Phrase dictionary real-time generation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of big data in artificial intelligence, and discloses a phrase dictionary real-time generation method comprising the steps that a real-time cache data setis acquired, and the real-time cache data set is a data set obtained after a real-time data set crawled according to a preset rule is transmitted to a distributed message queue to be cached in real time; extracting phrase texts in the real-time cache data set to generate a phrase text set; inputting the phrase text set into a preset distributed search engine for preprocessing operation to obtain atarget phrase text set; and receiving a to-be-queried phrase text, querying an associated phrase text of the to-be-queried phrase text according to a target phrase text set in the distributed searchengine, and generating a phrase dictionary. The invention further provides a phrase dictionary real-time generation device, electronic equipment and a computer readable storage medium. According to the invention, the phrase dictionary can be generated in real time.

Description

technical field [0001] The present invention relates to the technical field of big data in artificial intelligence, in particular to a method, device, electronic equipment and computer-readable storage medium for generating a phrase dictionary in real time. Background technique [0002] The phrase dictionary is used to record proper nouns in a certain field. For example, the phrase dictionary in the financial and insurance industry records proper words such as product names such as insurance and wealth management, such as enjoying life. With the passage of time and the development of society and economy, phrase dictionaries need to be continuously generated and updated. The generation and update of traditional phrase dictionaries is a long process, usually taking one to two months. Especially in the financial market analysis platform, merging new financial information with the existing phrase dictionary, and re-processing and restoring the word symbols of the phrase dictiona...

AI Technical Summary

Problems solved by technology

Especially in the financial market analysis platform, it will take a lot of time to merge the new financial information with the existing phrase dictionary, re-process the text symbols of the phrase dictionary and restore the form of the word

In addition, there are almost no real-time and effective phrase dictionaries in the financial market analysis market, which will lead to low reliability and effectiveness of the financial market behavior analysis platform, and cannot obtain the most real-time and effective data

Images