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 18128. Отображено 100.
19-01-2012 дата публикации

Intelligent Automated Assistant

Номер: US20120016678A1
Автор: Adam John Cheyer, Christopher Dean Brigham, Dag Kittlaus, Didier Rene Guzzoni, Harry Joseph Saddler, Marcello Bastea-Forte, Richard Donald Giuli, Thomas Robert Gruber
Принадлежит: Apple Inc

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Подробнее
Номер записи: 1
19-01-2012 дата публикации

System and method for user interface

Номер: US20120017161A1
Автор: David Hirshberg
Принадлежит: Individual

A text entry system for an electronic device comprising: (a) a text entry software engine receiving an interface description; (b) a server subsystem for storing a database of said interface descriptions; and (c) interface design tools providing a mean for interface designers to create said interface description. Condition upon the interface description the engine realize a text entry user interface by displaying objects on the device's screen, interrupting user input operations to text and send the text entered by the user to an application. A preferred interface description is selected and downloaded from a server to the device and used by the engine. Interface descriptions are created by the interface design tools are uploaded and stored in the database.

Подробнее
Номер записи: 2
26-01-2012 дата публикации

Information processing apparatus, information processing method, and information processing program

Номер: US20120023399A1
Автор: Akihiro Watanabe, Kenichiro Kobayashi, Masaaki Hoshino, Shouichi Doi
Принадлежит: Sony Corp

An information processing apparatus includes a selection unit selecting at least a part of a text included in contents, an acquisition unit acquiring a processing result of natural language processing for the part of the text selected by the selection unit, a specifying unit specifying a predetermined part of the text based on the processing result acquired by the acquisition unit, a detection unit detecting a keyword from the predetermined part of the text based on the processing result acquired by the acquisition unit, a tag generation unit automatically generating a tag in accordance with the keyword detected by the detection unit, and an association unit associating the tag generated by the tag generation unit with the predetermined part of the text.

Подробнее
Номер записи: 3
02-02-2012 дата публикации

Handheld Electronic Device and Method For Employing Contextual Data For Disambiguation of Text Input

Номер: US20120029905A1
Автор: Vadim Fux
Принадлежит: Research in Motion Ltd

A handheld electronic device includes a reduced QWERTY keyboard and is enabled with disambiguation software that is operable to disambiguate text input. In addition to identifying and outputting representations of language objects that are stored in the memory and that correspond with a text input, the device is able to employ contextual data in certain circumstances to prioritize output.

Подробнее
Номер записи: 4
02-02-2012 дата публикации

User interface for a handheld device

Номер: US20120030299A1
Автор: Andrew Bocking, Michael Hardy, Scotte Zinn, Theodore Van Belle
Принадлежит: Research in Motion Ltd

A user interface and method for composing a message to be sent over a wireless network environment using a handheld device is disclosed. According to the method, upon receipt of a user request to compose a message, a screen is displayed with a recipient field for a recipient address, an associated label to indicate that the recipient field is for a recipient address, and a message body field for holding message content. The method further includes, upon each keystroke entry of text to the recipient field, looking up entries from an address book which match the text, and displaying a selection menu representing addresses from at least a portion of the entries.

Подробнее
Номер записи: 5
09-02-2012 дата публикации

Hand-held electronic device

Номер: US20120032889A1
Автор: Craig Dunk, Harry R. Major, Herb A. Little, Jason T. Griffin, Jerome Lang, John A. Holmes, Michael Brown, Mihal Lazaridis
Принадлежит: Research in Motion Ltd

A hand-held electronic device with a keyboard, thumbwheel, display and associated software is optimized for use of the device with the thumbs. The associated software has a plurality of features to optimize efficient use of the limited keyboard space and encourage the use of the device by thumb-based data entry through the thumbwheel and/or through a combination of minimal number of keystrokes. Software features include international character scrolling, and auto-capitalization. The keys on the device keyboard are optimally shaped and configured for thumb-based input. In addition, the thumbwheel is inclined between the front and a side edge of the device so as to be reachable by either the thumb or index finger of the user's hand at the side edge of the device.

Подробнее
Номер записи: 6
12-04-2012 дата публикации

Method and system for predicting text

Номер: US20120089925A1
Автор: Hagit Perry, Uri Ron
Принадлежит: Individual

An electronic messager with a predictive text editor, including a storage unit for storing a data structure associating, for each one of a plurality of a user's contacts, usage data for the user's history of usage of words in communications with the user contact, a data manager coupled with the storage unit for generating the data structure in the storage unit, and for updating the data structure as additional communications with each user contact are performed and additional usage data is obtained therefrom, and a text predictor coupled with the storage unit, for receiving as input a character string and a designated user contact, and for generating as output an ordered list of predicted. A method is also described and claimed.

Подробнее
Номер записи: 7
24-05-2012 дата публикации

Process for Translating Machine Shorthand Into Text

Номер: US20120128252A1
Автор: Jeremy Thorne
Принадлежит: Individual

A method for translating stenographic strokes includes the steps of receiving a series of stenographic strokes, creating a table of translations of one or more strokes within the series of strokes, sequentially assigning a score to each of the one or more strokes, determining at least one alternate translation to at least one of the translations in the table of translations, ranking the translations and alternate translations based on an accumulation of the score of the strokes within, and selecting one of the ranked translations or one of the ranked alternate translations based on a best score.

Подробнее
Номер записи: 8
07-06-2012 дата публикации

Code Recognition Method, Device and Computer Readable Storage Medium for Storing Code Recognition Method

Номер: US20120141030A1
Автор: Jing-Fung CHEN, Yi-Chong Zeng
Принадлежит: INSTITUTE FOR INFORMATION INDUSTRY

A code recognition method includes the following steps: a first code-image block is received. Wherein, several first codes are displayed on the first code-image block. The first code-image block is partitioned into several second code-image blocks. Wherein, each of the second code-image blocks displays a second code respectively. Each of the second codes is one of the first codes. Each of the second code-image blocks is recognized as several third codes corresponding to each of the second codes respectively. Some of the neighboring second code-image blocks are combined to form several third code-image blocks. Wherein, each of the third code-image blocks displays a first code set, which comprises some of the second codes. Each of the third code-image blocks is recognized as a second code set corresponding to each of the first code sets respectively. Wherein, each of the second code sets includes the codes selected from the third codes.

Подробнее
Номер записи: 9
28-06-2012 дата публикации

Matching text to images

Номер: US20120163707A1
Автор: Anitha Kannan, Dahua Lin, Qifa Ke, Simon Baker
Принадлежит: Microsoft Corp

Text in web pages or other text documents may be classified based on the images or other objects within the webpage. A system for identifying and classifying text related to an object may identify one or more web pages containing the image or similar images, determine topics from the text of the document, and develop a set of training phrases for a classifier. The classifier may be trained and then used to analyze the text in the documents. The training set may include both positive examples and negative examples of text taken from the set of documents. A positive example may include captions or other elements directly associated with the object, while negative examples may include text taken from the documents, but from a large distance from the object. In some cases, the system may iterate on the classification process to refine the results.

Подробнее
Номер записи: 10
05-07-2012 дата публикации

Method and system for facilitating text input

Номер: US20120173222A1
Автор: Annie Chang, George Zhang, Hanping Feng, Henry Ou, Jian ZENG, Junyu WANG, Pan Jie, Xiangye Xiao, Yonggang Wang
Принадлежит: Google LLC

A method and system for facilitating text input is disclosed. The method comprises: invoking an input assistant from within an application in an operating environment at a client, the input assistant being a standalone input service within the same operating environment as the application, receiving a text string from a user in an input field of the application, providing, by the input assistant, input prediction for completing the text string, selecting an input text of at least one word in the input field of the application, retrieving, by the input assistant, text content related to the input text from one or more text assistance services in communication with the input assistant, presenting the received text content to the user for assistance in the user's text input.

Подробнее
Номер записи: 11
16-08-2012 дата публикации

Method and System for Controlling a Computer with a Mobile Device

Номер: US20120206365A1
Автор: Eryk Wangsness
Принадлежит: Individual

Methods and systems in accordance with the present invention allow connection of a cellular telephone or other mobile device to a computer or other receiving device with a processor and user interface and thus allow input of text into the computer via the keypad of the cellular telephone or other mobile device. Methods and systems in accordance with the present invention further allow input of abbreviations common to character limited messaging formats; for example text messaging, Twitter, and Facebook; and translate such abbreviations into the words or phrases they commonly represent.

Подробнее
Номер записи: 12
20-09-2012 дата публикации

Linking context-based information to text messages

Номер: US20120239761A1
Автор: Jonathon Linner, Juho-Pekka Virolainen, Robert Lawson
Принадлежит: HDmessaging Inc

A system and a method are disclosed for adding linked content to text messages. Messages are analyzed to determine the context and meaning of a conversation between users, and linked content relevant to the conversation is selected and associated with certain words or phrases in the messages. This process for enhancing text messages beneficially provides users with additional information related to the meaning of their conversation, and also provides advertisers with a valuable new way of delivering highly relevant advertisements to a precise group of users.

Подробнее
Номер записи: 13
22-11-2012 дата публикации

Advanced prediction

Номер: US20120297332A1
Автор: Byron H. Changuion, Chiwei Che, Taylor Tai
Принадлежит: Microsoft Corp

Described herein is an IME that makes text predictions (e.g., character, phonetic, symbol, word, phrase, and number) and suggests the predictions to a user based on text previously entered in a text box. The IME may base the predictive text on entries in a table or dictionary or historical user text entries. Initial predictions of text are suggested when nothing is entered in the text box. Numeric or punctuation may also be suggested when appropriate. If no predictions can be ascertained, the IME may suggest default predictions to the user.

Подробнее
Номер записи: 14
31-01-2013 дата публикации

Information processing apparatus, phrase output method, and program

Номер: US20130027535A1
Автор: Junichi Rekimoto, Tatsushi Nashida
Принадлежит: Sony Corp

In one aspect, an information processing system for determining complimentary phrases to present to a recipient is provided. The information processing system may receive an input image depicting a subject. A difference in appearance between the subject depicted in the input image and a model subject may be determined. One or more phrases (e.g., complimentary phrases) may be selected from a plurality of categorized phrase candidates based on the identified difference in appearance between the subject and the model subject. The difference in appearance may be determined by comparing selected features (e.g., skin, hair, eyes) of the subject with one or more predetermined features of the model subject. The model subject may be the same or different than the subject depicted in the input image.

Подробнее
Номер записи: 15
14-02-2013 дата публикации

Method for displaying candidate in character input, character inputting program, and character input apparatus

Номер: US20130041890A1
Автор: Takuya Nakayama
Принадлежит: Omron Corp

A character input apparatus has a storage section in which a conversion dictionary and a learning dictionary are stored, wherein a plurality of pieces of dictionary data each of which includes a pre-conversion character string and a post-conversion character string are registered in the conversion dictionary, and the learning dictionary is used to register a phrase fixed as an input character string while the phrase is correlated with collocation relationship between phrases, a first candidate extracting section that searches the conversion dictionary using the pre-conversion character string in response to an input of the pre-conversion character string to extract and display a candidate of the post-conversion character string, and a second candidate extracting section that extracts and displays a phrase that collocates with the phrase indicated by the fixed character string from the learning dictionary as the input character string is fixed.

Подробнее
Номер записи: 16
21-02-2013 дата публикации

Soft-sending chat messages

Номер: US20130047099A1
Автор: Arkady Trestman, Christian Shrigley, Drew Beechum, Paul Pak, Sean O'Dell, Vita Markman
Принадлежит: Disney Enterprises Inc

Techniques are disclosed for supplying users in an online environment with a safe and effective chat facility. The chat facility is “safe” in the sense that the ability of users to compose inappropriate messages is greatly restricted, while “effective” in the sense that users are still allowed a broad range of expressivity in composing and exchanging chat messages.

Подробнее
Номер записи: 17
09-05-2013 дата публикации

Personalized Vocabulary for Digital Assistant

Номер: US20130117022A1
Автор: Adam John Cheyer, Didier Rene Guzzoni, Lik Harry Chen, Thomas Robert Gruber
Принадлежит: Apple Inc

Methods, systems, and computer readable storage medium related to operating an intelligent digital assistant are disclosed. A text string is obtained from a speech input received from a user. The received text string is interpreted to derive a representation of user intent based at least in part on a plurality of words associated with a user and stored in memory associated with the user, the plurality of words including words from a plurality of user interactions with an automated assistant. At least one domain, a task, and at least one parameter for the task, are identified based at least in part on the representation of user intent. The identified task is performed. An output is provided to the user, where the output is related to the performance of the task.

Подробнее
Номер записи: 18
23-05-2013 дата публикации

Systems and methods of building and using custom word lists

Номер: US20130132073A1
Автор: Jason T. Griffin, Michael S. Brown, Robert J. Lowles
Принадлежит: Research in Motion Ltd

Standard word lists that are often used for such operations as predictive text, spell checking, and word completion are based on general linguistic data that might not accurately reflect actual text usage patterns of particular users. Systems and methods of building and using a custom word list for use in text operations on an electronic device are provided. A collection of text items associated with a user of the electronic device is scanned to identify words in the text items. A weighting is then assigned to each identified word, and the words and corresponding weightings are stored.

Подробнее
Номер записи: 19
23-05-2013 дата публикации

Intelligent client capability-based results related to a character stream

Номер: US20130132376A1
Автор: Gerald Campbell, Harmannus Vandermolen, Lara Mehanna, Shawkat Hasan
Принадлежит: Facebook Inc

Information may be presented to a user by using a first application to receive a character stream of one or more noncompletion characters. The noncompletion characters indicate that additional characters may be received. The character stream is exchanged with a host that analyzes the character stream to generate results that are responsive to the user's predicted interest. Results are received and displayed so that the user may select one of the results to launch a code segment related to the selected result.

Подробнее
Номер записи: 20
06-06-2013 дата публикации

Enhanced voice conferencing with history

Номер: US20130144603A1
Автор: Charles Whitmer, Clarence T. Tegreene, Craig J. Mundie, Desney S. Tan, Douglas C. Burger, Jordin T. Kare, Lin Zhong, Lowell L. Wood, JR., Matthew G. Dyor, Muriel Y. Ishikawa, Nathan P. Myhrvold, Paramvir Bahl, Paul Holman, Ranveer Chandra, Richard T. Lord, Robert W. Lord, Roderick A. Hyde, Tim Paek, Victoria Y.H. Wood, William H. Gates, III
Принадлежит: ELWHA LLC

Techniques for ability enhancement are described. Some embodiments provide an ability enhancement facilitator system (“AEFS”) configured to enhance voice conferencing among multiple speakers. Some embodiments of the AEFS enhance voice conferencing by recording and presenting voice conference history information based on speaker-related information. The AEFS receives data that represents utterances of multiple speakers who are engaging in a voice conference with one another. The AEFS then determines speaker-related information, such as by identifying a current speaker, locating an information item (e.g., an email message, document) associated with the speaker, or the like. The AEFS records conference history information (e.g., a transcript) based on the determined speaker-related information. The AEFS then informs a user of the conference history information, such as by presenting a transcript of the voice conference and/or related information items on a display of a conferencing device associated with the user.

Подробнее
Номер записи: 21
13-06-2013 дата публикации

Content-based automatic input protocol selection

Номер: US20130151508A1
Автор: Kosuke Takano, Naofumi Yoshida, Shuichi Kurabayashi
Принадлежит: EMPIRE TECHNOLOGY DEVELOPMENT LLC

Technologies for selecting an input protocol based on an input content are generally disclosed. In one example, a method for selecting an input protocol based on an input content can include: acquiring the input content; analyzing the input content; extracting one or more indivisible individual units from the input content; calculating a similarity between a first frequency of occurrence of the one or more indivisible individual units and a second frequency of occurrence of the one or more indivisible individual units, wherein the second frequency of occurrence of the one or more indivisible individual units is predetermined with a second value of frequency of occurrence; ranking the similarity; identifying the input protocol based on the similarity; and selecting a first ranked input protocol having a highest similarity.

Подробнее
Номер записи: 22
20-06-2013 дата публикации

Performing Searching for a List of Entries Using a Remote Control Device

Номер: US20130154923A1
Автор: Wayne E. Mock
Принадлежит: Individual

System and method for user interfaces using remote control devices. More specifically, these user interfaces may be particularly useful for providing an intuitive and user friendly interaction between a user and a device or application using a display, e.g., at a “10 foot” interaction level. The user interfaces may be specifically designed for interaction using a simple remote control device having a limited number of inputs. For example, the simple remote control may include directional inputs (e.g., up, down, left, right), a confirmation input (e.g., ok), and possibly a mute input. These user interfaces may allow a user to quickly browse and filter lists of items, efficiently provide input (e.g., having multiple data types), customize directional and/or mute functionality of the remote control, perform camera control (e.g., for videoconferencing), etc.

Подробнее
Номер записи: 23
27-06-2013 дата публикации

Workflow and in-context e-mail recipient handling

Номер: US20130166663A1
Автор: Brendan C. Fields, Diana J. Schwend, Jorge Pereira
Принадлежит: Microsoft Corp

Various technologies and techniques are disclosed that improve the workflow process for resolving data elements, such as email addresses. These technologies and techniques allow the user to perform such tasks in the same context as the activity or message. In addition, user can start and stop the resolution process at any point in the process of composing the activity or email. The activity cannot be finalized, such as an email message being sent, until all of the data elements are resolved.

Подробнее
Номер записи: 24
04-07-2013 дата публикации

System and method for information identification

Номер: US20130173646A1
Автор: Todd Garrett Simpson
Принадлежит: Zi Corp of Canada Inc

A system and a method of retrieving information is described. In a system according to the invention, software modules may be used to provide the user with information that is most likely to be the information desired.

Подробнее
Номер записи: 25
11-07-2013 дата публикации

Predicting a command in a command line interface

Номер: US20130179460A1
Автор: Ezequiel Cervantes, Jorge D. Acuna, Nedzad Taljanovic
Принадлежит: International Business Machines Corp

An apparatus for predicting a command in a command line interface includes a template command module, a parameter derivation module, and a parameter substitution module. The template command module is configured to determine a template command based on a command line history. The template command includes a command name and a parameter and the command line history includes two or more previously entered commands. The parameter derivation module is configured to determine a parameter derivation rule for deriving the parameter in the template command based on the command line history. The parameter substitution module is configured to substitute a substitute parameter for the parameter of the template command according to the parameter derivation rule.

Подробнее
Номер записи: 26
25-07-2013 дата публикации

Handheld electronic device and method for learning contextual data during disambiguation of text input

Номер: US20130187859A1
Автор: Vadim Fux
Принадлежит: Research in Motion Ltd

A handheld electronic device includes a reduced QWERTY keyboard and is enabled with disambiguation software that is operable to disambiguate text input. In addition to identifying and outputting representations of language objects that are stored in the memory and that correspond with a text input, the device is able to employ contextual data in certain circumstances to prioritize output and to learn new contextual data.

Подробнее
Номер записи: 27
01-08-2013 дата публикации

System and method for prioritizing resumes based on a job description

Номер: US20130198126A1
Автор: Anuj Kumar, SURESH Srinivasan
Принадлежит: FORMCEPT Tech AND SOLUTIONS P Ltd

A method for prioritizing one or more of resumes based on a job description is provided. The method includes (i) processing the job description to extract one or more keywords and a first period, (ii) extracting, from a first resume and a second resume of the one or more resumes, one or more section, one or more events, a first date range, and a second date range, (iii) obtaining a second period and a third period, (iv) comparing, is the first resume and the second resume, the one or more keywords with the one or more events and the first period with the third period to obtain a relevant event and a relevant section, (v) computing a first weight for the first resume and a second weight for the second resume, and (vi) prioritizing the first resume and the second resume based on the first weight and the second weight.

Подробнее
Номер записи: 28
15-08-2013 дата публикации

User Experience with Customized User Dictionary

Номер: US20130211821A1
Автор: Adam D. I. Kramer, Erick Tseng, Luke ST. CLAIR, Shaheen Ashok Gandhi
Принадлежит: Individual

In one embodiment, constructing one or more customized dictionaries for a particular user, each of the customized dictionaries comprising a different blending of one or more frequently used words collected from texts submitted by one or more users; and in response to the user inputting text to an electronic device, selecting one of the customized dictionaries and utilizing it to aid the particular user in inputting text.

Подробнее
Номер записи: 29
15-08-2013 дата публикации

System and method for finding desired results by incremental search using an ambiguous keypad with the input containing orthographic and/or typographic errors

Номер: US20130212097A1
Автор: Gopal Mishrimalji Rajpurohit, Pankaj Garg, Sashikumar Venkataraman
Принадлежит: Veveo LLC

A system for finding and presenting content items in response to keystrokes entered by a user on an input device having a known layout of overloaded keys selected from a set of key layouts. The system includes a database containing content items and terms characterizing the content items; input logic for receiving keystrokes from the user and building a string corresponding to incremental entries by the user, each item in the string having the set of alphanumeric symbols associated with a corresponding keystroke; mapping logic to map the string to the database to find the most likely content items corresponding to the incremental entries, the mapping logic operating in accordance with a defined error model corresponding to the known layout of overloaded keys; and presentation logic for ordering the most likely content items identified by the mapping logic and for presenting the most likely content items.

Подробнее
Номер записи: 30
29-08-2013 дата публикации

Information entry mechanism for small keypads

Номер: US20130226960A1
Автор: Robert B. O'Dell, Roland E. Williams, Todd G. Simpson
Принадлежит: Nuance Communications Inc

Presentation of results of a predictive analysis of text is delayed until entry of the text by a user is paused by a particular amount of time. The results are available for selection by the user for another particular amount of time. After the other particular amount of time is expired, the results are no longer available to for selection. If a particular result is selected, the selected result either replaces or supplements the entered text.

Подробнее
Номер записи: 31
05-09-2013 дата публикации

Method of using visual separators to indicate additional character combinations on a handheld electronic device and associated apparatus

Номер: US20130231915A1
Автор: Sherryl Lee Lorraine Scott, Zaheen Somani
Принадлежит: Research in Motion Ltd

A method and associated apparatus for using visual separators to indicate additional character combination choices from a disambiguation function on a handheld electronic device.

Подробнее
Номер записи: 32
19-09-2013 дата публикации

Method of e-mail address search and e-mail address transliteration and associated device

Номер: US20130246043A1
Автор: Dan Rubanovich, Michael Elizarov, Vadim Fux
Принадлежит: Research in Motion Ltd

An improved method of transliterating non-Latin input within an e-mail address field to the Latin equivalent. A routine in a handheld device is structured to detect a triggering event that indicates an e-mail address is being input into an e-mail address field. Following the triggering event, both prior and subsequent input is transliterated to Latin characters as these characters are required by Internet protocols. The transliteration routine may also be utilized to search an email address book wherein names are recorded using both Latin and non-Latin characters.

Подробнее
Номер записи: 33
26-09-2013 дата публикации

Handheld electronic device including automatic preferred selection of a punctuation, and associated method

Номер: US20130249804A1
Автор: Sherryl Lee Lorraine Scott
Принадлежит: Research in Motion Ltd

A method of enabling input on a handheld electronic device, which includes an input apparatus having a number of input members that are capable of being actuated, wherein at least one of the input members has a plurality of selectable output alternatives, includes detecting as a first input an actuation of an input member, generating a first output, detecting as a second input an actuation of an input member having a plurality of selectable output alternatives comprising at least a primary punctuation and a secondary punctuation, determining that said first output has a predetermined characteristic, preferring as a second output said secondary punctuation, and outputting said second output.

Подробнее
Номер записи: 34
14-11-2013 дата публикации

Providing a vertical candidate bar with an on-screen keyboard

Номер: US20130300664A1
Автор: Morgan H. Winer
Принадлежит: Apple Inc

Methods, systems, computer-readable media, and apparatuses for providing a vertical candidate bar with an on-screen keyboard are presented. In some embodiments, a computing device may display a keyboard on a touch-sensitive display screen. The keyboard may be a split keyboard that includes two panels of keys displayed on opposite sides of the display screen. The device also may display a candidate bar on the display screen, and the candidate bar may be vertically aligned with the keyboard. As character input is received via the keyboard, the device may update the candidate bar to include various candidate characters that are determined based on the received character input.

Подробнее
Номер записи: 35
26-12-2013 дата публикации

Targeted key press zones on an interactive display

Номер: US20130346904A1
Автор: Kevin G. Paterson, Lydia M. Do, Michael J. Fork
Принадлежит: International Business Machines Corp

Method, computer program product, and system for performing an operation to facilitate selection of user interface (UI) elements on an interactive display, the operation including providing at least a first UI element on the interactive display, defining an input area which, when selected, activates the first UI element, determining a first likelihood of the first UI element being selected, and modifying the input area of the first UI element, based on the first likelihood.

Подробнее
Номер записи: 36
26-12-2013 дата публикации

Targeted key press zones on an interactive display

Номер: US20130346905A1
Автор: Kevin G. Paterson, Lydia M. Do, Michael J. Fork
Принадлежит: International Business Machines Corp

Method, computer program product, and system for performing an operation to facilitate selection of user interface (UI) elements on an interactive display, the operation including providing at least a first UI element on the interactive display, defining an input area which, when selected, activates the first UI element, determining a first likelihood of the first UI element being selected, and modifying the input area of the first UI element, based on the first likelihood.

Подробнее
Номер записи: 37
02-01-2014 дата публикации

Handheld electronic device and associated method enabling phonetic text input in a text disambiguation environment and outputting an improved lookup window

Номер: US20140006008A1
Автор: Alexander Kornilovsky, Sergey V. Kolomiets, Vadim Fux
Принадлежит: Research in Motion Ltd

An improved handheld electronic device and associated method enable the phonetic inputting of text using a reduced keyboard and transformation algorithm. The handheld electronic device and method advantageously enable the inputting of languages such as Chinese, Japanese, Korean, and the like without limitation. The transformation algorithm subjects each of a number of linguistic element permutations to an algorithm such as the Maximum Matching Algorithm or other algorithm to generate a string of words and selects one string of words as a default textual output. The character interpretation and variations thereof are output in a lookup component along with a pin and variants thereof to enable the user to select among various character interpretations of an input as well as various alternative pins that correspond with the input.

Подробнее
Номер записи: 38
30-01-2014 дата публикации

Generating string predictions using contexts

Номер: US20140032206A1
Автор: Dmytro Rudchenko, Gleb Krivosheev, Itai Almog, Jason Grieves, Parthasarathy Sundararajan, Tim Paek
Принадлежит: Microsoft Corp

In a mobile device, a context is determined for the mobile device. The context is determined based on a variety of characteristics of the mobile device environment including, for example, the current application being used, any contacts that a user of the mobile device is interacting with or having a conversation with, the current date and/or time, a current topic of the conversation, a current style of the conversation, etc. Based on a set of strings associated with the determined context and user generated text, one or more string predictions are generated for the user generated text. The string predictions may be presented to the user as suggested completions of the user generated text.

Подробнее
Номер записи: 39
06-03-2014 дата публикации

Scoring predictions based on prediction length and typing speed

Номер: US20140067372A1
Автор: Donald Somerset Mcculloch Mckenzie, Jason Tyler Griffin, Jerome Pasquero
Принадлежит: Research in Motion Ltd

A method that includes receiving an input, determining, by the processor, a likelihood that a predicted string associated with the received input matches an intended input string, where the determination is a function of at least one of a length of the predicted string and a typing speed associated with the received input, and displaying the predicted string.

Подробнее
Номер записи: 40
13-03-2014 дата публикации

Static security analysis using a hybrid representation of string values

Номер: US20140075562A1
Автор: Marco Pistoia, Omer Tripp, Salvatore A. GUARNIERI
Принадлежит: International Business Machines Corp

Systems for constructing hybrid string representations include a string parser configured to parse received string information to produce one or more string components, a database configured to store a set of known concretizations, and a processor configured to compare the one or more string components to the set of known concretizations to determine string components that may be represented concretely, to abstract all string components that could not be represented concretely, and to create a hybrid string representation that includes at least one concrete string component and at least one abstracted string component.

Подробнее
Номер записи: 41
06-01-2022 дата публикации

Document search method, document search system, program, and non-transitory computer readable storage medium

Номер: US20220004570A1
Автор: Shoko SAITO, Tatsuya Okano
Принадлежит: Semiconductor Energy Laboratory Co Ltd

A similar document is retrieved in units of blocks of a document. Highly accurate document search is performed. A specific text block is searched for in a plurality of text blocks created by dividing each of a plurality of search target documents. A first search text block, which is a part of a search document, is prepared; full-text search is performed by using at least some of the plurality of text blocks as a first target and using the first search text block as a search criterion to calculate first relevance of each text block included in the first target to the first search text block; a second target is determined from the first target depending on a level of the first relevance; first similarities of each sentence included in the first search text block to sentences included in the second target are calculated; and at least one text block similar to the first search text block is retrieved using the first similarities.

Подробнее
Номер записи: 42
06-01-2022 дата публикации

ELECTRONIC DEVICE AND METHOD FOR CONVERTING SENTENCE BASED ON A NEWLY COINED WORD

Номер: US20220004701A1
Автор: CHOI Youngchan, GIL Honghee, LEE Changki, LEE Saegyeol, Song Chiwoo
Принадлежит:

Provided is an electronic device including a communication module, a memory, and at least one processor operatively connected to the communication module and the memory, and the memory stores instructions configured to, when executed, enable the at least one processor to: receive a first sentence via the communication module; identify a first newly coined word included in the first sentence; obtain a second sentence by identifying a first alternative word corresponding to the first newly coined word, and replacing the first newly coined word in the first sentence with the first alternative word; obtain a third sentence by correcting a grammatical error in the second sentence based on the first alternative word occurring the grammatical error when replacing the first newly coined word; and transmit the third sentence to an external device via the communication module. Other embodiments can be made. 1. An electronic device comprising:a communication module;a memory; andat least one processor operatively connected to the communication module and the memory, receive a first sentence via the communication module;', 'identify a first newly coined word included in the first sentence;', 'obtain a second sentence by identifying a first alternative word corresponding to the first newly coined word and replacing the first newly coined word in the first sentence with the first alternative word;', 'obtain a third sentence by correcting a grammatical error in the second sentence based on the first alternative word occurring the grammatical error when replacing the first newly coined word; and', 'transmit the third sentence to an external device via the communication module., 'wherein the memory stores instructions configured to, when executed, enable the at least one processor to2. The electronic device of claim 1 , wherein:the memory comprises a newly coined word database including words corresponding to newly coined words, andthe instructions are further configured to, when ...

Подробнее
Номер записи: 43
06-01-2022 дата публикации

SYSTEM AND METHOD FOR DETECTING UNDESIRABLE AND POTENTIALLY HARMFUL ONLINE BEHAVIOR

Номер: US20220004710A1
Автор: LELIWA GNIEWOSZ, Wroczynski Michal
Принадлежит: Samurai Labs sp. z o.o.

Embodiments include computer-implemented methods and systems for detecting undesirable and potentially harmful online behavior. The embodiments described and claimed could also be applied to detecting any other type of online behavior to be detected, but the descriptions focuses on detecting online violence. More particularly, the embodiments disclosed relate to detecting online violence using symbolic methods of natural language processing (NLP) that utilize and govern the usage of: 1) syntactic parser for analyzing grammatical context of the input text data, 2) unsupervised learning methods for improving selected aspects of the system and adjusting the system to new data sources and guidelines, and 3) statistical classifiers for resolving specific well-defined sub-tasks, in which statistical approaches surpass the symbolic methods. 1. A system for detecting one or more predetermined online behaviors , the system comprising: the at least one processor receiving plain text input;', normalization comprises the process of transforming the plain text input into a single predetermined canonical form to generate normalized text;', 'correction comprises the process of revising the normalized text in order to correct misspellings and any other types of intentional and non-intentional errors to generate corrected text; and', 'transformation comprises the process of revising the corrected text in order to replace, remove or add specific text fragments to generate transformed text that is optimally phrased for detecting one or more predetermined online behaviors; and, 'the at least one processor performing a plurality of functional modules, the plurality of functional modules comprising one or more of a text preparation module, a normalization module, and a correction and transformation module, wherein,'}, each contextual model comprises a detection model for detecting a single well-defined type of online violence; and', 'each contextual model classifies text as containing or ...

Подробнее
Номер записи: 44
06-01-2022 дата публикации

COGNITIVE ANALYSIS OF A PROJECT DESCRIPTION

Номер: US20220004951A1
Автор: Halappa Venkatesh, Santhar Sathya, Scriven Gerhardt Jacobus
Принадлежит: INTERNATIONAL BUSINESS MACHINES CORPORATION

An embodiment includes extracting a capability from a dataset representative of a project description of a proposed project using a first machine learning process to form a cluster representative of the capability. The embodiment assigns the capability to a first node of a business operations graph based on a classification result of the capability by a second machine learning process. The embodiment generates a visual indicator based, at least in part, on the assigning of the capability to the first node. The embodiment generates the visual indicator by a process comprising generating a first visual indicator of the capability being assigned to the first node, and a second visual indicator of a development sequence for the capability relative to another capability from the project description based at least in part on an association from the business operations graph between the first node and a second node of the graph. 1. A computer implemented method comprising:extracting a capability from a dataset representative of a project description of a proposed project using a first machine learning process to form a cluster representative of the capability;assigning the capability to a first node of a business operations graph based on a classification result of the capability by a second machine learning process; andgenerating a visual indicator based, at least in part, on the assigning of the capability to the first node,wherein the generating of the visual indicator comprises generating a first visual indicator of the capability being assigned to the first node and a second visual indicator of a development sequence for the capability relative to another capability from the project description based at least in part on an association from the business operations graph between the first node and a second node of the business operations graph.2. The method of claim 1 , further comprising parsing a plurality of documents to extract the dataset representative of the ...

Подробнее
Номер записи: 45
06-01-2022 дата публикации

METHOD AND DEVICE FOR TEXT-BASED IMAGE GENERATION

Номер: US20220005235A1
Автор: GONG Bo, GOU Yuchuan, HAN Mei, Li Minghao, WU Qiancheng
Принадлежит:

A method and device for image generation are provided. The method includes: obtaining a text describing a content of an image to be generated; extracting, using a text encoder, a text feature vector from the text; determining a semantic mask as spatial constraints of the image to be generated; and automatically generating the image using a generative adversarial network (GAN) model according to the semantic mask and the text feature vector. 1. A method for image generation , applied to a computing device , comprising:obtaining a text describing a content of an image to be generated;extracting, using a text encoder, a text feature vector from the text;determining a semantic mask as spatial constraints of the image to be generated; andautomatically generating the image using a generative adversarial network (GAN) model according to the semantic mask and the text feature vector.2. The method according to claim 1 , wherein the semantic mask is a binary image describing a shape of the content.3. The method according to claim 1 , wherein determining the semantic mask comprises:determining, from a dataset, a pre-existing mask as the semantic mask.4. The method according to claim 1 , wherein the text feature vector includes a sentence feature vector describing global feature of a whole sentence of the text; and obtaining a modified sentence feature vector by concatenating the sentence feature vector and a random latent vector; and', 'inputting the modified sentence feature vector to the GAN model to generate the image., 'the method further comprises5. The method according to claim 4 , wherein determining the semantic mask comprises:automatically determining, by a self-attention generator, the semantic mask according to the modified sentence feature vector.6. The method according to claim 4 , wherein:the GAN model includes multiple generators corresponding to multiple resolutions arranged in series from a lower resolution to a higher resolution; and determining, using a ...

Подробнее
Номер записи: 46
06-01-2022 дата публикации

CAPTION CUSTOMIZATION AND EDITING

Номер: US20220005477A1
Автор: "ORourke Ryan Michael", Guo Qikun, Ma Shannon, Mroz Martin, Williams Aaron, Zeng Sharon
Принадлежит:

Techniques are described that enable a user to edit and customize captions generated by a social networking system, such as transcriptions of an audio clip. In some cases, a social networking system receives, from a first user account, a video and an audio clip associated with the video, and determines that the audio clip contains speech. The social networking system may leverage a speech-to-text component to generate a first text caption based at least in part on the speech in the audio clip. The social networking system provides the first text caption to the first user account, and receives a user input to modify a word included in the first text caption. The social networking system generates a second text caption based at least in part on the user input, and provides the video, including the second text caption, to a second user account. 1. A method comprising:receiving, from a first user account on a social networking system, a video and an audio clip associated with the video;determining that the audio clip contains speech;generating, by a speech-to-text component and based at least in part on the speech in the audio clip, a first text caption corresponding to the speech;providing the first text caption to the first user account;receiving, from the first user account, a user input to modify a portion of the first text caption;generating a second text caption based at least in part on the user input; andproviding the video, including the second text caption, to a second user account on the social networking system.2. The method of claim 1 , wherein generating the first text caption comprises generating claim 1 , by the speech-to-text component claim 1 , a translation of the speech claim 1 , the method further comprising:determining that a word included in the translation is excluded from being output in automatically-generated text captions by the social networking system; andreplacing the word in the translation with a text string that is different from text ...

Подробнее
Номер записи: 47
06-01-2022 дата публикации

Group Chat Voice Information Processing Method and Apparatus, Storage Medium, and Server

Номер: US20220005483A1
Автор: YU Mingzu
Принадлежит:

A group chat voice information processing method and apparatus, a storage medium and a server are provided. The method includes: receiving first group chat voice information of a first user; determining a second user associated with the first group chat voice information; and when the first group chat voice information is sent to a target chat group, marking the second user as a target user of the first group chat voice information. 1. A group chat voice information processing method , comprising:receiving first group chat voice information of a first user;determining a second user associated with the first group chat voice information; andwhen the first group chat voice information is sent to a target chat group, marking the second user as a target user of the first group chat voice information.2. The method as claimed in claim 1 , wherein determining the second user associated with the first group chat voice information comprises:acquiring user information of each user in the target chat group; anddetermining the second user associated with the first group chat voice information in the target chat group according to the user information of each user.3. The method as claimed in claim 2 , wherein determining the second user associated with the first group chat voice information in the target chat group according to the user information of each user comprises:performing voice recognition on the first group chat voice information to convert into text information corresponding to the first group chat voice information;processing the text information to extract information meeting a preset rule from the text information;inquiring user information matched with the text information in the user information of each user according to the information meeting the preset rule; anddetermining a user corresponding to the user information matched with the text information as the second user.4. The method as claimed in claim 1 , wherein marking the second user as the target user of ...

Подробнее
Номер записи: 48
04-01-2018 дата публикации

Task-oriented messaging system

Номер: US20180004731A1
Автор: Asima Silva, Christopher D. Johnson, James J. Stadtmiller, Jonathan F. Brunn, Jonathan T. Coffey, Marit L. Imsdahl, Mark A. DuFresne, Razeyah Stephen, Yuriy B. Veytsman
Принадлежит: International Business Machines Corp

Task-oriented messages are presented to a user in an interactive format for disposition. Natural language processing techniques parse task-oriented messages for individual tasks, such as assignments, information requests, and requests for approval or authorization. A user interface provides a recipient of a task-oriented message with selectable tasks for individual, or group, disposition, such as respond, defer, delegate, mark answered, and ignore. Recipients are notified if an incomplete response is generated, such as when an identified task is not dispositioned.

Подробнее
Номер записи: 49
07-01-2021 дата публикации

Method for making music recommendations and related computing device, and medium thereof

Номер: US20210004402A1
Автор: Bo Chen, Hanjie WANG, Hao YE, Yan Li
Принадлежит: Tencent Technology Shenzhen Co Ltd

This application discloses a method for making music recommendations. The method for making music recommendations is performed by a server device. The method includes obtaining a material for which background music is to be added; determining at least one visual semantic tag of the material, the at least one visual semantic tag describing at least one characteristic of the material; identifying a matched music matching the at least one visual semantic tag from a candidate music library; sorting the matched music according to user assessing information of a user corresponding to the material; screening the matched music based on a sorting result and according to a preset music screening condition; and recommending matched music obtained through the screening as candidate music of the material.

Подробнее
Номер записи: 50
04-01-2018 дата публикации

System performance logging of complex remote query processor query operations

Номер: US20180004796A1
Автор: Charles Wright, David R. Kent, IV, Radu Teodorescu, Ryan CAUDY
Принадлежит: Illumon LLC

Described are methods, systems and computer readable media for performance logging of complex query operations.

Подробнее
Номер записи: 51
02-01-2020 дата публикации

Social autonomous agent implementation using lattice queries and relevancy detection

Номер: US20200004813A1
Автор: Boris Galitsky
Принадлежит: Oracle International Corp

Techniques for computer-generated conversation are disclosed. In an example, a method identifies text postings from a conversation. The method creates, for each text fragment of each text posting, a syntactic tree and a discourse tree. The method creates parse thickets, each parse thicket including the syntactic tree and discourse tree of a unique pair of text postings. The method extracts, from each parse thicket, a common text segment and obtains a set of candidate search results by providing the common text segments to a search engine. The candidate search results can be further refined for relevancy and mental state and posted as a response to a conversation.

Подробнее
Номер записи: 52
07-01-2021 дата публикации

On-device lightweight natural language understanding (nlu) continual learning

Номер: US20210004532A1
Автор: Hongxia Jin, Xiangyu Zeng, Yilin Shen
Принадлежит: SAMSUNG ELECTRONICS CO LTD

A method includes obtaining, using at least one processor of an electronic device, a base model trained to perform natural language understanding. The method also includes generating, using the at least one processor, a first model expansion based on knowledge from the base model. The method further includes training, using the at least one processor, the first model expansion based on first utterances without modifying parameters of the base model. The method also includes receiving, using the at least one processor, an additional utterance from a user. In addition, the method includes determining, using the at least one processor, a meaning of the additional utterance using the base model and the first model expansion.

Подробнее
Номер записи: 53
07-01-2021 дата публикации

SYSTEM AND METHOD FOR TEXT-ENABLED AUTOMATED AGENT ASSISTANCE WITHIN A CLOUD-BASED CONTACT CENTER

Номер: US20210004536A1
Автор: Adibi Jafar, Antunes Bruno, Carmo Joao, Costa Marco, Kannan Charanya, Paiva Tiago
Принадлежит:

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing. 1. A method , comprising:receiving a text communication from a customer;performing inference processing on the text to determine a customer intent;automatically analyzing the text to determine a subject of the text communication and key terms associated with the subject;automatically parsing a knowledgebase using the key terms for at least one responsive answer associated with the subject; andproviding the solution to an agent in a unified interface during the communication with the customer.21. The method of , further comprising:querying a customer relationship management (CRM) platform/a customer service management (CSM) platform using the key terms; anddisplaying responsive results from the CRM/CSM in the second field in the unified interface.3. The method of claim 1 , further comprising:querying a database of customer-agent transcripts using the key terms; anddisplaying responsive results from the database of customer-agent transcripts in the second field in the unified interface.4. The method of claim 1 , wherein the method is performed in real-time as the customer communication progresses with the agent.5. The method of claim 1 , further comprising concurrently displaying to the agent the text in a first field of the unified interface and the solution in a second field of the unified interface.6. The method of claim 1 , further comprising authenticating the customer claim 1 , predicting a customer gender claim 1 , predicting a customer age category claim 1 , predicting a customer accent claim 1 , and predict customer demographics. ...

Подробнее
Номер записи: 54
13-01-2022 дата публикации

ELECTRONIC DEVICE FOR CONVERTING HANDWRITING TO TEXT AND METHOD THEREFOR

Номер: US20220012409A1
Автор: KIM Dohyeon, LEE Donghyuk, SHIN Jinsu
Принадлежит:

An electronic device is provided. The electronic device includes a display including a sensing panel that senses a handwriting input, at least one processor operatively connected to the display, and memory storing instructions that, when executed by the at least one processor, cause the electronic device to acquire the handwriting input through the display, wherein the handwriting input includes a first handwriting input corresponding to a first line and a second handwriting input corresponding to a second line, determine whether to merge the second line into the first line or to maintain the second line based on whether at least one of the first handwriting input and/or the second handwriting input satisfies a specified condition, convert the handwriting input where the merging or the maintenance of the second line is applied into text, and display the converted text through the display. 1. An electronic device comprising:a display comprising a sensing panel configured to sense a handwriting input;at least one processor operatively connected to the display; and acquire the handwriting input to the display, the handwriting input comprising a first handwriting input corresponding to a first line and a second handwriting input corresponding to a second line,', 'based on whether at least one of the first handwriting input or the second handwriting input satisfies a specified condition, determine to merge the second line into the first line or maintain the second line,', 'convert the handwriting input into text by merging the second line into the first line or maintaining the second line, and', 'control the display to display the converted handwriting input., 'memory storing instructions which, when executed by the at least one processor, cause the electronic device to2. The electronic device of claim 1 , wherein the instructions claim 1 , when executed claim 1 , further cause the electronic device to claim 1 , based on the second line being merged into the first line ...

Подробнее
Номер записи: 55
04-01-2018 дата публикации

Content leakage protection

Номер: US20180004975A1
Автор: John Bryan
Принадлежит: Sophos Ltd

Methods and systems for identifying content of interest. Accessed textual information is processed by at least one of character unification, phrase unification, and concept unification. A configured processor executes at least one predefined rule to determine whether the unified content includes certain types of information. Unified content that matches may be subject to further action such as alerts, encryption, logging, etc.

Подробнее
Номер записи: 56
07-01-2021 дата публикации

System and method for automated agent assistance within a cloud-based contact center

Номер: US20210004817A1
Автор: Bruno Antunes, Charanya Kannan, Jafar Adibi, Joao Carmo, Marco Costa, Tiago Paiva
Принадлежит: Talkdesk Inc

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

Подробнее
Номер записи: 57
07-01-2021 дата публикации

System and method for automated scheduling using agent assist within a cloud-based contact center

Номер: US20210004824A1
Автор: Bruno Antunes, Charanya Kannan, Jafar Adibi, Joao Carmo, Marco Costa, Tiago Paiva
Принадлежит: Talkdesk Inc

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

Подробнее
Номер записи: 58
07-01-2021 дата публикации

System and method for speech-enabled automated agent assistance within a cloud-based contact center

Номер: US20210005206A1
Автор: Bruno Antunes, Charanya Kannan, Jafar Adibi, Joao Carmo, Marco Costa, Tiago Paiva
Принадлежит: Talkdesk Inc

Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.

Подробнее
Номер записи: 59
01-01-2015 дата публикации

Detect and Automatically Hide Spoiler Information in a Collaborative Environment

Номер: US20150007014A1
Автор: Corville O. Allen
Принадлежит: International Business Machines Corp

An approach is provided to detect and hide spoiler information. In the approach, potential spoiler content included user text entries submitted to a collaborative environment are automatically detected. The system inhibits display of the potential spoiler content from the collaborative environment in response to the detection.

Подробнее
Номер записи: 60
02-01-2020 дата публикации

Voice interaction method and device

Номер: US20200005780A1
Автор: Yongshuai LU
Принадлежит: Baidu Online Network Technology Beijing Co Ltd

Embodiments of the present disclosure provide voice interaction method and device. The method includes: determining whether a first query statement currently received is a query statement first received within a preset time period; if not, obtaining a second query statement, where the second query statement is a query statement lastly received before receiving the first query statement; obtaining a third sentence vector according to a first sentence vector of the first query statement and a second sentence vector of the second query statement; and obtaining, from a bottom corpus, a first question and answer result corresponding to a fourth sentence vector a similarity between which and the third sentence vector satisfies a preset condition, and returning the first question and answer result. The method provided in the embodiment can return a bottom reply irrelevant to the query statement to the user, thereby improving the user experience.

Подробнее
Номер записи: 61
20-01-2022 дата публикации

METHOD FOR INFORMATION PROCESSING IN USER CONVERSATION, ELECTRONIC DEVICE AND STORAGE MEDIUM THEREOF

Номер: US20220019747A1
Автор: Guo Zhen, LIU Zhanyi, WU Wenquan
Принадлежит:

A method for information processing in a user conversation, an electronic device and a storage medium thereof, which relate to the field of artificial intelligence and the natural language processing field, are disclosed. The method may include: acquiring conversation preceding information in a conversation between a first user and a second user; acquiring a target conversation strategy employed by the first user; generating initial reply content with a pre-trained response generating model according to the target conversation strategy and the conversation preceding information; and sending the initial reply content to a client of the first user, so as to display the initial reply content on a conversation interface of the first user with the second user. 1. A method for information processing in a user conversation , comprising:acquiring conversation preceding information in a conversation between a first user and a second user;acquiring a target conversation strategy employed by the first user;generating initial reply content with a pre-trained response generating model according to the target conversation strategy and the conversation preceding information; andsending the initial reply content to a client of the first user, so as to display the initial reply content on a conversation interface of the first user with the second user.2. The method of claim 1 , wherein acquiring the target conversation strategy employed by the first user comprises:acquiring the target conversation strategy selected by the first user from a preset conversation strategy set.3. The method of claim 1 , wherein acquiring the target conversation strategy employed by the first user comprises:predicting the target conversation strategy with a pre-trained conversation-strategy predicting model and historical conversation information of the first and second users.4. The method of claim 1 , further comprising:transforming a style of the initial reply content to obtain target reply content.5. ...

Подробнее
Номер записи: 62
27-01-2022 дата публикации

METHOD AND SYSTEM FOR EXTRACTING KEYWORDS FROM TEXT

Номер: US20220027558A1
Автор: AIKOH Kazuhide, BELTRAN-GUERRERO Jose Luis, PENG Shouchun, SUGIMOTO Ken
Принадлежит:

Example implementations described herein involve extracting keywords and dependency information from a text; and generating a co-occurrence dictionary for the text, the generating the co-occurrence dictionary involving selecting ones of the keywords for inclusion in the co-occurrence dictionary based on a number of times the ones of the keywords satisfy the dependency rules; determining for the selected ones of the keywords included in the co-occurrence dictionary, surrounding words to be associated with the selected ones of the keywords in the co-occurrence dictionary based on a number of instances of co-occurrence of the surrounding words with the selected ones of the keywords; and generating weights for each of the selected ones of the keywords in the co-occurrence dictionary based on a number of the surrounding words associated with the selected ones of the keywords. 1. A method , comprising:extracting keywords and dependency information from a text; and selecting ones of the keywords for inclusion in the co-occurrence dictionary based on a number of times the ones of the keywords satisfy the dependency rules;', 'determining for the selected ones of the keywords included in the co-occurrence dictionary, surrounding words to be associated with the selected ones of the keywords in the co-occurrence dictionary based on a number of instances of co-occurrence of the surrounding words with the selected ones of the keywords; and', 'generating weights for each of the selected ones of the keywords in the co-occurrence dictionary based on a number of the surrounding words associated with the selected ones of the keywords., 'generating a co-occurrence dictionary for the text, the generating the co-occurrence dictionary comprising2. The method of claim 1 , further comprising applying labels on each word of text claim 1 , wherein the dependency rules comprises regex patterns of labels indicative of keywords to be included in the co-occurrence dictionary claim 1 , wherein co- ...

Подробнее
Номер записи: 63
27-01-2022 дата публикации

Automatic lexical sememe prediction system using lexical dictionaries

Номер: US20220027567A1
Автор: Chao WENG, Chengzhu YU, Dong Yu, Kun Xu
Принадлежит: Tencent America LLC

Method and apparatus for automatically predicting lexical sememes using a lexical dictionary, comprising inputting a word, retrieving the word's semantic definition and sememes corresponding to the word from an online dictionary, setting each of the retrieved sememes as a candidate sememe, inputting the word's semantic definition and candidate sememe, and estimating the probability that the candidate sememe can be inferred from the word's semantic definition.

Подробнее
Номер записи: 64
27-01-2022 дата публикации

MEDICAL SCAN NATURAL LANGUAGE ANALYSIS SYSTEM, METHODS AND ARTICLES

Номер: US20220028530A1
Автор: Basham Brian, Bernard Devon, Lyman Kevin, MCKINNEY Scott, Yao Li
Принадлежит: Enlitic, Inc.

A medical report natural language model includes an artificial neural network implemented via the processor and is trained based a plurality of medical reports wherein each of the medical reports is mapped to at least one medical code of a plurality of medical codes and further based a plurality of medical condition terms from a plurality of alias mapping pairs, wherein each of the plurality of medical condition terms are unique, wherein each of the plurality of medical condition terms indicates a corresponding medical condition and wherein each of the plurality of alias mapping pairs includes a one of the plurality of medical condition terms and a corresponding single one of the plurality of medical codes that is a deterministic function of the one of the plurality of medical condition terms and wherein the plurality of alias mapping pairs includes two or more alias mapping pairs that map a corresponding two or more of the plurality of medical condition terms to a same one of the plurality of medical codes. A system operates by determining a first medical code of the plurality of medical codes utilizing the medical report natural language model on the first medical report by: recognizing, via the artificial neural network of the medical report natural language model, a first medical condition term of the plurality of medical condition terms in the first medical report; and determining the first medical code of the plurality of medical codes, based on the plurality of alias mapping pairs, wherein the determining the first medical code includes identifying a first alias mapping pair of the plurality of alias mapping pairs that pairs the first medical condition term deterministically to the first medical code; and mapping the first medical code of the plurality of medical codes and the first medical condition term of the plurality of medical condition terms to a first medical scan corresponding to the first medical report. 1. A medical scan natural language analysis ...

Подробнее
Номер записи: 65
12-01-2017 дата публикации

Contact-Based Predictive Response

Номер: US20170011303A1
Автор: Keir Finlow-Bates, Koushik Annapureddy
Принадлежит: Qualcomm Inc

Various embodiments include methods implemented on a mobile communication device for using a contact-based predictive response database on a communication device. The methods include determining communication context information from a communication exchange between a user using the communication device and a contact, selecting a predictive response database associated with the contact, determining a suggested communication element from the predictive response database based on a prior communication element identified from the communication exchange and the communication context information, and providing the suggested communication element to the user.

Подробнее
Номер записи: 66
08-01-2015 дата публикации

Partial gesture text entry

Номер: US20150012873A1
Автор: Shumin Zhai, Xiaojun Bi, Yu Ouyang
Принадлежит: Google LLC

A graphical keyboard including a number of keys is output for display at a display device. The computing device receives an indication of a gesture to select at least two of the keys based at least in part on detecting an input unit at locations of a presence-sensitive input device. In response to the detecting and while the input unit is detected at the presence-sensitive input device: the computing device determines a candidate word for the gesture based at least in part on the at least two keys and the candidate word is output for display at a first location of the output device. In response to determining that the input unit is no longer detected at the presence-sensitive input device, the displayed candidate word is output for display at a second location of the display device.

Подробнее
Номер записи: 67
14-01-2021 дата публикации

CONTENT MANIPULATION USING SWIPE GESTURE RECOGNITION TECHNOLOGY

Номер: US20210011600A1
Автор: HOUCK Todd, MANOFF Robert S., SHAY Caleb K., SQUIRE Jesse D.
Принадлежит:

A method of manipulation of content provided by a hosting server using swipe gesture recognition on a user device having a touch input display. The method includes storing the content, combined with a swipe gesture recognition module to form a content package, on the hosting server. The swipe gesture recognition module is associated with at least one displayable content element of the content. The method further includes receiving, at the hosting server, a request for the content package from the user device and transmitting the content package from the hosting server to the user device for display by an application running on the user device. A defined action is applied to the at least one displayable content element if it is determined that a swipe gesture has occurred on the at least one displayable content element. 1. A method for manipulation of content provided by a hosting server using swipe gesture recognition on a user device having a touch input display , the method comprising:storing the content, combined with a swipe gesture recognition module to form a content package, on the hosting server, wherein the swipe gesture recognition module is associated with at least one displayable content element of the content;receiving, at the hosting server, a request for the content package from the user device; andtransmitting the content package from the hosting server to the user device for display by an application running on the user device,wherein the swipe gesture recognition module is configured to perform swipe gesture recognition when the at least one displayable content element is displayed on the user device, the swipe gesture recognition comprising:receiving touch input data from the touch input display of the user device,accessing, using the swipe gesture recognition module, a swipe gesture determination module stored on the hosting server or a second server to analyze the touch input data to determine whether a swipe gesture has occurred on the at least ...

Подробнее
Номер записи: 68
10-01-2019 дата публикации

Selection biasing

Номер: US20190012064A1
Автор: Diego Melendo Casado, Glen Shires, Jakob Nicolaus Foerster
Принадлежит: Google LLC

In some implementations, data indicating a touch received on a proximity-sensitive display is received while the proximity-sensitive display is presenting one or more items. In one aspect, the techniques describe may involve a process for disambiguating touch selections of hypothesized items, such as text or graphical objects that have been generated based on input data, on a proximity-sensitive display. This process may allow a user to more easily select hypothesized items that the user may wish to correct, by determining whether a touch received through the proximity-sensitive display represents a selection of each hypothesized item based at least on a level of confidence that the hypothesized item accurately represents the input data.

Подробнее
Номер записи: 69
10-01-2019 дата публикации

Typing assistance for editing

Номер: US20190012076A1
Автор: Andrew Douglas Peterson, Drew Elliott Linerud, Eric Norman Badger, Itai Almog, Kenneth R. Walters, Parthasarathy Sundararajan, Shawna Julie Davis, Timothy S. Paek, Tirthankar Sengupta
Принадлежит: Microsoft Technology Licensing LLC

Apparatus and methods are disclosed for providing feedback and guidance to touch screen device users to improve the text entry user experience and performance. According to one embodiment, a method comprises receiving a text entry, receiving input on a touch screen in the form of a first single touch input located over a word of previously entered text, and presenting the user with one or more suggestion candidates indicated possible replacement words related to the selected word. The user can then select one of the suggestion candidates using a second single touch input to replace the selected word with a word associated with the selected suggestion candidate.

Подробнее
Номер записи: 70
14-01-2021 дата публикации

Defect description generation for a software product

Номер: US20210011713A1
Автор: Chong Liu, Juan Wu, Linbo WANG
Принадлежит: International Business Machines Corp

The present invention provides a method, computer system and computer program product for generating a defect description. According to the method, one or more keywords from a user for depicting a defect encountered when using a software product are received. A search for one or more terms matching at least one of the keywords and a path corresponding to the one or more terms in an operation map is conducted, wherein the operation map includes terms and paths describing all possible operations of a software product based on a user interface of the software product. And in response to the one or more terms matching the at least one of the keywords and a corresponding path are searched out, a defect description based on the one or more matched terms, the corresponding path and the received keywords is generated.

Подробнее
Номер записи: 71
14-01-2021 дата публикации

Extracting Structured Data from Handwritten and Audio Notes

Номер: US20210012062A1
Автор: "ONEILL Chris", Buryak IIya, Galaktionova Natalia, Gorbatov Boris, Livshitz Eugene, Malcolm Andrew, Pashintsev Alexander
Принадлежит:

This application is directed to recognizing unstructured information based on hints provided by structured information. A computer system obtains unstructured information collected from a handwritten or audio source, and identifies one or more terms from the unstructured information. The one or more terms includes a first term that is ambiguous. The computer system performs a recognition operation on the first term to derive a first plurality of candidate terms for the first term, and obtains first contextual information from an information template associated with the unstructured information. In accordance with the first contextual information, the computer system selects a first answer term from the first plurality of candidate terms, such that the first term is recognized as the first answer term. 1. (canceled)2. A computer-implemented method , comprising: obtaining unstructured information collected from a handwritten or audio source;', 'identifying one or more terms from the unstructured information, the one or more terms including at least one ambiguous term;', 'performing a recognition operation on a first term from the unstructured information to derive a first plurality of candidate terms for the first term;', 'obtaining contextual information from an information template associated with the unstructured information;', 'selecting a first answer term from the first plurality of candidate terms based on the contextual information; and', 'associating the first answer term with the information template., 'at a computer system having one or more processors and memory storing one or more programs executed by the one or more processors3. The method of claim 2 , further comprising:performing a recognition operation on a second term to derive a second plurality of candidate terms, wherein the second term is adjacent to the first term;obtaining contextual information from an information template associated with the unstructured information;selecting a second answer ...

Подробнее
Номер записи: 72
14-01-2021 дата публикации

Recording medium recording complementary program, complementary method, and information processing device

Номер: US20210012064A1
Автор: Kiyonori Morioka, Sayuri Nakayama, Taro Togawa
Принадлежит: Fujitsu Ltd

A recording medium stores a program causing a computer to execute processing including: specifying demonstrative words from character information; extracting a first feature of a first referent corresponding to a first demonstrative word, and a second feature of a second referent corresponding to a second demonstrative word; calculating a similarity between the first feature and the second feature corresponding to a same one of the genres; calculating a degree of attention based on information out of the voice information, the character information, and the image information; selecting at least genres based on the similarity and the degree of attention; creating a first complementary word obtained by modifying a name of the first referent with the first feature corresponding to each of the selected genres; and creating a second complementary word obtained by modifying a name of the second referent with the second feature corresponding to each of the selected genres.

Подробнее
Номер записи: 73
14-01-2021 дата публикации

Methods Circuits Devices Systems and Functionally Associated Machine Executable Code for Generating a Scene Guidance Instruction

Номер: US20210012065A1
Автор: Shmuel Yaniv
Принадлежит:

Disclosed are methods, circuits, devices, systems and functionally associated machine executable code for generating a scene interaction guidance instruction. One or more sensors directed towards an area of the interaction capture information about messages generated by an agent and a subject participants, wherein the captured messages can be verbal or visual in format. A computing platform receives and processes the captured information using a computerized message interpreter to extract meaning from the captured messages information; and a message impact assessment module to characterize, based on the extracted meaning, an impact of each agent generated message on the subject, wherein each impact characterization indicates whether a respective message brought the interaction closer to, or further away from, the specific objective. 1. A system for assessment of an in-person interaction between a subject and an agent having a specific objective for said interaction , wherein said system comprises:one or more sensors directed towards an area of the interaction and adapted to capture information about messages generated by the agent and the subject, wherein the captured messages can be verbal or visual in format; a computerized message interpreter adapted to extract meaning from the captured messages information; and', 'a message impact assessment module to characterize, based on the extracted meaning, an impact of each agent generated message on the subject, wherein each impact characterization indicates whether a respective message brought the interaction closer to, or further from, the specific objective., 'a computing platform to receive and process the captured information using2. The system according to claim 1 , wherein said computer platform further includes a message classification logic for classifying claim 1 , based on the extracted meaning claim 1 , a specific interaction message claim 1 , as expressed by either the agent or subject interacting.3. The ...

Подробнее
Номер записи: 74
14-01-2021 дата публикации

DETERMINING ERRONEOUS CODES IN MEDICAL REPORTS

Номер: US20210012066A1
Автор: JIA Yugang, Sevenster Merlijn, WANG Xin
Принадлежит:

Systems for determining an erroneous code in a medical report comprising a plurality of codes, each code representing a comment in the medical report the system, comprise a memory comprising instruction data representing a set of instructions and a processor configured to communicate with the memory and to execute the set of instructions. The set of instructions, when executed by the processor, cause the processor to determine a respective vector representation for each of the plurality of codes in the medical report, wherein relative values of any selected pair of vector representations are correlated with a co-occurrence of the corresponding codes in a set of reference medical reports. The set of instructions when exectured by the processor further cause the processor to determine an erroneous code in the medical report, based on the vector representations. 1. A computer implemented method of determining an erroneous code in a medical report , wherein the medical report comprises a plurality of codes , each code representing a comment in the medical report , the method comprising:determining a respective vector representation for each of the plurality of codes in the medical report, wherein relative values of any selected pair of vector representations are correlated with a co-occurrence of the corresponding codes in a set of reference medical reports; anddetermining an erroneous code in the medical report, based on the vector representations.2. A method as in wherein determining a respective vector representation for each of the plurality of codes comprises: 'determining a plurality of word vector representations, the plurality of word vector representations comprising a vector representation for each word in the comment represented by the code, wherein relative values of any selected pair of vector representations in the plurality of word vector representations are correlated with a co-occurrence of the corresponding words in the set of reference medical reports ...

Подробнее
Номер записи: 75
14-01-2021 дата публикации

Expanding knowledge graphs using external data source

Номер: US20210012218A1
Автор: Kyle Croutwater, Le Zhang, Vikrant Verma, Zhe Zhang
Принадлежит: International Business Machines Corp

An approach is provided that selects an original entity from an original knowledge graph. The approach then accesses a data source that is external to the original knowledge graph, such as an online encyclopedia. An entity in the data source is identified based on the entity matching the original entity. A new relation is then identified in the data source between the identified entity and a new entity with the new entity being absent from the original knowledge graph. An expanded knowledge graph is then generated with the expanded knowledge graph formed by adding the new entity to the original knowledge graph.

Подробнее
Номер записи: 76
14-01-2021 дата публикации

INTELLIGENT MEETING CLASSIFIER

Номер: US20210012257A1
Автор: Lundin Jessica, Ni Tachen Chester
Принадлежит:

Techniques and technologies for using an intelligent meeting classifier to assess and enhance a work-related productivity are described. In at least some embodiments, a system includes a processing component operatively coupled to a memory; a productivity analyzer configured to perform operations including classifying one or more calendar events based at least partially on calendar data associated with one or more users; assessing one or more productivity metrics based at least partially on one or more calendar event classifications; determining one or more situation-enhancing operations based on the assessed one or more productivity metrics; and performing the one or more situation-enhancing operations. 1. A system for assessing and enhancing work-related productivity , comprising:a processing component operatively coupled to a memory; [ analyzing a textual content associated with a calendar event to determine one or more ngrams associated with the textual content of the calendar event,', 'determining a subset of possible tags associated with the calendar event based on the one or more ngrams,', 'determining one or more additional aspects associated with the calendar event,', 'assigning a tag to the calendar event from the subset of possible tags based on the one or more additional aspects associated with the calendar event, and', 'classifying the calendar event based at least partially on the tag associated with the calendar event;, 'classifying one or more calendar events based at least partially on calendar data associated with one or more users by, 'assessing one or more productivity metrics based at least partially on one or more calendar event classifications;', 'determining one or more situation-enhancing operations based on the assessed one or more productivity metrics; and', 'performing the one or more situation-enhancing operations, wherein performing the one or more situation-enhancing operations includes providing a productivity improvement ...

Подробнее
Номер записи: 77
14-01-2021 дата публикации

Customer service assistance system and customer service assistance method

Номер: US20210012352A1
Автор: Takashi Yamagishi
Принадлежит: HITACHI LTD

A customer service assistance system includes: storage device that stores an address of an automated response device accumulating knowledge of a provided business in the output screen; and an arithmetic device that, when an inquiry specifying the address is received from a customer terminal, checks identification information of the output screen and an inquiry sentence indicated by the inquiry against questions-and-answers information held for each output screen of the provided business in the automated response device associated with the address, estimates a question matching an intention of the inquiry out of questions in the questions-and-answers information according to whether a screen associated with each question included in the questions-and-answers information matches the output screen and a degree of similarity between a sentence of each question included in the questions-and-answers information and the inquiry sentence, and extracts an answer to the question, and returns the answer to the customer terminal.

Подробнее
Номер записи: 78
09-01-2020 дата публикации

Context-based autocompletion suggestion

Номер: US20200012718A1
Автор: Cheng-Lun Yang, Chih-Hsiung Liu, Joanne Kuei-Chen HO, Norman Kung
Принадлежит: International Business Machines Corp

A process for context-based autocompletion suggestion includes, based on initiating an online chat by a user of a computer system, the chat having as participants the user and a target participant, providing participant information that identifies the participants. The process maintains at the computer system a relation-based autocompletion model for use in word autocompletion suggesting. The maintained relation-based autocompletion model is initially a template model based on to relationship between chat participants, and is updated over time via training. The process suggests to the user words for autocompletion in the user's composition of chat messages, the suggested words being selected as suggestions based on the maintained relation-based autocompletion model. Maintaining the relation-based autocompletion model includes sending chat messages as training data to further train the autocompletion model.

Подробнее
Номер записи: 79
03-02-2022 дата публикации

ANALYTICS CENTER HAVING A NATURAL LANGUAGE QUERY (NLQ) INTERFACE

Номер: US20220035802A1
Автор: Ma Size, Mouzouris Dimosthenis, Penzo Marta, Redkina Olga, Tabak Aida Rikovic
Принадлежит:

An analytics server is disclosed that enables natural language queries (NLQs) to be used to access key performance indicator (KPI) data. The analytics server includes a graphical user interface (GUI) that presents a set of KPIs associated with a user. The GUI includes suitable user interface elements to enable the user to provide natural language queries regarding these KPIs. The user interface elements provide the user with suggested NLQs based on, for example, KPIs to which the user has access and/or previous NLQs of the user. In response to the analytics server receiving a suitable NLQ from the user, the analytics server generates an appropriate database query to retrieve the KPI data requested by the NLQ. The GUI is then updated to present a visual representation (e.g., a bar graph, a pie chart, a trend line, a single value) of the retrieved KPI data. 1. A system , comprising:at least one memory configured to store a configuration management database (CMDB), wherein the CMDB includes one or more tables storing key performance indicator (KPI) data; and providing, to a client device, a graphical user interface (GUI) that is presented on the client device;', 'receiving, from the client device, a natural language query (NLQ);', 'processing the NLQ using a natural language processor (NLP) to extract query details from the NLQ;', 'generating a database query based on the query details extracted from the NLQ;', 'processing the database query against the one or more tables of the CMDB to retrieve KPI data of a particular KPI; and', 'providing the KPI data of the particular KPI to the client device in response to the NLQ, wherein the GUI is updated to present a visual representation of the KPI data of the particular KPI on the client device., 'at least one processor configured to execute stored instructions to perform actions comprising2. The system of claim 1 , wherein the at least one processor is configured to execute the stored instructions to perform actions ...

Подробнее
Номер записи: 80
03-02-2022 дата публикации

ELECTRONIC APPARATUS FOR RECOMMENDING WORDS CORRESPONDING TO USER INTERACTION AND CONTROLLING METHOD THEREOF

Номер: US20220035999A1
Автор: PAWELEC Krzysztof
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

An electronic apparatus and a controlling method thereof are provided. The electronic apparatus includes a memory storing an artificial intelligence model, a display configured to display a keypad screen, and a processor configured to, based on a swipe interaction contacting a first key and connecting a plurality of keys being on the keypad screen, remove from the input window, a first word that is pre-input to the input window, obtain a word candidate list corresponding to the swipe interaction by inputting information regarding a trajectory of the swipe interaction to an artificial intelligence model, and control the display to display, in the input window, a second word having a highest score in the word candidate list. 1. An electronic apparatus comprising:a display;a memory storing a first model configured to provide a recommended word corresponding to a user input that is input to the display; and control the display to display a keypad screen and an input window that displays a word that is input through the keypad screen;', 'obtain a first word candidate list corresponding to a first swipe interaction by inputting, to the first model, first information regarding a first trajectory of the first swipe interaction connecting a plurality of keys on the keypad screen, and control the display to display in the input window, a first word having a highest score in the first word candidate list;', 'based on a second swipe interaction contacting a first key on the keypad screen and connecting the plurality of keys being input while the first word is displayed, remove the first word displayed in the input window and obtain a second word candidate list corresponding to the second swipe interaction by inputting, to the first model, second information regarding a second trajectory of the second swipe interaction; and', 'control the display to display a second word having a highest score in the second word candidate list in the input window., 'a processor configured to2. ...

Подробнее
Номер записи: 81
03-02-2022 дата публикации

DEVICE-BASED COMPLIANCE BASED ON NATURAL LANGUAGE PROCESSING

Номер: US20220036000A1
Автор: Angst Debra L., Dahlman Rebecca Lynn, La Rocca Jennifer Lynn, Lorenzo Mario J., McNeil Kristin E.
Принадлежит:

Examples described herein provide a computer-implemented method that includes performing a text analysis on unstructured text to identify a restriction associated with a subject. The method further includes identifying an environmental requirement associated with the subject based at least in part on the restriction. The method further includes identifying one or more devices associated with the subject based at least in part on the environmental requirement. The method further includes receiving data from the one or more devices. The method further includes determining device usage information based at least in part on the data. The method further includes determining a compliance of the subject to the restriction based at least in part on the device usage information. The method further includes, responsive to determining non-compliance of the subject, changing a function of the one or more devices. 1. A computer-implemented method comprising:performing, by a text analysis engine, a text analysis on unstructured text to identify a restriction associated with a subject;identifying, by a logic engine, an environmental requirement associated with the subject based at least in part on the restriction;identifying, by a device engine, one or more devices associated with the subject based at least in part on the environmental requirement;receiving, by the device engine, data from the one or more devices;determining, by a data engine, device usage information based at least in part on the data;determining, by a compliance engine, a compliance of the subject to the restriction based at least in part on the device usage information; andresponsive to determining non-compliance of the subject, changing, by the device engine, a function of the one or more devices.2. The computer-implemented method of claim 1 , wherein the text is medical text claim 1 , and wherein the restriction a medical restriction.3. The computer-implemented method of claim 1 , wherein the text analysis is ...

Подробнее
Номер записи: 82
03-02-2022 дата публикации

Labeled Knowledge Graph Based Priming Of A Natural Language Model Providing User Access To Programmatic Functionality Through Natural Language Input

Номер: US20220036001A1
Автор: Taylor John Anthony
Принадлежит:

A natural language model can be primed utilizing optimized examples generated from a labeled knowledge graph corresponding to an independently developed application program. Parsing of the labeled knowledge graph can include the identification of triples, comprising a source node, a destination node, and a link between them, each of which can be labeled. One or more natural language input examples can be generated from an individual triple by concatenating the natural language words or phrases utilized to label the source node in the link. Determinations that subsequently received natural language user input is similar to the generated examples can result in an identification of the triple, which can, in turn, trigger the performance of a function associated with the destination node of the triple. Labels can include preferred labels and alternative labels, and various permutations thereof can be concatenated to generate alternative natural language input examples. 120-. (canceled)21. One or more computer-readable storage media comprising computer-executable instructions , which , when executed by one or more processing units , cause one or more computing devices , in aggregate , to:receive a labeled knowledge graph of an application program, the labeled knowledge graph comprising:nodes, wherein at least some of the nodes correspond to application program functionality provided by the application program;links between the nodes, the links delineating programmatic relationships within the application program; andlabels applied to one or more of: at least some of the nodes or at least some of the links, each label individually comprising a natural language word or phrase;generate natural language input examples by concatenating together the natural language words or phrases of multiple labels; andtransmit the generated natural language input examples to a natural language processor;wherein user access to the application program functionality through user natural ...

Подробнее
Номер записи: 83
15-01-2015 дата публикации

Methods and devices for providing a text prediction

Номер: US20150019539A1
Автор: Andrew Douglas Bocking, Christopher Wormald, Conrad Delbert Seaman, Gerald Beard, William Alexander Cheung
Принадлежит: BlackBerry Ltd

A method for use in an electronic device including a display and a keyboard, the method including: receiving input reflecting selection of one or more characters through the keyboard; generating a predicted string of one or more characters based on the received input; determining a confidence value for the predicted string, based on a determination that the received input associated with a first one of the one or more selected characters reflects more than a single tap on a key of the keyboard; and displaying the predicted string on the display based on the determined confidence value.

Подробнее
Номер записи: 84
21-01-2016 дата публикации

Matching large sets of words

Номер: US20160019204A1
Автор: Matthew Fuchs
Принадлежит: Salesforce com Inc

Word phrases are stored in a phrase structure. Each word is stored as a keyword in a keyword structure. Each keyword is associated with usage attributes identifying use of a word in a word phrase. Any preceding words associated with a keyword, and a mapping from any preceding words to a word phrase, is stored for each word. A word string is input. Match attributes are updated in a match structure if a word in the word string matches any keyword and if any preceding words associated with any matching keyword includes a preceding word which precedes the word in the word string. The match attributes indicate use of the matching word in the word string and in a word phrase. Whether a word phrase is present in the word string is determined based on the usage attributes and the match attributes associated with multiple matching words.

Подробнее
Номер записи: 85
17-01-2019 дата публикации

Content manipulation using swipe gesture recognition technology

Номер: US20190018566A1
Автор: Caleb K. SHAY, Jesse D. SQUIRE, Robert S. MANOFF, Todd Houck
Принадлежит: Swipethru LLC

A method of manipulation of content provided by a hosting server using swipe gesture recognition on a user device having a touch input display. The method includes storing the content, combined with a swipe gesture recognition module to form a content package, on the hosting server. The swipe gesture recognition module is associated with at least one displayable content element of the content. The method further includes receiving, at the hosting server, a request for the content package from the user device and transmitting the content package from the hosting server to the user device for display by an application running on the user device. A defined action is applied to the at least one displayable content element if it is determined that a swipe gesture has occurred on the at least one displayable content element.

Подробнее
Номер записи: 86
17-01-2019 дата публикации

Electronic content insertion systems and methods

Номер: US20190018827A1
Автор: Alexander Friedrich Kuscher, Jennifer Chen, Trond Thomas Wuellner, Zachary Daniel ALCORN
Принадлежит: Google LLC

Aspects of the subject technology relate to systems and methods for instant insert of external content into a content-editor application. An assistant application is provided, separate from the content-editor application, that can identify, obtain, and insert the external content into the content-editor application. The assistant application can identify the external content responsive to a user request while the user is inputting or editing content in the content-editor application and/or the assistant can provide predictive options for insertion of content based on the already input content by the user. As one example, the assistant can insert a photo related to text the user has recently typed into the content-editor application. The assistant may obtain the photo from a public source such a public web server or from a local database for the user.

Подробнее
Номер записи: 87
17-04-2014 дата публикации

Feature-based autocorrection

Номер: US20140104175A1
Автор: Shumin Zhai, Yu Ouyang
Принадлежит: Google LLC

A computing device is described that outputs for display at a presence-sensitive screen, a graphical keyboard having keys. The computing device receives an indication of a selection of one or more of the keys. Based on the selection the computing device determines a character string from which the computing device determines one or more candidate words. Based at least in part on the candidate words and a plurality of features, the computing device determines a spelling probability that the character string represents an incorrect spelling of at least one candidate word. The plurality of features includes a spatial model probability associated with at least one of the candidate words. If the spelling probability satisfies a threshold, the computing device outputs for display the at least one candidate word.

Подробнее
Номер записи: 88
17-04-2014 дата публикации

Multi-gesture text input prediction

Номер: US20140104177A1
Автор: Shumin Zhai, Xiaojun Bi, Yu Ouyang
Принадлежит: Google LLC

A computing device outputs a keyboard for display, receives an indication of a first gesture to select a first sequence of one or more keys, determines a set of candidate strings based in part on the first sequence of keys, and outputs for display at least one of the set of candidate strings. The computing device receives an indication of a second gesture to select a second sequence of one or more keys, and determines that characters associated with the second sequence of keys are included in a first candidate word based at least in part on the set of candidate strings, or are included in a second candidate word not based on the first sequence of keys. The computing device modifies the set of candidate strings based at least in part on the determination and outputs for display at least one of the modified candidate strings.

Подробнее
Номер записи: 89
21-01-2021 дата публикации

INFORMATION PROCESSING DEVICE, NON-TRANSITORY COMPUTER READABLE MEDIUM, AND INFORMATION PROCESSING METHOD

Номер: US20210019031A1
Автор: TOKUCHI Kengo
Принадлежит: FUJI XEROX CO., LTD.

An information processing device includes a processor configured to cause a display to display posts to a conversation space created for a conversation group. In response to a user operation, the processor is configured to determine a set of a first post of the posts and one or more second posts of the posts based upon the user operation, extract the first post and the one or more second posts, and cause the display to display only the extracted posts among the posts, where each of the one or more second posts is a post identified as a reply directed to the first post. 1. An information processing device comprising: cause a display to display a plurality of posts to a conversation space created for a conversation group; and', determine, based upon the user operation, a set of a first post of the plurality of posts and one or more second posts of the plurality of posts, the one or more second posts each being a post identified as a reply directed to the first post,', 'extract the first post and the one or more second posts, and', 'cause the display to display only the extracted posts among the plurality of posts., 'in response to a user operation,'}], 'a processor configured to2. The information processing device of claim 1 , wherein the processor is configured to: 'align the extracted posts based on conversation participants in the conversation space.', 'when causing the display to display only the extracted set of the first post and the one or more second posts,'}3. The information processing device of claim 2 , wherein the processor is configured to: 'align a first group of posts that have been sent by a first conversation participant in the conversation space to a first line and align a second group of posts that have been sent by a second conversation participant in the conversation space other than the first conversation participant to a second line that is different from the first line.', 'when causing the display to display only the extracted posts among the ...

Подробнее
Номер записи: 90
21-01-2021 дата публикации

Data Association and Linking System and Apparatus

Номер: US20210019474A1
Автор: Baer Soul
Принадлежит:

A method of linking data is disclosed. The method comprises receiving and analyzing an anchor word and determining one or more related words to the anchor word using one or more data sources. Further, the method comprises displaying the anchor word and the one or more related words in a graphical user interface (GUI) in a display, wherein the one or more related words are clustered around the anchor word. 1. A method of linking data , the method comprising:receiving and analyzing an anchor word;determining one or more related words to the anchor word using one or more data sources; anddisplaying the anchor word and the one or more related words in a graphical user interface (GUI) in a display, wherein the one or more related words are clustered around the anchor word.2. The method of claim 1 , wherein the one or more data sources includes a book claim 1 , a newspaper article claim 1 , a periodical claim 1 , a magazine claim 1 , and a plurality of books.3. The method of claim 1 , further comprising:connecting the anchor word with the one or more related words in the GUI.4. The method of claim 3 , further comprising:creating a plurality of similar words for each of the one or more related words and creating a plurality of dissimilar words for each of the one or more related words; anddisplaying a respective plurality of similar words and a respective plurality of dissimilar words for each related word in the GUI.5. The method of claim 4 , wherein the displaying further comprises:displaying a respective plurality of similar words and a respective plurality of dissimilar words adjacent to each related word in the GUI.6. The method of claim 1 , wherein the analyzing an anchor word comprises analyzing a context within the one or more data sources within which the anchor word was used.7. The method of claim 1 , wherein the anchor word and each of the one or more related words in the graphical user interface (GUI) comprise a hyperlink claim 1 , wherein a user may click on a ...

Подробнее
Номер записи: 91
21-01-2021 дата публикации

INFORMATION PROCESSING DEVICE AND INFORMATION PROCESSING METHOD

Номер: US20210019554A1
Автор: Kawara Satoshi
Принадлежит:

The present disclosure determines whether or not a character string of a result obtained by a character recognition process matches a word of a word dictionary; and when a pattern that is similar to a predefined arrangement pattern of a character type is present in the character string of the result obtained by the character recognition process that is determined not to match a word of the word dictionary, changes the character recognition process for the character string based on the pattern. 1. An information processing device comprising:at least one memory that stores a program; andat least one processor that executes the program to perform instructions for:determining whether or not a character string of a result obtained by a character recognition process matches a word of a word dictionary; andwhen a pattern that is similar to a predefined arrangement pattern of a character type is present in the character string of the result obtained by the character recognition process that is determined not to match a word of the word dictionary, changing the character recognition process for the character string based on the pattern.2. The information processing device according to claim 1 ,wherein the at least one processor that executes the program to further perform instructions for:determining whether or not a pattern that is similar to a predefined arrangement pattern of a character type is present in the character string of the result obtained by the character recognition process;wherein when it is determined that a pattern that is similar to a predefined arrangement pattern of a character type is present in the character string, the character recognition process for the character string is changed based on the pattern.3. The information processing device according to claim 1 , wherein when a pattern that is similar to the predefined arrangement pattern of a character type is present in a character string of a result obtained by a character recognition process which ...

Подробнее
Номер записи: 92
21-01-2021 дата публикации

Extraction of entities having defined lengths of text spans

Номер: US20210019615A1
Автор: Anup Kalia, Daniela Rosu, Ruchi Mahindru, SHU Tao, Tarek Sakakini, YU Deng
Принадлежит: International Business Machines Corp

Systems, computer-implemented methods, and computer program products that can facilitate extraction of entities having defined lengths of text spans 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 configuration component that defines different hyperparameters of multiple artificial intelligence models, and determines target hyperparameters of an artificial intelligence model based on performance of the multiple artificial intelligence models. The computer executable components can further comprise an application component that employs the artificial intelligence model to extract one or more entities from a data source based on the target hyperparameters.

Подробнее
Номер записи: 93
16-01-2020 дата публикации

Methods and apparatus for determining non-textual reply content for inclusion in a reply to an electronic communication

Номер: US20200021544A1
Автор: Balint MIKLOS, Ijeoma Emeagwali, Phillip Sharp, Prabhakar Raghavan
Принадлежит: Google LLC

Methods and apparatus related to determining non-textual reply content for a reply to an electronic communication and providing the non-textual reply content for inclusion in the reply. Some of those implementations are directed to determining, based on an electronic communication sent to a user, one or more electronic documents that are responsive to the electronic communication, and providing one or more of those electronic documents for inclusion in a reply by the user to the electronic communication. For example, the electronic documents may be automatically attached to the reply and/or link(s) to the electronic documents automatically provided in the reply.

Подробнее
Номер записи: 94
21-01-2021 дата публикации

SYSTEM AND METHOD FOR ASSESSING SECURITY THREATS AND CRIMINAL PROCLIVITIES

Номер: US20210021703A1
Автор: VOLKART Mitch
Принадлежит: Global Tel*Link Corporation

A centralized and robust threat assessment tool is disclosed to perform comprehensive analysis of previously-stored and subsequent communication data, activity data, and other relevant information relating to inmates within a controlled environment facility. As part of the analysis, the system detects certain keywords and key interactions with the dataset in order to identify particular criminal proclivities of the inmate. Based on the identified proclivities, the system assigns threat scores to inmate that represents a relative likelihood that the inmate will carry out or be drawn to certain threats and/or criminal activities. This analysis provides a predictive tool for assessing an inmate's ability to rehabilitate. Based on the analysis, remedial measures can be taken in order to correct an inmate's trajectory within the controlled environment and increase the likelihood of successful rehabilitation, as well as to prevent potential criminal acts. 1. A threat prediction system for predicting a threat potential of an inmate , the system comprising:one or more circuits and/or processors configured to:receive a previously-stored inmate communication;receive a plurality of topics and a plurality of topic weights that correspond to the plurality of topics;determine one or more topics present in the previously-stored inmate communication;assign a topic score to each of the determined one or more topics;retrieve previously-stored threat information of the inmate;compare the received topics to the previously-stored threat information; andassign a threat score to the inmate based on the comparison.2. The threat prediction system of claim 1 , wherein the one or more circuits and/or processors are further configured to scale the topic weights by a number of data points examined for the inmate;3. The threat predication system of claim 2 , wherein the one or more circuits and/or processors are further configured to normalize the scaled weights based on scaled weights of other ...

Подробнее
Номер записи: 95
17-04-2014 дата публикации

Incremental multi-word recognition

Номер: US20140108991A1
Автор: Ken Wakasa, Satoshi Kataoka, Shumin Zhai, Yu Ouyang
Принадлежит: Google LLC

In one example, a computing device includes at least one processor that is operatively coupled to a presence-sensitive display and a gesture module operable by the at least one processor. The gesture module may be operable by the at least one processor to output, for display at the presence-sensitive display, a graphical keyboard comprising a plurality of keys and receive an indication of a continuous gesture detected at the presence-sensitive display, the continuous gesture to select a group of keys of the plurality of keys. The gesture module may be further operable to determine, in response to receiving the indication of the continuous gesture and based at least in part on the group of keys of the plurality of keys, a candidate phrase comprising a group of candidate words.

Подробнее
Номер записи: 96
26-01-2017 дата публикации

Identifying errors in medical data

Номер: US20170024517A1
Автор: Brendan C. Bull, David Contreras, Keith P. Biegert, Robert C. Sizemore, Sterling R. Smith
Принадлежит: International Business Machines Corp

A computer processor may receive medical data including a report and an image. The computer processor may analyze the report using natural language processing to identify a condition and a corresponding criterion. The computer processor may also analyze the image using an image processing model to generate an image analysis. The computer processor may determine whether the report has a potential problem by comparing the image analysis to the criterion.

Подробнее
Номер записи: 97
10-02-2022 дата публикации

COOKING SUPPORT DEVICE, COOKING SUPPORT METHOD, AND COOKING SUPPORT PROGRAM

Номер: US20220043966A1
Автор: HASHIMOTO Naoki
Принадлежит: Cookpad Inc.

A cooking support device includes a memory that stores recipe information and processing circuitry which subjects the recipe information stored in the memory to natural language processing, extracts words related to cooking operations therefrom, classifies the words into predetermined categories representing cooking concepts, arranges the words in an order of occurrence of the cooking concepts in an entire cooking process, and generates a summary of the recipe information. 2. The cooking support device according to claim 1 , wherein the processing circuitry is further configured to classify the words by being further configured toidentify, among the words extracted, only words that appear in a range from start of cooking and before first heating processing and that belong to a preparation category in a predetermined classification dictionary,identify, among the words extracted, only words that appear in a range from the first heating processing to last heating processing and that belong to a main cooking category in the classification dictionary, andidentify, among the words extracted, only words that appear in a range after the last heating processing and that belong to a finish category in the classification dictionary.3. The cooking support device according to claim 1 , wherein claim 1 , in extraction of the words related to cooking operations claim 1 , the processing circuitry is further configured toidentify, based on a predetermined recipe format, a part in the recipe information unrelated to a cooking process, andexclude from the part in the extraction.4. The cooking support device according to claim 1 , wherein claim 1 , in extraction of the words related to cooking operations claim 1 , the processing circuitry is further configured toperform at least one of: processing of limiting the number of extracted words corresponding to ingredients to a predetermined number, and processing of avoiding extraction of words corresponding to seasonings.5. The cooking ...

Подробнее
Номер записи: 98
10-02-2022 дата публикации

Future potential natural language processing annotations

Номер: US20220043968A1
Автор: Andrew J Lavery, Igor S. Ramos, Paul Joseph Hake, Scott Carrier
Принадлежит: International Business Machines Corp

Aspects of the invention include resolving future reference identifiers for documents. Aspects of the invention include processing a document including a reference to a future event, wherein processing includes performing natural language processing (NLP) on the document, and identifying the reference to the future event included in the document. Aspects of the invention also include generating a future reference identifier for the reference to the future event, and responsive to processing an occurrence of the future event, resolving the future reference identifier by providing data from a subsequent document for the future event associated with the future reference identifier.

Подробнее
Номер записи: 99
10-02-2022 дата публикации

Data transmission system and method thereof

Номер: US20220043974A1
Автор: Yung Chang Hsu
Принадлежит: Ez Ai Inc

The present invention provides a data transmission device and method thereof. A data transmission system includes: an electric device generating an input message; a Natural Language Processing (NLP) engine connected to the electric device, receiving the input message, and judging whether an output message corresponding to the input message is available on a real-time basis or on a non-real-time basis; a plurality of third-party servers; a service cloud framework connected to one of the NLP engine, the electric device, and the plurality of third-party servers to obtain a real-time information; and a buffer cloud framework connected to one of the NLP engine, the electric device and the plurality of third-party servers, proactively downloading at least one updated data from the plurality of third-party servers once in a predetermined period of time, automatically saving the at least one updated data therein, and obtaining a non-real-time information therefrom.

Подробнее
Номер записи: 100