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

Financial event extraction method based on combination of pre-training language and deep learning model

A deep learning and event extraction technology, applied in finance, computing model, machine learning and other directions, can solve the problem that financial text cannot build corpus data set, and achieve the effect of reducing time cost and labor cost, improving effect, and reducing data noise.

Inactive Publication Date: 2022-01-14
中电积至(海南)信息技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a financial event extraction method based on a pre-trained language combined with a deep learning model, which solves the problem that financial texts cannot construct an effective corpus data set

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
  • Financial event extraction method based on combination of pre-training language and deep learning model
  • Financial event extraction method based on combination of pre-training language and deep learning model
  • Financial event extraction method based on combination of pre-training language and deep learning model

Examples

Experimental program
Comparison scheme
Effect test

no. 2 example

[0088] Based on the first embodiment of the present invention based on the pre-training language combined with the financial event extraction method of the deep learning model, the second embodiment of the present invention provides another financial event extraction method based on the pre-trained language combined with the deep learning model, wherein the second implementation Examples will not hinder the independent implementation of the technical solution of the first embodiment.

[0089] Specifically, the present invention provides another financial event extraction method based on pre-trained language combined with a deep learning model. The difference lies in:

[0090] It also includes a running system for completing financial event extraction, the running system includes a data acquisition module for obtaining public financial event text corpus, a data processing module for text preprocessing of the original financial event text corpus, and a data processing module for ...

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 financial event extraction method based on combination of a pre-training language and a deep learning model. The financial event extraction method based on combination of a pre-training language and a deep learning model comprises the following operation steps: S1, data acquisition and preprocessing: crawling public financial event text corpora by using a web crawler, and performing text preprocessing on the original financial event text corpora. According to the financial event extraction method based on combination of a pre-training language and a deep learning model provided by the invention, financial field event types and templates are defined by using a mode of combining machine learning with field knowledge, so that the time cost and the labor cost of manually defining events are greatly reduced; large-scale automatic labeling of financial field event corpus data is realized by using a remote supervised learning mode; data noise is effectively reduced by using a heuristic pruning method; and the blank of lack of large-scale corpus data in the current financial event extraction field is filled.

Description

technical field [0001] The invention relates to the field of financial intelligence, in particular to a method for extracting financial events based on a pre-trained language combined with a deep learning model. Background technique [0002] Financial event extraction is the application of event extraction technology in the field of financial intelligence. In the financial field, investors' decisions are affected by various factors, such as the company's own news, political policies, and macroeconomic factors. These factors are often presented in the form of text To the public, and the event information contained in most texts will become the main factor affecting the market status in the financial field; therefore, financial event extraction can help investors obtain the company's main events, identify investment risks and investment opportunities, predict the stock market trend, and do make sound investment decisions. [0003] With the rapid development of information tec...

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): G06F16/951G06F40/216G06F40/289G06K9/62G06N20/00G06Q40/02G06V10/762
CPCG06F16/951G06F40/289G06F40/216G06Q40/02G06N20/00G06F18/23213
Inventor 郑超黄园园张智勇孙彦斌田志宏
Owner 中电积至(海南)信息技术有限公司
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