Enterprise national industry category prediction method and system based on LSTM deep learning

Abstract

The invention provides an enterprise national industry category prediction method and system based on LSTM deep learning. According to the invention, the method comprises: using the enterprise operation range as basic data; obtaining valid data therefrom, establishing an industry classification model matched with the acquired effective data; predicting the national industry category of the newly added enterprise according to the industry classification model. According to the prediction method, the neural network algorithm LSTM is fused, so that the position information of the enterprise in the industry chain can be obtained more flexibly and accurately, a plurality of vigorously developed small and micro innovative enterprises are subjected to scientific industry division, tax bureau personnel are facilitated to the greatest extent, and the requirements of the personnel are not limited.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a method and system for predicting enterprise and national industry categories based on LSTM deep learning. Background technique [0002] The national economic industry classification is the basic classification for classifying the economic activities of the whole society, the most widely used and most frequently used classification standard in statistical work, and the basis for processing and exchanging economic census information. [0003] National economic industry classification is an important application in the field of natural language processing. First of all, in terms of text feature representation, there are two types of word vectors and word bag models. Since most industry-wide descriptions are proper nouns, word vectors are not suitable for this scenario. Moreover, how to extract the business keywords in the enterprise description has be...

Images