Enterprise portrait method based on label layered depth-delay modeling

Abstract

The invention discloses an enterprise portrait method based on label layered depth-delay modeling, and the method comprises the steps: firstly carrying out the statistics and screening of fuzzy labelsof an enterprise, screening out labels which cannot completely summarize the characteristics of the enterprise, such as wholesale industry and retail industry, and carrying out the classification anddepth-delay of the screened-out labels through employing a Bert model according to the business range of the enterprise and the labels of the enterprise; secondly, integrating enterprise names, enterprise brief introductions and operation range information, performing feature expansion based on a pre-established enterprise lexicon, extracting keywords from comprehensive information by using TextRank, TF-IDF and LDA topic models respectively, and taking the processed keywords as deeper enterprise delay labels; finally, applying the modeling method to an enterprise portrait system, and optimizing the accurate summarization capability of the label. The method is universally suitable for label delay modeling and label extraction, the hierarchical relationship of label delay is fully considered, and the accuracy of labels and enterprise portrait systems can be effectively improved.

Description

technical field [0001] The invention belongs to the technical field of enterprise portraits and natural language processing, and in particular relates to a method for enterprise portraits based on label layered deepening modeling. Background technique [0002] The layered extension of the label in the present invention has an important effect and significance on the image technology. When faced with the problem of portrait labeling, researchers usually choose classification matching, but this model has obvious shortcomings, ignoring the hierarchical relationship of labels from shallow to deep. Do further extended modeling. Therefore, the problem of label extension modeling can be well solved by combining neural network and natural language processing, thereby improving the accuracy of the label and portrait system. [0003] The existing research foundations of Li Xiang, Zhu Quanyin and others include: X.Li, Z.Wang, S.Gao, R.Hu, Q.Zhu and L.Wang,"An Intelligent Context-Awar...

AI Technical Summary

Problems solved by technology

[0006] Yang Lingyun, Yang Wenfeng, etc. A method and system for providing corporate portraits: CN111666377A, 2020.06.03. This invention provides a method and system for corporate portraits. By collecting corporate identification information, analyzing and processing label data to establish corporate portraits, Although this invention provides a method for constructing corporate portraits, it does not conduct further research on labels; Xu Qingyuan, Wang Qili, etc. A method and device for creating corporate portraits: CN108572967A, 2018.09.25, this invention proposes a The method and system for enterprise portraits classify by obtaining enterprise portrait data, and then match the classified data with enterprise information. Although this invention can divide enterprise labels, the generalization ability of classified labels is limited and cannot accurately describe the characteristics of enterprises. ; Ni Xiaochun, Zeng Shuai, etc. A method of building a corporat

Images