Self-learning method and device for customer service robot

A self-learning method and robot technology, applied in the field of self-learning methods and devices of customer service robots, can solve problems such as inability to effectively obtain user feedback information, and achieve the effect of ensuring practicability

Active Publication Date: 2015-06-10
CHINA MOBILE GRP BEIJING
View PDF4 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention is to overcome the defect that the expert system in the customer service robot in the prior art adopts a single question and answer and c

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
  • Self-learning method and device for customer service robot
  • Self-learning method and device for customer service robot
  • Self-learning method and device for customer service robot

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0080] Example one

[0081] In the first embodiment, after receiving the user question message, the optimal answer is determined by comparing the public preference weight values ​​of all answers pair by pair, and the user is asked about the satisfaction degree of the optimal answer, and then the maximum answer is updated according to the satisfaction degree returned by the user. The public preference weight value of the excellent answer. See figure 2 As shown, the detailed process of the self-learning method of the customer service robot is as follows:

[0082] Step 201: The user sends a user question message "How to charge the mobile phone number?" to the customer service robot through the user terminal.

[0083] Step 202: After receiving the user question message, remove the stop words in the question message according to the stop word list.

[0084] The stop word list is not fixed, and the stop words in the stop word list can be deleted or added according to the actual situation....

Example Embodiment

[0134] Example two

[0135] In the second embodiment, the self-learning device of the customer service robot includes: a natural language transceiver module 301, an intelligent answer selection module 302, an answer satisfaction collecting module 303, a weight processing module 304, and a data storage module 305.

[0136] See Figure 4 As shown, the self-learning process of the customer service robot self-learning device is as follows:

[0137] Step S401: The user submits a question to the natural language transceiver module 301 through the user terminal.

[0138] Step S402: The natural language transceiver module 301 initiates a question response request to the intelligent answer selection module 302.

[0139] Step S403: The intelligent answer selection module 302 understands and processes the question.

[0140] Step S404: The intelligent answer selection module 302 sends a data request message to the data storage module 305.

[0141] Step S405: The data storage module 305 returns the da...

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 self-learning method and device for a customer service robot. The method comprises the following steps: receiving a user message from a user terminal; retrieving a knowledge base according to the user message, selecting an optimal answer according to public preference weight values of retrieval results, and returning the optimal answer to the user terminal; after the optimal answer is returned to the user terminal, transmitting a satisfaction survey message to the user terminal; receiving a satisfaction reply message from the user terminal, recalculating a public preference weight value of the optimal answer according to the satisfaction reply message, and updating the knowledge base. According to the method and the device, user satisfaction is surveyed after the optimal answer is returned to a user, and the knowledge base is updated according to the feedback information of the user, so that the optimal answer can be provided for each user as far as possible, and the practicability of the knowledge base can be ensured.

Description

technical field [0001] The present invention relates to the technical field of human-computer interaction, in particular to a self-learning method and device for a customer service robot. Background technique [0002] Customer service robot is a human-machine question-and-answer service method derived from natural language processing technology. It has penetrated into various fields such as telecommunications, finance, and aviation, and has become an important service provision method for commercial enterprises. The service provided by the customer service robot to the user is one-way, that is, the question-and-answer knowledge is formulated in advance, and the corresponding answer is given after matching the user's question. This method cannot know the perception of the user after obtaining the service, and thus cannot improve the user experience. [0003] The disadvantages of the question answering system approach are: [0004] - The expert system adopts one-way question...

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
IPC IPC(8): G06F17/30
Inventor 武帅孟详粤魏静苗乔章玮杨英苹吴杰
Owner CHINA MOBILE GRP BEIJING
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