Natural language semantic extraction method and system

Abstract

The invention relates to a natural language semantic extraction method and system. The method comprises the steps of: performing word segmentation on a target file with sentences as units to obtain word segmentation units; analyzing whether a plurality of word segmentation units in one sentence form a keyword or not; in response to one or more keywords formed by a plurality of word segmentation units in one sentence, extracting the sentence containing the keywords; performing syntactic analysis on sentences containing the keywords to obtain a syntax tree; and extracting effective keywords and corresponding semantic tags from the syntax tree. According to the method and the system provided by the invention, the keyword meeting the information recommendation requirement is extracted from the content of the related target file, and the effective keyword is obtained by performing grammatical analysis on the sentence containing the keyword and splitting and reconstructing the syntax tree, so that the real intention of the target file can be obtained, and the understanding degree of the target demand of the user is improved.

Description

technical field [0001] The invention relates to the technical field of semantic recognition, in particular to a natural language semantic extraction method and system applied to an information recommendation system. Background technique [0002] In the current information age, all kinds of professional or comprehensive information platforms can provide the information they need for both users with supply and demand relationships. For example, professional recruitment platforms provide a lot of recruitment information and job-seeking information for both supply-side recruiters and demand-side job seekers; some comprehensive websites provide a lot of advertising bidding information and advertising demand information, etc. Taking the recruitment market as an example, most job seekers and recruiters will choose to find suitable positions and talents from some online recruitment platforms. Usually, job seekers and recruiters will register on platforms such as recruitment website...

AI Technical Summary

Problems solved by technology

However, from practical experience, the position that the job seeker finally gets is not completely in line with the position indicated on the resume, and the recruiter's final recruitment is not completely in line with the recruitment information. Therefore, if you only stick to the content in the resume or recruitment information, A lot of jobs / talents that match the applicant / recruiter's intent will obviously be missed

Images