Label recommendation method fused with implicit connection relationship of users and oriented on question and answer platform

Abstract

The invention relates to a label recommendation method fused with the implicit connection relationship of users and oriented on a question and answer platform, and can solve the technical problem thatuser requirements cannot be satisfied due to the fact that the recommendation result of the traditional label recommendation method is limited. The label recommendation method comprises the steps of:constructing a question set, a label set corresponding to questions, and a user set; constructing the network of a user; processing to obtain characteristic vectors of the user; then, obtaining characteristic vectors of the questions; splicing the characteristic vectors of the user with the characteristic vectors of the questions, so that a multi-characteristic vector set fused with implicit connection of users is obtained through a layer of fully-connected network; mapping the multi-characteristic vector set into the probability by using a logistic regression model, performing descending sorting of labels based on the output probability value, and taking previous top labels; training an initial model, and obtaining the final recommendation model after training is ended; and, when the user submits the questions to a website, recommending the previous top labels to the user in the recommendation model. By means of the label recommendation method disclosed by the invention, the varietyand the accuracy of the label system can be improved; and user requirements can be satisfied.

Description

technical field [0001] The invention relates to the technical field of information retrieval, in particular to a tag recommendation method for a question-and-answer platform that integrates user implicit connection relationships. Background technique [0002] On some question-and-answer websites, users can submit questions, search questions, browse questions, answer questions, etc., resulting in explosive growth of information. Labels help to improve the disorganization of question information and help users browse questions, and indexing according to labels can help users more easily obtain interesting questions from a large amount of information on the web. It is very common to see tags on Q&A sites, which allow users to tag various questions in their own language. This tag not only describes the important characteristics of the questions they post, but also reflects the interests of users. [0003] However, when users tag the questions, they will tag the questions accord...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a tag recommendation method oriented to the question-and-answer platform that integrates user implicit connection relationships, which solves the problem that the traditional tag recommendation method does not take into account the co-occurrence relationship between users on the website, and the recommendation results lack diversity. technical problems that cannot meet the needs of users

Images