Information processing method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses an information processing method and device, equipment and a storage medium. The method comprises the following steps: at least two candidate hot words in a to-be-analyzed phrase being extracted; calculating a first heat degree of each candidate hot word based on a Bayesian average method; calculating a second heat degree of each candidate hot word based on the Newton cooling law; performing weighted calculation on the first popularity and the second popularity of the same candidate hot word to obtain comprehensive popularity of the corresponding candidate hot word; and sorting at least two candidate hot words in the to-be-analyzed phrase according to the comprehensive heat of each candidate hot word, and determining the hot words in the to-be-analyzed phrase from the sorting result according to a set sorting sequence. According to the embodiment of the invention, the hot degree of each entry is accurately calculated by analyzing the network information, so that the hot words are mined.

Description

technical field [0001] The present invention relates to information processing, in particular to an information processing method, device, equipment and storage medium. Background technique [0002] Social networking sites such as Weibo, Tencent, Toutiao, etc. publish massive amounts of content every day. In order to facilitate users to understand the current popular content from the massive content, each website will analyze the massive content to determine the popularity of each entry. , so as to extract some popular entries as hot words. [0003] In related technologies, solutions for determining the popularity of entries include: Bayesian average method, Newton's law of cooling and other heat analysis methods. Among them, the ranking of hot words based on the Bayesian averaging method is more reasonable, but the popularity calculated by this method is not very differentiated, and some popularity is not reasonable. The cooling coefficient calculated according to Newton'...

AI Technical Summary

Problems solved by technology

Among them, the ranking of hot words obtained by the Bayesian averaging method is more reasonable, but the popularity calculated by this method is not very differentiated, and some popularity is not reasonable

The cooling coefficient calculated according to Newton’s law of cooling has a relatively large change range, and its heat change is relatively clear, but it is overestimated for words with a relatively high word frequency today and yesterday. Therefore, these schemes cannot accurately calculate the heat of each entry

Images