Expert system update method, business processing method and device

An expert system and business technology, applied in the field of artificial intelligence, can solve problems such as high labor costs and low business processing efficiency, achieve accurate decision-making results, improve business processing efficiency, and realize the effect of intelligence
CN113256275BActive Publication Date: 2021-11-02ALIPAY (HANGZHOU) INFORMATION TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
Publication Date
2021-11-02

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

This specification provides an update method, business processing method and device of an expert system, wherein the update method of the expert system includes: obtaining sample business characteristic data of the target business and optimization target data of the target business; Data, train the probability graph network corresponding to the target business, and obtain the network parameters of the trained probability graph network. The probability graph network is generated according to the fuzzy logic information corresponding to the target business received by the expert system; based on the network parameters obtained from the training, the output is for the expert Update information of the fuzzy logic information of the system. The embodiment of the present specification enables the expert system to have the ability to learn network parameters, and can optimize the input information of the expert system accordingly, which is beneficial to the decision result of the expert system to be more accurate.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] This specification relates to artificial intelligence technology, in particular to an updating method of an expert system, a business processing method and a device. Background technique

[0002] For business scenarios dominated by manual decision-making, it is usually necessary to conduct logical deduction based on the business data in the business scenario and the manual experience of the leader (also called a domain expert), and finally obtain the business decision result in this scenario. Most of these scenarios have the characteristics of small samples and high sample imbalance. For example, in the credit approval field scenario, the credit bad debt rate is low, there are few negative samples, and the number of historical samples in the scenario is also limited. This makes traditional supervised algorithm models difficult to use in this human-decision-dominated business scenario.

[0003] Therefore, in related technologies, evaluation and decisio...

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