Intelligent scoring method and device based on semantic recognition and storage medium

A semantic recognition and intelligent technology, applied in the field of semantic recognition, can solve problems such as low efficiency, inaccurate scoring, affecting customer experience, repair system evaluation, etc., to achieve the effect of increasing attention and enhancing expression ability

Inactive Publication Date: 2020-10-09
SOUTH CHINA UNIV OF TECH
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the service level of the repair system can only be evaluated according to the actual situation of the repaired equipment. This method is inefficient and ignores whether the technicians have professionalism and good communication skills when communicating with customers. These factors can affect customer experience and evaluation of the repair system
Similarly, in communication, banking and other service industries, there is a process of telephone communication between customer service and customers. Usually, each service of customer service is scored by the customer, but there are problems that the scoring is not objective enough and many customers do not rate.

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
  • Intelligent scoring method and device based on semantic recognition and storage medium
  • Intelligent scoring method and device based on semantic recognition and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] like figure 1 and figure 2 As shown, the speech data is converted into text data based on the stochastic model method, which involves three technologies: Dynamic Time Programming (DTW), Hidden Markov Model (HMM) theory and Vector Quantization (VQ) technology.

[0032] An intelligent scoring method based on semantic recognition is used in the evaluation method of voice and text service levels in the communication process between maintenance personnel and service personnel in the mechanical field.

[0033] Including the following steps:

[0034] S1 recognizes the voice information, converts the voice information into a text form, and obtains the voice text;

[0035] It mainly recognizes and records the voice information of maintenance technicians and converts it into text. The voice information is mainly the voice chat record or telephone communication record of the communication APP. It can also collect text information, mainly the text chat record of the communicatio...

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 an intelligent scoring method and device based on semantic recognition and a storage medium, and the method comprises the steps: S1, recognizing voice information, converting the voice information into a text form, and obtaining a voice text; S2, training a word vector, and representing a voice text in the form of a data matrix; S3, extracting semantic features of the voicetext by using a convolutional neural network; and S4, scoring the service level according to the voice text and the semantic features after truncation and completion in the S2. According to the invention, the intelligent technology is used for assisting the manual service, the service of the mechanical equipment repair system is scored from the perspective of language, and the overall service level and the customer experience of the repair system can be effectively improved.

Description

technical field [0001] The invention relates to the field of semantic recognition, in particular to an intelligent scoring method, device and storage medium based on semantic recognition. Background technique [0002] When all kinds of large and small mechanical equipment fail in actual application, they need to report to the equipment repair system for repair. The repair system usually sends technicians to connect with customers and put forward maintenance opinions in communication with customers. At present, the service level of the repair system can only be evaluated according to the actual situation of the repaired equipment. This method is inefficient and ignores whether the technicians have professionalism and good communication skills when communicating with customers. These factors can affect customer experience And the evaluation of the repair system. Similarly, in communication, banking and other service industries, there is a telephone communication process betwe...

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): G10L15/01G10L15/26G10L15/16G06F40/30G06N3/04G06N3/08
CPCG10L15/01G10L15/16G06F40/30G06N3/049G06N3/08G06N3/044G06N3/045
Inventor 姚望黄延禄
Owner SOUTH CHINA UNIV OF TECH
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