Real-time individuation video recommending method based on text stream network

Abstract

The invention relates to a real-time individuation video recommending method based on a text stream network. The method includes the steps: S1 real-time user documents are built by using current tweets published and forwarded by users on the text stream network, a hot spot event space is built for a plurality of real-time user documents, and a plurality of current hot spot events followed by the users are obtained; S2 user documents are built by using all information of the users on the text stream network, a long-term interest topic space is built for the plurality of user documents, and long-term interest distribution vectors of the users on the space are obtained; S3 the plurality of hot spot events are ranked by using the long-term interest distribution vectors of the users, and the most interested current hot spot event of the users is obtained; S4 a plurality of videos relevant to the most interested current hot spot event of the users are retrieved on a video application platform; S5 long-term interest feature vectors of the users are obtained by using information of the users on the video application platform; S6 the plurality of videos are ranked again by using the long-term interest feature vectors of the users, and top N videos are recommended to the users.

Description

technical field [0001] The invention relates to the technical field of Internet personalized recommendation, in particular to a real-time personalized video recommendation method based on a text stream network. Background technique [0002] With the development of Internet technology, especially the arrival of the WEB2.0 era, the dissemination of online video has reached an unprecedented level. Although such a large amount of video data can meet the needs of almost all users, it also makes it very tedious to search and find videos that users are really interested in. Therefore, personalized video recommendation is very necessary for today's information overload. [0003] Traditional approaches to personalized video recommendation are based on static user models, which utilize user registration information, historical behaviors to understand users' long-term interests. Today, however, information is updated more and more frequently. Users are faced with a large amount of n...

AI Technical Summary

Problems solved by technology

[0009] 1) Pay attention to the long-term interest of the user, and cannot capture the short-term interest preference of the user in real time;

[0010] 2) Only use the information of a single network platform to learn user interests, often there are problems of cold-start and data sparsity

Images