Supercharge Your Innovation With Domain-Expert AI Agents!

Analysis comment text generation method based on financial data

A financial data and text technology, applied in the field of analysis and comment text generation based on financial data, can solve the problems of high maintenance and migration costs, poor quality of generated text, lack of reasoning ability, etc., to expand the scope of action and enrich the text information , the effect of improving the production efficiency

Pending Publication Date: 2021-12-10
JIANGXI UNIVERSITY OF FINANCE AND ECONOMICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Currently, the most used method is the template-based method, which has the advantage of stable performance and speed, but it is not flexible enough, and as the complexity of the template increases, the cost of maintenance and migration is very high; the current most advanced method is based on neural networks. The method of the model, its advantage is that it is very flexible, and the generated text has good readability and diversity
However, there are still relatively few researches and applications of neural network text generation methods in the field of finance and economics. The public text models do not take into account the particularity of the field of finance and economics. The training speed is slow and the reasoning ability is generally lacking. The quality of the generated text is not good and the cost is high.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Analysis comment text generation method based on financial data
  • Analysis comment text generation method based on financial data
  • Analysis comment text generation method based on financial data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] The neural network text generation model generates the financial commentary text as follows:

[0053] Set the hyperparameters of the neural network text generation model to fine-tune the neural network text generation model;

[0054] Train a neural network text generation model using training set samples;

[0055] Use the verification set sample to verify the neural network text generation model, when the verification result shows that the error rate of the neural network text generation model remains stable, stop training the neural network text generation model, and save the current neural network text generation model;

[0056] Input the test set sample into the currently saved neural network text generation model to generate financial commentary text.

Embodiment 2

[0058]The data preprocessing step also includes: defining inference paradigm terms, position terms, numerical unification terms and dividing training set, verification set and test set.

[0059] The steps to create a text-table mapping vector are:

[0060] Traverse the tabular data in the enterprise's financial tables, and use the reasoning paradigm to standardize the tabular data;

[0061] Set the error threshold for tabular data;

[0062] If the standardized tabular data is within the error threshold, construct the reference text and text-table mapping vector of the financial commentary text, record the financial commentary text corresponding to the reasoning paradigm tabular data in the reference text, and record it in the text-table mapping vector Indexing of inference paradigm tabular data in sample vocabularies;

[0063] If the normalized table data is not within the error threshold, record the text content of the financial commentary text in the reference text of the ...

Embodiment 3

[0074] The neural network text generation model includes an embedding module, an encoding module, a decoding module, a generation module, an inference module and a semantic consistency check module;

[0075] The embedding module uses the sample vocabulary to build a vocabulary index embedding matrix, and the embedding module has different embedding representation strategies for value and text;

[0076] The encoding module is composed of two layers of encoders, the bottom layer encoder is used to maintain the dimension shape of the input data, and the high layer encoder is used to reduce the data dimension;

[0077] The decoding module is a recurrent neural network structure, which is used to calculate attention distribution and context vectors according to time steps;

[0078] The inside of the generating module includes a fully connected network and a softmax logistic regression model network;

[0079] The reasoning module locates the words to be reasoned according to the at...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an analysis comment text generation method based on financial data, and relates to the technical field of financial data processing. The method comprises the following steps of constructing a research corpus by adopting the listed company financial statements and the corresponding professional analysis comments disclosed on the Internet; pre-processing a data table and a comment text in the corpus, building a neural network text generation model, training the model, and performing text generation by using the model. According to the present invention, the production efficiency of the analysis comment texts in the financial field can be remarkably improved, and investors are helped to know the main content of financial newspapers. According to the analysis comment text generation method based on the financial data, the financial comments can be automatically generated according to the financial statements, and the generated text is rich in information, smooth in statement and high in readability.

Description

technical field [0001] The invention relates to the technical field of financial data processing, in particular to a method for generating analysis comment text based on financial data. Background technique [0002] Listed companies are obliged to publish their own financial statements on time and accurately, and report their financial status to regulators and investors. However, financial statements are highly professional, making it difficult for non-professionals to read. To solve this pain point, professional organizations will summarize the main information of listed companies’ financial statements, write relevant financial comments and publish them to investors. This approach is inefficient and expensive. [0003] The automatic generation of financial texts has a lot of room for development, but there is no relatively mature automatic generation system of financial texts. The core technology of this type of automatic financial text generation system is the data-to-te...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F40/166G06F40/174G06F40/205G06F40/237G06N3/04G06N3/08
CPCG06F40/166G06F40/174G06F40/237G06F40/205G06N3/08G06N3/047G06N3/044
Inventor 刘喜平谈锐万常选刘德喜
Owner JIANGXI UNIVERSITY OF FINANCE AND ECONOMICS
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com