CLASSIFICATION MODEL-BASED FIELD EXTRACTION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND MEDIUM

摘要

A classification model-based field extraction method and apparatus, an electronic device, and a medium. The method comprises: when a public field extraction request is received, extracting a plurality of texts and preprocessing the texts; integrating the preprocessed texts to obtain a text fragment; sequentially selecting target values from a configuration interval, and extracting phrases from the text fragment by using the target values as extraction lengths (S12); calculating the degree of solidification of the phrases, and determining the phrases having the degree of solidification greater than a first threshold as first phrases (S13); calculating the frequency of the first phrases in the text fragment, and determining the first phrase having the frequency greater than a second threshold as a second phrase (S14); obtaining the context information of the second phrase in the text fragment (S15); inputting the second phrase, the frequency of the second phrase, and the context information into a pre-trained classification model so as to obtain an output result corresponding to the second phrase (S16); and when the output result is a public field, analyzing the second phrase to obtain an analysis result. Further involved is a blockchain technique, and an analysis result is stored in a blockchain.