Large sample research report information extraction method and apparatus, device, and storage medium

Abstract

The invention relates to a large sample research report information extraction method and apparatus, a computer device and a readable storage medium, and the method comprises the steps: carrying out text conversion on research report information to obtain table data, and storing the table data in a pure text form; counting the table data, and outputting the word frequency of each word in the tabledata; carrying out statistics on the research report information to obtain a similarity degree index between each piece of research report information and the rest of research report information, andsorting the indexes; and drawing a relationship network of the research and report information by taking the number of the research and report information as a node and taking the obtained similarityindex as a branch. The method has the advantages that the research message meaning similarity degree index is obtained based on the Zipf law and the two-eight law, the relation network of the research message information is drawn, most research messages which are important and approximate in meaning can be screened out according to the relation network, and therefore valuable research message information can be screened out more efficiently.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of financial data processing, and in particular to a method, device, and readable access medium for extracting large sample research report information. Background technique [0002] Research report information is referred to as research report. In the financial industry, it refers to the analysis of the operating conditions and profitability of some listed companies based on an independent and objective standpoint. It is of great significance to fund managers. [0003] For most fund managers on the buy side, they are faced with a large number of research reports every day, and it is obviously impossible to read most of them in a limited time. At present, for fund managers in the industry, even if they selectively read the research reports based on their personal experience and industry understanding, they cannot fully reflect all the key information or central issues in the massive...

AI Technical Summary

Problems solved by technology

At present, for fund managers in the industry, even if they selectively read the research reports based on their personal experience and industry understanding, they cannot fully reflect all the key information or central issues in the massive research reports, let alone It is said that personal experience and industry understanding itself has a lag and there are still unfamiliar areas for individuals. Therefore, how to help fund managers screen research reports in as little time as possible and obtain sufficient and useful information is a problem. important practical issues

Images