An enterprise risk rule engine operation method based on semi-structured text data

Abstract

The invention discloses an enterprise risk rule engine overall operation method based on semi-structured text data. The enterprise risk rule engine overall operation method comprises the following steps that S1, defining a calculation mode between data types; S2, defining an operation system of a bottom layer quantification module; S3, formulating an index-dependent field according to an index demand, and connecting the field in series through the operation system defined in the S2 to obtain an index conforming to the user service demand; S4, allowing the data access module to read the data ofthe database according to the index set by the index configuration module and transmit the data to the data screening layer; S5, allowing the data access module to read data of an external database and screens the data through the M condition filters; S6, obtaining data with a uniform format from the screened data through a data standardization module, and transmitting the data to an index operation module; And S7, allowing the index operation module to carry out operation on the data according to the rule configured by the index configuration module. According to the method and the device, the rule engine can obtain the quantization index in the semi-structured text data.

Description

technical field [0001] The invention relates to the field of computer science software information technology, in particular to an enterprise risk rule engine calculation method based on semi-structured text data. Background technique [0002] In recent years, rule engines have been widely used in the fields of finance and anti-fraud to help monitor and discover abnormalities, risks, and business opportunities in target customer groups. The overall design of most rule engines can be roughly divided into two major parts, one is the construction of the rule system, and the other is the construction of the computing system of the data flow. At present, the data used by the rule engine in the industry mainly includes user behavior (such as login, registration, browsing, collection, consumption, etc.) data, corporate financial data, etc.; most of this type of data has structured and measurable characteristics . For example, user behavior data is inseparable from concepts such a...

AI Technical Summary

Problems solved by technology

However, in the field of unstructured or semi-structured text data, "computability" has become not so easy to achieve, and the flexibility of rule configuration has been greatly challenged

For example, when a piece of news mentions the legal representative of a certain company, how will it affect the company? If people come to observe, there will be a perceptual cognition, but the machine cannot give a possible quantitative index when a certain goal is not defined

Therefore, there is no need to talk about the configuration and triggering of rules.

Images