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 3. Отображено 3.
22-08-2023 дата публикации

Multi-network identity alignment system and method based on same-space user feature transmission

Номер: CN116628515A
Автор: TONG LINGLING, SHI LEI, DUAN RONGCHANG, HOU WEI, DUAN YUNQIANG, DUAN DONGSHENG, DANG ZHONGKAI, JING YAQI, WANG HAIYANG, REN BOYA, LYU DONG
Принадлежит:

The invention relates to the technical field of social networks, in particular to a multi-network identity alignment system and method based on same-space user feature transmission, and the system comprises a data collection module which is used for collecting user data in a social network; the identity learning module is used for carrying out multi-social-network identity learning of the user by constructing a network topological structure and combining the network topological structure with the collected user data; the identity transmission module is used for performing multi-social network transmission on the user data through a network topology structure; the vector generation module is used for acquiring user vectors of multiple social network users in the same space through the network topology structure and the user data; and the identity alignment module is used for performing user identity alignment on the unlabeled potential anchor chain through a similarity algorithm. According ...

Подробнее
Номер записи: 1
16-05-2023 дата публикации

Detection method for fraud information fused with propagation relationship

Номер: CN116127964A
Автор: MA HONGYUAN, WANG LEI, WANG LIHONG, SHI LEI, HE MIN, JIA YUNGANG, SUN JIE, DUAN YUNQIANG, LU RUI, DUAN RONGCHANG, WANG ZIHAN, REN BOYA, JING YAQI, DANG ZHONGKAI, PENG XIN
Принадлежит:

The invention discloses a method for detecting fraud information fused with a propagation relationship. The method comprises the following steps: acquiring a first information group, a fraud account library and a normal account library, wherein each piece of information in the first information group comprises text information and a sending account; determining a second information group from the first information group according to the fraud account library and the normal account library, wherein the sending account of each piece of information in the second information group does not exist in the fraud account library and the normal account library; obtaining a plurality of target information groups according to the second information group, wherein the number of similar text information of the first sending account and the second sending account in each target information group is greater than a first threshold value; calculating a fraud weight value of each target information group; ...

Подробнее
Номер записи: 2
25-08-2023 дата публикации

Recommendation information over-pan entertainment prediction method and device, and server

Номер: CN116644229A
Автор: AI ZHENGYANG, LI PENGXIAO, ZHAI YUJIA, MA HONGYUAN, TONG LINGLING, WANG HONGBING, WANG YUANYUAN, XIANG FEI, DUAN YUNQIANG, DUAN RONGCHANG, DUAN DONGSHENG, DANG ZHONGKAI, ZHAO NING
Принадлежит:

The invention relates to a recommendation information over-pan entertainment prediction method and device and a server, the method is applied to the server, and the method comprises the following steps: obtaining real-time behavior data and first historical behavior data of a to-be-predicted moment in a user personalized recommendation scene; performing feature extraction on the real-time behavior data at the to-be-predicted moment and the first historical behavior data to obtain to-be-input features; inputting the to-be-input features into the recommendation information over-generic entertainment prediction model; and obtaining an output result of the recommended information over-pan entertainment prediction model, wherein the output result represents whether the recommended information over-pan entertainment occurs at the to-be-predicted moment of the user. By means of the mode, the problem that there is a blank in research on the prediction angle of excessive generic entertainment information ...

Подробнее
Номер записи: 3