Automatic corpus acquisition method, device, computer equipment and storage medium

Abstract

The invention discloses a corpus automatic acquisition method, device, computer equipment and storage medium, and relates to artificial intelligence technology. First, the LDA model is trained to obtain the LDA model according to each document in the corpus that has pre-marked the topic probability distribution result, and then the LDA model It is used to calculate the predicted topic probability distribution result according to the description text data of the input object, and finally, according to the predicted topic probability distribution result, select the corpus with the same topic in the corpus to form the first target corpus subset and send it to the client. The LDA model realizes the prediction of the required corpus in the interview process, and automatically screens and pushes the target corpus based on the predicted prediction topic, which not only improves the acquisition efficiency of the target text, but also improves the real-time performance by pushing the target text in a more timely manner.

Description

technical field [0001] The present invention relates to the technical field of speech and semantics of artificial intelligence, in particular to a method, device, computer equipment and storage medium for automatic acquisition of corpus. Background technique [0002] At present, in enterprise interview scenarios, interviewers communicate or test with interviewers based on a set of fixed interview procedures, and then obtain evaluation results for interviewers. During this process, the words and communication materials used by the interviewer can be the pre-stored text on the user terminal used by the interviewer, or the text provided in the printed materials. In this way, the user needs to operate the user terminal to edit the text or The text is selected from a large number of text databases in the database, and then it is determined whether to print the text according to the actual use requirements, which leads to the fact that the text finishing process is not the text se...

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a method, device, computer equipment, and storage medium for automatic acquisition of corpus, aiming to solve the problem that the words and communication materials used by the interviewer in the on-site interview scene in the prior art can be pre-installed on the user terminal used by the interviewer. The stored text can also be the text provided in the printed materials. The process of organizing the text is not automatically receiving the text sent by the system on the client side. There are problems of low text acquisition efficiency and poor real-time performance.

Images