Financial label extraction method and system based on keyword semantics

A tag extraction and keyword technology, applied in semantic analysis, natural language data processing, special data processing applications, etc., can solve the problems of tag recognition or classification method acquisition, achieve high vocabulary coverage, improve accuracy, and enrich The effect of financial labels

Pending Publication Date: 2020-05-05
新华智云科技有限公司
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the labels of industries, sectors, concepts, markets and other dimensions of financial public opinion are usually difficult to obtain by conventional entity recognition or classification methods, so further improvements to existing technologies are needed

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 label extraction method and system based on keyword semantics
  • Financial label extraction method and system based on keyword semantics
  • Financial label extraction method and system based on keyword semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Embodiment 1, a kind of financial tag extraction method based on keyword semantics, such as figure 1 shown, including the following steps:

[0057] S100, configuring a predefined label and a word vector table;

[0058] The above-mentioned predefined tags are the tags that users want to extract in advance, including but not limited to organizations, people, geographic locations, industries, sectors, concepts, markets and other dimensions. Users can freely set the categories and quantities of predefined tags according to actual needs .

[0059] S200. Extract keywords of the public opinion text, extract word vectors corresponding to the keywords from the word vector table to obtain keyword vectors, and extract word vectors corresponding to the predefined tags to obtain tag words vector;

[0060] The method for extracting keywords of the public opinion text in this embodiment is to use the existing keyword extraction algorithm to extract keywords from the public opinion ...

Embodiment 2

[0106] Embodiment 2, a kind of financial tag extraction system based on keyword semantics, such as Figure 4 As shown, it includes an information configuration module 100, an information extraction module 200 and a label output module 300;

[0107] The information configuration module 100 is configured to configure predefined labels and word vector tables;

[0108] The information extraction module 200 is configured to extract keywords of public opinion texts, extract word vectors corresponding to the keywords from the word vector table, obtain keyword vectors, and extract keywords corresponding to the predefined tags. The word vector of , get the label word vector;

[0109] In this embodiment, the information extraction module 200 includes a keyword extraction unit and a word vector extraction unit;

[0110] The keyword extraction unit is used to extract keywords of public opinion texts;

[0111] The word vector extraction unit is used to extract the word vector correspond...

Embodiment 3

[0118] Embodiment 3, a computer-readable storage medium stores a computer program, and when the program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

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 a financial label extraction method and system based on keyword semantics. The method comprises the following steps: configuring a predefined label and a word vector table; extracting a keyword of a public opinion text, extracting a word vector corresponding to the keyword from the word vector table to obtain a keyword vector, and extracting a word vector corresponding to the predefined tag to obtain a tag word vector; and calculating the similarity between each predefined label and the public opinion text based on the keyword vector and the label word vector, and extracting the corresponding predefined label according to the similarity to serve as a financial label of the public opinion text to be output. The multi-dimensional financial tags of the public opinion text can be accurately extracted.

Description

technical field [0001] The invention relates to the field of tag extraction, in particular to a method and system for extracting financial tags based on keyword semantics. Background technique [0002] Financial tags are of great significance to financial public opinion. Financial tags not only include physical tags such as relevant institutions, people, and geographical locations, but also need to extract specific tags related to the financial industry, stock sectors, financial concepts, markets, etc. to reflect the financial industry. Only financial public opinion with rich labels can provide financial public opinion consumers with fast analysis and processing of relevant data. [0003] Existing methods for extracting financial tags include using entity links to perform entity recognition on the text of financial public opinion, outputting tags based on the recognition results, and extracting tags using multi-classification. However, it is usually difficult to obtain the ...

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): G06F16/383G06F40/237G06F40/289G06F40/30
CPCG06F16/383
Inventor 李明玉
Owner 新华智云科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap