Financial expenditure behavior anomaly prediction method based on power grid infrastructure investment plan model

Abstract

The invention discloses a financial expenditure behavior anomaly prediction method based on a power grid infrastructure investment plan model, and relates to the technical field of power grid infrastructure. According to the method, various risk factors in the power grid infrastructure project are comprehensively identified, a scientific risk assessment model is used for quantitative assessment, prediction accuracy is improved, potential financial expenditure abnormity can be found in time in the early stage of the project, countermeasures can be taken in advance, problem deterioration is avoided, and project loss is reduced; a risk assessment model is combined with a power grid capital construction investment plan model, an investment plan is optimized according to a predicted financial expenditure abnormal condition, resources are reasonably allocated, it is ensured that a project is smoothly propelled, and the overall benefit of the project is improved; through comparison between actual financial expenditure data and a prediction result, the risk assessment model parameters are adjusted, so that the model can continuously adapt to the actual condition of a project, and the prediction reliability is continuously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid infrastructure, and in particular to a method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model. Background Art

[0002] In the field of power grid infrastructure, the scale of grid infrastructure projects has continued to expand in recent years, driven by rapid economic development and continued growth in energy demand. The number of new substations and transmission line lengths has increased significantly, and project complexity has also grown, encompassing complex scenarios such as the application of advanced smart grid technologies and multi-regional coordinated construction. In this context, effective financial expenditure management has become critical to ensuring smooth project implementation and achieving expected returns.

[0003] Currently, traditional financial expenditure management methods often focus on post-event accounting and lack forward-looking predictions of unusual financial expenditure behavior. During project implementation, this inability to promptly detect unusual financial expenditures leads to frequent cost overruns and delays. While some existing methods attempt to identify unusual financial expenditures through simple budget comparisons, these methods fail to fully consider the numerous and complex risk factors inherent in power grid infrastructure projects, resulting in low prediction accuracy and a failure to meet practical needs.

[0004] The present invention provides a method for predicting abnormal financial expenditure behavior based on risk assessment, which comprehensively considers the risk factors in power grid infrastructure projects, realizes accurate prediction of financial expenditure abnormalities, and improves the level of project financial management. Summary of the Invention

[0005] (1) Technical problems solved

[0006] In response to the deficiencies of the existing technology, the present invention adopts a method of comprehensively identifying various risk factors in power grid infrastructure projects and using scientific risk assessment models for quantitative assessment. It can fully consider the uncertainty in the project implementation process, greatly improve the accuracy of the prediction of abnormal financial expenditure behavior, provide a reliable basis for project decision-making, and timely discover potential financial expenditure anomalies in the early stage of the project, take countermeasures in advance, avoid the problem from worsening, and reduce project losses; by combining the risk assessment model with the power grid infrastructure investment plan model, the investment plan is optimized according to the predicted financial expenditure anomalies, and resources are reasonably allocated to ensure the smooth progress of the project and improve the overall project benefits; by comparing the actual financial expenditure data with the predicted results, the risk assessment model parameters are adjusted so that the model can continuously adapt to the actual situation of the project and continuously improve the reliability of the prediction.

[0007] (2) Technical solution

[0008] To achieve the above-mentioned object, the present invention provides the following technical solution: a method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model, comprising the following steps:

[0009] S1: Conduct in-depth research on the entire life cycle of power grid infrastructure investment plans, covering all stages of project planning, design, construction, acceptance, and operation and maintenance, and identify risk factors that affect financial expenditures at each stage;

[0010] S2: Evaluate the risk value of each risk factor to determine the extent to which the financial expenditure of power grid infrastructure exceeds the expected value, and classify the risk level based on the resulting risk assessment value;

[0011] S3: Assign risk weights based on the derived risk levels, thereby building a prediction model for abnormal financial expenditure behavior based on risk factors;

[0012] S4: Associate the abnormal prediction model of financial expenditure behavior based on risk factors with the power grid infrastructure investment plan model, and determine the abnormal financial expenditure results corresponding to different risk levels in different periods of power grid infrastructure based on data input and time determination.

[0013] Preferably, the risk factors identified in the power grid infrastructure project include policy risk, market risk, technical risk and management risk, and the identification of each risk factor should run through the entire life cycle of the project from project establishment to operation, and the dynamic changes of risk factors should be tracked in real time.

[0014] Preferably, the policy risks involve the impact of changes in national and local energy policies, environmental protection policies, etc. on the project; the market risks include fluctuations in raw material prices, changes in labor costs, and changes in the supply and demand relationship in the electricity market; the technical risks cover the uncertainty of new technology applications, failures of existing technologies, and the speed of technology updates; the management risks involve aspects such as unreasonable project organizational structure, poor personnel management, and errors in controlling project progress.

[0015] Preferably, the risk level classification includes: no risk level, controllable risk level, dangerous risk level and uncontrollable risk level;

[0016] The risk-free level means that the probability of change of the risk factor during the power grid infrastructure investment plan period is extremely small or the possible change is within the predicted range of financial expenditure;

[0017] The controllable risk level indicates that the risk factor is allowed to change within the power grid infrastructure investment plan cycle;

[0018] The dangerous risk level indicates that the risk factor will experience significant changes during the power grid infrastructure investment plan cycle, and the impact of the changes on financial expenditure is close to requiring additional investment;

[0019] The uncontrollable risk level means that the financial expenditure of this risk factor during the power grid infrastructure investment plan cycle far exceeds the investment plan, and additional investment from the outside is needed to continue infrastructure construction.

[0020] Preferably, the construction of the abnormal financial expenditure behavior prediction model based on risk factors includes the following steps:

[0021] S11: Construct a fuzzy relationship matrix based on the risk level of each risk factor. For each risk factor, construct a fuzzy relationship matrix with 3 rows corresponding to the controllable risk level, dangerous risk level and uncontrollable risk level, and n columns, where n is the number of specific sub-factors that affect the risk factor.

[0022] S12: Based on the relative magnitude of the impact of different risk factors on abnormal financial expenditure behavior, the analytic hierarchy process is used to determine the weight of each risk factor. The risk assessment target is used as the target layer, policy risk, market risk, technical risk, and management risk are used as the criterion layer, and the sub-factors under each criterion layer are used as the indicator layer. Several industry experts are invited to compare the risk factors at different levels in pairs and construct a judgment matrix A. By calculating the judgment matrix The maximum eigenvalue λ and its corresponding eigenvector are normalized to obtain the weight vector w of each risk factor and the judgment matrix element a ij It indicates the importance of the i-th risk factor relative to the j-th risk factor. The value is determined by the 1-9 scale method, indicating that the two are equally important, 3 indicates that the former is slightly more important than the latter, 5 indicates that the former is obviously more important than the latter, 7 indicates that the former is strongly more important than the latter, and 9 indicates that the former is extremely more important than the latter. 2, 4, 6, and 8 are the intermediate values ​​of adjacent judgments. If j is more important than i, then a ij =1 / a ji ;

[0023] S13: Perform fuzzy transformation calculation on the fuzzy relationship matrix of each risk factor and the corresponding weight vector to obtain the corresponding risk factor comprehensive fuzzy assessment result vector, and use fuzzy synthesis operator o to perform fuzzy transformation calculation ∧ is the minimum operation, and V is the maximum operation;

[0024] S14: Further integrate the comprehensive fuzzy assessment result vectors of each risk factor to obtain the comprehensive assessment result of the entire project risk. Among them, B 政策 、B 市场 、B 技术 、B 管理 For comprehensive assessment of risk factors, b l，i The i-th value corresponding to risk level l in the comprehensive evaluation vector B of each risk factor.

[0025] Preferably, after predicting abnormal financial expenditures based on the comprehensive assessment results of project risks, a risk threshold is set, and when the risk assessment result exceeds the risk threshold, an early warning signal is issued.

[0026] Preferably, the abnormal prediction model of financial expenditure behavior based on risk factors is combined with the power grid infrastructure investment plan model, and the abnormal prediction risk assessment of financial expenditure behavior can be performed on a regular basis. If it is predicted that a certain type of risk may lead to a substantial increase in financial expenditure, the corresponding funds can be reserved in the investment plan in advance, or the project schedule can be adjusted to ensure the smooth progress of the project.

[0027] Preferably, after the execution of the abnormal financial result prediction result, the data needs to be re-input into the correlation model after the prediction result is executed in the cycle, and the correlation model is continuously revised to ensure the accuracy of the correlation model's prediction of abnormal financial expenditure behavior.

[0028] (3) Beneficial effects

[0029] Compared with the existing technology, the present invention adopts a method of comprehensively identifying various risk factors in power grid infrastructure projects and using scientific risk assessment models for quantitative assessment. It can fully consider the uncertainty in the project implementation process, greatly improve the accuracy of the prediction of abnormal financial expenditure behavior, provide a reliable basis for project decision-making, and timely discover potential financial expenditure anomalies in the early stage of the project, take countermeasures in advance, avoid the problem from worsening, and reduce project losses; by combining the risk assessment model with the power grid infrastructure investment plan model, the investment plan is optimized according to the predicted financial expenditure anomalies, and resources are reasonably allocated to ensure the smooth progress of the project and improve the overall project benefits; by comparing the actual financial expenditure data with the predicted results, the risk assessment model parameters are adjusted so that the model can continuously adapt to the actual situation of the project and continuously improve the reliability of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 Flowchart of the prediction method of the present invention. DETAILED DESCRIPTION

[0031] In order to better understand the purpose, structure and function of the present invention, and to achieve accurate prediction of financial expenditure of power grid infrastructure investment, the present invention adopts the method of comprehensively identifying various risk factors in power grid infrastructure projects and using scientific risk assessment models for quantitative assessment, which can fully consider the uncertainty in the project implementation process, greatly improve the accuracy of abnormal prediction of financial expenditure behavior, provide a reliable basis for project decision-making, and timely discover potential financial expenditure anomalies in the early stage of the project, take countermeasures in advance, avoid the problem from worsening, and reduce project losses; by combining the risk assessment model with the power grid infrastructure investment plan model, the investment plan is optimized according to the predicted financial expenditure anomalies, resources are reasonably allocated, the project is ensured to proceed smoothly, and the overall project benefits are improved; by comparing the actual financial expenditure data with the prediction results, the risk assessment model parameters are adjusted so that the model can continuously adapt to the actual situation of the project and continuously improve the reliability of the prediction. The present invention further describes in detail the method for predicting abnormal financial expenditure behavior based on the power grid infrastructure investment plan model.

[0032] refer to Figure 1 The present invention provides a method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model, comprising the following steps:

[0033] S1: Conduct in-depth research on the entire life cycle of power grid infrastructure investment plans, covering all stages of project planning, design, construction, acceptance, and operation and maintenance, and identify risk factors that affect financial expenditures at each stage;

[0034] Specifically, the risk factors identified in power grid infrastructure projects include policy risk, market risk, technical risk, and management risk. In the actual power grid infrastructure construction process, the risk factors involved are not limited to the above-mentioned ones. They need to be increased or decreased according to the actual situation. The identification of each risk factor should run through the entire life cycle of the project from project initiation to operation, and the dynamic changes of risk factors should be tracked in real time to ensure accurate prediction.

[0035] Furthermore, the policy risks involve the impact of changes in national and local energy policies, environmental protection policies, etc. on the project; the market risks include fluctuations in raw material prices, changes in labor costs, and changes in the supply and demand relationship in the electricity market; the technical risks cover the uncertainty of new technology applications, failures of existing technologies, and the speed of technology updates; the management risks involve unreasonable project organizational structure, poor personnel management, and errors in controlling project progress.

[0036] S2: Evaluate the risk value of each risk factor to determine the extent to which the financial expenditure of power grid infrastructure exceeds the expected value, and classify the risk level based on the resulting risk assessment value;

[0037] Specifically, the risk level classification includes: no risk level, controllable risk level, dangerous risk level and uncontrollable risk level;

[0038] The risk-free level means that the probability of change of the risk factor during the power grid infrastructure investment plan period is extremely small or the possible change is within the predicted range of financial expenditure;

[0039] The controllable risk level indicates that the risk factor is allowed to change within the power grid infrastructure investment plan cycle;

[0040] The dangerous risk level indicates that the risk factor will experience significant changes during the power grid infrastructure investment plan cycle, and the impact of the changes on financial expenditure is close to requiring additional investment;

[0041] The uncontrollable risk level means that the financial expenditure of this risk factor during the power grid infrastructure investment plan cycle far exceeds the investment plan, and additional investment from the outside is needed to continue infrastructure construction.

[0042] Furthermore, to determine the risk level, senior experts in the industry can be invited to conduct assessments and collect and analyze historical power grid infrastructure data to complete a comprehensive assessment.

[0043] S3: Assign risk weights based on the derived risk levels, thereby building a prediction model for abnormal financial expenditure behavior based on risk factors;

[0044] Specifically, the construction of the abnormal financial expenditure behavior prediction model based on risk factors includes the following steps:

[0045] S11: Construct a fuzzy relationship matrix based on the risk level of each risk factor. For each risk factor, construct a fuzzy relationship matrix with 3 rows corresponding to the controllable risk level, dangerous risk level and uncontrollable risk level, and n columns, where n is the number of specific sub-factors that affect the risk factor.

[0046] S12: Based on the relative magnitude of the impact of different risk factors on abnormal financial expenditure behavior, the analytic hierarchy process is used to determine the weight of each risk factor. The risk assessment target is used as the target layer, policy risk, market risk, technical risk, and management risk are used as the criterion layer, and the sub-factors under each criterion layer are used as the indicator layer. Several industry experts are invited to compare the risk factors at different levels in pairs and construct a judgment matrix A. By calculating the judgment matrix The maximum eigenvalue λ and its corresponding eigenvector are normalized to obtain the weight vector w of each risk factor and the judgment matrix element a ijIt indicates the importance of the i-th risk factor relative to the j-th risk factor. The value is determined by the 1-9 scale method, indicating that the two are equally important, 3 indicates that the former is slightly more important than the latter, 5 indicates that the former is obviously more important than the latter, 7 indicates that the former is strongly more important than the latter, and 9 indicates that the former is extremely more important than the latter. 2, 4, 6, and 8 are the intermediate values ​​of adjacent judgments. If j is more important than i, then a ij =1 / a ji ;

[0047] S13: Perform fuzzy transformation calculation on the fuzzy relationship matrix of each risk factor and the corresponding weight vector to obtain the corresponding risk factor comprehensive fuzzy assessment result vector, and use fuzzy synthesis operator o to perform fuzzy transformation calculation ∧ is the minimum operation, and ∨ is the maximum operation;

[0048] S14: Further integrate the comprehensive fuzzy assessment result vectors of each risk factor to obtain the comprehensive assessment result of the entire project risk. Among them, B 政策 、B 市场 、B 技术 、B 管理 For comprehensive assessment of risk factors, b l,i The i-th value corresponding to risk level l in the comprehensive evaluation vector B of each risk factor.

[0049] Furthermore, the quantitative assessment described above can clearly determine the risk status of the project, providing a strong basis for subsequent predictions of abnormal financial expenditures. After predicting abnormal financial expenditures based on the comprehensive project risk assessment results, a risk threshold is set. When the risk assessment result exceeds the risk threshold, an early warning signal is issued. A high high-risk assessment value indicates that the project may have a significant risk of abnormal financial expenditures, requiring special attention and appropriate measures.

[0050] S4: The financial expenditure behavior anomaly prediction model based on risk factors is linked to the power grid infrastructure investment plan model. Based on the input of data and the determination of time, the financial expenditure anomaly results corresponding to different risk levels in different periods of power grid infrastructure are determined;

[0051] Specifically, the abnormal financial expenditure behavior prediction model based on risk factors is combined with the power grid infrastructure investment plan model, and the abnormal financial expenditure behavior prediction risk assessment can be performed on a weekly basis. If it is predicted that a certain type of risk may lead to a substantial increase in financial expenditure, the corresponding funds can be reserved in the investment plan in advance, or the project schedule can be adjusted to ensure the smooth progress of the project.

[0052] Furthermore, after the execution of the forecast results of the financial abnormal results, the data needs to be re-input into the correlation model after the forecast results are executed in the cycle, and the correlation model needs to be continuously revised to ensure the accuracy of the correlation model's forecast of abnormal financial expenditure behavior; if the deviation of the correlation model's forecast of abnormal financial expenditure behavior is within 8%, the correlation model is installed to continue to promote the power grid infrastructure investment plan. If it exceeds 8%, the correlation model needs to be revised again, and then the financial expenditure abnormality forecast is recalculated to ensure the accuracy of the correlation model and the reasonable allocation of resources for the power grid benchmark investment, ensure the smooth progress of the project, and improve the overall project benefits.

[0053] It will be understood that the present invention is described by way of some embodiments, and it will be appreciated by those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are intended to be protected by the present invention.

Claims

1. A method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model, characterized by: The following steps are involved: S1: Conduct in-depth research on the entire life cycle of power grid infrastructure investment plans, covering all stages of project planning, design, construction, acceptance, and operation and maintenance, and identify risk factors that affect financial expenditures at each stage; S2: Evaluate the risk value of each risk factor to determine the extent to which the financial expenditure of power grid infrastructure exceeds the expected value, and classify the risk level based on the resulting risk assessment value; S3: Assign risk weights based on the derived risk levels, thereby building a prediction model for abnormal financial expenditure behavior based on risk factors; S4: Associate the abnormal prediction model of financial expenditure behavior based on risk factors with the power grid infrastructure investment plan model, and determine the abnormal financial expenditure results corresponding to different risk levels in different periods of power grid infrastructure based on data input and time determination.

2. The method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model according to claim 1, characterized in that: The risk factors identified in power grid infrastructure projects include policy risks, market risks, technical risks and management risks, and the identification of various risk factors should run through the entire life cycle of the project from project initiation to operation, and the dynamic changes of risk factors should be tracked in real time.

3. The method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model according to claim 2, characterized in that: The policy risks mentioned above involve the impact of changes in national and local energy policies, environmental protection policies, etc. on the project; the market risks mentioned above include fluctuations in raw material prices, changes in labor costs, and changes in the supply and demand relationship in the electricity market; the technical risks mentioned above cover the uncertainty of the application of new technologies, failures of existing technologies, and the speed of technological updates; the management risks mentioned above involve aspects such as unreasonable project organizational structure, poor personnel management, and errors in controlling project progress.

4. The method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model according to claim 3, characterized in that: The risk level classification includes: no risk level, controllable risk level, dangerous risk level and uncontrollable risk level; The risk-free level means that the probability of change of the risk factor during the power grid infrastructure investment plan period is extremely small or the possible change is within the predicted range of financial expenditure; The controllable risk level indicates that the risk factor is allowed to change within the power grid infrastructure investment plan cycle; The dangerous risk level indicates that the risk factor will experience significant changes during the power grid infrastructure investment plan cycle, and the impact of the changes on financial expenditure is close to requiring additional investment; The uncontrollable risk level means that the financial expenditure of this risk factor during the power grid infrastructure investment plan cycle far exceeds the investment plan, and additional investment from the outside is needed to continue infrastructure construction.

5. The method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model according to claim 4 is characterized in that: The construction of the abnormal financial expenditure behavior prediction model based on risk factors includes the following steps: S11: Construct a fuzzy relationship matrix based on the risk level of each risk factor. For each risk factor, construct a fuzzy relationship matrix with 3 rows corresponding to the controllable risk level, dangerous risk level and uncontrollable risk level, and n columns, where n is the number of specific sub-factors that affect the risk factor. S12: Based on the relative magnitude of the impact of different risk factors on abnormal financial expenditure behavior, the analytic hierarchy process is used to determine the weight of each risk factor. The risk assessment target is used as the target layer, policy risk, market risk, technical risk, and management risk are used as the criterion layer, and the sub-factors under each criterion layer are used as the indicator layer. Several industry experts are invited to compare the risk factors at different levels in pairs and construct a judgment matrix A. By calculating the judgment matrix The maximum eigenvalue λ and its corresponding eigenvector are normalized to obtain the weight vector w of each risk factor and the judgment matrix element a ij It indicates the importance of the i-th risk factor relative to the j-th risk factor. The value is determined by the 1-9 scale method, indicating that the two are equally important, 3 indicates that the former is slightly more important than the latter, 5 indicates that the former is obviously more important than the latter, 7 indicates that the former is strongly more important than the latter, and 9 indicates that the former is extremely more important than the latter. 2, 4, 6, and 8 are the intermediate values ​​of adjacent judgments. If j is more important than i, then a ij =1 / a ji ; S13: Perform fuzzy transformation calculation on the fuzzy relationship matrix of each risk factor and the corresponding weight vector to obtain the corresponding risk factor comprehensive fuzzy assessment result vector, and use fuzzy synthesis operator o to perform fuzzy transformation calculation ∧ is the minimum operation, and ∨ is the maximum operation; S14: Further integrate the comprehensive fuzzy assessment result vectors of each risk factor to obtain the comprehensive assessment result of the entire project risk. Among them, B 政策 、B 市场 、B 技术 、B 管理 For comprehensive assessment of risk factors, b l，i The i-th value corresponding to risk level l in the comprehensive evaluation vector B of each risk factor.

6. The method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model according to claim 5, characterized in that: After predicting abnormal financial expenditures based on the comprehensive assessment results of project risks, a risk threshold is set, and when the risk assessment results exceed the risk threshold, an early warning signal is issued.

7. The method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model according to claim 6, characterized in that: By combining the abnormal prediction model of financial expenditure behavior based on risk factors with the power grid infrastructure investment plan model, it is possible to conduct abnormal prediction risk assessment of financial expenditure behavior on a regular basis. If it is predicted that a certain type of risk may lead to a substantial increase in financial expenditure, corresponding funds can be reserved in the investment plan in advance, or the project schedule can be adjusted to ensure the smooth progress of the project.

8. The method for predicting abnormal financial expenditure behavior based on a power grid infrastructure investment plan model according to claim 7, characterized in that: After the execution of the abnormal financial result prediction results, the data needs to be re-input into the correlation model after the prediction results are executed in the cycle, and the correlation model needs to be continuously revised to ensure the accuracy of the correlation model's prediction of abnormal financial expenditure behavior.

Images