Live broadcast room recommending method and system based on weighted k nearest neighbor scores

Abstract

The invention discloses a live broadcast room recommending method and system based on weighted k nearest neighbor scores and relates to the field of popularization of live broadcast rooms. The method comprises the steps of obtaining a live broadcast room watching vector of each user in a live broadcast platform; calculating a similarity between every two users according to the live broadcast room watching vectors; selecting the appointed number of neighbor users for each user according a similarity descending sort method; calculating degree of interest of each user for each watched live broadcast room according to the similarities and the neighbor users of each user; and selecting the appointed number of recommended live broadcast rooms for each user according to a degree of interest descending sort method. According to the method and the system, the recommended live broadcast rooms are evaluated and selected according to the degree of interest calculated according to the similarities; the recommended live broadcast rooms are more consistent with the hobbies, interests and individual demands of the users; the recommending accuracy is relatively high; and the recommending effect is relatively good.

Description

technical field [0001] The invention relates to the promotion field of network live broadcast rooms, in particular to a live broadcast room recommendation method and system based on weighted k-nearest neighbor scoring. Background technique [0002] With the multi-screen development of smart terminals, the active users of China's social video live broadcast platforms are constantly growing, and people's demand for "watching their favorite live broadcast content and interacting with the host in real time" is getting higher and higher. Therefore, how to discover users' points of interest, accurately recommend live broadcast rooms to users to increase user stickiness, and promote user payment conversion will be a difficult problem that the live broadcast industry will face for a long time. [0003] At present, the traditional live broadcast platform recommends live rooms (that is, links to watched live content) for users. The method is generally based on k-nearest neighbors. Thi...

AI Technical Summary

Problems solved by technology

[0004] However, when the above-mentioned recommendation method based on k-nearest neighbors recommends live rooms for users, there are the following defects: when user A chooses from the recommendation list formed by K users’ favorite live rooms, because different users among the K users are similar to user A’s The degree (watching taste) is different, so it is difficult for user A to quickly find the live room recommended by the user who is the closest or the same as himself in the recommendation list; because the higher the similarity, the more accurate the recommended live room, therefore, now Some recommendation methods based on k-nearest neighbors are difficult to quickly recommend live broadcast rooms with a high degree of similarity for users, that is, the accuracy of recommendation is not enough, and the recommendation effect needs to be improved

Images