Method and device for mining quality checking rules through multi-dimensional modeling of indexes

By generating quality inspection rules through multi-dimensional data mining and target models, the high cost and low recall caused by manual experience-based formulation and single-dimensional mining in existing technologies are solved, thereby achieving automation and improved accuracy of data quality inspection rules.

CN122241629APending Publication Date: 2026-06-19CSC FINANCIAL CO LTD
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CSC FINANCIAL CO LTD
Filing Date
2026-03-13
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

In existing technologies, the addition and supplementation of data quality inspection rules mainly rely on manual experience and single-dimensional mining, resulting in high costs, low recall rates, and easy omissions.

⚗Method used

By extracting multi-dimensional data from the pairs of indicators to be judged, including time, data lineage, and data meaning, similarity is calculated, and a pre-built target model is called to generate quality inspection rules, thus achieving full-process automation.

🎯Benefits of technology

It reduces labor costs, improves the accuracy and efficiency of rule generation, increases recall rate, generates more effective rules, ensures data quality, and provides a data foundation for upper-level analysis applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

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

Abstract

This invention provides a method and apparatus for mining quality inspection rules through multi-dimensional modeling of indicators. The method includes: extracting multi-dimensional data from a pair of indicators to be judged, wherein the multi-dimensional data is related to time, data lineage, and data meaning; determining the similarity of the pair of indicators to be judged in each dimension based on the multi-dimensional data; calling a pre-built target model to process the multi-dimensional data and the similarity to obtain a judgment result characterizing whether the pair of indicators to be judged is a valid association pair; and generating quality inspection rules based on the indicator pairs whose judgment result is a valid association pair. The method described in this embodiment can quickly and accurately generate effective quality inspection rules.
Need to check novelty before this filing date? Find Prior Art