Service decision logic updating method based on decision engine and model platform

Abstract

The invention relates to a service decision logic updating method and device based on a decision engine and a model platform, computer equipment and a storage medium. The method comprises the following steps: obtaining to-be-tested decision logic and historical service data; according to the historical traffic data, testing the decision logic to be tested, and obtaining a test result; according tothe test result and an expected value corresponding to historical service data, optimizing decision logic, obtaining optimized decision logic, obtaining current decision logic and production servicedata; according to the optimized decision logic and the current decision logic, deciding production service data respectively; when the decision result of the optimization decision logic is superior to the decision result of the current decision logic, updating the optimization decision logic to the current decision logic. Double verification is performed on the decision logic before the decisionlogic is operated online through the historical service data and the generated service data, so that the reasonability of the service decision logic is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a business decision logic update method, device, computer equipment and storage medium based on a decision engine and a model platform. Background technique [0002] With the development of the economy, the financial business is faced with complex and changeable financial risks, strict financial supervision, and faster and faster updates and iterations of regulatory rules. In the current financial system of the power system, risk control rules are coupled with models, business strategies and other logics of the business system, and are scattered in every corner of the business system. The implementation of business decision logic such as risk control rules and models, business strategies, etc. is invisible to business experts. [0003] When it is necessary to update the business decision logic, relevant business personnel deliver the implementation of risk control ru...

AI Technical Summary

Problems solved by technology

[0003] When it is necessary to update the business decision logic, relevant business personnel deliver the implementation of risk control rules, models, and business strategies to IT (Internet Technology, Internet Technology) personnel, and it takes a week or even longer for IT personnel to complete the risk control rules The implementation of changes related to models and business strategies, the processing process is complicated, and it is difficult to meet the changing needs of the market

Once the deployment goes online, the updated business decision logic cannot be verified, resulting in poor rationality of the business decision logic

Images