A recommendation processing method and processing system for related articles

Abstract

The invention discloses a recommendation processing method and system for related articles. The method includes that (1) candidate related articles are searched out according to content characteristics of given articles; (2) user correlation of each candidate related article is determined according to given user characteristics and user characteristics of each candidate related article; and (3) candidate related articles with high correlations are preferentially recommended according to the given articles. The system comprises a characteristic searching module, a correlation determining module and a recommendation control module, wherein the characteristic searching module is used for searching out the candidate related articles according to the content characteristics of the given articles, the correlation determining module is used for determining the correlation of each candidate related article according to the content characteristics and the user characteristic of each candidate related article, and the recommendation control module is used for preferentially recommending the candidate related articles with the high correlations according to the given articles. By means of the method and the system, the accuracy of a recommended result of the related articles can be improved, man-machine interaction times of users for searching for target articles are reduced, and the occupied machine side resources are reduced.

Description

technical field [0001] The invention relates to Internet information processing technology, in particular to a method and system for recommending related articles in the Internet. Background technique [0002] At present, with the development of Internet technology, the Internet has gradually become an important source of information for people, especially after the Internet enters the Web2.0 era, users are not only the viewers of website content, but also the creators of website content. The content created by users is called User Generated Content (UGC, User Generated Content). In the era of Web 2.0, due to the emergence of a large number of UGC, the amount of network information is growing exponentially. In order to provide information to interested users quickly and in a targeted manner, various website systems and Internet community systems recommend relevant articles to users when users read a given article, so as to reduce the human-computer interaction caused by user...

AI Technical Summary

Problems solved by technology

[0005] The disadvantage of this recommended processing method is: the labor cost is too high, the efficiency is low, and it is difficult to process a large amount of UGC content every day

[0007] The disadvantage of this recommendation processing method is that all recommended articles for a given article are the same, and relevant and different content cannot be recommended for each given article, and it is difficult to meet the user's demand for personalized information acquisition, which is inconvenient The user finds a target article that is highly relevant to a given article from the recommendation results

[0009] The shortcoming of this recommended processing mode is: only by the core word matching retrieval relevant article of current given article, does not consider the user characteristic of relevant article and this user characteristic and given user (such as the reader or author of described given article) User relevance leads to no difference in the recommendation results obtained by different readers at the same time, which cannot meet the individual needs of different readers, and makes it inconvenient for users to find target articles that are highly relevant to a given article and a given user from the recommendation results

In short, the existing technical solutions for recommending related articles are not accurate in the recommendation results when faced with the massive amount of information on the Internet, and it is inconvenient for users to find relevant articles (such as the currently read article) and given articles from the recommendation results. A target article with high relevance to a user (such as a reader or author of a given article), in order to find a target article with a high relevance to a given article and a given user, the user often needs to click to view more pages for manual search and Searching leads to an increase in the number of human-computer interactions between the user and the Internet machine side, and each human-computer interaction operation will send out operation request information, trigger the calculation process, and generate response result information, which will occupy a large amount of resources on the machine side, including client resources. , server resources, network bandwidth resources, etc.

Images