Unlock instant, AI-driven research and patent intelligence for your innovation.

Robot-based knowledge base deep auditing and tuning method and system, and storage medium

A knowledge base and robot technology, applied in the field of robot-based knowledge base in-depth review and tuning, can solve the problems of real-time data update, misleading, etc., to achieve the effect of timeliness and improved accuracy

Inactive Publication Date: 2022-04-15
NANJING NICEBRIDGE INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the content in the knowledge base is not connected to the Internet, that is, when the actual data is updated, the real-time data in the knowledge base is not updated accordingly, which means that when the user asks a related question, the robot never The answers searched in the knowledge base are not correct answers and are somewhat misleading

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
  • Robot-based knowledge base deep auditing and tuning method and system, and storage medium
  • Robot-based knowledge base deep auditing and tuning method and system, and storage medium
  • Robot-based knowledge base deep auditing and tuning method and system, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0033] At present, when the robot talks, it is based on the existing knowledge base and the matched question keywords, and asks questions through the user's question keywords. The robot retrieves the corresponding answers based on the existing knowledge base, and Display it to the user in the form of text or broadcast, and give the user some help.

[0034] However, in fact, the content in the knowledge base is not connected to the Internet, that is, when the actual data is updated, the real-time data in the knowledge base is not updated correspondingly, which means that when the user body asks related questions , the answer that the robot searches from the knowledge base is not the correct answer, which is somewhat misleading.

[0035] Example: Taking navigation as an example, robots are used as guides in existing shopping malls. When a user asks "wher...

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 robot-based knowledge base deep auditing and tuning method and system, and a storage medium, and belongs to the technical field of artificial intelligence. Comprising the steps that an original knowledge base is divided into an audited database and a to-be-audited database; constructing a model, wherein the model comprises an auditing module and an optimizing module; calling an auditing module or an optimizing module based on the type of the input instruction; the auditing module is used for auditing the information in the to-be-audited database one by one, and if an error is found, correcting and storing the error in the audited database to obtain a real-time knowledge base; and the optimization model performs content optimization and storage on the information in the real-time knowledge base. According to the method, the data in the original knowledge base is irregularly or regularly audited and optimized, so that the precision of the data in the original knowledge base is continuously improved, the precision not only starts from answers, but also starts from questions, and two-way different-level training is carried out. And the data in the original knowledge base is ensured to keep pace with the times, and the timeliness is realized.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method, a system, and a storage medium for in-depth review and optimization of a robot-based knowledge base. Background technique [0002] With the increasing development of artificial intelligence technology and the widespread application of artificial intelligence customer service, such as chatbots, the means of identifying user intentions through artificial intelligence customer service are becoming more and more mature. [0003] Among them, user intention recognition means that when a user communicates with a chat robot, the robot quickly judges the user's true intention based on the stored knowledge base and the direct or indirect information provided by the user. For example, chatbots can identify the user's travel consumption intentions, such as booking air tickets and hotels, based on the user's questions. [0004] However, the content in th...

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): G06F16/21G06F16/23
Inventor 郭志扬
Owner NANJING NICEBRIDGE INFORMATION TECH CO LTD