template including one or more learned ...

Подробнее
Номер записи: 48
30-01-2020 дата публикации

Drone air traffic control and flight plan management

Номер: US20200035111A1
Автор: Anca A. Chandra, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Pawan R. Chowdhary, Sunhwan Lee, Susanne M. Glissmann-Hochstein, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method comprising receiving a flight plan request for a drone. The flight plan request comprises a drone identity, departure information, and arrival information. The method further comprises constructing a modified flight plan for the drone based on the flight plan request, wherein the modified flight plan represents an approved, congestion reducing, and executable flight plan for the drone, and the modified flight plan comprises a sequence of four-dimensional (4D) cells representing a planned flight path for the drone. For each 4D cell of the modified flight plan, the method further comprises attempting to place an exclusive lock on behalf of the drone on the 4D cell, and in response to a failure to place the exclusive lock on behalf of the drone on the 4D cell, rerouting the modified flight plan around the 4D cell to a random neighboring 4D cell.

Подробнее
Номер записи: 49
22-02-2018 дата публикации

DRONE AIR TRAFFIC CONTROL AND FLIGHT PLAN MANAGEMENT

Номер: US20180053426A1
Автор: Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Glissmann-Hochstein Susanne M., Griffin Thomas D., Jadav Divyesh, JR. Hovey R., Lee Sunhwan, Strong
Принадлежит:

One embodiment provides a method comprising receiving a flight plan request for a drone. The flight plan request comprises a drone identity, departure information, and arrival information. The method further comprises constructing a modified flight plan for the drone based on the flight plan request, wherein the modified flight plan represents an approved, congestion reducing, and executable flight plan for the drone, and the modified flight plan comprises a sequence of four-dimensional (4D) cells representing a planned flight path for the drone. For each 4D cell of the modified flight plan, the method further comprises attempting to place an exclusive lock on behalf of the drone on the 4D cell, and in response to a failure to place the exclusive lock on behalf of the drone on the 4D cell, rerouting the modified flight plan around the 4D cell to a random neighboring 4D cell. 1. A method comprising:receiving a flight plan and a drone profile, wherein the flight plan comprises a sequence of four-dimensional (4D) cells representing a planned flight path for the drone, and the drone profile comprises one or more controlled flight conditions for the drone;determining one or more weather conditions at one or more 4D cells of the flight plan; anddetermining whether the one or more weather conditions exceed the one or more controlled flight conditions, wherein one or more contingency plans are provided in response to determining the one or more weather conditions exceed the one or more controlled flight conditions.2. The method of claim 1 , further comprising:maintaining weather information relating to an air traffic control zone, wherein the weather information includes at least one or more independent observations of wind conditions at one or more 4D cells within the air traffic control zone.3. The method of claim 2 , further comprising:maintaining a weather model for the air traffic control zone relating to the air traffic control zone.4. The method of claim 3 , wherein ...

Подробнее
Номер записи: 50
15-03-2018 дата публикации

Providing recommendations utilizing a user profile

Номер: US20180075355A1
Автор: Anca A. Chandra, Divyesh Jadav, Eric K. Butler, Guangjie Ren, Hovey R. Strong, Jr., Pawan R. Chowdhary, Shun Jiang, Sunhwan Lee, Susanne M. Glissmann-Hochstein
Принадлежит: International Business Machines Corp

A computer-implemented method according to one embodiment includes creating a profile for a user, the profile including one or more default aspects created automatically by a system and one or more custom aspects created in response to textual input by the user, comparing event data to the profile, and providing a recommendation to the user, based on the comparing.

Подробнее
Номер записи: 51
22-03-2018 дата публикации

Cargo logistics dispatch service with integrated pricing and scheduling

Номер: US20180082253A1
Автор: Markus R. Ettl, Pawan R. Chowdhary, Roger D. Lederman, Zhengliang Xue, Zhenyu Hu
Принадлежит: International Business Machines Corp

System and method that improves cargo logistics may be presented. For instance, shipping capacity in cargo logistics may be best utilized based on providing pricing and scheduling solutions that are jointly optimized and prices differentiated based on flexibility of service request. Scheduled service and pricing may be transmitted as a signal to control execution of the cargo logistics.

Подробнее
Номер записи: 52
23-03-2017 дата публикации

MEETING ROOM RESERVATION SYSTEM

Номер: US20170083872A1
Автор: Blomberg Jeanette L., Chandra Anca A., Chowdhary Pawan R., Glissmann-Hochstein Susanne M., JR. Hovey Raymond, Lee Sunhwan, Strong
Принадлежит:

Embodiments of the present invention provide a method comprising maintaining historical meeting information, receiving an event data stream corresponding to a meeting, and delaying confirmation of an assignment of a meeting room for the meeting for a period of delay defined by a confirmation condition to predict a number of in-person attendees at the meeting based on the event data stream and the historical meeting information. The meeting room is tentatively assigned to the meeting based on the predicted number of in-person attendees. The method further comprises sending confirmation of the assignment of the meeting room for the meeting to at least one invitee only after the period of delay has elapsed. 1. A method , comprising:maintaining historical meeting information on at least one hardware storage device;receiving an event data stream corresponding to a meeting, wherein the event data stream comprises an electronic meeting invitation for the meeting and one or more meeting invitation responses received from one or more invitees to the meeting, and wherein each invitee is provided with multiple options of attending the meeting, the multiple options including an option of attending the meeting in-person;delaying confirmation of an assignment of a meeting room for the meeting for a period of delay defined by a confirmation condition to predict, utilizing an attendance predictor module executing on a hardware processor, a number of in-person attendees at the meeting based on the event data stream and the historical meeting information, wherein the meeting room is tentatively assigned to the meeting based on the predicted number of in-person attendees; andsending confirmation of the assignment of the meeting room for the meeting to at least one invitee only after the period of delay has elapsed.2. The method of claim 1 , wherein:the historical meeting information comprises multiple historical event data streams;each historical event data stream corresponds to a ...

Подробнее
Номер записи: 53
03-05-2018 дата публикации

TRAINING A MACHINE TO AUTOMATE SPOT PRICING OF LOGISTICS SERVICES IN A LARGE-SCALE NETWORK

Номер: US20180121829A1
Автор: Chowdhary Pawan R., Ettl Markus R., Lederman Roger D., Nonner Tim, Schimpel Ulrich B., Xue Zhengliang, YANG Hongxia
Принадлежит:

A machine learning algorithm is trained to learn to cluster a plurality of original-destination routes in a network for transporting cargo into a plurality of clusters based on similarities of the original-destination routes, and to learn to cluster the plurality of clusters into a plurality of subgroups based on customer behavior. Influencing criteria associated with each of the subgroups may be determined and based on the influencing criteria, a price elasticity curve for each of the subgroups may be generated. Based on the price elasticity curve and current network traffic, cargo transportation price associated with each of the subgroups may be determined. 1. A method of training a machine to automate spot pricing of logistics services , the method performed by at least one hardware processor , comprising:receiving a plurality of original-destination routes in a network for transporting cargo;clustering the plurality of original-destination routes into a plurality of clusters based on similarities of the original-destination routes;clustering the plurality of clusters into a plurality of subgroups based on customer related factors,wherein based on a machine learning algorithm, a machine learning model is trained to perform the clustering and the clustering is performed by the trained machine learning model;determining influencing factors associated with each of the subgroups;based on the influencing factors, generating a price elasticity curve for each of the subgroups;based on the price elasticity curve and current network traffic, determining cargo transportation price associated with each of the subgroups,wherein the influencing factors comprise at least rate, chargeable weight (CWT), density, weight, volume, leadtime, number of pieces, freighter route, number of stops, customer industry, product code, special handling flag, seasonality indices indicating CWT demand relative to average CWT, revenue demand relative to average revenue and orders demand relative ...

Подробнее
Номер записи: 54
24-07-2014 дата публикации

METHODS AND APPARATUS FOR PROCUREMENT

Номер: US20140207513A1
Автор: Chowdhary Pawan R., Drissi Youssef, Katircioglu Kaan K., Pollyea Scott W.
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Systems and techniques for procurement of equipment and services are disclosed. Data is collected relating to operations of an organization and the information is made accessible to vendors who may supply goods and services for carrying out the operations. The collected data may include information relating to inputs of the operations, size, shape, and weight of objects handled in the operations, actual and desired throughput, energy use, waste, and other data. Data may be anonymized before being made accessible to vendors, and proposals made by vendors in response to data from a particular organization may be directed to the organization from which the data is collected. 120-. (canceled)21. An apparatus comprising:at least one processor; andat least one memory including computer program code; collectin data relating to carrying out an operation, wherein data is collected relating to at least one of inputs to and results of the operation, material usage of the operation, and waste produced by the operation; and', 'making the collected data accessible to one or more vendors providing at least one of products and services relating to carrying out the operation., 'wherein the at least one processor, in response to execution of the computer program code, is configured to perform at least the following22. The apparatus of claim 21 , wherein the at least one processor claim 21 , in response to execution of the computer program code claim 21 , is further configured to cause the apparatus to further perform at least the following:assembling data into at least two groups, wherein each of the groups is associated with an aspect of the operation.23. The apparatus of claim 21 , wherein the groups comprise at least one of data associated with supply chain management claim 21 , data associated with product production claim 21 , data associated with handling of goods claim 21 , and data associated with transportation.24. The apparatus of claim 21 , wherein the collected data ...

Подробнее
Номер записи: 55
24-07-2014 дата публикации

Methods and Apparatus for Procurement

Номер: US20140207516A1
Автор: Kaan K. Katircioglu, Pawan R. Chowdhary, Scott W. Pollyea, Youssef Drissi
Принадлежит: International Business Machines Corp

Systems and techniques for procurement of equipment and services are disclosed. Data is collected relating to operations of an organization and the information is made accessible to vendors who may supply goods and services for carrying out the operations. The collected data may include information relating to inputs of the operations, size, shape, and weight of objects handled in the operations, actual and desired throughput, energy use, waste, and other data. Data may be anonymized before being made accessible to vendors, and proposals made by vendors in response to data from a particular organization may be directed to the organization from which the data is collected.

Подробнее
Номер записи: 56
25-08-2022 дата публикации

TICKET-AGENT MATCHING AND AGENT SKILLSET DEVELOPMENT

Номер: US20220270019A1
Автор: Asthana Shubhi, Chowdhary Pawan, Megahed Aly, Mujumdar Rohit Avinash, ZHANG BING
Принадлежит:

Embodiments are provided for ticket-agent matching and agent skillset development. In some embodiments, a system includes a processor that executes computer-executable components stored in memory. The computer-executable components can include a matching component that determines, using a ticket profile and a space of agent profiles, a ticket-agent pair including a ticket identifier of a service request and an agent identifier of a particular agent within a pool of agents. The computer-executable components also can include a rematching component that assigns a second agent identifier to the service request to develop a skillset of a second particular agent within the pool of agents, the second agent identifier being associated with an unsatisfactory skill score for a defined skill to resolve the service request. 1. A system , comprising: a matching component that determines, using a ticket profile and a space of agent profiles, a ticket-agent pair including a ticket identifier of a service request and an agent identifier of a particular agent within a pool of agents; and', 'a rematching component that assigns a second agent identifier to the service request to develop a skillset of a second particular agent within the pool of agents, the second agent identifier being associated with an unsatisfactory skill score for a defined skill to resolve the service request., 'a processor that executes computer-executable components stored in memory, the computer-executable components comprising,'}2. The system of claim 1 , further comprising:an ingestion component that receives the ticket profile, wherein the ticket profile represents a difficulty level and skillset for resolution of the service request, and wherein a first agent profile of the agent profiles represents efficacy of a first agent within the pool of agents in resolving service requests;; anda report component that sends the ticket-agent pair to a device, sending the ticket-agent pair causes the device to record ...

Подробнее
Номер записи: 57
10-05-2018 дата публикации

Topic bridging determination using topical graphs

Номер: US20180129752A1
Автор: Anca A. Chandra, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Sunhwan Lee, Susanne M. Glissmann-Hochstein, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method that includes obtaining information including profile information and current event information. A processor generates a topic graph by converting the information to topic nodes in the topic graph. The processor determines a weight assignment for each topic node based on ratios of sums of weights of edges from topic nodes. Bridges are provided from a given topic node to a neighbor based on the weight assignment.

Подробнее
Номер записи: 58
28-06-2018 дата публикации

DRONE RECEIVER

Номер: US20180178912A1
Автор: Blomberg Jeanette L., Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Griffin Thomas D., Jadav Divyesh, JR. Hovey R., Lee Sunhwan, Moore Robert J., Strong
Принадлежит:

Embodiments of the present invention provide an apparatus comprising a body including a cavity for storing one or more packages, and a conveyor belt disposed above a top surface of the body. The belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the top surface for dispatch. A package comprises at least one of a drone and a payload transported by the drone. The apparatus further comprises a landing mechanism for stabilizing a drone landing on the apparatus. 1. A method comprising:storing one or more packages in a cavity of a body of an apparatus;controlling a conveyor belt disposed above a top surface of the body, wherein the belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the top surface for dispatch; andstabilizing a drone landing on the apparatus via a landing mechanism of the apparatus;wherein a package comprises at least one of a drone and a payload transported by the drone.2. The method of claim 2 , further comprising:slowing and stabilizing the fall of a drone landing from above the apparatus via the landing mechanism; andre-charging one or more batteries of one or more drones stored in the cavity using a recharge unit of the body.3. A computer program product comprising a computer-readable hardware storage device having program code embodied therewith claim 2 , the program code being executable by a computer to implement a method comprising:storing one or more packages in a cavity of a body of an apparatus;controlling a conveyor belt disposed above a top surface of the body, wherein the belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the ...

Подробнее
Номер записи: 59
16-10-2014 дата публикации

PRICING PERSONALIZED PACKAGES WITH MULTIPLE COMMODITIES

Номер: US20140310064A1
Автор: Chowdhary Pawan R., Ettl Markus R., Subramanian Shivaram, Wang Zizhuo, Xue Zhengliang
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A top-down and bottom-up approach that decomposes product bundles to components, classifies them into different groups corresponding to a component similarity measure, and detects their inherent values. The bundles are reassembled and characterized by several key attributes according to their component inherent values, and classified into segments. A normalized utility model is constructed for each product bundle segment, taking into account the additive effect among different commodity types and product families. The goodness of fit of the top-down and the bottom-up model may be validated. The model may be applied in an RFQ pricing environment. 1. A method of pricing a package with multiple commodities , comprising:decomposing the package into the multiple commodities;computing, by a processor, a value score for each of the multiple commodities based on at least one or more characteristics associated with said each of the multiple commodities;computing, by the processor, a value score for the package based on at least the value score of each of the multiple commodities;determining a package type of the package based on at least the value score of each of the multiple commodities;identifying a segment for the package based at least on the package type and the value score of the package, from a plurality of segments each associated with a utility function; andcomputing the utility function associated with the identified segment to determine a package price.2. The method of claim 1 , wherein the utility function is generated based on historical data associated with historical packages claim 1 , wherein generating the utility function comprises:decomposing each of the historical packages into component parts;determining value scores for the component parts based at least on prices of the historical packages;generating a relationship between each of the component parts and associated value score based on one or more features of the component parts;characterizing the ...

Подробнее
Номер записи: 60
16-10-2014 дата публикации

PRICING PERSONALIZED PACKAGES WITH MULTIPLE COMMODITIES

Номер: US20140310065A1
Автор: Chowdhary Pawan R., Ettl Markus R., Subramanian Shivaram, Wang Zizhuo, Xue Zhengliang
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

A top-down and bottom-up approach that decomposes product bundles to components, classifies them into different groups corresponding to a component similarity measure, and detects their inherent values. The bundles are reassembled and characterized by several key attributes according to their component inherent values, and classified into segments. A normalized utility model is constructed for each product bundle segment, taking into account the additive effect among different commodity types and product families. The goodness of fit of the top-down and the bottom-up model may be validated. The model may be applied in an RFQ pricing environment. 1. A computer readable storage medium storing a program of instructions executable by a machine to perform a method of pricing a package with multiple commodities , comprising:decomposing the package into the multiple commodities;computing, by a processor, a value score for each of the multiple commodities based on at least one or more characteristics associated with said each of the multiple commodities;computing, by the processor, a value score for the package based on at least the value score of each of the multiple commodities;determining a package type of the package based on at least the value score of each of the multiple commodities;identifying a segment for the package based at least on the package type and the value score of the package, from a plurality of segments each associated with a utility function; andcomputing the utility function associated with the identified segment to determine a package price.2. The computer readable storage medium of claim 1 , wherein the utility function is generated based on historical data associated with historical packages claim 1 , wherein generating the utility function comprises:decomposing each of the historical packages into component parts;determining value scores for the component parts based at least on prices of the historical packages;generating a relationship between ...

Подробнее
Номер записи: 61
11-07-2019 дата публикации

Training a machine to automate spot pricing of logistics services in a large-scale network

Номер: US20190213500A1
Автор: Hongxia Yang, Markus R. Ettl, Pawan R. Chowdhary, Roger D. Lederman, Tim Nonner, Ulrich B. Schimpel, Zhengliang Xue
Принадлежит: International Business Machines Corp

A machine learning algorithm is trained to learn to cluster a plurality of original-destination routes in a network for transporting cargo into a plurality of clusters based on similarities of the original-destination routes, and to learn to cluster the plurality of clusters into a plurality of subgroups based on customer behavior. Influencing criteria associated with each of the subgroups may be determined and based on the influencing criteria, a price elasticity curve for each of the subgroups may be generated. Based on the price elasticity curve and current network traffic, cargo transportation price associated with each of the subgroups may be determined.

Подробнее
Номер записи: 62
20-08-2015 дата публикации

PREDICTING DEMAND OF A NEWLY INTRODUCED SHORT LIFECYCLE PRODUCT WITHIN AN ASSORTMENT

Номер: US20150235239A1
Автор: Chowdhary Pawan R., Subramanian Shivaram, ZHANG Xiaoxuan
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

Predicting demand of a newly launched product may comprise obtaining customer sentiment data associated with the newly launched product, the customer sentiment data obtained at least from social media. A mean sentiment lag associated with the customer sentiment data may be determined. A weight given to a predicted PLC effect of the newly launched product relative to customer sentiment identified in the customer sentiment data may be determined. Numerical prediction parameters from parameter values associated with a like-item that is determined to be similar to the newly launched product may be obtained. A product utility valuation may be computed as a weighted combination of the predicted PLC effect and a lagged social media sentiment determined from the customer sentiment data accounted by the mean sentiment lag. The product utility valuation provides an indication of the future demand of the newly launched product. 1. A method of predicting demand of a newly launched product , comprising:obtaining customer sentiment data associated with the newly launched product, the customer sentiment data obtained at least from social media;computing, by a processor, a mean sentiment lag associated with the customer sentiment data;computing, by the processor, a weight given to a predicted product lifecycle (PLC) effect of the newly launched product relative to customer sentiment identified in the customer sentiment data;identifying a like-item associated with the newly launched product;obtaining numerical prediction parameters from parameter values associated with the like-item; andcomputing, by the processor, a product utility valuation as a weighted combination of the predicted PLC effect and a lagged social media sentiment determined from the customer sentiment data accounted by the mean sentiment lag, wherein the predicted PLC effect valuation is determined using the numerical prediction parameters;wherein the product utility valuation provides an indication of the future ...

Подробнее
Номер записи: 63
18-07-2019 дата публикации

Quantitative discovery of name changes

Номер: US20190220780A1
Автор: Anca A. Chandra, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Se Chan Oh, Suppawong Tuarob
Принадлежит: International Business Machines Corp

Embodiments of the present invention provide a method for detecting a temporal change of name associated with performance data. The method comprises receiving at least one candidate name replacement pair comprising a pair of names. The method further comprises, in a training stage, for each known name replacement pair included in the performance data, determining a window of time covering a most recent appearance of a first name of the known name replacement pair. The window of time is determined based on quantitative features of a time series model comprising performance data for the first name and a second name of the known name replacement pair. The method further comprises, in the training stage, training a machine learning classifier based on quantitative features computed using a portion of the performance data for the first name and the second name, where the portion is within the window of time determined.

Подробнее
Номер записи: 64
16-08-2018 дата публикации

DRONE CARRIER

Номер: US20180233053A1
Автор: Blomberg Jeanette L., Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Griffin Thomas D., Jadav Divyesh, Jiang Shun, JR. Hovey R., Lee Sunhwan, Moore Robert J., Strong, Tan Chung-hao
Принадлежит:

Embodiments of the present invention provide a method comprising receiving a task set comprising multiple tasks, receiving operational information identifying one or more operating characteristics of multiple drones, and obtaining an initial heuristic ordering of the multiple tasks based on the operational information and the climate information. Each task has a corresponding task location. The method further comprises scheduling the multiple tasks to obtain a final ordering of the multiple tasks. The final ordering represents an order in which the multiple tasks are scheduled, and the final ordering may be different from the initial heuristic ordering. 1. A method comprising:receiving a task set comprising a plurality of tasks carried out by a plurality of drones, wherein each task has a corresponding task location;receiving operational information identifying one or more operating characteristics of one or more of the plurality of drones carrying out one or more of the plurality of tasks;identifying a drone of the plurality of drones that requires rescue based on the operational information; andprogramming a drone receiver to rescue the drone identified utilizing one or more mechanisms of the drone receiver.2. The method of claim 1 , wherein the drone identified is drone that has a power failure.3. The method of claim 1 , wherein the one or more mechanisms comprise utilizing one or more mechanical shock absorbers to catch the drone identified.4. The method of claim 1 , wherein the one or more mechanisms comprise utilizing magnetic levitation to catch the drone identified.5. The method of claim 1 , wherein the one or more mechanisms comprise utilizing a net to facilitate catching the drone identified.6. A system comprising a computer processor claim 1 , a computer-readable hardware storage medium claim 1 , and program code embodied with the computer-readable hardware storage medium for execution by the computer processor to implement a method comprising:receiving a ...

Подробнее
Номер записи: 65
23-08-2018 дата публикации

CONVERSATION AND CONTEXT AWARE FRAUD AND ABUSE PREVENTION AGENT

Номер: US20180240028A1
Автор: Baracaldo Angel Nathalie, Chowdhary Pawan R., Ludwig Heiko H., Moore Robert J., Strong Hovey Raymond
Принадлежит:

One embodiment provides a method comprising intercepting a voice communication, collecting multi-sensory inputs associated with the voice communication, and determining an overall risk assessment metric for the voice communication based on the multi-sensory inputs and learned signatures. The multi-sensory inputs are indicative of content of the voice communication and one or more contextual factors associated with a target of the voice communication. The overall risk assessment metric indicates a likelihood the voice communication is a scam.

Подробнее
Номер записи: 66
23-08-2018 дата публикации

BOT-BASED HONEYPOT POISON RESILIENT DATA COLLECTION

Номер: US20180240473A1
Автор: Baracaldo Angel Nathalie, Chowdhary Pawan R., Ludwig Heiko H., Moore Robert J., Nakamura Taiga
Принадлежит:

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data. 1. A method comprising:answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot, wherein the bot is configured to engage in a conversation with a caller who initiates an incoming phone call by utilizing a voice recording that impersonates an individual belonging to a type of demographic targeted by the caller and dynamically conversing with the caller based on a conversation template including one or more learned conversation patterns corresponding to the individual belonging to the type of demographic targeted by the caller;recording each conversation the bot engages in; andcollecting training data for training a system in detecting unwanted phone solicitations, wherein the collecting comprises classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data, and the training data each comprises each recorded conversation classified as truthful training data.2. The method of claim 1 , wherein each recorded conversation classified as truthful training data represents poison resilient training data available for use as the training data in training the system for filtering unwanted phone solicitations.3. The method of claim 1 , wherein the bot is configured to select the voice recording and ...

Подробнее
Номер записи: 67
23-08-2018 дата публикации

OUTGOING COMMUNICATION SCAM PREVENTION

Номер: US20180241647A1
Автор: Baracaldo Angel Nathalie, Chowdhary Pawan R., Ludwig Heiko H., Moore Robert J., Safavi Amir J.
Принадлежит:

One embodiment provides a method comprising intercepting an incoming communication for a user, and determining whether to classify the incoming communication as a suspicious incoming communication based on content of the incoming communication and a learned classification model or learned signatures. The method further comprises monitoring one or more outgoing communications from the user, and invoking an action relating to scam prevention in response to determining an outgoing communication from the user is linked to a suspicious incoming communication. 1. A method comprising:intercepting an incoming communication for a user;determining whether to classify the incoming communication as a suspicious incoming communication based on content of the incoming communication and a learned classification model or learned signatures;monitoring one or more outgoing communications from the user; andinvoking an action relating to scam prevention in response to determining an outgoing communication from the user is linked to a suspicious incoming communication.2. The method of claim 1 , wherein:the incoming communication comprises one of an incoming phone call, an incoming voicemail, an incoming electronic message, an incoming email, or incoming physical mail; andthe outgoing communication comprises one of an outgoing phone call, an outgoing electronic message, an outgoing email, or outgoing physical mail.3. The method of claim 1 , wherein determining whether to classify the incoming communication as a suspicious incoming communication comprises:determining a predicted scam type and a risk assessment metric for the incoming communication based on the content of the incoming communication and the learned classification model or the learned signatures.4. The method of claim 3 , further comprising:generating a risk report comprising one or more risk assessment results for the incoming communication based on the risk assessment metric and the predicted scam type, wherein the risk ...

Подробнее
Номер записи: 68
14-09-2017 дата публикации

DRONE RECEIVER

Номер: US20170259940A1
Автор: Blomberg Jeanette L., Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Griffin Thomas D., Jadav Divyesh, JR. Hovey R., Lee Sunhwan, Moore Robert J., Strong
Принадлежит:

Embodiments of the present invention provide an apparatus comprising a body including a cavity for storing one or more packages, and a conveyor belt disposed above a top surface of the body. The belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the top surface for dispatch. A package comprises at least one of a drone and a payload transported by the drone. The apparatus further comprises a landing mechanism for stabilizing a drone landing on the apparatus. 1. An apparatus , comprising:a body including a cavity for storing one or more packages;a conveyor belt disposed above a top surface of the body, wherein the belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the top surface for dispatch; anda landing mechanism for stabilizing a drone landing on the apparatus;wherein a package comprises at least one of a drone and a payload transported by the drone.2. The apparatus of claim 1 , wherein the body further includes a recharge unit for re-charging one or more batteries of one or more drones stored in the cavity.3. The apparatus of claim 1 , wherein the landing mechanism facilitates landing of a drone from above the apparatus.4. The apparatus of claim 3 , wherein:the landing mechanism comprises one or more retractable shock absorbers for slowing and stabilizing the fall of a drone landing from above the apparatus; andthe apparatus provides power to extend and retract the shock absorbers.5. The apparatus of claim 3 , wherein:the landing mechanism comprises an array of electromagnets for slowing and stabilizing the fall of a drone landing from above the apparatus; andthe apparatus provides alternating current to power the array of electromagnets.6. The apparatus of claim 3 , wherein:the landing ...

Подробнее
Номер записи: 69
14-09-2017 дата публикации

Drone carrier

Номер: US20170263131A1
Автор: Anca A. Chandra, Chung-Hao Tan, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Shun Jiang, Sunhwan Lee, Thomas D. Griffin
Принадлежит: International Business Machines Corp

Embodiments of the present invention provide a method comprising receiving a task set comprising multiple tasks, receiving operational information identifying one or more operating characteristics of multiple drones, and obtaining an initial heuristic ordering of the multiple tasks based on the operational information and the climate information. Each task has a corresponding task location. The method further comprises scheduling the multiple tasks to obtain a final ordering of the multiple tasks. The final ordering represents an order in which the multiple tasks are scheduled, and the final ordering may be different from the initial heuristic ordering.

Подробнее
Номер записи: 70
14-09-2017 дата публикации

DRONE AIR TRAFFIC CONTROL AND FLIGHT PLAN MANAGEMENT

Номер: US20170263132A1
Автор: Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Glissmann-Hochstein Susanne M., Griffin Thomas D., Jadav Divyesh, JR. Hovey R., Lee Sunhwan, Strong
Принадлежит:

One embodiment provides a method comprising receiving a flight plan request for a drone. The flight plan request comprises a drone identity, departure information, and arrival information. The method further comprises constructing a modified flight plan for the drone based on the flight plan request, wherein the modified flight plan represents an approved, congestion reducing, and executable flight plan for the drone, and the modified flight plan comprises a sequence of four-dimensional (4D) cells representing a planned flight path for the drone. For each 4D cell of the modified flight plan, the method further comprises attempting to place an exclusive lock on behalf of the drone on the 4D cell, and in response to a failure to place the exclusive lock on behalf of the drone on the 4D cell, rerouting the modified flight plan around the 4D cell to a random neighboring 4D cell. 1. A method , comprising:receiving a flight plan request for a drone, wherein the flight plan request comprises an identity of the drone, departure information for the drone, and arrival information for the drone, and the arrival information comprises one or more locations that the drone is programmed to perform one or more tasks at;constructing a flight plan for the drone based on the flight plan request, wherein the flight plan represents an executable flight plan for the drone that reduces air traffic congestion, and the flight plan comprises a sequence of four-dimensional (4D) cells representing a planned flight path for the drone; and determining whether an exclusive lock on behalf of the drone on the 4D cell is available;', 'in response to determining an exclusive lock on behalf of the drone on the 4D cell is available, placing the exclusive lock on behalf of the drone on the 4D cell, thereby restricting use of air space within the 4D cell to the drone only; and', 'in response to determining an exclusive lock on behalf of the drone on the 4D cell is not available, rerouting the flight plan ...

Подробнее
Номер записи: 71
14-09-2017 дата публикации

Programming language for execution by drone

Номер: US20170263133A1
Автор: Anca A. Chandra, Chung-Hao Tan, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Shun Jiang, Sunhwan Lee, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method comprising maintaining a weather model based on predicted weather conditions for an air traffic control zone. A hash table comprising multiple hash entries is maintained. Each hash entry comprises a timestamped predicted weather condition for a cell in the zone. A flight plan request for a drone is received. The request comprises a planned flight path for the drone. For at least one cell on the planned flight path, same latitude or same longitude cells, whichever is most closely orthogonal to a direction of the planned flight path, are heuristically probed. Weather conditions for the at least one cell are estimated based on predicted weather conditions for the same latitude or same longitude cells. An executable flight plan is generated if the planned flight path is feasible based on the estimated weather conditions; otherwise, a report including an explanation of infeasibility is generated instead.

Подробнее
Номер записи: 72
14-09-2017 дата публикации

DRONE MANAGEMENT DATA STRUCTURE

Номер: US20170263134A1
Автор: Blomberg Jeanette L., Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Griffin Thomas D., Jadav Divyesh, JR. Hovey R., Moore Robert J., Strong
Принадлежит:

One embodiment provides a method comprising maintaining a multi-dimensional data structure partitioned into cells utilizing a tree data structure (“tree”) comprising intervals for each dimension of a multi-dimensional space. To partition an interval for a node of the tree into multiple subintervals, multiple leaf nodes (“leaves”) are generated, each leaf descending from the node. To merge multiple intervals for multiple nodes of the tree, a parent node (“parent”) and multiple leaves descending from the parent are generated, the parent and the leaves are time constrained, and the leaves are scheduled for a merger. When transient data in cells included in a list that corresponds to a leaf scheduled for merger expires, each cell in the list is converted into a cell for inclusion in a different list corresponding to a parent of the leaf, each leaf of the parent removed, and the parent turned into a leaf. 1. A method , comprising:maintaining a multi-dimensional data structure partitioned into cells utilizing a tree data structure comprising intervals for each dimension of a multi-dimensional space, wherein some nodes of the tree data structure are associated with lists of cells, and the cells are configured to maintain sparse and transient data;in response to a request to partition an interval for a node of the tree data structure into multiple subintervals, generating multiple leaf nodes corresponding to the multiple subintervals, wherein each leaf node descends from the node;in response to a request to merge multiple intervals corresponding to multiple nodes of the tree data structure, generating a parent node and multiple leaf nodes descending from the parent node, wherein the parent node and the multiple leaf nodes are time constrained, and the multiple leaf nodes are scheduled for a merger; andin response to an expiration of transient data in cells included in a list that correspond to all but one leaf node scheduled for merger, converting each cell in the list for ...

Подробнее
Номер записи: 73
18-10-2018 дата публикации

PROGRAMMING LANGUAGE FOR EXECUTION BY DRONE

Номер: US20180301042A1
Автор: Blomberg Jeanette L., Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Griffin Thomas D., Jadav Divyesh, Jiang Shun, JR. Hovey R., Lee Sunhwan, Moore Robert J., Strong, Tan Chung-hao
Принадлежит:

One embodiment provides a method comprising maintaining a weather model based on predicted weather conditions for an air traffic control zone. A hash table comprising multiple hash entries is maintained. Each hash entry comprises a timestamped predicted weather condition for a cell in the zone. A flight plan request for a drone is received. The request comprises a planned flight path for the drone. For at least one cell on the planned flight path, same latitude or same longitude cells, whichever is most closely orthogonal to a direction of the planned flight path, are heuristically probed. Weather conditions for the at least one cell are estimated based on predicted weather conditions for the same latitude or same longitude cells. An executable flight plan is generated if the planned flight path is feasible based on the estimated weather conditions; otherwise, a report including an explanation of infeasibility is generated instead. 1. A method comprising:receiving an executable flight plan for a drone, wherein the executable flight plan is based on a planned flight path for the drone, and the executable flight plan comprises a first set of commands in a first programming language;converting the first set of commands to a second set of commands in a second programming language compatible with an Application Programming Interface (API) for the drone; andproviding the second set of commands to the API, wherein flight of the drone to one or more locations included in the planned flight path is controlled in accordance with the second set of commands.2. The method of claim 1 , wherein the first set of commands comprises one or more time and location sensitive commands that are incompatible with the API.3. The method of claim 2 , further comprising:determining time and location information for the drone utilizing at least one of a Global Positioning System (GPS), a compass, a gyroscopic sensor, or triangulation.4. The method of claim 3 , wherein the time and location ...

Подробнее
Номер записи: 74
24-10-2019 дата публикации

BOT-BASED DATA COLLECTION FOR DETECTING PHONE SOLICITATIONS

Номер: US20190325345A1
Автор: Baracaldo Angel Nathalie, Chowdhary Pawan R., Ludwig Heiko H., Moore Robert J., Nakamura Taiga
Принадлежит:

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data. 1. A method comprising:detecting an unsolicited phone call based on a real-time analysis of a conversation between a caller who initiated the unsolicited phone call and a bot configured to dynamically converse with the caller utilizing a voice recording that impersonates an individual; andblocking the unsolicited phone call.2. The method of claim 1 , wherein the bot is configured to dynamically converse with the caller based on a conversation template including one or more learned dialogue patterns.3. The method of claim 1 , wherein the bot is configured to impersonate the individual by using the voice recording that corresponds to a type of demographic or population the individual belongs to.4. The method of claim 1 , wherein detecting an unsolicited phone call comprises:analyzing the conversation in real-time by applying a learned detection model to the conversation to detect one or more attributes that indicate the unsolicited phone call is a phone scam or a telemarketing call.5. The method of claim 4 , wherein applying a learned detection model comprises:applying a classifier from a set of classifiers to the conversation.6. The method of claim 5 , further comprising:rotating which of the set of classifiers is applied to each conversation analyzed to reduce a likelihood of a phone scammer or telemarketer circumventing at least one classifier of the set of classifiers.7. A ...

Подробнее
Номер записи: 75
22-11-2018 дата публикации

BOT-BASED HONEYPOT POISON RESILIENT DATA COLLECTION

Номер: US20180336916A1
Автор: Baracaldo Angel Nathalie, Chowdhary Pawan R., Ludwig Heiko H., Moore Robert J., Nakamura Taiga
Принадлежит:

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data. 1. A method comprising:answering one or more incoming phone calls utilizing a bot, wherein the bot is configured to engage in a conversation with a caller who initiates an incoming phone call utilizing a voice recording that impersonates a human being;detecting one or more unwanted phone solicitations based on a real-time analysis of each conversation the bot engages in; andfiltering each unwanted phone solicitation detected.2. The method of claim 1 , wherein the bot is configured to dynamically converse with a caller initiating an incoming phone call based on a conversation template including one or more learned dialogue/conversation patterns.3. The method of claim 1 , wherein the bot is configured to impersonate an individual belonging to any type of demographic or population by selecting and using a voice recording corresponding to the individual.4. The method of claim 1 , wherein detecting one or more unwanted phone solicitations comprises:applying a learned detection model to each conversation the bot engages in to detect one or more attributes indicating a scam or telemarketing.5. The method of claim 4 , wherein detecting one or more unwanted phone solicitations further comprises:determining an identity of a caller initiating an incoming phone call by comparing voice patterns of the caller against one or more voice samples of one or more known scammers or telemarketers.6. ...

Подробнее
Номер записи: 76
08-12-2016 дата публикации

Quantitative discovery of name changes

Номер: US20160358097A1
Автор: Anca A. Chandra, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Se Chan Oh, Suppawong Tuarob
Принадлежит: International Business Machines Corp

Embodiments of the present invention provide a method for detecting a temporal change of name associated with performance data. The method comprises receiving at least one candidate name replacement pair comprising a pair of names. The method further comprises, in a training stage, for each known name replacement pair included in the performance data, determining a window of time covering a most recent appearance of a first name of the known name replacement pair. The window of time is determined based on quantitative features of a time series model comprising performance data for the first name and a second name of the known name replacement pair. The method further comprises, in the training stage, training a machine learning classifier based on quantitative features computed using a portion of the performance data for the first name and the second name, where the portion is within the window of time determined.

Подробнее
Номер записи: 77
22-10-2020 дата публикации

OUTGOING COMMUNICATION SCAM PREVENTION

Номер: US20200336453A1
Автор: Baracaldo Angel Nathalie, Chowdhary Pawan R., Ludwig Heiko H., Moore Robert J., Safavi Amir J.
Принадлежит:

One embodiment provides a method comprising intercepting an incoming communication for a user, and determining whether to classify the incoming communication as a suspicious incoming communication based on content of the incoming communication and a learned classification model or learned signatures. The method further comprises monitoring one or more outgoing communications from the user, and invoking an action relating to scam prevention in response to determining an outgoing communication from the user is linked to a suspicious incoming communication. 1. A method comprising:intercepting an incoming communication;classifying the incoming communication with a corresponding classification class indicative of a type of scam that the incoming communication involves;generating a risk report comprising the corresponding classification class;monitoring one or more outgoing communications; andproviding a warning in response to determining at least one of the one or more outgoing communications is linked to the incoming communication.2. The method of claim 1 , further comprising:determining, via a learned classification model trained using machine learning, a risk assessment metric for the incoming communication based on content of the incoming communication, wherein the risk assessment metric represents a confidence level the incoming communication is predicted as a scam via the learned classified model.3. The method of claim 2 , wherein the learned classification model is trained based on training data comprising information indicative of known scams.4. The method of claim 2 , wherein the risk report further comprises follow-up contact information for responding to the incoming communication and the risk assessment metric.5. The method of claim 4 , further comprising:storing the incoming communication and the risk report in a database indexed by the follow-up contact information for responding to the incoming communication.6. The method of claim 4 , further comprising: ...

Подробнее
Номер записи: 78
13-12-2018 дата публикации

DRONE RECEIVER

Номер: US20180354621A1
Автор: Blomberg Jeanette L., Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Griffin Thomas D., Jadav Divyesh, JR. Hovey R., Lee Sunhwan, Moore Robert J., Strong
Принадлежит:

Embodiments of the present invention provide an apparatus comprising a body including a cavity for storing one or more packages, and a conveyor belt disposed above a top surface of the body. The belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the top surface for dispatch. A package comprises at least one of a drone and a payload transported by the drone. The apparatus further comprises a landing mechanism for stabilizing a drone landing on the apparatus. 1. A method comprising:receiving a set of tasks, wherein each task has a corresponding task location and a corresponding task action to be performed at the corresponding task location;determining an order of task locations for a drone receiver to visit based on the set of tasks; andscheduling travel of the drone receiver based on the order of task locations.2. The method of claim 1 , further comprising:determining whether there is a task location of the order that the drone receiver is not yet scheduled to visit.3. The method of claim 2 , further comprising:in response to determining there is no task location of the order that the drone receiver is not yet scheduled to visit, scheduling the drone receiver to return to an initial location of the drone receiver.4. The method of claim 2 , further comprising:in response to determining there is a task location of the order that the drone receiver is not yet scheduled to visit, scheduling the drone receiver to travel from a current location of the drone receiver to the task location.5. The method of claim 1 , further comprising:determining whether the drone receiver is within a pre-determined distance of a task location of the order; andin response to determining the drone receiver is within the pre-determined distance of the task location, scheduling a launch of a drone carried by the drone receiver to perform a task action ...

Подробнее
Номер записи: 79
21-11-2019 дата публикации

DRONE MANAGEMENT DATA STRUCTURE

Номер: US20190355261A1
Автор: Blomberg Jeanette L., Butler Eric K., Chandra Anca A., Chowdhary Pawan R., Griffin Thomas D., Jadav Divyesh, JR. Hovey R., Moore Robert J., Strong
Принадлежит:

One embodiment provides a method comprising maintaining a multi-dimensional data structure partitioned into cells utilizing a tree data structure (“tree”) comprising intervals for each dimension of a multi-dimensional space. To partition an interval for a node of the tree into multiple subintervals, multiple leaf nodes (“leaves”) are generated, each leaf descending from the node. To merge multiple intervals for multiple nodes of the tree, a parent node (“parent”) and multiple leaves descending from the parent are generated, the parent and the leaves are time constrained, and the leaves are scheduled for a merger. When transient data in cells included in a list that corresponds to a leaf scheduled for merger expires, each cell in the list is converted into a cell for inclusion in a different list corresponding to a parent of the leaf, each leaf of the parent removed, and the parent turned into a leaf. 1. A method , comprising:partitioning a map representing multi-dimensional air space within an air traffic control zone into a plurality of multi-dimensional cell structures; andmanaging a flight plan for a drone to maintain air traffic control within the air traffic control zone based on the plurality of multi-dimensional cell structures, wherein flight of the drone within the air traffic control zone is controlled in accordance with the flight plan.2. The method of claim 1 , further comprising:locking one or more cell structures of the plurality of multi-dimensional cell structures on behalf of the drone, wherein the flight plan comprises the one or more locked cells.3. The method of claim 1 , further comprising:subdividing at least one cell structure of the plurality of multi-dimensional cell structures into additional multi-dimensional cell structures in response to an increase in a number of conflicts within the air traffic control zone, thereby increasing a total number of cell structures available in the plurality of multi-dimensional cell structures for locking ...

Подробнее
Номер записи: 80
19-12-2019 дата публикации

Topic bridging determination using topical graphs

Номер: US20190384791A1
Автор: Anca A. Chandra, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Sunhwan Lee, Susanne M. Glissmann-Hochstein, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method that includes generating, by a processor, a topic graph by converting information to topic nodes and edges in the topic graph. Bridges from a given topic node are provided to a neighbor node based on a weight assignment. The bridges are converted to an electronic form of communication. The processor orders suggested paths based on a determined distance from at least one other topic node to a topic goal node via an earliest topic node on each suggested path. The determined distance is found by a first search of the topic graph.

Подробнее
Номер записи: 81
25-08-2020 дата публикации

Outgoing communication scam prevention

Номер: US10757058B2
Автор: Amir J. Safavi, Heiko H. Ludwig, Nathalie Baracaldo Angel, Pawan R. Chowdhary, Robert J. Moore
Принадлежит: International Business Machines Corp

One embodiment provides a method comprising intercepting an incoming communication for a user, and determining whether to classify the incoming communication as a suspicious incoming communication based on content of the incoming communication and a learned classification model or learned signatures. The method further comprises monitoring one or more outgoing communications from the user, and invoking an action relating to scam prevention in response to determining an outgoing communication from the user is linked to a suspicious incoming communication.

Подробнее
Номер записи: 82
23-10-2008 дата публикации

Updating a data warehouse schema based on changes in an observation model

Номер: US20080263104A1
Автор: George Andrei Mihaila, Hui Lei, Pawan R. Chowdhary, Themis Palpanas
Принадлежит: Chowdhary Pawan R, George Andrei Mihaila, Hui Lei, Themis Palpanas

A method, information processing system, and computer readable medium for modifying at least one data warehouse schema based on detected changes in an associated observation model are disclosed. The method includes determining if at least one new observation model has been created. The method also includes determining if at least one existing observation model is associated with the new observation model. In response to the existing observation model being associated with the new observation model, at least one changed attribute is identified by comparing the new observation model and the existing observation model. A set of files associated with the existing observation model is updated to reflect the changed attribute between the new observation model and the existing observation model.

Подробнее
Номер записи: 83
25-09-2018 дата публикации

Drone receiver

Номер: US10081425B2
Автор: Anca A. Chandra, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Sunhwan Lee, Thomas D. Griffin
Принадлежит: International Business Machines Corp

Embodiments of the present invention provide an apparatus comprising a body including a cavity for storing one or more packages, and a conveyor belt disposed above a top surface of the body. The belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the top surface for dispatch. A package comprises at least one of a drone and a payload transported by the drone. The apparatus further comprises a landing mechanism for stabilizing a drone landing on the apparatus.

Подробнее
Номер записи: 84
20-12-2007 дата публикации

Updating a data warehouse schema based on changes in an observation model

Номер: US20070294208A1
Автор: George Andrei Mihaila, Hui Lei, Pawan R. Chowdhary, Themis Palpanas
Принадлежит: International Business Machines Corp

A method, information processing system, and computer readable medium for modifying at least one data warehouse schema based on detected changes in an associated observation model are disclosed. The method includes determining if at least one new observation model has been created. The method also includes determining if at least one existing observation model is associated with the new observation model. In response to the existing observation model being associated with the new observation model, at least one changed attribute is identified by comparing the new observation model and the existing observation model. A set of files associated with the existing observation model is updated to reflect the changed attribute between the new observation model and the existing observation model.

Подробнее
Номер записи: 85
22-09-2020 дата публикации

Bot-based data collection for detecting phone solicitations

Номер: US10783455B2
Автор: Heiko H. Ludwig, Nathalie Baracaldo Angel, Pawan R. Chowdhary, Robert J. Moore, Taiga Nakamura
Принадлежит: International Business Machines Corp

One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Подробнее
Номер записи: 86
19-10-2021 дата публикации

Drone management data structure

Номер: US11151885B2
Автор: Anca A. Chandra, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method comprising maintaining a multi-dimensional data structure partitioned into cells utilizing a tree data structure (“tree”) comprising intervals for each dimension of a multi-dimensional space. To partition an interval for a node of the tree into multiple subintervals, multiple leaf nodes (“leaves”) are generated, each leaf descending from the node. To merge multiple intervals for multiple nodes of the tree, a parent node (“parent”) and multiple leaves descending from the parent are generated, the parent and the leaves are time constrained, and the leaves are scheduled for a merger. When transient data in cells included in a list that corresponds to a leaf scheduled for merger expires, each cell in the list is converted into a cell for inclusion in a different list corresponding to a parent of the leaf, each leaf of the parent removed, and the parent turned into a leaf.

Подробнее
Номер записи: 87
28-08-2018 дата публикации

Programming language for execution by drone

Номер: US10062292B2
Автор: Anca A. Chandra, Chung-Hao Tan, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Shun Jiang, Sunhwan Lee, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method comprising maintaining a weather model based on predicted weather conditions for an air traffic control zone. A hash table comprising multiple hash entries is maintained. Each hash entry comprises a timestamped predicted weather condition for a cell in the zone. A flight plan request for a drone is received. The request comprises a planned flight path for the drone. For at least one cell on the planned flight path, same latitude or same longitude cells, whichever is most closely orthogonal to a direction of the planned flight path, are heuristically probed. Weather conditions for the at least one cell are estimated based on predicted weather conditions for the same latitude or same longitude cells. An executable flight plan is generated if the planned flight path is feasible based on the estimated weather conditions; otherwise, a report including an explanation of infeasibility is generated instead.

Подробнее
Номер записи: 88
01-01-2009 дата публикации

System and Method for Modeling Slow Changing Dimension and Auto Management Using Model Driven Business Performance Management

Номер: US20090006146A1
Автор: David W. Harrison, Hung-Yang Chang, Pawan Raghunath Chowdhary
Принадлежит: International Business Machines Corp

A system for generating a model for tracking a changing dimension feature of data in a business model includes a memory for storing the business model and a computer readable code for modeling the changes in the changing dimension feature and a processor for executing the computer readable code to perform method steps including capturing the changing dimension feature of the business model, transforming the changing dimension feature into a data warehouse model corresponding the business model, identifying changing dimensions and attributes in the changing dimension feature according to the data warehouse model, and generating a run-time deployable component for tracking the changing dimension feature based on the identified changing dimensions and attributes.

Подробнее
Номер записи: 89
28-12-2023 дата публикации

Joint learning of time-series models leveraging natural language processing

Номер: US20230419338A1
Автор: Indervir Singh Banipal, Pawan Raghunath Chowdhary, Shikhar KWATRA, Shubhi Asthana
Принадлежит: International Business Machines Corp

Disclosed are methods, computer program products, and systems for maximizing renewals of purchase orders. One embodiment of the method may comprise utilizing a classifier machine learning model to identify metrics that are most relevant to whether customers will renew purchase orders, predicting respective risks of non-renewal for the purchase orders using the identified metrics, applying a tone analyzer natural language processing (NLP) model to determine current sentiments for respective customers, and recommending which of the respective customers to pursue with additional resources based the respectively determined sentiments and risks of non-renewal.

Подробнее
Номер записи: 90
01-04-2014 дата публикации

Management of time-variant data schemas in data warehouses

Номер: US8688658B2
Автор: George Andrei Mihaila, Pawan R. Chowdhary
Принадлежит: International Business Machines Corp

A system, method, and computer readable medium for preserving information in time variant data schemas are disclosed. The method includes determining if at least one modification request associated with a database schema has been received. In response to the modification request being received, a metadata table associated with the database schema is updated to include at least one entry associated with the modification request. The entry identifies an instance in time when an action associated with the modification request was performed.

Подробнее
Номер записи: 91
07-12-2021 дата публикации

Topic bridging determination using topical graphs

Номер: US11194862B2
Автор: Anca A. Chandra, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Sunhwan Lee, Susanne M. Glissmann-Hochstein, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method that includes generating, by a processor, a topic graph by converting information to topic nodes and edges in the topic graph. Bridges from a given topic node are provided to a neighbor node based on a weight assignment. The bridges are converted to an electronic form of communication. The processor orders suggested paths based on a determined distance from at least one other topic node to a topic goal node via an earliest topic node on each suggested path. The determined distance is found by a first search of the topic graph.

Подробнее
Номер записи: 92
28-08-2008 дата публикации

Method and system for estimating supply impact on a firm under a global crisis

Номер: US20080208658A1
Автор: Ching-Hua Chen-Ritzo, Dharmashankar Subramanian, Pawan Raghunath Chowdhary, Thomas Robert Ervolina
Принадлежит: Individual

The availability of relevant business resources, or supply, during a global crisis or disruption are estimated by using a forecast of a baseline supply of human resources and various forms of infrastructure and raw materials for a firm as input. That forecast is corrected to account for the impact of a crisis or other disruption, and a corrected forecast as output is provided. The corrected forecast reflects changes in the availability of business resources due to the crisis or disruption, dependencies between resources, as well as any mitigating effects resulting from the implementation of mitigation policies.

Подробнее
Номер записи: 93
06-06-2024 дата публикации

Automatic processing and matching of invoices to purchase orders

Номер: US20240185326A1
Автор: BING ZHANG, Pawan Raghunath Chowdhary, Shubhi Asthana, Taiga Nakamura
Принадлежит: International Business Machines Corp

An embodiment for methods of processing invoices and purchase orders is provided. The embodiment may receive a set of invoices. The embodiment may cluster the set of invoices based on a series of invoice attributes. The embodiment may then utilize a multitask deep neural network model to split a generated cluster of invoices into subsets of invoices based on a series of invoice features. The embodiment may utilize a second deep neural network model to identify one or more prioritized subsets of invoices in the subsets of invoices that meet a purchase order match probability threshold. The embodiment may perform text mining on the one or more prioritized subsets of invoices to identify matching item-level services between individual invoices in the prioritized subset of invoices and a target purchase order. The embodiment may output matching invoices corresponding to the target purchase order.

Подробнее
Номер записи: 94
15-08-2024 дата публикации

Data management system using neural networks and risk modeling

Номер: US20240273354A1
Автор: BING ZHANG, Pawan Raghunath Chowdhary, Shubhi Asthana, Taiga Nakamura
Принадлежит: International Business Machines Corp

A data management system may receive, via a network and from different computing devices, first data regarding a plurality of first documents and second data regarding a plurality of second documents. The system may perform a correlation coefficient analysis to identify a subset of labels and train a neural network model, based on the subset of labels, to determine a mapping between the plurality of first documents and the plurality of second documents. The mapping may indicate that one or more second documents are associated with a particular first document. The system may train a time-series forecasting model to predict one or more second documents for the particular first document. The system may perform a risk analytics process on the particular first data to determine a measure of risk associated with the particular first document. The system may evaluate the particular first data dynamically using a reinforcement learning model.

Подробнее
Номер записи: 95
24-04-2018 дата публикации

Drone receiver

Номер: US09950791B2
Автор: Anca A. Chandra, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Jeanette L. Blomberg, Pawan R. Chowdhary, Robert J. Moore, Sunhwan Lee, Thomas D. Griffin
Принадлежит: International Business Machines Corp

Embodiments of the present invention provide an apparatus comprising a body including a cavity for storing one or more packages, and a conveyor belt disposed above a top surface of the body. The belt is shaped to receive one or more packages, and the belt is controllable to rotate a package placed on the belt either from the top surface to the cavity for storage or from the cavity to the top surface for dispatch. A package comprises at least one of a drone and a payload transported by the drone. The apparatus further comprises a landing mechanism for stabilizing a drone landing on the apparatus.

Подробнее
Номер записи: 96
26-12-2017 дата публикации

Drone air traffic control and flight plan management

Номер: US09852642B2
Автор: Anca A. Chandra, Divyesh Jadav, Eric K. Butler, Hovey R. Strong, Jr., Pawan R. Chowdhary, Sunhwan Lee, Susanne M. Glissmann-Hochstein, Thomas D. Griffin
Принадлежит: International Business Machines Corp

One embodiment provides a method comprising receiving a flight plan request for a drone. The flight plan request comprises a drone identity, departure information, and arrival information. The method further comprises constructing a modified flight plan for the drone based on the flight plan request, wherein the modified flight plan represents an approved, congestion reducing, and executable flight plan for the drone, and the modified flight plan comprises a sequence of four-dimensional (4D) cells representing a planned flight path for the drone. For each 4D cell of the modified flight plan, the method further comprises attempting to place an exclusive lock on behalf of the drone on the 4D cell, and in response to a failure to place the exclusive lock on behalf of the drone on the 4D cell, rerouting the modified flight plan around the 4D cell to a random neighboring 4D cell.

Подробнее
Номер записи: 97