Unlock instant, AI-driven research and patent intelligence for your innovation.

Text error correction method based on knowledge graph

A knowledge map and text error correction technology, applied in the field of speech recognition, can solve problems such as difficulty in getting started, high personnel requirements, and low levels, and achieve the effect of assisting in scheduling words

Pending Publication Date: 2022-07-26
GUIZHOU POWER GRID CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the power grid dispatching system verifies whether the call content of dispatchers is correct in the process of issuing / returning orders, mainly through experience judgment and comparison with operation tickets. The existing methods have high requirements for personnel, and it is difficult for people who are not familiar with power grid business to get started. , and it is error-prone and inefficient to judge based on the experience of dispatchers

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
  • Text error correction method based on knowledge graph
  • Text error correction method based on knowledge graph
  • Text error correction method based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] refer to figure 1 , is the first embodiment of the present invention, which provides a text error correction method based on knowledge graph, including:

[0035] S1: Build a knowledge graph based on substation information and equipment switch information.

[0036] (1) Extract and integrate the organization, personnel, and phone number information in the DCCS database to obtain call information;

[0037] (2) Semantically analyze the operation ticket instruction data to obtain substation information and equipment switch information;

[0038] (3) Perform word sense disambiguation and synonym conversion processing on substation information and equipment switch information, and then store the processed information in the knowledge map, such as figure 1 shown.

[0039] Specifically, the steps of word sense disambiguation are as follows:

[0040] ① Mark the entities to be disambiguated in the substation information and equipment switch information, and then use the context...

Embodiment 2

[0069] The technical effect adopted in this method is verified and explained. In this embodiment, the traditional technical solution is selected and this method is used for comparative testing, and the test results are compared by means of scientific demonstration to verify the real effect of this method.

[0070] The traditional technical solution mainly corrects text errors through empirical judgment and comparison with operation tickets, which has a high error rate and low efficiency.

[0071] In order to verify that this method has a higher text error correction capability than the traditional technical solution, in this embodiment, the traditional technical solution and this method will be used to correct and compare the collected texts respectively.

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 text error correction method based on a knowledge graph, and the method comprises the steps: constructing the knowledge graph according to transformer substation information and equipment switch information; collecting call information of an on-duty dispatcher, and converting the call information into a dispatching text through an ASR automatic voice recognition technology; a scheduling instruction in the scheduling text is extracted through regularization, and then substation information and equipment switch information contained in the scheduling instruction are extracted through a knowledge graph; institution information is inquired through the call information, and substation information and equipment switch information of an institution are inquired according to the institution information; transformer substation information and equipment switch information contained in the dispatching instruction are compared with transformer substation information and equipment switch information of the mechanism, information with the highest matching degree is found through a similarity matching algorithm, namely, correct call information is found, and text error correction is completed; according to the method, technologies such as voice recognition, a knowledge graph and natural language processing are combined, scheduling term error correction is achieved, and then scheduling term standardization is assisted.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a text error correction method based on knowledge graph. Background technique [0002] At present, the power grid dispatching system verifies whether the content of the dispatcher's call is correct in the process of issuing / returning the order mainly through experience judgment and comparison with the operation ticket. , and judged by the experience of dispatchers, it is error-prone and inefficient. SUMMARY OF THE INVENTION [0003] The purpose of this section is to outline some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the application to avoid obscuring the purpose of this section, abstract and title, and such simplifications or omissions may not be used to limit the scope of the invention. [0004] The present inve...

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): G06F40/284G06F16/36G06F40/30G06F40/295G10L15/26
CPCG06F40/284G06F16/367G06F40/30G06F40/295G10L15/26
Inventor 冯义高适金宇朱鹏苏畅孙已茹潘嵩沈云春蒋猛
Owner GUIZHOU POWER GRID CO LTD