A model building, testing method and device

By iteratively optimizing the sampling ratio and combining the chi-square probability and model test statistics, the problem of the lack of quantitative basis for the sampling ratio in geological models was solved, thus achieving the accuracy of model establishment and the rationality of testing.

CN117195459BActive Publication Date: 2026-06-19PETROCHINA CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
PETROCHINA CO LTD
Filing Date
2022-06-01
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

The lack of quantitative basis in existing technologies to reasonably determine the sampling ratio of geological models leads to insufficient accuracy and rationality in model establishment and verification.

Method used

By iteratively optimizing the sampling ratio and combining the chi-square probability and model test statistics, the optimal sampling ratio was determined, and the geological model was established and tested.

Benefits of technology

This effectively solves the problem of a lack of basis for random sampling ratios, ensures the accuracy of the model and the rationality of the test, and improves the rationality of model establishment and the reliability of the test.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117195459B_ABST
    Figure CN117195459B_ABST
Patent Text Reader

Abstract

This invention discloses a model building and testing method and apparatus. The method includes: obtaining test data and modeling data from a sample dataset based on the current sampling ratio; building a model based on the modeling data; determining the chi-square probability based on the model, test data, and a chi-square table; determining the test statistic of the model based on the chi-square probability and the current sampling ratio; determining whether the test statistic meets the set conditions; if not, determining a new sampling ratio and returning to the model building steps; if yes, using the current model as the optimal model and determining the accuracy of the optimal model based on the current sampling ratio. This method can determine the optimal sampling ratio through multiple iterations, ensuring the accuracy of the established model and the rationality of the testing.
Need to check novelty before this filing date? Find Prior Art