Water injection business index evaluation system construction method and device, processor and storage medium

Abstract

The invention provides a water injection business index evaluation system construction method and device, a processor and a storage medium, and relates to the technical field of oilfield water injection. The construction method comprises the following steps: determining a total target index; determining a user target by using the total target index and the basic model and constructing an index set; calculating relevance and relevance weights corresponding to the sub-targets and the user targets by utilizing forward modeling, screening the sub-targets corresponding to the user targets based on the relevance and relevance weights corresponding to the sub-targets and the user targets, taking the sub-targets as multi-level hierarchical indexes, determining a relationship among the multi-level hierarchical indexes, and constructing an initial water injection business index evaluation system; verifying the initial water injection business index evaluation system by using inversion simulation; and taking the verified initial water injection service index evaluation system as a final water injection service index evaluation system. Through the method, the water injection evaluation indexes of the analysis level and the control level are coupled, and the response sensitivity of the water injection evaluation indexes of the control level and the final effect of oilfield development is improved.

Description

Technical Field

[0001] This invention relates to the field of oilfield water injection technology, specifically to a method for constructing an evaluation system for water injection business indicators, a device for constructing an evaluation system for water injection business indicators, a processor, and a machine-readable storage medium. Background Technology

[0002] With the rapid development of my country's economy, the importance attached to oil and gas energy development is constantly increasing. Therefore, achieving efficient development technologies is a major research topic. Water injection is a primary means of increasing production in my country's major oilfields. It achieves efficient oil extraction by maintaining reservoir pressure and reducing the rate of crude oil deceleration. Moreover, water is a displacement liquid, low in cost and pollution-free. my country possesses abundant low-permeability oil and gas resources, but due to geological conditions, natural recharge is low, and the level of extraction technology limits production, leading to low yields and significant development difficulties. Therefore, applying water injection, analyzing and evaluating its effects, identifying shortcomings in implementation, and making improvements are of great significance to oil and gas field development.

[0003] In existing technologies, the effectiveness of water injection can be evaluated by establishing an evaluation system of water injection business indicators. However, the indicators in the existing evaluation system are based on the needs of different personnel in different roles, and are system standards that meet their own needs. The evaluation of water injection effectiveness focuses more on the reservoir's final recovery rate. However, the final development effect of the oilfield is affected by multiple factors. The water injection evaluation indicators at the analysis and control levels are weakly coupled, and the development process control and the final result are often not closely integrated. Summary of the Invention

[0004] To address the technical problem that existing technologies for evaluating water injection effectiveness often focus on reservoir recovery rates, resulting in weak coupling between analytical and control-level water injection evaluation indicators and a lack of close integration between process control and final results, this invention provides a method for constructing a water injection operational indicator evaluation system, a device for constructing such a system, a processor, and a machine-readable storage medium. This method enables the establishment of an end-to-end indicator evaluation system, from process to result, to set overall target indicators for oilfield water injection operations. It meets the indicator requirements of different roles, couples analytical and control-level water injection evaluation indicators, and improves the sensitivity of control-level water injection evaluation indicators to the final oilfield development results.

[0005] To achieve the above objectives, the first aspect of the present invention provides a method for constructing a water injection business indicator evaluation system. This method includes: determining the overall target indicators for water injection business; wherein the overall target indicators correspond to analytical indicators and control indicators; determining user objectives and constructing an indicator set using the overall target indicators and a basic model; wherein the indicator set includes multiple sub-objectives; user objectives include, but are not limited to: water injection qualification rate, water distribution qualification rate, water distribution rate, and water distribution time qualification rate; using forward simulation to calculate the correlation and correlation weights between the sub-objectives in the indicator set and the user objectives, and selecting sub-objectives corresponding to the user objectives from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-objectives and the user objectives, and determining the correspondence between the multi-level hierarchical indicators to construct an initial water injection business indicator evaluation system; verifying the initial water injection business indicator evaluation system using inverse simulation; and using the verified initial water injection business indicator evaluation system as the final water injection business indicator evaluation system.

[0006] Furthermore, the basic model includes, but is not limited to: a user strategy method model, an intermediate basic model, and mutually independent detailed analysis models, wherein the intermediate basic model is used to indicate the process or influencing factors of achieving the user goal.

[0007] Furthermore, determining the user objective using the overall objective metric and the basic model includes: determining the user objective based on the overall objective metric and the user strategy method model.

[0008] Furthermore, constructing an indicator set using the overall target indicator and the basic model includes: determining the overall architecture based on the user strategy method model; wherein the overall architecture includes a tree-like hierarchical architecture composed of multi-level hierarchical indicators; determining the implementation path of the user target based on the overall architecture and the intermediate basic model; wherein the intermediate basic model includes a pirate rule model or a user journey map model; and decomposing the user target into multiple sub-targets to form the indicator set based on the implementation path and mutually independent detailed analysis models.

[0009] Further, the hierarchical indicators include: first-level indicators, second-level indicators, and third-level indicators; the step of using forward modeling to calculate the correlation and correlation weights between sub-objectives in the indicator set and the user target, selecting sub-objectives corresponding to the user target from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-objectives and the user target, and determining the correspondence between the multi-level hierarchical indicators to construct an initial water-filling business indicator evaluation system includes: using forward modeling to calculate the correlation and correlation weights between sub-objectives in the indicator set and the user target, and selecting sub-objectives corresponding to the user target from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-objectives and the user target. First-level indicators are selected from the indicator set to identify sub-objectives corresponding to the user objective. Forward modeling is used to calculate the correlation and correlation weights between the sub-objectives and the first-level indicators in the indicator set. Based on the correlation and correlation weights between the sub-objectives and the first-level indicators, second-level indicators corresponding to the first-level indicators are selected from the indicator set. Forward modeling is used to calculate the correlation and correlation weights between the sub-objectives and the second-level indicators in the indicator set. Based on the correlation and correlation weights between the sub-objectives and the second-level indicators, third-level indicators corresponding to the second-level indicators are selected from the indicator set, thus constructing an initial evaluation system for water-injection business indicators.

[0010] Furthermore, the step of using forward modeling to calculate the correlation and correlation weight between the sub-targets in the indicator set and the user target, and selecting sub-targets corresponding to the user target from the indicator set as first-level indicators based on the correlation and correlation weight between the sub-targets and the user target, includes: calculating the correlation between the sub-targets in the indicator set and the user target; selecting multiple sub-targets corresponding to the user target from the indicator set as first-level sub-targets based on the correlation between the sub-targets in the indicator set and the user target; calculating the weight factor between the first-level sub-targets and the user target; comparing the weight factor between the first-level sub-targets and the user target with a set weight factor; and selecting the first-level indicators from the first-level sub-targets based on the comparison result of the weight factor of the first-level sub-targets and the set weight factor.

[0011] Furthermore, calculating the correlation between the sub-targets in the indicator set and the user target includes: using principal component analysis to calculate the correlation between the sub-targets in the indicator set and the user target.

[0012] Furthermore, the calculation of the weighting factor between the primary sub-objective and the user objective includes: calculating the weighting factor between the primary sub-objective and the user objective using the grey relational analysis method.

[0013] Furthermore, the overall target indicators include, but are not limited to: injecting water properly, injecting enough water, injecting water precisely, and injecting water effectively.

[0014] A second aspect of the present invention provides a device for constructing a water injection business indicator evaluation system. The device includes: a total target indicator determination module, used to determine the total target indicators for the water injection business; wherein the total target indicators correspond to analytical indicators and control indicators; a target set determination module, used to determine user targets and construct an indicator set using the total target indicators and a basic model; wherein the indicator set includes multiple sub-targets; the user targets include, but are not limited to: water injection qualification rate, sub-injection qualification rate, water distribution rate, and sub-injection qualification time rate; an initial water injection business indicator evaluation system determination module, used to calculate the correlation and correlation weights between the sub-targets in the indicator set and the user targets using forward simulation, select sub-targets corresponding to the user targets from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-targets and the user targets, and determine the correspondence between the multi-level hierarchical indicators to construct an initial water injection business indicator evaluation system; a verification module, used to verify the initial water injection business indicator evaluation system using inverse simulation; and the water injection business indicator evaluation system determination module uses the verified initial water injection business indicator evaluation system as the final water injection business indicator evaluation system.

[0015] Furthermore, the hierarchical indicators include: first-level indicators, second-level indicators, and third-level indicators; the step of using forward modeling to calculate the correlation and correlation weights between sub-objectives in the indicator set and the user objective, and selecting sub-objectives corresponding to the user objective from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-objectives and the user objective, and determining the correspondence between the multi-level hierarchical indicators to construct an initial water-filling business indicator evaluation system, includes: using forward modeling to calculate the correlation and correlation weights between sub-objectives in the indicator set and the user objective, and selecting sub-objectives corresponding to the user objective from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-objectives and the user objective. The system selects sub-targets corresponding to the user's objective from the indicator set as first-level indicators; it uses forward modeling to calculate the correlation and correlation weights between the sub-targets and the first-level indicators in the indicator set, and selects second-level indicators corresponding to the first-level indicators from the indicator set based on the correlation and correlation weights between the sub-targets and the first-level indicators; it uses forward modeling to calculate the correlation and correlation weights between the sub-targets and the second-level indicators in the indicator set, and selects third-level indicators corresponding to the second-level indicators from the indicator set based on the correlation and correlation weights between the sub-targets and the second-level indicators, thus constructing an initial evaluation system for water-injection business indicators.

[0016] Furthermore, the step of using forward modeling to calculate the correlation and correlation weight between the sub-targets in the indicator set and the user target, and selecting sub-targets corresponding to the user target from the indicator set as first-level indicators based on the correlation and correlation weight between the sub-targets and the user target, includes: calculating the correlation between the sub-targets in the indicator set and the user target; selecting multiple sub-targets corresponding to the user target from the indicator set as first-level sub-targets based on the correlation between the sub-targets in the indicator set and the user target; calculating the weight factor between the first-level sub-targets and the user target; comparing the weight factor between the first-level sub-targets and the user target with a set weight factor; and selecting the first-level indicators from the first-level sub-targets based on the comparison result of the weight factor of the first-level sub-targets and the set weight factor.

[0017] Furthermore, the overall target indicators include, but are not limited to: injecting water properly, injecting enough water, injecting water precisely, and injecting water effectively.

[0018] A third aspect of the present invention provides a processor configured to execute the water injection business indicator evaluation system construction method described above.

[0019] A fourth aspect of the present invention provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the water injection business indicator evaluation system construction method described above.

[0020] The present invention has at least the following technical effects through the technical solution provided by the present invention: The method for constructing a water injection business indicator evaluation system in this invention first determines the overall target indicators for water injection business. These overall target indicators correspond to research and management indicators, satisfying the indicator requirements of different work roles and coupling water injection evaluation indicators from the research and management levels. Next, based on the overall target indicators and the basic model, user objectives are determined and an indicator set is constructed. Multi-level indicators are selected, and the correspondence between these indicators is determined, thus constructing an initial water injection business indicator evaluation system. Through forward simulation, an end-to-end indicator evaluation system from process to result can be established for oilfield water injection business operations, with overall target indicators. Furthermore, the method couples water injection evaluation indicators from the research and management levels, improving the sensitivity of management-level water injection evaluation indicators to the final oilfield development results and enhancing the accuracy of the evaluation system construction.

[0021] Other features and advantages of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 A flowchart illustrating the method for constructing a water injection business indicator evaluation system provided in this embodiment of the invention; Figure 2 This is a schematic diagram illustrating the construction of an indicator set in the method for constructing a water injection business indicator evaluation system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the water injection business indicator evaluation system established in the water injection business indicator evaluation system construction method provided in the embodiments of the present invention; Figure 4 A schematic diagram illustrating the forward and inverse simulation processes in the water injection business indicator evaluation system construction method provided in this embodiment of the invention; Figure 5 This is a schematic diagram illustrating the specific implementation logic of forward modeling in the water injection business indicator evaluation system construction method provided in this embodiment of the invention; Figure 6 A schematic diagram illustrating the specific implementation logic of the gradient improvement method in the water injection business indicator evaluation system construction method provided in this embodiment of the invention; Figure 7 The specific implementation logic of the collinearity analysis method in the water injection business indicator evaluation system construction method provided in the embodiments of the present invention; Figure 8 A comparison chart of water injection development indicators in the water injection business indicator evaluation system construction method provided in this embodiment of the invention. Detailed Implementation

[0023] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0024] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0025] In this invention, unless otherwise stated, directional terms such as "upper," "lower," "top," and "bottom" are generally used to describe the relative positions of components in relation to the directions shown in the accompanying drawings or in relation to the vertical, perpendicular, or gravitational directions.

[0026] As described in the background section, existing semiconductor structures have poor performance. This will be explained in detail below with reference to the accompanying drawings.

[0027] Please refer to Figure 1 The first aspect of this invention provides a method for constructing a water injection business indicator evaluation system. The method includes: S101: determining the overall target indicator for the water injection business; wherein the overall target indicator corresponds to analytical indicators and control indicators; S102: using the overall target indicator and a basic model to determine user objectives and construct an indicator set; wherein the indicator set includes multiple sub-objectives; user objectives include, but are not limited to: water injection qualification rate, water distribution qualification rate, water distribution rate, and water distribution time qualification rate; S103: using forward simulation to calculate the correlation and correlation weight between the sub-objectives in the indicator set and the user objectives, and based on the correlation and correlation weight between the sub-objectives and the user objectives, selecting sub-objectives corresponding to the user objectives from the indicator set as multi-level hierarchical indicators, and determining the correspondence between the multi-level hierarchical indicators to construct an initial water injection business indicator evaluation system; S104: using inverse simulation to verify the initial water injection business indicator evaluation system; S105: using the verified initial water injection business indicator evaluation system as the final water injection business indicator evaluation system.

[0028] Specifically, in this embodiment of the invention, the overall target indicators for the water injection business are first determined. These overall target indicators encompass all work roles within the water injection business, including both research and management levels. Then, based on the overall target indicators and the basic model, multiple user objectives are determined. Using the basic model, the overall target indicators are broken down into multiple core business KPIs as user objectives. These user objectives include: water injection qualification rate, water distribution qualification rate, water distribution rate, and water distribution time qualification rate. An indicator set is constructed based on the overall target indicators and the basic model. The ultimate goal of all sub-objectives in the indicator set is to achieve the user objectives, thereby reaching the final overall target indicators for the water injection business. Then, forward simulation is used to select multi-level hierarchical indicators corresponding to the user objectives from the indicator set, and the correspondence between these multi-level hierarchical indicators is determined, constructing an initial water injection business indicator evaluation system. Finally, inverse simulation is used to verify the initial water injection business indicator evaluation system, and the verified initial water injection business indicator evaluation system is used as the final water injection business indicator evaluation system.

[0029] According to the water injection business indicator evaluation system construction method provided by the present invention, an end-to-end indicator evaluation system from process to result can be established for the overall target indicators of oilfield water injection business, which can meet the indicator requirements of different work roles, couple water injection evaluation indicators at the analysis level and control level, improve the sensitivity of water injection evaluation indicators at the control level to the final effect of oilfield development, and improve the accuracy of indicator evaluation system construction.

[0030] Furthermore, the overall target indicators include, but are not limited to: injecting water properly, injecting enough water, injecting water precisely, and injecting water effectively.

[0031] Specifically, in this embodiment of the invention, the overall target indicators include: good water injection, sufficient water injection, precise water injection, and effective water injection. The water injection business indicator evaluation system is established based on the overall target indicators. The overall target indicators can be broken down into multiple user targets, including: water injection qualification rate, sub-injection qualification rate, water distribution rate, and sub-injection qualification time rate.

[0032] Furthermore, the basic model includes, but is not limited to: a user strategy method model, an intermediate basic model, and mutually independent detailed analysis models, wherein the intermediate basic model is used to indicate the process or influencing factors of achieving the user goal.

[0033] Furthermore, determining the user objective using the overall objective metric and the basic model includes: determining the user objective based on the overall objective metric and the user strategy method model.

[0034] Furthermore, constructing an indicator set using the overall target indicator and the basic model includes: determining the overall architecture based on the user strategy method model; wherein the overall architecture includes a tree-like hierarchical architecture composed of multi-level hierarchical indicators; determining the implementation path of the user target based on the overall architecture and the intermediate basic model; wherein the intermediate basic model includes a pirate rule model or a user journey map model; and decomposing the user target into multiple sub-targets to form the indicator set based on the implementation path and mutually independent detailed analysis models.

[0035] Specifically, in the embodiments of the present invention, the basic models used include, but are not limited to: the User Strategy Method Model (OSM, Object, Strategy, Measure), the intermediate basic model, and the Mutually Exclusive and Collectively Exhaustive Analysis Model (MECE), wherein the intermediate basic model is used to indicate the process or influencing factors of achieving user goals.

[0036] First, the overall target metric is broken down into multiple user targets based on the user strategy methodology model. The overall architecture, determined by the model, is a tree-like hierarchical structure composed of multi-level metrics. User targets can be decomposed level by level and achieved through multi-level metrics. In this embodiment, a user target can be achieved through multiple first-level metrics, ..., and each nth-level metric can be achieved through the (n-1)th-level metric, where n is an integer greater than 2, and so on, ultimately forming the overall tree-like hierarchical architecture.

[0037] Then, based on the overall architecture and intermediate foundational models of the tree-like hierarchical structure, the implementation path of user goals is determined. These intermediate foundational models include the Pirate Rule model (AARRR: Acquisition, Activation, Retention, Revenue, Referral) or the User Journey Map model (UJM: User, Journey, Map). Next, based on the implementation path and mutually independent detailed analysis models, user goals are continuously subdivided from broad to narrow, down to indivisible business activities. The corresponding metrics for each indivisible business activity are determined, thus breaking down user goals into multiple sub-goals and forming a set of metrics.

[0038] Please refer to Figure 2 In one possible implementation, the overall target indicators are analyzed based on the business objectives (Objects) in the OSM model to obtain the core business KPIs (multiple user objectives); the product lifecycle and user behavior paths are analyzed based on the action strategy (Strategy), and the implementation path of the user objectives is determined using the AARRR model or the UJM model; the core KPIs are drilled down based on the evaluation indicators (Measures), and the user objectives are continuously subdivided from large to small using the MECE model and the implementation path, until the smallest business activity defined by the business side that cannot be subdivided, forming the indicator set of the business domain.

[0039] According to the water injection business indicator evaluation system construction method provided by the present invention, user objectives can be decomposed, indicators can be classified and managed, graded indicators can be determined and backtracked, key factors affecting each step can be identified as secondary indicators, and a holistic solution for business management can be proposed from macro objectives, process control and micro details, the direction can be identified and the business cycle and process can be clarified.

[0040] Further, the hierarchical indicators include: first-level indicators, second-level indicators, and third-level indicators; the process involves using forward modeling to calculate the correlation and correlation weights between sub-objectives in the indicator set and the user objective, selecting sub-objectives corresponding to the user objective from the indicator set based on the correlation and correlation weights between the sub-objectives and the user objective as multi-level hierarchical indicators, determining the correspondence between the multi-level hierarchical indicators, and constructing an initial water-filling business indicator evaluation system, including: Forward modeling is used to calculate the correlation and correlation weight between sub-objectives in the indicator set and the user objective. Based on the correlation and correlation weight between the sub-objectives and the user objective, sub-objectives corresponding to the user objective are selected from the indicator set as first-level indicators. Forward modeling is used to calculate the correlation and correlation weight between the sub-objectives in the indicator set and the first-level indicators. Based on the correlation and correlation weight between the sub-objectives and the first-level indicators, second-level indicators corresponding to the first-level indicators are selected from the indicator set. Forward modeling is used to calculate the correlation and correlation weight between the sub-objectives in the indicator set and the second-level indicators. Based on the correlation and correlation weight between the sub-objectives and the second-level indicators, third-level indicators corresponding to the second-level indicators are selected from the indicator set. This constructs an initial water injection business indicator evaluation system.

[0041] Specifically, in this embodiment of the invention, the hierarchical indicators include: first-level indicators, second-level indicators, and third-level indicators. In the overall architecture, user goals correspond to multiple first-level indicators, each first-level indicator corresponds to multiple second-level indicators, and each second-level indicator corresponds to multiple third-level indicators.

[0042] First, forward modeling is used to calculate the correlation and correlation weight between sub-objectives and user objectives in the indicator set. Based on this correlation and correlation weight, sub-objectives corresponding to user objectives are selected from the indicator set as first-level indicators. Next, the correlation and correlation weight between sub-objectives and first-level indicators are calculated. Based on this correlation and correlation weight, second-level indicators corresponding to the first-level indicators are selected from the indicator set. Then, forward modeling is used to calculate the correlation and correlation weight between sub-objectives and second-level indicators. Based on this correlation and correlation weight, third-level indicators corresponding to the second-level indicators are selected from the indicator set, thus constructing the initial evaluation system for water-injection business indicators. Please refer to [reference needed]. Figure 3 , Figure 3 The initial water injection business indicator evaluation system constructed in this embodiment includes 6 primary level indicators, 15 secondary level indicators, and 18 tertiary level indicators.

[0043] According to the method for constructing an evaluation system for water injection business indicators provided by this invention, a hierarchical governance model of "Level I result indicators to identify gaps, Level II cause indicators to investigate problems, and Level III operation indicators to determine direction" is established, and a complete and clear water injection benchmarking and control indicator system is constructed.

[0044] Furthermore, the step of using forward modeling to calculate the correlation and correlation weight between the sub-targets in the indicator set and the user target, and selecting sub-targets corresponding to the user target from the indicator set as first-level indicators based on the correlation and correlation weight between the sub-targets and the user target, includes: calculating the correlation between the sub-targets in the indicator set and the user target; selecting multiple sub-targets corresponding to the user target from the indicator set as first-level sub-targets based on the correlation between the sub-targets in the indicator set and the user target; calculating the weight factor between the first-level sub-targets and the user target; comparing the weight factor between the first-level sub-targets and the user target with a set weight factor; and selecting the first-level indicators from the first-level sub-targets based on the comparison result of the weight factor of the first-level sub-targets and the set weight factor.

[0045] Furthermore, calculating the correlation between the sub-targets in the indicator set and the user target includes: using principal component analysis to calculate the correlation between the sub-targets in the indicator set and the user target.

[0046] Furthermore, the calculation of the weighting factor between the primary sub-objective and the user objective includes: calculating the weighting factor between the primary sub-objective and the user objective using the grey relational analysis method.

[0047] Specifically, in this embodiment of the invention, Principal Component Analysis (PCA) is used to calculate the correlation between sub-objectives in the indicator set and the user objective. Based on the correlation between sub-objectives in the indicator set and the user objective, multiple sub-objectives corresponding to the user objective are selected from the indicator set as first-level sub-objectives. Then, Grey Relation Analysis (GRA) is used to determine the weight factors of the first-level sub-objectives. Next, the weight factors of the first-level sub-objectives are compared with the set weight factors. If the weight factor of the first-level sub-objective is less than or equal to the set weight factor, it indicates that the first-level sub-objective has a low correlation with the user objective, and the first-level sub-objective is not a first-level indicator corresponding to the user objective. If the weight factor of the first-level sub-objective is greater than the set weight factor, it indicates that the first-level sub-objective has a high correlation with the user objective, and the first-level sub-objective is determined as a first-level indicator corresponding to the user objective.

[0048] The multiple second-level indicators corresponding to each first-level indicator, and the multiple third-level indicators corresponding to each second-level indicator, can all be obtained through forward modeling, which will not be elaborated in this embodiment.

[0049] The method for constructing an evaluation system for water injection business indicators provided by this invention can reduce dimensionality and extract the main factors affecting user objectives, and construct a strong correlation matrix based on user objectives.

[0050] Next, inversion simulation is used to verify the initial water injection operational indicator evaluation system. In this embodiment, the Gradient Boosting Machines (GBM) method is adopted, with the positive trend of water injection economic and technical indicators as the constraint direction. The indicator evaluation system is simulated and trained using actual oil reservoirs. Collinearity Analysis (CA) is used to identify collinearity among multi-level indicators, i.e., the high correlation between indicators. The reasonable distribution of second-level and third-level indicators under the condition that the first-level indicators are positive is selected to verify the initial water injection operational indicator evaluation system. If the water injection initial control indicator evaluation system obtained by inversion simulation corresponds to the initial water injection operational indicator evaluation system, the verified water injection operational indicator evaluation system is used as the final water injection operational indicator evaluation system. If the water injection operational indicator evaluation system obtained by inversion simulation does not correspond to the initial water injection operational indicator evaluation system, the initial water injection operational indicator evaluation system is corrected using the water injection operational indicator evaluation system obtained by inversion simulation, and the corrected initial water injection operational indicator evaluation system is used as the final water injection operational indicator evaluation system.

[0051] In one possible implementation, please refer to Figure 4 , Figure 4The process provides workflows for forward and inverse simulations: ① Water Injection Index Data Standardization: The original oilfield water injection index data is standardized so that the mean of each variable is 0 and the standard deviation is 1. The purpose of this step is to standardize the range of continuous initial variables so that each variable contributes equally to the analysis. ② Covariance Matrix Calculation: The covariance matrix is ​​calculated based on the standardized data. The covariance matrix helps us understand how the variables in the input dataset change relative to their mean, or in other words, to see if there are any relationships between them. ③ Eigenvalue and Eigenvector Calculation: By performing eigenvalue decomposition on the covariance matrix, its eigenvalues ​​and eigenvectors can be obtained. The eigenvectors represent the degree of variation of the original oilfield water injection index data in different directions, while the eigenvalues ​​represent the magnitude of the degree of variation in each direction. ④ Principal Component Selection: Principal components are selected based on the magnitude of the eigenvalues. Usually, the first few principal components with larger eigenvalues ​​are selected, as these principal components can explain most of the variance of the original variables. ⑤ Calculate principal component scores: Calculate the score of each indicator on the principal components. The score describes the relative position of each indicator on the principal components. The score matrix is ​​used to calculate the principal component scores. ⑥ Interpret principal components: By analyzing the eigenvectors of the principal components, determine the weights on the principal components corresponding to the original oilfield water injection indicators. If the weights are greater than the set values, it is determined that the indicator is correlated with the user's objective.

[0052] Please refer to Figure 5 , Figure 5 The specific implementation logic of forward modeling is as follows: ① Standardize the original oilfield water injection index data to construct the original dataset and principal component dataset; ② Construct the covariance matrix of the data and calculate the variance of the principal components; ③ Extract the eigenvalues ​​and eigenvectors of the principal components; ④ Select the most important eigenvectors as principal components based on the magnitude of the eigenvalues; ⑤ Obtain the sequence of influencing factors through principal component analysis; ⑥ Perform dimensionless processing on the principal component sequence data; ⑦ Calculate the correlation coefficient between the reference sequence and each comparison sequence; ⑧ Calculate the average correlation coefficient between the reference sequence and each comparison sequence; ⑨ Sort the comparison sequences according to the average correlation coefficient, and determine the indicators that are correlated with the user's target based on the top-ranked (which can be set by the user).

[0053] In this embodiment, the gradient boosting method identifies and classifies factors that cannot be identified linearly by establishing different gradients. Linear analysis is used to determine whether there is a collinear relationship; for indicators with a variance inflation factor greater than 5, a regression linear calculation model is used to obtain a quantitative relationship.

[0054] Please refer to Figure 6 , Figure 6The specific implementation logic of the gradient boosting method is as follows: ① Initialize the water injection index model: Initialize a weak learner and construct a decision tree. ② Calculate residuals: For each sample in the training set, use the current model to make a prediction, and then calculate the residual between the true value and the predicted value. ③ Fit a new weak learner: Based on the residuals calculated in the previous step, fit a new weak learner (CART regression tree), with the positive trend of the water injection business's economic and technical indicators as the constraint direction. The new weak learner will learn how to best fit the previous residuals. ④ Update the model: Add the predicted values ​​of the new learner to the existing model to form an updated model. ⑤ Iteration process: Repeat the above steps until the influence of the three-level indicators is maximized. ⑥ Output the final model and obtain the indicator evaluation system: The final output model is a weighted combination of the learners in all iterations.

[0055] Please refer to Figure 7 , Figure 7 The specific implementation logic of the collinearity analysis method is as follows: ① Determine whether multicollinearity exists among multilevel indicators. If all VIF values ​​are less than 10 (strictly 5), it indicates that the model does not have a multicollinearity problem and the model is well-constructed; conversely, if the VIF is greater than 10, it indicates a poor model construction. ② Manually remove collinear independent variables: First, perform correlation analysis. If the correlation coefficient between two independent variables X (explanatory variables) is found to be greater than 0.7, remove one independent variable (explanatory variable) and repeat step 6. ③ Automatically select and eliminate independent variables. Stepwise regression will automatically remove collinear independent variables. ④ Increase sample size: This is one way to explain collinearity, but it may not be very suitable in practice because sample collection requires costs and time. ⑤ Ridge regression: Currently the most effective way to explain collinearity, but ridge regression analysis is relatively complex. ⑥ Use factor analysis to merge variables: Use mathematical transformations to reduce the dimensionality of the data and extract several components, that is, condense the information. Finally, use the condensed information as independent variables (explanatory variables) to enter the model for analysis and identify collinearity between multi-level indicators.

[0056] The method described in this application has been applied to the water injection operations of three oilfield production plants in Xinjiang Oilfield: the No. 2 Oil Production Plant, the Baikouquan Oil Production Plant, and the Shixi Oilfield Operation Area, and has achieved good results. Figure 8 As shown, after applying the method of this embodiment, the five water injection rates and five development rates in 2023 were significantly improved compared to those in 2022. Based on the significant improvement in the water injection business indicators of Xinjiang Oilfield, it is estimated that production will decrease by 1.57 million tons less over five years. Calculated at an oil price of 2980 yuan per ton, this translates to a profit of 4.6 billion yuan over five years (1570000 * 298046 billion).

[0057] A second aspect of the present invention provides a device for constructing a water injection business indicator evaluation system. The device includes: a total target indicator determination module, used to determine the total target indicators for the water injection business; wherein the total target indicators correspond to analytical indicators and control indicators; a target set determination module, used to determine user targets and construct an indicator set using the total target indicators and a basic model; wherein the indicator set includes multiple sub-targets; the user targets include, but are not limited to: water injection qualification rate, sub-injection qualification rate, water distribution rate, and sub-injection qualification time rate; an initial water injection business indicator evaluation system determination module, used to calculate the correlation and correlation weights between the sub-targets in the indicator set and the user targets using forward simulation, select sub-targets corresponding to the user targets from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-targets and the user targets, and determine the correspondence between the multi-level hierarchical indicators to construct an initial water injection business indicator evaluation system; a verification module, used to verify the initial water injection business indicator evaluation system using inverse simulation; and the water injection business indicator evaluation system determination module uses the verified initial water injection business indicator evaluation system as the final water injection business indicator evaluation system.

[0058] Furthermore, the hierarchical indicators include: first-level indicators, second-level indicators, and third-level indicators; the step of using forward modeling to calculate the correlation and correlation weights between sub-objectives in the indicator set and the user objective, and selecting sub-objectives corresponding to the user objective from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-objectives and the user objective, and determining the correspondence between the multi-level hierarchical indicators to construct an initial water-filling business indicator evaluation system, includes: using forward modeling to calculate the correlation and correlation weights between sub-objectives in the indicator set and the user objective, and selecting sub-objectives corresponding to the user objective from the indicator set as multi-level hierarchical indicators based on the correlation and correlation weights between the sub-objectives and the user objective. The system selects sub-targets corresponding to the user's objective from the indicator set as first-level indicators; it uses forward modeling to calculate the correlation and correlation weights between the sub-targets and the first-level indicators in the indicator set, and selects second-level indicators corresponding to the first-level indicators from the indicator set based on the correlation and correlation weights between the sub-targets and the first-level indicators; it uses forward modeling to calculate the correlation and correlation weights between the sub-targets and the second-level indicators in the indicator set, and selects third-level indicators corresponding to the second-level indicators from the indicator set based on the correlation and correlation weights between the sub-targets and the second-level indicators, thus constructing an initial evaluation system for water-injection business indicators.

[0059] Furthermore, the step of using forward modeling to calculate the correlation and correlation weight between the sub-targets in the indicator set and the user target, and selecting sub-targets corresponding to the user target from the indicator set as first-level indicators based on the correlation and correlation weight between the sub-targets and the user target, includes: calculating the correlation between the sub-targets in the indicator set and the user target; selecting multiple sub-targets corresponding to the user target from the indicator set as first-level sub-targets based on the correlation between the sub-targets in the indicator set and the user target; calculating the weight factor between the first-level sub-targets and the user target; comparing the weight factor between the first-level sub-targets and the user target with a set weight factor; and selecting the first-level indicators from the first-level sub-targets based on the comparison result of the weight factor of the first-level sub-targets and the set weight factor.

[0060] Furthermore, the overall target indicators include, but are not limited to: injecting water properly, injecting enough water, injecting water precisely, and injecting water effectively.

[0061] A third aspect of the present invention provides a processor configured to execute the water injection business indicator evaluation system construction method described above.

[0062] A fourth aspect of the present invention provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the water injection business indicator evaluation system construction method described above.

[0063] The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the specific details of the above embodiments. Within the scope of the technical concept of the present invention, various simple modifications can be made to the technical solution of the present invention, and these simple modifications all fall within the protection scope of the present invention.

[0064] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not describe the various possible combinations separately.

[0065] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed by the present invention.

Claims

1. A water injection service index evaluation system construction method, characterized in that, The water injection business index evaluation system construction method comprises: determining a total target index of the water injection business; wherein the total target index corresponds to analysis indexes and control indexes; determining a user target by using the total target index and a basic model and constructing an index set; wherein the index set comprises multiple sub-targets; the user target comprises but is not limited to: water injection qualification rate, separate injection qualification rate, separate water rate and separate injection qualification time rate; calculating the correlation and correlation weight between the sub-targets in the index set and the user target by using forward simulation, screening the sub-targets corresponding to the user target from the index set as multiple-level hierarchical indexes based on the correlation and correlation weight between the sub-targets and the user target, determining the corresponding relationship between the multiple-level hierarchical indexes, and constructing an initial water injection business index evaluation system; verifying the initial water injection business index evaluation system by using inversion simulation; taking the verified initial water injection business index evaluation system as a final water injection business index evaluation system.

2. The method according to claim 1, wherein, The basic model comprises but is not limited to: a user strategy method model, an intermediate basic model and a mutually independent detailed analysis model; wherein the intermediate basic model is used to indicate the implementation process or influencing factors of the user target.

3. The method according to claim 2, wherein, The determination of the user target by using the total target index and the basic model comprises: determining the user target based on the total target index and the user strategy method model.

4. The method according to claim 3, characterized in that, The construction of the index set by using the total target index and the basic model comprises: determining an overall architecture according to the user strategy method model; wherein the overall architecture comprises a tree-like hierarchical architecture composed of multiple-level hierarchical indexes; determining an implementation path of the user target according to the overall architecture and the intermediate basic model; wherein the intermediate basic model comprises a pirate rule model or a user travel graph model; dissolving the user target into multiple sub-targets according to the implementation path and the mutually independent detailed analysis model to form the index set.

5. The water injection business index evaluation system construction method according to claim 1, wherein: the hierarchical indexes comprise: first-level hierarchical indexes, second-level hierarchical indexes and third-level hierarchical indexes; the construction of the initial water injection business index evaluation system by using forward simulation to calculate the correlation and correlation weight between the sub-targets in the index set and the user target, screening the sub-targets corresponding to the user target from the index set as multiple-level hierarchical indexes based on the correlation and correlation weight between the sub-targets and the user target, and determining the corresponding relationship between the multiple-level hierarchical indexes comprises: calculating the correlation and correlation weight between the sub-targets in the index set and the user target by using forward simulation, and screening the sub-targets corresponding to the user target from the index set as first-level hierarchical indexes based on the correlation and correlation weight between the sub-targets and the user target; calculating the correlation and correlation weight between the sub-targets in the index set and the first-level hierarchical indexes by using forward simulation, and screening the second-level hierarchical indexes corresponding to the first-level hierarchical indexes from the index set based on the correlation and correlation weight between the sub-targets and the first-level hierarchical indexes; The forward simulation is used to calculate the correlation and correlation weight between the sub-targets and the secondary hierarchical indicators in the index set, and the tertiary hierarchical indicators corresponding to the secondary hierarchical indicators are selected from the index set based on the correlation and correlation weight between the sub-targets and the secondary hierarchical indicators, so as to construct an initial water injection business index evaluation system.

6. The method according to claim 5, wherein, The forward simulation is used to calculate the correlation and correlation weight between the sub-targets and the user target in the index set, and the sub-targets corresponding to the user target are selected from the index set as primary hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target. The correlation between the sub-targets and the user target in the index set is calculated. A plurality of sub-targets corresponding to the user target are selected from the index set as primary sub-targets based on the correlation between the sub-targets and the user target in the index set. The weight factor between the primary sub-targets and the user target is calculated. The weight factor between the primary sub-targets and the user target is compared with a set weight factor. The primary hierarchical indicators are selected from the primary sub-targets based on the comparison result of the weight factor of the primary sub-targets and the set weight factor.

7. The method according to claim 6, characterized in that, The correlation between the sub-targets and the user target in the index set is calculated. The correlation between the sub-targets and the user target in the index set is calculated by using a principal component analysis method.

8. The water injection service indicator evaluation system construction method of claim 6, characterized in that, The weight factor between the primary sub-targets and the user target is calculated by using a grey correlation analysis method. The total target indicators include but are not limited to: good water injection, sufficient water injection, fine water injection and effective water injection.

9. The method according to claim 1, wherein, The water injection business index evaluation system construction device includes:

10. A water injection service indicator evaluation system construction device, characterized by, A total target indicator determination module is configured to determine a total target indicator of water injection business, wherein the total target indicator corresponds to analysis indicators and control indicators. A target set determination module is configured to determine a user target by using the total target indicator and a basic model and construct an index set, wherein the index set includes a plurality of sub-targets, and the user target includes but is not limited to: water injection qualification rate, separate injection qualification rate, separate water rate and separate injection qualification time rate. An initial water injection business index evaluation system determination module is configured to calculate the correlation and correlation weight between the sub-targets and the user target in the index set by using forward simulation, select the sub-targets corresponding to the user target from the index set as multi-level hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target, determine the corresponding relationship between the multi-level hierarchical indicators, and construct an initial water injection business index evaluation system. A verification module is configured to verify the initial water injection business index evaluation system by using inverse simulation. A water injection business index evaluation system determination module regards the initial water injection business index evaluation system that passes the verification as a final water injection business index evaluation system.

11. The water injection business index evaluation system construction device according to claim 10, wherein The hierarchical indicators include: primary hierarchical indicators, secondary hierarchical indicators and tertiary hierarchical indicators. ​ The correlation and correlation weight between the sub-targets in the index set and the user target are calculated by using forward simulation, and the sub-targets corresponding to the user target are screened from the index set as the multi-level hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target, and the corresponding relationship between the multi-level hierarchical indicators is determined to construct an initial water injection business indicator evaluation system, including: The correlation and correlation weight between the sub-targets in the index set and the user target are calculated by using forward simulation, and the sub-targets corresponding to the user target are screened from the index set as the multi-level hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target, and the corresponding relationship between the multi-level hierarchical indicators is determined to construct an initial water injection business indicator evaluation system, including: The correlation and correlation weight between the sub-targets in the index set and the user target are calculated by using forward simulation, and the sub-targets corresponding to the user target are screened from the index set as the multi-level hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target, and the corresponding relationship between the multi-level hierarchical indicators is determined to construct an initial water injection business indicator evaluation system, including: The correlation and correlation weight between the sub-targets in the index set and the user target are calculated by using forward simulation, and the sub-targets corresponding to the user target are screened from the index set as the multi-level hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target, and the corresponding relationship between the multi-level hierarchical indicators is determined to construct an initial water injection business indicator evaluation system, including:

12. The water injection service indicator evaluation system construction apparatus according to claim 11, wherein, The correlation and correlation weight between the sub-targets in the index set and the user target are calculated by using forward simulation, and the sub-targets corresponding to the user target are screened from the index set as the multi-level hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target, and the corresponding relationship between the multi-level hierarchical indicators is determined to construct an initial water injection business indicator evaluation system, including: The correlation and correlation weight between the sub-targets in the index set and the user target are calculated by using forward simulation, and the sub-targets corresponding to the user target are screened from the index set as the multi-level hierarchical indicators based on the correlation and correlation weight between the sub-targets and the user target, and the corresponding relationship between the multi-level hierarchical indicators is determined to construct an initial water injection business indicator evaluation system, including: The total target indicator includes but is not limited to: good water injection, sufficient water injection, fine water injection and effective water injection. The water injection business indicator evaluation system construction method is configured to execute any one of claims 1-9. The instruction, when executed by the processor, causes the processor to be configured to execute the water injection business indicator evaluation system construction method of any one of claims 1-9. The instruction, when executed by the processor, causes the processor to be configured to execute the water injection business indicator evaluation system construction method of any one of claims 1-9.

13. The water injection service indicator evaluation system construction apparatus according to claim 10, wherein ​ 14. A processor, comprising: ​ 15. A machine-readable storage medium having stored thereon instructions, the instructions comprising: ​

Images