Listed-company announcement classification and abstract generation method based on deep learning

Abstract

The invention discloses a listed-company announcement classification and abstract generation method based on deep learning. The method comprises the following steps: step 1, acquiring announcement original-text data, extracting text, picture and form information, and establishing structured documents. step 2, establishing a classification rule word library of different announcements on the basis of industry knowledge of announcement fields according to various company operation change event keyword differences, and carrying out statistical judgment on announcement classes; and step 3, for the announcements of the different classes, extracting announcement document contents, combining the rule word library of corresponding class keywords to train an announcement content classification model, and automatically generating document abstract contents, wherein content extraction, training set selection, keyword model optimization, model training, model testing, result analysis and content generation are included. The method can solve technical problems of automatically classifying the announcements for a large amount of announcement information generated each day, automatically extracting key and important information according to classification situations, generating the abstract contents and the like.

Description

technical field [0001] The invention relates to a method for classifying announcements of listed companies and generating abstracts. Background technique [0002] Listed company announcements: In the securities market, listed companies need to regularly disclose or announce to the public their financial changes, operating conditions and other major corporate events related to securities transactions, such as prospectuses, listing announcements, in accordance with the information disclosure system of relevant regulatory agencies. Books, semi-annual reports, quarterly reports, interim reports, etc. In my country, there are more than 2,000 A-share main board announcements produced on the Shanghai and Shenzhen stock exchanges every day, and more than 2,000 announcements on the New Third Board every day, covering information on business changes of all listed companies on the third board and the main board. For most investors, it is difficult to read and analyze the contents of t...

AI Technical Summary

Problems solved by technology

Since the supervised classification method requires a large amount of labeled data as a training set, and the current corporate announcements of listed companies are complicated, and the judgment standards of different people cannot be unified, so the text summarization method based on machine learning still needs to be continuously explored and improved.

Images