CN-121998141-A - Parameter weight determining method, device, equipment, storage medium and program product

CN121998141ACN 121998141 ACN121998141 ACN 121998141ACN-121998141-A

Abstract

The invention discloses a parameter weight determining method, a device, equipment, a storage medium and a program product, wherein the method comprises the steps of calculating subjective weights of various factors influencing shale gas productivity through an analytic hierarchy process; the method comprises the steps of obtaining objective weights of factors affecting shale gas productivity through XGBoost regression models, carrying out consistency detection on subjective weights and objective weights of the factors, and obtaining comprehensive weights of the factors through calculation based on the subjective weights and the objective weights of the factors when a consistency detection result is passing. The invention solves the technical problem of lower accuracy of parameter weight determination in the related technology.

Inventors

SUN YUDUO
SONG YI
SHEN CHENG
HU JUNJIE
CHEN BOWEN
LI RUI

Assignees

中国石油天然气股份有限公司

Dates

Publication Date: 20260508
Application Date: 20241101

Claims (11)

1. A method for determining a parameter weight, the method comprising: the subjective weight of each factor affecting the shale gas productivity is obtained through analytic hierarchy process calculation; objective weights of all factors affecting shale gas productivity are obtained through calculation through XGBoost regression models; consistency detection is carried out on the subjective weight and the objective weight of each factor; And when the consistency detection result is passing, calculating the comprehensive weight of each factor based on the subjective weight and the objective weight of each factor.
2. The method for determining the parameter weight according to claim 1, wherein the step of calculating the subjective weight of each factor affecting the shale gas productivity by the analytic hierarchy process comprises the following steps: determining the importance ratio among the factors affecting the shale gas productivity by adopting a 1-9 scale method, and constructing a judgment matrix; and calculating subjective weights of the factors affecting the shale gas productivity based on the scale values of the factors in the judgment matrix.
3. The method for determining the parameter weight according to claim 1, wherein the step of calculating objective weights of the factors affecting the shale gas productivity through XGBoost regression models comprises the steps of: Training XGBoost regression models based on each factor affecting shale gas productivity and the final recoverable reserve of the actual single well evaluation corresponding to each factor, and obtaining a XGBoost regression model after training when the loss function of the XGBoost regression model converges; Sequentially inputting each factor affecting shale gas productivity into a XGBoost regression model which is trained, and obtaining the final recoverable reserve of the predicted single well evaluation corresponding to each factor output by the XGBoost regression model which is trained; and carrying out normalization processing on the final recoverable reserves of the predicted single well evaluations corresponding to the factors, and taking the final recoverable reserves of the predicted single well evaluations corresponding to the factors after normalization processing as objective weights of the factors.
4. A method according to claim 3, wherein the XGBoost regression model has a loss function as follows: in the formula, Representing XGBoost the loss function of the regression model, y i the final recoverable reserve of the actual single well estimate for the ith said factor, Representing the final recoverable reserve of the predicted single well estimate for the ith said factor, Representing regularization terms, f k representing the kth tree in the decision tree model, L (phi) representing the objective function, n representing the total number of individual factors affecting shale gas production, T represents the number of leaf nodes on the decision tree, gamma and lambda are constants, and omega represents the vector formed by all the leaf node values on the decision tree.
5. The method of claim 1, wherein the step of performing consistency detection on the subjective weight and the objective weight of each factor comprises: Substituting the subjective weight and the objective weight of each factor into a consistency detection formula, and calculating to obtain consistency indexes between the subjective weight and the objective weight of all the factors; Comparing the consistency index with a threshold value; If the consistency index is greater than or equal to the threshold value, determining that the consistency detection result is not passing; If the consistency index is smaller than the threshold value, determining that a consistency detection result is passing; the consistency detection formula is as follows: Wherein S represents a consistency index between subjective weights and objective weights of all the factors, a i represents the subjective weight of the ith factor, b i represents the objective weight of the ith factor, and n represents the total number of the factors affecting the shale gas productivity.
6. The method according to claim 1, wherein the step of calculating the integrated weight of each of the factors based on the subjective weight and the objective weight of each of the factors comprises: and carrying out any linear combination on the subjective weight and the objective weight of each factor by adopting a game combination weighting method to obtain the comprehensive weight of each factor.
7. The method for determining the parameter weight according to claim 1, wherein after the subjective weight of each factor affecting the shale gas productivity is calculated by the analytic hierarchy process, the method comprises the steps of: Hierarchical division is carried out according to the classification of each factor affecting the shale gas productivity, and the target layer is a final thought result of a problem, and the criterion layer comprises each factor affecting the shale gas productivity; Based on the subjective weight of each factor and the weight of each scheme in the scheme layer about each factor, the method comprises the following steps of Calculating to obtain subjective weights of all schemes in the scheme layer; Where w j represents the subjective weight of the jth scheme in the scheme layer, w ij represents the weight of the jth scheme in the scheme layer with respect to the ith factor, C i represents the subjective weight of the ith factor, and n represents the total number of factors affecting shale gas productivity.
8. A parameter weight determining apparatus, the apparatus comprising: the first calculation module is configured to calculate subjective weights of all factors affecting shale gas productivity through an analytic hierarchy process; The second calculation module is configured to calculate objective weights of the factors affecting the shale gas productivity through XGBoost regression models; The detection module is configured for carrying out consistency detection on the subjective weight and the objective weight of each factor; And a third calculation module configured to calculate a comprehensive weight of each factor based on the subjective weight and the objective weight of each factor when the consistency detection result is passing.
9. An electronic device comprising a memory and a processor, the processor being adapted to read and execute a computer program stored in the memory for implementing the steps of the parameter weight determination method according to any one of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein computer executable instructions which, when executed, implement the steps of the parameter weight determining method according to any of claims 1-7.
11. A computer program product comprising computer program/instructions which, when executed by a processor, implement the steps of the parameter weight determination method according to any one of claims 1-7.

Description

Parameter weight determining method, device, equipment, storage medium and program product Technical Field The invention relates to the technical field of shale gas development, in particular to a method, a device, equipment, a storage medium and a program product for determining parameter weights. Background Currently, in multi-criterion decision analysis (MCDA), the parameter weights reflect the relative importance of the decision criteria in the overall evaluation, and therefore, the determination of the parameter weights is critical to the overall decision process. The traditional parameter weight determining method mainly depends on subjective experience of an expert, and the method is simple and easy to operate, but often lacks enough scientific basis, is easily influenced by personal preference and irrational factors, and has lower accuracy of parameter weight determination. Disclosure of Invention The invention provides a method, a device, equipment, a storage medium and a program product for determining parameter weights, which can solve the technical problem of low accuracy of parameter weight determination in the prior art. In order to achieve the above purpose, the present invention provides the following technical solutions: in a first aspect, an embodiment of the present invention provides a method for determining a parameter weight, where the method includes: the subjective weight of each factor affecting the shale gas productivity is obtained through analytic hierarchy process calculation; objective weights of all factors affecting shale gas productivity are obtained through calculation through XGBoost regression models; consistency detection is carried out on the subjective weight and the objective weight of each factor; And when the consistency detection result is passing, calculating the comprehensive weight of each factor based on the subjective weight and the objective weight of each factor. In a second aspect, an embodiment of the present invention provides a parameter weight determining apparatus, including: the first calculation module is configured to calculate subjective weights of all factors affecting shale gas productivity through an analytic hierarchy process; The second calculation module is configured to calculate objective weights of the factors affecting the shale gas productivity through XGBoost regression models; The detection module is configured for carrying out consistency detection on the subjective weight and the objective weight of each factor; And a third calculation module configured to calculate a comprehensive weight of each factor based on the subjective weight and the objective weight of each factor when the consistency detection result is passing. In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, and a processor, where the processor is configured to read and execute a computer program stored in the memory, so as to implement the steps of the foregoing method for determining a parameter weight. In a fourth aspect, embodiments of the present invention further provide a computer storage medium having stored therein computer-executable instructions that when executed implement the steps of a method for determining a parameter weight as described above. In a fifth aspect, embodiments of the present invention also provide a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of a method for determining a parameter weight as described above. The technical scheme provided by the embodiment of the invention has the beneficial effects that: The method comprises the steps of obtaining subjective weights of factors affecting shale gas productivity through analytic hierarchy process calculation, obtaining objective weights of the factors affecting shale gas productivity through XGBoost regression model calculation, carrying out consistency detection on the subjective weights and objective weights of the factors, and obtaining comprehensive weights of the factors through calculation based on the subjective weights and objective weights of the factors when the consistency detection result is passing. According to the invention, on one hand, an Analytic Hierarchy Process (AHP), a XGBoost machine learning algorithm and a game theory method are combined, the importance of each parameter in a comprehensive evaluation system can be reflected more scientifically, so that the accuracy of the productivity prediction of the shale gas well is improved, on the other hand, the weight acquisition method is not only suitable for the productivity prediction of the shale gas well, but also has high flexibility and expandability, the adaptability and the flexibility of a model are improved, the weight acquisition process is simplified, the weight acquisition process is more efficient and easy to understand and apply, the dependence on professional knowle