Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Emotion analysis method and system for enterprise subjects in financial news

A sentiment analysis, enterprise technology, applied in the field of data processing, can solve the problems of RNN gradient disappearance, limited memory effect, powerlessness, etc., to achieve the effect of high classification accuracy, reduced labor costs, and easy maintenance

Pending Publication Date: 2019-10-01
郭刚
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the long-term short-term memory network (LSTM) commonly used in the past has effectively improved the problem of RNN gradient disappearance through the gating mechanism on the basis of the recurrent neural network (RNN), the improvement of its memory effect is also very limited, and it involves sentiment analysis. When it comes to natural language reasoning tasks, it seems quite weak

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
  • Emotion analysis method and system for enterprise subjects in financial news
  • Emotion analysis method and system for enterprise subjects in financial news
  • Emotion analysis method and system for enterprise subjects in financial news

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1 Shown, the present invention provides a kind of sentiment analysis method of business main body in financial news, it is characterized in that, described method comprises the following steps:

[0043] S1: collect news data, perform model training according to the collected news data, and obtain a classification prediction model;

[0044] S2: Input the news data to be classified into the classification prediction model, and perform classification prediction on the emotional labels of the business entities in the news data to be classified.

[0045] Preferably, the step S1 includes: using crawler technology to collect financial news data; and summarizing the names of companies that need attention into a table.

[0046] Specifically, a web crawler is used to grab as many financial news materials as possible from news data sources, and the financial news materials are stored in the database in the form of text. Sources of news data include the company new...

Embodiment 2

[0067] Figure 6 A flow chart of the method for training the classification prediction model and classifying the emotional labels of the enterprise subjects is shown in the present invention.

[0068] Among them, the specific implementation of the method for training the classification prediction model and the method for classifying the emotional labels of the main body of the enterprise is the same as the implementation of the model training method and label classification method described in the first embodiment. Let me repeat.

Embodiment 3

[0070] The present invention provides an emotional analysis system for business entities in financial news, the system includes a data capture module, a model training module, and a label classification prediction module;

[0071] The data capture module is used to collect financial news data using crawler technology;

[0072] The model training module is used to obtain training samples and test samples Sample=(N, ST, T, L) from the data set according to a predetermined ratio; text is input into the BERT model, and the hidden layer of the last layer of the BERT model is obtained Layer output as a word vector representation of the text;

[0073] Use the deep learning network to encode the full text of the news N and put it into the main memory of the model, and store the vector representation of each sentence obtained after processing into the main storage module; use the deep learning network to encode the sentence S where the main body of the enterprise is located and put it ...

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 relates to an emotion analysis method and system for enterprise subjects in financial news, and the method comprises the following steps: S1, collecting news data, carrying out the modeltraining according to the collected news data, and obtaining a classification prediction model; and S2, inputting to-be-classified news data into the classification prediction model, and performing classification prediction on the emotion tags of the enterprise subjects in the to-be-classified news data. The method is designed on the basis of a more advanced text representation model BERT and a memory network model of a double-storage structure, the classification accuracy is higher, meanwhile, domain experts do not need to formulate a rule template to extract additional features, the labor cost is reduced, and maintenance is convenient.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a sentiment analysis method and system for business entities in financial news. Background technique [0002] With the rapid development of Internet technology, the speed of news generation far exceeds the speed that humans can process manually. Therefore, it is necessary to use computers to mine and process massive amounts of data. In the financial field, financial news plays a very important role in evaluating the credit risk of a company. By classifying the emotions of the main body of the company in the financial news (usually positive, negative and neutral), we can effectively understand the positive side of the company. Or negative reports, thus providing a basis for further adjustments to corporate credit risk ratings. [0003] In financial news, there are three categories of sentiment analysis methods for specific corporate entities: sentiment dictionary-based me...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06F16/951G06F17/27
CPCG06F16/951G06F40/30G06F18/24G06F18/214
Inventor 高正杰郭刚郭敏陈涵昱喻娇贺晶莹
Owner 郭刚
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com