Text information recommendation method and device and readable medium

Abstract

The invention discloses a text information recommendation method and device and a readable medium, and the method comprises the steps: obtaining user data and a corresponding text corpus, carrying out the preprocessing of the text corpus, and obtaining text data; processing the user data to obtain user attribute features, generating text features from the text data through a word attention network, generating user knowledge graph features from the user data by using a knowledge graph representation learning model, and splicing the user attribute features, the text features and the user knowledge graph features to obtain comprehensive features; and inputting the comprehensive features into a multi-layer perceptron to obtain a user preference category and a corresponding pushing quantity. According to the method, the recognition degree and expansibility of user interests are enhanced, so that the accuracy and diversity of recommendation results are improved, multi-dimensional abstract feature representation can be obtained through comprehensive features, and the problems of data sparsity, cold start and the like in traditional personalized information recommendation are solved. And the attention mechanism is applied to text recommendation, so that the accuracy is further improved.

Description

technical field [0001] The invention relates to the field of information retrieval and recommendation, in particular to a text information recommendation method, device and readable medium. Background technique [0002] Social network has become one of the main channels for people to socialize in daily life. Weibo and other social network platforms, as the new generation of social network platforms, have effectively improved the shortcomings of traditional media such as flatness and single dimension, so they are deeply loved by the majority of network users. Faced with all kinds of massive data on the Internet, people are overwhelmed, let alone digested in time. The problem of information overload has become one of the main problems for netizens in the Internet age. To push the right content to the right users through the right channel at the right time, information recommendation is an effective way to alleviate information overload. The recommendation system is essentiall...

AI Technical Summary

Problems solved by technology

The difference between text recommendation and item recommendation is that users not only have rich attribute and text feature data, but also complex social relations and interactive behaviors, which indeed provide a lot of additional information for recommendation algorithms, but also bring huge challenge

[0003] Among them, Weibo content is a kind of social short text, which has the characteristics of fast update, sparse information content, and irregular words. It is necessary to extract effective features of users from noisy data, and data related to user privacy cannot be made public. As a result, data information becomes limited, and public data sets in the field of Weibo recommendation are also relatively scarce.

Images