Professional term extraction method and device in intelligent interview, equipment and medium

Abstract

The invention discloses a professional term extraction method and device in intelligent interview, computer equipment and a storage medium. The method comprises the following steps: based on preset Ndimensions, segmenting each character in the response statement, obtaining N phrase sets corresponding to each character, and taking all phrases corresponding to the character as candidate phrases; meanwhile, calculating the word frequency of each word group in the historical interview word bank; determining weight information of the phrase set; endowing the candidate phrases with the weight moreconforming to the interview scene; determining representation information of each character through the weight information; in combination with the representation information of the characters, determining the named entity contained in the response statement by adopting a preset sequence marking model with a simple structure, and storing the named entity in the blockchain network as a professionalterm without using a complex named entity extraction model, so that the efficiency of determining the named entity is improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a method, device, equipment and medium for extracting professional terms in intelligent interviews. Background technique [0002] Recruitment interview is a time-consuming and labor-intensive job, because there are many candidates but limited interviewers, and the interviewers need to continuously interview a large number of candidates in one day. In order to ask relevant questions about the candidate's experience in a timely manner, it is very important to understand the candidate's mastery of professional skills, extract the candidate's experience description and professional terms mentioned in the resume, and ask further questions. [0003] However, the extraction of technical terms needs to rely on named entity recognition. Named entity recognition is carried out through natural language processing algorithms. , currency and percentage) named entity extraction, the exi...

AI Technical Summary

Problems solved by technology

[0003] However, the extraction of technical terms needs to rely on named entity recognition. Named entity recognition is carried out through natural language processing algorithms. , currency and percentage) named entity extraction, the existing algorithm will directly select the most likely segmentation label for the character during word segmentation, instead of considering all possibilities, and the interview process involves more technical terms, these Most of the professional terms are difficult to be included in the preset named entities, so that the recognition accuracy is greatly affected by the training corpus, and there are more or less problems that the recognition accuracy is not high enough. At the same time, due to the use of more corpus, it is necessary to The complex structure of the model is processed, making the calculation efficiency low

Images