Industry classification model training method and device, industry classification model classification method and device

Abstract

The embodiment of the invention relates to the field of big data processing, in particular to an industry classification model training method and device and an industry classification model classification method and device, and the method comprises the steps that a client constructs a field word library, and the field word library is composed of texts of field words and corresponding fields to which the fields belong; the client processes a training text set including the enterprise name and the label category according to the field word lexicon, including word segmentation and semantic enhancement of the enterprise name to obtain word vector features of the enterprise name, and the word vector features of the enterprise name are obtained by weighted combination of word vectors after word segmentation of the enterprise name. And finally, the client trains a classifier for industry classification according to the word vector features and the label categories of the enterprise names to obtain a supervised machine learning multi-classification model, and the model can complete industry classification of the enterprise based on the enterprise abbreviation, so that the accuracy of enterprise classification is ensured, and the processing efficiency can be improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of big data processing, and in particular to a method for training an industry classification model, a classification method and a device. Background technique [0002] With the rapid development of the economy, more and more credit cards have penetrated into people's daily life. A credit card is a non-cash transaction payment method and a simple credit service. When applying for a credit card, the applicant needs to fill in the name of the employed company and the type of industry corresponding to the company. The industry of the applicant is an important factor to be considered in evaluating its risk and precision marketing. However, in the actual application, due to the subjectivity of some applicants, it is easy to fill in the incomplete name of the enterprise and the wrong type of industry. For this reason, the auditors of commercial banks need to spend a lot of time and cost to check,...

AI Technical Summary

Problems solved by technology

However, in the actual application, due to the subjectivity of some applicants, it is easy to fill in the incomplete name of the company and the wrong type of industry

For this reason, the auditors of commercial banks need to spend a lot of time and cost to check, which is inefficient

Images