Method and system for pushing messages

Abstract

The invention provides a method for pushing messages. The method includes: according to pre-generated related labels and corresponding related strengths, adding messages of the related labels into a label recommendation list, ranking the messages in the recommendation list, and pushing the ranked recommendation list to a user. The invention further provides a system for pushing messages. The method and the system according to the technical scheme have the advantages that the messages in the recommendation list can be more diversified and recommendation needs of users are met.

Description

【Technical field】 [0001] The invention relates to the field of Internet applications, in particular to a method and system for pushing information. 【Background technique】 [0002] Information information is a kind of information that users can bring value to themselves in a relatively short period of time because they obtain and use it in a timely manner. Information information mainly includes news, dynamic information, technical information, policies, reviews and academic papers, etc. The scope of timeliness of information is far greater than the scope of timeliness of news. At present, information information has corresponding tags (tags). Tags are keywords that are more specific and accurate than classification, and can summarize the main content of information information; in order to understand the meaning of tags in various scenarios, and diversity To recommend tag-related information to users, it is necessary to mine the relationship between tags, that is, the corre...

AI Technical Summary

Problems solved by technology

[0004] 1. Only tag-related information is recommended to users, resulting in too single recommended content, and the amount of information is small, and the homogeneity is serious

[0005] 2. The association between tags is obtained manually based on encyclopedia and other resources, combined with their own knowledge, resulting in the tag relationship network being limited by personal knowledge and resources, so the scale of the tag relationship network is relatively small, which is not conducive to Recommended information for user diversity; for example, users who are not majors in physics do not know that there is a relationship between "cat" and "Schrödinger"

[0006] 3. Due to the limited knowledge, there must be some wrong relationships in the tag relationship network, which leads to wrong recommendations of information

[0007] 4. There are millions of tags in the tag relationship network. If a large-scale tag update is performed, it is necessary to manually check and update the association relationship between all tags. Therefore, it is currently impossible to perform large-scale automatic update

Images