Key public opinion recommendation method, readable storage medium and data processing device

Abstract

The invention provides a key public opinion recommendation method, a readable storage medium and a data processing device. The method comprises the steps of processing massive internet data, obtaining hot topics and corresponding keywords, generating a hot field short sentence library after expansion, analyzing the proportion of hot field topics of an article by using a text semantic similarity model, and completing hot field recommendation; screening to obtain news data with high popularity rating and microblog data with high popularity value, and completing news and microblog recommendation; according to the personalized user dictionary, training a text semantic similarity model to analyze the personalized content proportion of the article, and completing personalized customization recommendation; and in combination with all the recommendations, pushing the hot articles in real time. Compared with the prior art, the method has the advantages that the popularity can be calculated according to diversification of different platforms, the defect of single hotspot field judgment is overcome, real-time key public opinion recommendation of diversified platforms is met, the accuracy of recommended content is improved, the coverage of the recommended content is expanded, and the method has excellent real-time performance and stability.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a key public opinion recommendation method, a readable storage medium and a data processing device. Background technique [0002] The rapid development of the Internet makes it easier and faster for people to obtain massive amounts of information, and to learn about real-time happenings around the world without leaving home. But what followed was an explosive amount of information, which made users unable to efficiently obtain information due to information overload. Among them, the reasons for information overload include two aspects. First, users cannot fully browse the information on the entire network, and second, users cannot effectively summarize the information they are interested in. [0003] In order to solve the problem that users cannot efficiently obtain information due to information overload, it is necessary to process massive amounts of information throu...

AI Technical Summary

Problems solved by technology

However, there are obvious problems with these two types: one is that the pre-set rules cannot cover all hotspots, and the hotspots are constantly changing with time; the other is that the evaluation of hotspot fields in social media is relatively simple, and hotspots should be comprehensively evaluated in many ways. Evaluate

Images