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 7. Отображено 7.
07-07-2023 дата публикации

Adversarial sample detection method and device, computer equipment and storage medium

Номер: CN116403079A
Автор: LIN XIAORUI, ZHANG JINYUAN, LIU CHANG, ZHANG LEI
Принадлежит:

The invention relates to an adversarial sample detection method and device, computer equipment, a storage medium and a computer program product, and relates to the field of artificial intelligence. The method comprises the following steps: for an original face sample image set, acquiring at least two different shape types of simulated adversarial disturbances by simulating general adversarial disturbances; the general adversarial disturbance is generated through at least two general adversarial attack methods based on gradients; adding the simulation confrontation disturbance of each shape type to an original face sample image in the original face sample image set to obtain a simulation confrontation sample image set; generating a target confrontation detection training set according to the simulated confrontation sample image set and the original face sample image set; the target confrontation detection training set is used for training a face confrontation detection model; the face confrontation ...

Подробнее
Номер записи: 1
09-05-2023 дата публикации

Data insertion method and device and data query method and device

Номер: CN116089995A
Автор: CHEN LONGSHENG, CHEN HAOZHONG, LI LIULIU, LU SEN, ZHU ZIJING, WU SHUPING, ZHOU SHANGXIANG, TIAN FANGHUA, LI MENGJUN, LIN XIAORUI, SUN LIN, MO XUEHUI, LIU MINGDA, GUO XIAN
Принадлежит:

The invention discloses a data insertion method and device and a data query method and device, and relates to the technical field of database operation. A specific embodiment of the method comprises the steps of receiving an insertion request for a database, and obtaining a to-be-inserted record corresponding to the insertion request; determining whether the record to be inserted contains sensitive information; in response to sensitive information contained in the to-be-inserted record, obtaining at least one piece of sensitive information contained in the to-be-inserted record, and generating a splicing field corresponding to the at least one piece of sensitive information; encrypting the spliced field by using a first cryptographic algorithm to generate a data ciphertext, and generating summary information corresponding to the spliced field by using a second cryptographic algorithm; and storing the data ciphertext and the summary information in a data table corresponding to the to-be-inserted ...

Подробнее
Номер записи: 2
23-06-2023 дата публикации

Multi-modal emotion recognition method and device

Номер: CN116310983A
Автор: LIU CHANG, ZHANG JINYUAN, LIN XIAORUI, YANG JIEQIONG
Принадлежит:

The invention provides a multi-mode emotion recognition method and device which can be used in the financial field or other fields, and the method comprises the steps: obtaining a video data sample and an actual emotion label; obtaining single-mode feature data and emotion feature data of each mode according to the original data of the video data sample in the multiple modes and the single-mode emotion learning model of each mode; according to the multi-modal emotion recognition model and the original data of each modal, obtaining emotion prediction data; the sentiment feature data, the sentiment prediction data and the actual sentiment labels are substituted into an overall loss function, parameters of all models are adjusted, when the overall loss function value is minimum, training of the models is completed, and the overall loss function comprises a loss function of a multi-mode sentiment recognition model and a loss function of all single-mode sentiment learning models; and obtaining ...

Подробнее
Номер записи: 3
23-06-2023 дата публикации

User information processing method and device based on multi-channel registration, equipment and medium

Номер: CN116303509A
Автор: CHEN HAOZHONG, SUN LIN, LIN XIAORUI, LI MENGJUN
Принадлежит:

The invention provides a user information processing method and device based on multi-channel registration, equipment and a medium, and relates to the technical field of big data and artificial intelligence, and the method comprises the steps: obtaining user information of a user, the user information being determined through the input of an interface provided by the user to a management platform, or the user information being sent by first equipment, the user information comprises a first user identifier; when it is determined that the user does not register on the management platform according to the first user identifier, newly adding a user record of the user and a second user identifier generated by the management platform for the user; and updating the user record of the user according to the user information under the condition of determining that the user is registered on the management platform according to the first user identifier. The management platform can perform unified ...

Подробнее
Номер записи: 4
16-09-2009 дата публикации

Parallel mechanism to implement tri-translation and mono-rotation

Номер: CN0101531003A
Автор: BING LI, YUAN CHEN, XIAOJUN YANG, XIAORUI LIN, LI BING, CHEN YUAN, YANG XIAOJUN, LIN XIAORUI
Принадлежит:

The invention relates to a parallel mechanism to implement tri-translation and mono-rotation, consisting of a slider (8) and an end effector (7), and three groups of planar linkage mechanisms connecting said two, where the three groups include a five bar slider mechanism, a slider-crank mechanism and a plane four bar mechanism. The plane four bar mechanism consists of a driving element (5) and a driven element (6, 20). The end effector (7) has a rotary shaft connected to a connecting bar (2), while the driven element (20) of the plane four bar mechanism is connected with the end effector. The five bar slider mechanism and the slider-crank mechanism share a slider (4) and a drive motor (12), while the slider (4) is served as a driving element of the five bar slider mechanism. The slider-crank mechanism and the five bar slider mechanism form a planar combination mechanism to implement two degrees of freedom (DOF) motion required by the end effector by use of a drive motor (12). The plane ...

Подробнее
Номер записи: 5
23-05-2023 дата публикации

Face image recognition method and device, processor and electronic equipment

Номер: CN116152884A
Автор: LIN XIAORUI, ZHANG JINYUAN, LIU CHANG, WU FAN
Принадлежит:

The invention discloses a face image recognition method and device, a processor and electronic equipment. Relates to the field of artificial intelligence, and the method comprises the steps that N target confrontation samples are determined, each target confrontation sample is input into a preset face recognition model to obtain N face recognition results, the target confrontation samples are obtained through processing of a face recognition model set, and the face recognition model set comprises m face recognition models; judging whether each face recognition result is the same as a preset result or not; under the condition that the face recognition result is different from the preset result, determining a target confrontation sample corresponding to the face recognition result as a training sample; and updating a preset face recognition model through the training sample to obtain a target face recognition model, and recognizing a face image through the target face recognition model. Through ...

Подробнее
Номер записи: 6
07-04-2023 дата публикации

Privacy computing method, algorithm plug-in and heterogeneous privacy computing joint system

Номер: CN115941156A
Автор: ZHANG JINYUAN, LIN XIAORUI, LIU CHANG, CAI WEIBIN
Принадлежит:

The invention provides a privacy calculation method, and belongs to the field of information security. The method can be executed by an algorithm plug-in and comprises the steps that external forwarding information sent by a local privacy computing system according to a local privacy computing protocol is received, the external forwarding information comprises first outgoing data and destination information, and the local privacy computing system and the algorithm plug-in are both installed in the same heterogeneous privacy computing system; and when the local privacy computing protocol is inconsistent with the first universal privacy computing protocol, the first outgoing data is converted into second outgoing data according to a first conversion algorithm, and then the second outgoing data is forwarded to the destination privacy computing system. Wherein the first conversion algorithm is an algorithm used for converting data adopting a local privacy computing protocol into data conforming ...

Подробнее
Номер записи: 7