Enterprise-industry classification system based on automatic information screening

Abstract

The invention relates to the information processing field and particularly relates to an enterprise-industry classification system based on automatic information screening. According to the system, an industry classification neural network model is constructed by combining a circulating neural network with a threshold control method, and the automatic classification judgment of secondary industries of enterprises is realized according to business scope information and name information of the enterprises. According to the system, features of text data are automatically extracted by virtue of a deep learning technique and a GRU circulating neural network, the automatic information screening and filtering of the business scope based on a company name can be realized by adding a threshold controlled neural network, and key information is automatically screened from different types of the secondary industries which are difficultly differentiated, so that the efficient and precise prediction of the types of the secondary industries is realized. The deficiency that a circulating neural network is independently used is remedied, and meanwhile, the advantage of the neural network that the features are automatically extracted without manual intervention is developed.

Description

technical field [0001] The invention relates to the field of information processing, in particular to an enterprise industry classification system based on automatic information screening. Background technique [0002] With the progress of society and the prosperity and development of the market, China's economy has been on a high-speed development track. As the most important activity subject in the social economy, enterprises play an important role in the economy. Help relevant decision makers understand the business status of the company and discover potential business risks. There are many secondary industry categories of enterprises. If a large number of enterprises are manually classified, it will consume a lot of manpower. [0003] Usually, data mining is carried out with the help of machine learning to automatically complete industry classification. There are two mainstream methods: one is to use traditional machine learning methods, first to manually extract featu...

AI Technical Summary

Problems solved by technology

Compared with the first-level industry classification, the second-level industry classification has more similarities between different industries in the description of business scope, which makes it difficult to find such small differences with conventional methods, and thus makes it difficult to make correct judgments

If you use traditional machine learning methods, you need to do a lot of feature engineering, such as TF-IDF, N-GRAM and other methods to extract important features to form high-dimensional vectors and put them into different classifier algorithms for experimentation and parameter adjustment. The workload is heavy. But it is heavy, and it is all based on some people's experience and conjectures. It is likely that a lot of energy has been spent, but the final effect is not significant.

Even if deep learning methods are used, such as recurrent neural networks, although some manual feature extraction tasks are eliminated, since the description information of the business scope is usually scattered and contains the content of multiple industries, it is impossible to determine which ones from the business scope alone. The information is effective for judging the industry category

Images