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

Chinese natural language processing and multi-core classifier based multi-information-source stock price prediction method

A technology of natural language processing and prediction method, applied in text database clustering/classification, electronic digital data processing, special data processing applications, etc., can solve the problem of not considering the influence and stay of text variable market

Inactive Publication Date: 2016-12-14
GUANGDONG UNIV OF TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing technical solutions do not consider the impact of text variables on the market. Even after the artificial intelligence method is adopted, some text variables are also used in the study of stock market changes, but these studies only stay at a certain level. on the text variable

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
  • Chinese natural language processing and multi-core classifier based multi-information-source stock price prediction method
  • Chinese natural language processing and multi-core classifier based multi-information-source stock price prediction method
  • Chinese natural language processing and multi-core classifier based multi-information-source stock price prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] Attached below figure 1 The present invention is further described. The invention conducts research on three aspects of multi-source stock price data collection, data processing, and stock price prediction model selection. figure 1 designed for our system.

[0012] The specific content of each step is described below:

[0013] 1. Multi-source stock price data collection

[0014] This step mainly collects domestic mainstream stock bar posts, research reports issued by the Research Report Center, financial announcements and financial data issued by some securities companies within a certain period of time.

[0015] 2. Raw data processing

[0016] The key is to score text data. In this step, two key technologies are involved. The first is Chinese word segmentation technology, and the second is how to score specific texts based on specific words. For Chinese word segmentation technology, we use n-gram algorithm for Chinese word segmentation and matching, statistical la...

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 provides a Chinese natural language processing and multi-core classifier based stock price prediction method and mainly relates to the fields of text message processing, financial sentiment analysis and the like. The Chinese natural language processing and multi-core classifier based stock price prediction method is characterized in that with development of networks and various media, people pay more and more attention to various text data issued through various media, the information published by users also has a certain tendency of stock trading, text type variables have larger influence on the stock market, the text type variables are converted into numeric data by collecting and analyzing multi-information-source stock data, a multi-core classifier is adopted for predicting stock prices, accordingly the internal relation of the tendency and fluctuation of various public opinion and stock movements is revealed, and meanwhile the part which cannot explain stock market change of traditional economical financial variables is supplemented.

Description

technical field [0001] The invention relates to the fields of data mining, machine learning, artificial intelligence and the like, and in particular relates to a sentiment analysis scoring model based on text keyword extraction. Background technique [0002] With the rapid development of more than 30 years, the stock market has taken a dominant position in my country's modern financial system, and many stock investment enthusiasts are emerging day by day. Due to the impact of politics, economy, technology, etc., the stock price fluctuates greatly. In order to maximize investment benefits, stock investors are eager to obtain a method that can accurately predict stock price changes. By comprehensively analyzing the variables that affect stock price changes, we can then predict the future trend of stock prices and better guide investment. Such applications fall under the category of data mining. [0003] The variables that affect the changes in the stock market include both n...

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): G06F17/30G06K9/62
CPCG06F16/35G06F18/2411
Inventor 饶东宁邓福栋
Owner GUANGDONG UNIV OF TECH
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