Semantic analysis method and system based on complex scene

A semantic analysis and complex scene technology, applied in semantic analysis, speech analysis, speech recognition, etc., can solve the problems of insufficient intelligent customer service information resolution and processing capabilities, data processing deviations, etc., to ensure service quality, improve accuracy, and avoid The effect of semantic interference

Active Publication Date: 2021-09-03
图观(天津)数字科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a complex scene-based semantic analysis method and system, which solves the lack of intelligent customer service information resolution and processing capabilities of electric power services in the prior art, especially in complex scenes where customer consultation content is subject to other interference information The impact of data processing has biased technical issues

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
  • Semantic analysis method and system based on complex scene
  • Semantic analysis method and system based on complex scene
  • Semantic analysis method and system based on complex scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Such as figure 1As shown, the embodiment of the present application provides a complex scene-based semantic analysis method, the method is applied in the power grid customer service system, and the method includes:

[0035] Step S100: Obtain the first voice information through the grid customer service system;

[0036] Specifically, the era of mobile Internet has arrived, and the various needs of Internet users based on PCs have gradually shifted to mobile terminals. The development of full-featured mobile browsers has broken technical barriers, and it is no longer possible to rely solely on existing Web-side website services. To meet the needs of users for convenient power services in the era of mobile Internet, it has become an inevitable trend in the development of power services in the new era to closely focus on user experience and focus on convenient power services for users. It is necessary to expand the WAP version of mobile terminals on the basis of Web sites. ...

Embodiment 2

[0106] Based on the same inventive concept as the complex scene-based semantic analysis method in the foregoing embodiments, the present invention also provides a complex scene-based semantic analysis system, such as figure 2 As shown, the system includes:

[0107] A first obtaining unit 11, the first obtaining unit 11 is used to obtain the first voice information;

[0108] The second obtaining unit 12, the second obtaining unit 12 is configured to perform audio decomposition on the first speech information to obtain the audio analysis result of the first speech;

[0109] The first judging unit 13, the first judging unit 13 is used to judge whether the first speech audio analysis result contains interfering audio;

[0110] A third obtaining unit 14, the third obtaining unit 14 is configured to obtain the first user audio information according to the first speech audio analysis result when included;

[0111] A fourth obtaining unit 15, the fourth obtaining unit 15 is configu...

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 semantic analysis method and system based on a complex scene, and the method comprises the steps: carrying out audio decomposition of first voice information to obtain a first voice audio analysis result; judging whether interference information is included; if yes, obtaining first user audio information according to the first voice audio analysis result; obtaining a first audio feature according to the first user audio information; inputting the first audio feature and the first voice information into an audio extraction model to obtain a first voice analysis result; obtaining a preset power service term database; according to the first voice analysis result and a preset power service term database, obtaining first matched power information; and when the matching degree of the first matching power information and the first voice analysis result meets a condition, taking as a first voice semantic processing result. The technical problems that intelligent customer service information distinguishing and processing capacity of electric power service is insufficient, and particularly, customer consultation content in a complex scene is affected by other interference information, and data processing has deviation are solved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a complex scene-based semantic analysis method and system. Background technique [0002] With the advent of the Internet age, various network service systems have brought convenience to people's lives, and the power industry has also followed the army of the Internet. State Grid Corporation vigorously promotes the "Internet +" strategy to create a unified online service platform. The company requires to speed up the establishment of an Internet service platform for customer aggregation, business integration, and openness and sharing, so as to realize online processing of all businesses and all-weather "one-stop" service. Integrate into the needs of social public service ecology. At present, there are a large number of energy-using customers in society and a wide range of energy-using needs, but efficient, convenient, and personalized energy services are s...

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): G10L15/10G10L15/20G06F40/30G10L15/18
CPCG10L15/10G10L15/20G10L15/1815G10L15/1822G06F40/30
Inventor 张安华董艳敏刘畅李颖王凯吉瑞贤王维孙晓婕
Owner 图观(天津)数字科技有限公司
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