News information processing method, news recommendation method and related devices

Abstract

The invention provides a news information processing method, a news recommendation method and related devices. The news information processing method comprises the steps that the text content of news is obtained; word segmentation processing is conducted on the text content of the news to obtain multiple words; the word vector of each word is calculated; the tfidf value of each word is calculated; accumulating summing is conducted on all the word vectors of the news with the tfidf values of all the words as weights, and feature vectors of the news are obtained through calculation; clustering calculation is conducted on all the feature vectors, obtained through the calculation, of the news by utilizing a text clustering method, grouping of different pieces of news is achieved, and each group of the news is called a class cluster; all the obtained class clusters and the central vector of each class cluster are stored in a database. By means of the news information processing method, the news recommendation method and the related devices, the news with a higher similarity degree can be classified into one class cluster, and the class clusters can be stored in the database; when the news needs to be recommended, other news in the class cluster corresponding to the news can be recommended to a user.

Description

technical field [0001] The present invention relates to the technical field of news information processing, and more specifically, to a news information processing method, a news recommendation method and related devices. Background technique [0002] News recommendation means that when a user browses a certain news or after browsing the news, the system automatically recommends to the user other news that is related or similar to the content of the news that the user is currently browsing. [0003] The current news recommendation methods in the prior art mainly include the following two types: [0004] One is to recommend other news based on keywords in the current news content, and the other is to generate a space vector model based on the frequency of words in the current news content, calculate the similarity between news according to the space vector model, and then recommend Other news with content similar to the current news. [0005] However, the inventors of the p...

AI Technical Summary

Problems solved by technology

[0005] However, the inventors of the present invention have studied the existing news recommendation methods and found that for the first method of recommending other news based on keywords in the current news content, some keywords have multiple meanings, such as "apple" It means both a mobile phone and a fruit, so after the user browses the news related to the "Apple" mobile phone, the system may continue to recommend other news related to the "Apple" fruit for the user. At this time, most of the recommended news content is The content is not what the user needs, and the accuracy of news recommendation is reduced

For the second news recommendation method in the prior art, when the number of news is large, for example, when there are 10,000 news articles, after the noise vocabulary is preprocessed, hundreds of thousands of words will probably be generated. For these hundreds of thousands Words to generate a space vector model, the dimension of the generated space vector model is hundreds of thousands, then when calculating news similarity based on the space vector model of hundreds of thousands of dimensions, the calculation is quite complicated and time-consuming.

[0006] Based on the above content, none of the solutions in the prior art can accurately and efficiently implement news recommendation for users

Images