Problem locating method and device of feedback contents, computer equipment and storage medium

A positioning method and content technology, applied in the computer field, can solve the problems of low positioning accuracy and poor versatility, and achieve the effect of precise automatic positioning and universality.

Active Publication Date: 2017-11-07
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a problem location method and device for feedback content, computer equipment, and storage media to solve the problems of low problem location accuracy and poor versatility in the prior art

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
  • Problem locating method and device of feedback contents, computer equipment and storage medium
  • Problem locating method and device of feedback contents, computer equipment and storage medium
  • Problem locating method and device of feedback contents, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 The flow chart of the problem locating method for feedback content provided by Embodiment 1 of the present invention, this embodiment is applicable to the situation of automatically locating text feedback problems, and this method can be executed by a device for locating problems of feedback content, which can It is realized by means of software and / or hardware. Such as figure 1 As shown, the method specifically includes:

[0026] S110. Use a pre-trained classifier to classify the feedback content to obtain the question category to which the feedback content belongs.

[0027] Wherein, the feedback content may be feedback content extracted through various feedback channels. Exemplarily, the feedback content may be extracted through the mail feedback system, thus, before S110, the method may further include:

[0028] Polling the email feedback system according to the preset frequency to obtain full feedback emails;

[0029] Acquiring newly added feedback mai...

Embodiment 2

[0044] figure 2 The flow chart of the problem location method for feedback content provided by the second embodiment of the present invention, the second embodiment is further optimized on the basis of the first embodiment. Such as figure 2 As shown, the method includes:

[0045] S210. Determine whether the current accuracy rate of the classifier satisfies the preset threshold. If so, execute S220. Otherwise, execute S270 and then execute S230 and S280 respectively.

[0046] Wherein, the current classifier accuracy rate is the accuracy rate calculated after the pre-trained classifier performs prediction according to the current training samples.

[0047] What needs to be explained here is that since the extracted samples directly affect the effect of machine learning, in order to satisfy the self-iterative update of the classifier model and continuously strengthen the recognition accuracy, the embodiment of the present invention pre-sets the accuracy threshold. When the cl...

Embodiment 3

[0058] image 3 It is a schematic structural diagram of a problem location device for feedback content in Embodiment 3 of the present invention. Such as Figure 4 As shown, the problem locator of the feedback content includes:

[0059] A classification module 310, configured to use a pre-trained classifier to classify the feedback content to obtain the question category to which the feedback content belongs;

[0060] The positioning parameter extraction module 320 is configured to obtain at least one parameter extraction template corresponding to the problem category, and extract positioning parameters from the feedback content according to the at least one parameter extraction template;

[0061] The rule verification module 330 is configured to obtain at least one verification rule corresponding to the positioning parameter, and perform verification in sequence according to the positioning parameter to obtain a verification result of each verification rule.

[0062] Prefer...

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

Embodiments of the invention disclose a problem locating method and device of feedback contents, computer equipment and a storage medium. The method comprises the following steps: classifying the feedback contents by utilizing a pre-trained classifier to obtain problem categories to which the feedback contents belong; obtaining at least one parameter extraction template corresponding to the problem categories, and extracting locating parameters from the feedback contents respectively according to the at least one parameter extraction templates; and obtaining the at least one verification rule corresponding to the locating parameters, and successively performing verification according to the locating parameters to obtain verification results of the verification rules. A problem is located through classification for the feedback contents, locating parameter extraction and rule verification, so accurate automatic locating for a feedback problem can be achieved and be universal.

Description

technical field [0001] The embodiments of the present invention relate to computer technology, and in particular to a method and device for locating problems in feedback content, computer equipment, and storage media. Background technique [0002] Enterprises usually have a dedicated problem feedback channel to receive user feedback, so as to continuously improve their products and services. For example, email has gradually become one of the most important feedback channels, and efficient identification of email and other various Feedback the problems in the content and automatically locate them, which can greatly reduce the repetitive work of customer service and R&D personnel, and save the cost of the enterprise. [0003] At present, some enterprises have used natural language processing technology to identify and automatically reply to questions. Set reply message. However, the positioning accuracy of this kind of problem is low, and it is impossible to make further ana...

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): G06K9/62
CPCG06F18/2411
Inventor 王辉姚垒
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
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