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

Financial field-oriented generalization entity identification method and system

A kind of entity recognition and entity technology, which is applied in the direction of instruments, electrical digital data processing, calculation, etc., can solve the problems of lack, organization name nesting, alias and acronym, entity context information difficult to obtain, etc., to achieve efficient information acquisition and solution Effects of Entity Recognition Difficulty

Pending Publication Date: 2021-10-29
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (2) Lack of high-quality annotated corpus resources in the financial field
[0006] (3) There are a large number of entities with complex structures in the financial field. For example, organization names have a large number of nesting, aliases, acronyms, etc., and there are no strict rules to follow, making it difficult to obtain entity context information and entity boundaries.
Due to the lack of high-quality labeled corpus resources in the current named entity recognition research in the financial field, there is still a lack of excellent models in named entity recognition in the financial field, while information extraction, information filtering, information retrieval, question answering systems, etc. This kind of natural language processing technology needs named entity recognition as an important basic technical support, so it is difficult to carry out more information exploration in the financial field

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 field-oriented generalization entity identification method and system
  • Financial field-oriented generalization entity identification method and system
  • Financial field-oriented generalization entity identification method and system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0059] Input sentence: The Granger causality test shows that the financial development of Ningxia Hui Autonomous Region becomes the reason for promoting economic development. At the same time, economic growth is also the cause of financial development, that is, economic development and financial development are mutually causal. Economic development is inseparable from financial support, and as an underdeveloped region, Ningxia's economic development needs financial support even more. To develop the finance of Ningxia Autonomous Region, it is necessary to optimize the allocation of regional financial resources and promote the leapfrog development of Ningxia's economy. By directing financial funds to investment-oriented industries, it will drive Ningxia's economic growth and further promote Ningxia's financial development. First of all, it is necessary to actively introduce foreign capital, encourage private investment, and increase the total amount of financial resources. The...

example 2

[0062] Input sentence: The meeting pointed out that financial infrastructure is the basic guarantee for the stable and efficient operation of the financial market, and an important starting point for implementing macro-prudential management and strengthening risk prevention and control. It is necessary to strengthen the overall supervision of important financial infrastructure, unify regulatory standards, improve access management, optimize the layout of facilities, improve the governance structure, and promote the formation of a financial infrastructure system with reasonable layout, effective governance, advanced reliability, and flexibility.

[0063] The list of entities obtained: {"Risk Prevention and Control", "Regulation", "Financial Market", "Conference", "Financial Infrastructure", "Unified Regulatory Standards", "Prudential Management", "Fundamental", "Macro" }.

[0064] This project aims at the interaction between Chinese word segmentation and named entity recognition...

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 generalized financial entity identification method for the financial field comprises the following steps of: for an input long sentence in a financial related field, performing short sentence division by taking a comma and a score as units; calling a BiLSIM-CRF model to carry out entity recognition on the short sentences to obtain an entity list; determining whether the boundary of the entity separates the entity words; checking whether the separated boundary words meet conditions for forming entities or not; deleting the identified entities from the original sentences to obtain deleted sentences, and feeding the deleted sentences to a pattern matching function of the rule as input; according to the dictionary, performing word segmentation and part-of-speech tagging on the input short sentences; finding out all words marked as nouns, dynamic nouns or form nouns; calling a CN-DBpedia API for searching; and matching the IF conditional statements. The invention further comprises a generalization financial entity recognition system for the financial field. According to the method, the identification accuracy of the generalization entity in the financial field can be improved, and support is provided for related management mechanisms and researchers in the aspects of industry dynamic mastering, scientific decision making, model research and the like.

Description

technical field [0001] The invention relates to a BiLSTM-CRF model and a named entity recognition method and system, in particular to a generalized entity recognition method and system for the financial field, which can extract generalized entities in related fields from input financial sentences. Background technique [0002] With the continuous development of big data processing technology and the rapid development of global finance, financial information has shown explosive growth, and Internet finance has also entered the era of big data. Investors and decision makers often struggle with how to efficiently obtain content that needs attention when faced with the vast amount of Internet financial information. Using natural language processing technology to analyze it has become an inevitable trend of technology development. As an important basis in natural language processing technology, named entity recognition provides important basic technical support for various natur...

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): G06F40/295G06F40/242
CPCG06F40/295G06F40/242
Inventor 高楠俞凯乐周越冯伟强董嘉豪葛婧
Owner ZHEJIANG 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