Voice detection analysis method, device thereof, computer equipment and storage medium

A technology of speech detection and analysis method, applied in speech analysis, speech recognition, instruments, etc., which can solve the problems of high difficulty and high maintenance cost, and achieve the effects of enhancing flexibility, improving user experience, and reducing implementation cost and complexity

Active Publication Date: 2018-12-07
京北方信息技术股份有限公司
View PDF17 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the detection model usually uses professional technical languages ​​such as regular expressions or database structured query language SQL statements to describe the quality inspection conditions, which usually requires technical personnel with computer programming background to complete, and ordinary business personnel have no way to start, and High maintenance cost and difficulty

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
  • Voice detection analysis method, device thereof, computer equipment and storage medium
  • Voice detection analysis method, device thereof, computer equipment and storage medium
  • Voice detection analysis method, device thereof, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Figure 1a It is a flow chart of a speech detection and analysis method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of evaluating whether the speech conforms to the regulations, and is especially suitable for the situation of performing quality inspection on the speech of a business call. Generally speaking, the speech quality Detection can be to check whether the speech content and method of business personnel (such as agents or customer managers, etc.) meet the regulations and requirements of the unit, including whether there are polite words, opening remarks, etc., and whether there are taboo words such as swear words and rude words, and identity verification is required Whether the business has completed the identity verification, whether the speaking order meets the requirements of the speaking skills, and whether the speaking speed is appropriate and other requirements. Or whether the content that the business p...

Embodiment 2

[0052] figure 2 It is a flow chart of a speech detection and analysis method provided by Embodiment 2 of the present invention, and this embodiment is the embodiment of the foregoing embodiments. The detection rule is embodied into multiple different types of detection rules to detect the speech to be analyzed. Specific as figure 2 As shown, the method of this embodiment specifically includes:

[0053] S201. Acquire speech to be analyzed.

[0054] S202. Determine at least one voice detection model matching the voice to be analyzed according to the type of the voice to be analyzed and the detected voice type information of the voice detection model, wherein the voice detection model includes at least one detection rule.

[0055] In this embodiment, the keyword rule can specify that the speech text to be analyzed for speech conversion contains keywords or excludes (cannot appear) keywords, and these keywords can be set by at least one setting detection condition, and at the...

Embodiment 3

[0122] Figure 3a It is a flow chart of a speech detection and analysis method provided by Embodiment 3 of the present invention. This embodiment is further optimized on the basis of the above-mentioned embodiments. In this embodiment, before obtaining the speech to be analyzed, it also includes: establishing a speech detection models and corresponding detection rules. Such as Figure 3a As shown, the method of this embodiment specifically includes:

[0123] S310. Establish a speech detection model according to model parameter information input by the user, where the model parameter information includes direct warning sign information of the speech detection model and speech type information of the detected speech to be analyzed.

[0124] In this embodiment, the direct warning flag information of the speech to be analyzed may refer to when the direct warning flag of the speech detection model is "yes" and the speech to be analyzed satisfies any detection rule in the speech d...

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

An embodiment of the invention discloses a voice detection analysis method, a device thereof, computer equipment and a storage medium. The method comprises the steps of acquiring a to-be-analyzed voice; according to the type of the to-be-analyzed voice and detecting voice type information of a voice detecting model, determining at least one voice detecting model which matches the to-be-analyzed voice; for aiming at each voice detecting model which matches the to-be-analyzed voice, determining the operation result of each detecting rule according to the speaker kind, content information, the rule type of each detecting rule, the operator and the preset detecting content in the to-be-analyzed voice; determining the operation result of each voice detecting model according to the operation result of the detecting rule, and evaluating the to-be-analyzed voice according to the operation result of each voice detecting model. The voice detection analysis method, the device thereof, the computer equipment and the storage medium have advantages of optimizing an existing voice detecting analysis method, improving voice detecting analysis flexibility, reducing realizing cost and complexity invoice detection analysis, and improving user experience.

Description

technical field [0001] The embodiments of the present invention relate to the field of voice detection, and in particular, to a voice detection and analysis method, device, computer equipment, and storage medium. Background technique [0002] In order to improve service quality and performance, call centers or customer service centers in banking, insurance, telecommunications, transportation, and other industries will conduct quality inspections of the voice conversations of agents or account managers in customer service work, marketing work, and other business scenarios to check the agent or account manager. Whether the content and method of the speech conform to the regulations and requirements of the unit. [0003] At present, existing voice quality inspection methods include manual quality inspection methods and voice quality inspection systems based on artificial intelligence technology. [0004] Among them, the manual quality inspection method is mainly through the qu...

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): G10L25/60G10L25/69G10L15/04G10L15/08G10L15/26
CPCG10L15/04G10L15/08G10L15/26G10L25/60G10L25/69G10L2015/088
Inventor 高昊江孙刚杨飞
Owner 京北方信息技术股份有限公司
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