Dynamic power grid investment benefit evaluation and consultation platform

Abstract

The invention relates to the technical field of power grid investment management and decision support systems, in particular to a dynamic power grid investment benefit evaluation and consultation platform which comprises a cross-domain data fusion module, a real-time intelligent analysis module, a comprehensive evaluation index generation module, an investment decision support module, a strategy dynamic updating module and a user interaction module. Wherein the cross-domain data fusion module is used for collecting heterogeneous data in multiple aspects; the real-time intelligent analysis module is used for carrying out dynamic analysis and generating intermediate data containing power grid investment benefit evaluation; the comprehensive evaluation index generation module is used for generating a comprehensive power grid investment benefit index; the investment decision support module is used for generating optimized investment strategy suggestions; and the strategy dynamic updating module dynamically adjusts the power grid investment strategy. According to the invention, by integrating multi-source data in real time and providing an interaction function, the adaptability, the accuracy and the participation degree of power grid investment decision making are remarkably improved, so that the return on investment is optimized and the risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid investment management, and in particular to a dynamic power grid investment benefit evaluation and consulting platform. Background Art

[0002] With the rapid changes in the global energy market and increasingly stringent environmental policies, power grid investment faces unprecedented challenges and opportunities. Power grid operators need to rationally allocate funds to support sustainable development, meet the growing demand for electricity, and comply with technological innovation and environmental regulations. However, the existing power grid investment evaluation and strategy formulation process lacks a rapid response mechanism to real-time market data and policy changes. In addition, the investment decision-making process often fails to fully consider historical data analysis and comprehensive trend forecasts, resulting in strategy formulation that cannot fully reflect the latest changes in the market and policies.

[0003] Most current power grid investment strategies are based on static decision-making models, which are difficult to adapt to the rapidly changing market environment and policy framework. This lack of flexibility in strategy formulation often results in delayed response to investment decisions, and is unable to effectively predict and respond to future market risks and opportunities, increasing the possibility of investment errors. In addition, existing technologies fail to provide an effective user interaction platform, making it difficult for various users (such as investors, policymakers, and power grid operators) to participate in the strategy adjustment and decision-making process, limiting the transparency and participation of investment strategies.

[0004] Therefore, there is an urgent need for a power grid investment benefit evaluation and consulting platform that can dynamically integrate multi-source data (such as market trends, policy changes, environmental impacts and social feedback) and provide real-time strategy adjustment and user interaction, so as to optimize power grid investment decisions and enhance the adaptability and benefits of strategies. Summary of the invention

[0005] Based on the above purpose, the present invention provides a dynamic power grid investment benefit evaluation and consulting platform.

[0006] The dynamic power grid investment benefit evaluation and consulting platform includes a cross-domain data fusion module, a real-time intelligent analysis module, a comprehensive evaluation index generation module, an investment decision support module, a strategy dynamic update module, and a user interaction module; among which:

[0007] Cross-domain data fusion module: used to collect heterogeneous data from grid operations, finance, environmental impact and social feedback, and standardize them into a unified format through data cleaning and preprocessing technology;

[0008] Real-time intelligent analysis module: receives data sets from the cross-domain data fusion module, uses a prediction model based on machine learning to dynamically analyze real-time data, generates intermediate data including power grid investment benefit evaluation, and provides it to the comprehensive evaluation index generation module;

[0009] Comprehensive evaluation index generation module: obtains intermediate data from the real-time intelligent analysis module, combines historical data and industry standards, applies multi-dimensional evaluation algorithms, and generates comprehensive power grid investment benefit indicators;

[0010] Investment decision support module: receives the power grid investment benefit indicators provided by the comprehensive evaluation index generation module, combines market forecasts and policy change data, uses decision support algorithms, and generates optimized investment strategy recommendations;

[0011] Strategy dynamic update module: Receives strategy suggestions from the investment decision support module, and dynamically adjusts the power grid investment strategy based on the latest industry trends and policy change data provided by the cross-domain data fusion module, and feeds back the updated strategy to the comprehensive evaluation index generation module for continuous improvement;

[0012] User interaction module: Based on the investment strategy output by the strategy dynamic update module, it presents the latest power grid investment recommendations to users.

[0013] Optionally, the cross-domain data fusion module includes a data acquisition unit, a data cleaning unit and a data preprocessing unit; wherein:

[0014] Data collection unit: used to extract heterogeneous data from the power grid operation system, financial management system, environmental monitoring equipment and social feedback system, respectively. The heterogeneous data includes power load data, financial statement data, environmental pollutant emission data and user satisfaction survey data. Each type of data is collected through an independent interface and stored in a preliminary data warehouse;

[0015] Data cleaning unit: connected to the data acquisition unit, used to clean the data in the preliminary data warehouse, the cleaning process includes removing abnormal values, filling missing data, correcting the problem of inconsistent data format and eliminating duplicate data. The clean data generated after data cleaning is transmitted to the data preprocessing unit;

[0016] Data preprocessing unit: used to perform standardization processing on clean data, which includes converting heterogeneous data from different sources into a unified format according to a predetermined data model to make it conform to the general data structure requirements of the platform, and forming the standardized data into a data set in a unified format and storing it in the standardized data warehouse of the cross-domain data fusion module.

[0017] Optionally, the real-time intelligent analysis module includes a data input unit, a model training unit, a real-time analysis unit and an intermediate data storage unit; wherein:

[0018] Data input unit: used to receive standardized data sets from the cross-domain data fusion module, the data sets including cleaned and pre-processed power grid operation data, financial data, environmental impact data and social feedback data;

[0019] Model training unit: connected to the data input unit, training the data set based on the random forest model. The model training unit uses the historical data set to generate multiple decision tree models through multiple random sampling and decision tree construction, and forms the final prediction model by integrating the prediction results of each decision tree. The trained random forest model is stored in the model library for the real-time analysis unit to call;

[0020] Real-time analysis unit: connected to the model training unit and the data input unit, responsible for calling the trained random forest model to dynamically analyze the received real-time data, and generating intermediate data containing the investment benefits of the power grid by applying the random forest model to evaluate each new input data. The intermediate data includes multiple indicators such as investment return prediction, risk assessment, and environmental impact assessment;

[0021] Intermediate data storage unit: connected to the real-time analysis unit, used to store the intermediate data generated by the real-time analysis unit.

[0022] Optionally, the model training unit includes:

[0023] Historical data set preparation: receiving a standardized historical data set from a data input unit, the data set including power grid operation data, financial data, environmental impact data, and social feedback data, and dividing the data set into a training set and a validation set, wherein the training set is used to build a random forest model, and the validation set is used to evaluate the prediction performance of the model;

[0024] Multiple random sampling: The model training unit performs multiple random samplings on the data in the training set. Each sampling generates a new subset. The size of each subset is the same as the original training set. Assuming that the training set contains N samples, the probability of each sampling is: Among them, x i represents the i-th sample extracted from the original training set, P(x i ) is the probability of drawing the sample;

[0025] Decision tree model construction: For each subset generated by random sampling, a decision tree model is constructed using the decision tree algorithm. The decision tree creates branch nodes by recursively splitting the data space. Each branch node selects a feature A and its threshold to maximize the information gain. The calculation formula for information gain is: Among them, IG(T, A) represents the information gain when selecting feature A in data set T, H(T) is the entropy of data set T, V is the set of possible values ​​of feature A, T v is the subset divided according to the value v of feature A;

[0026] Generation of multiple decision tree models: Multiple decision tree models are generated by repeating random sampling and decision tree model construction. Each decision tree model corresponds to a subset sampled from the training set. If M random samplings are performed, M decision tree models are generated.

[0027] Prediction results of the comprehensive decision tree: For given input data, the model training unit inputs it into all M decision tree models to obtain the prediction results of each decision tree. Specifically for classification problems, the final prediction result is determined by voting, that is, the category with the most occurrences is selected as the final prediction result; for regression problems, the final prediction result is the average of the prediction values ​​of all decision trees.

[0028] Optionally, the comprehensive evaluation index generation module includes an intermediate data receiving unit, a historical data fusion unit, an industry standard reference unit, a multi-dimensional evaluation algorithm unit and an evaluation result generation unit; wherein:

[0029] Intermediate data receiving unit: used to receive intermediate data generated by the real-time intelligent analysis module, wherein the intermediate data includes preliminary evaluation results of multiple dimensions such as investment return prediction, risk evaluation, and environmental impact evaluation;

[0030] Historical data fusion unit: connected to the intermediate data receiving unit, used to extract historical data related to the intermediate data from the system's historical database, the historical data including past power grid investment performance data, environmental impact history records, and social feedback historical trends. The historical data fusion unit generates an extended data set with historical references by comparing and fusing the historical data with the received intermediate data;

[0031] Industry standard reference unit: connected to the historical data fusion unit, used to compare the extended data set with industry standards, including best practice indicators for power grid investment, national or regional environmental protection regulations and standards, and technical specifications for the power industry. By scaling the extended data set, the data meets the industry standard requirements in different dimensions.

[0032] Multi-dimensional evaluation algorithm unit: connected to the industry standard reference unit, used to apply the multi-dimensional evaluation algorithm to conduct a comprehensive analysis on the scaled data. The multi-dimensional evaluation algorithm adopts the hierarchical analysis method for analysis, and the formula is: Among them, A is the evaluation result, λ k is the weight of the kth level, r k is the comprehensive evaluation value of the kth level, and m is the total number of evaluation levels;

[0033] Evaluation result generation unit: connected to the multi-dimensional evaluation algorithm unit, used to integrate the evaluation results generated by the multi-dimensional evaluation algorithm unit, and finally generate a comprehensive power grid investment benefit index, which covers multiple dimensions of economic benefits, environmental impact, social responsibility and technological innovation, and transmits the generated comprehensive evaluation index to the investment decision support module.

[0034] Optionally, the industry standard reference unit includes:

[0035] Industry standard matching step: first receive the extended data set, which contains the intermediate data with historical references from the historical data fusion unit; then match the data of each dimension with the corresponding industry standards, which include economic benefit standards, environmental impact standards, social responsibility standards and technological innovation standards; for each data dimension, the matched industry standard value is recorded as S i , where i is the index of the data dimension;

[0036] Difference calculation steps: For each data point in the extended data set, calculate its difference with the industry standard. Let the data point in the extended data set be d i , the corresponding industry standard value is S i , then the difference value Δ i The calculation formula is: i =d i -S i , where Δ i Represents data point d i Compared with the industry standard value S i The difference between

[0037] Standardization step: For the difference value Δ i , standardize it so that it is within the predetermined range, so as to uniformly process the data of each dimension;

[0038] Scaling step: The standardized value v i Scaling is performed to ensure that each data dimension meets the industry standard requirements. Scaling adjusts the data points so that their relative positions within the standardized range meet the preset industry standards.

[0039] Scaling result generation step: combining the scaling results of all dimensions to generate a scaled extended data set.

[0040] Optionally, the investment decision support module includes a comprehensive evaluation receiving unit, a market data fusion unit, a decision support algorithm unit and a strategy suggestion generating unit; wherein:

[0041] Comprehensive evaluation receiving unit: used to receive the power grid investment benefit index from the comprehensive evaluation index generating module;

[0042] Market data fusion unit: connected to the comprehensive evaluation receiving unit, used to receive and process market forecast data and policy change data. Market forecast data includes future power demand, energy price trends and industry competition. Policy change data includes national or regional power industry policy adjustments, new environmental protection regulations and energy transformation policies. The market data fusion unit also includes fusing the received data with comprehensive evaluation indicators to generate an extended investment decision data set.

[0043] Decision support algorithm unit: connected to the market data fusion unit, applying decision support algorithms to analyze the expanded investment decision data set, the decision support algorithms including multi-objective optimization algorithms and linear programming algorithms;

[0044] Strategy recommendation generation unit: used to format the final optimized investment strategy solution generated by the linear programming algorithm and generate an investment strategy recommendation report, which includes specific investment projects, capital allocation, expected returns and risk assessment.

[0045] Optionally, the decision support algorithm unit specifically includes:

[0046] Objective function definition: First, define the corresponding objective function for each power grid investment benefit indicator, specifically setting x as the investment strategy variable vector, f j (x) is the objective function of the jth dimension, where j = 1, 2, ..., m, and m is the total number of objective dimensions; then the form of each objective function is: Among them, a ij is the contribution coefficient of the i-th investment strategy variable to the j-th target dimension, x i is the i-th investment strategy variable, n is the total number of investment strategy variables;

[0047] Pareto frontier analysis: Apply multi-objective optimization algorithms to find non-inferior solutions in all objective dimensions through Pareto frontier analysis. The Pareto frontier is defined as the sum of all objective functions f j (x) A set of solutions that cannot be optimized without degrading other objective functions;

[0048] Linear objective function setting: For each solution in the Pareto frontier solution set, a linear programming algorithm is applied for optimization, and the objective function is set to minimize the investment cost;

[0049] Constraint setting: When solving linear programming problems, a set of constraints needs to be set based on market data and policy change data;

[0050] Linear programming solution: Use the linear programming algorithm to solve the investment strategy solution that minimizes the objective function under the above constraints;

[0051] Result integration: Compare the optimal investment strategy solution obtained by linear programming with the preliminary solution set obtained in the multi-objective optimization step, select the solution with the best performance in each dimension as the final investment strategy plan, and integrate the final optimized investment strategy to generate a comprehensive report.

[0052] Optionally, the strategy dynamic update module includes a strategy receiving unit, an industry trend analysis unit, a policy change analysis unit, a strategy adjustment unit and a strategy feedback unit; wherein:

[0053] Strategy receiving unit: used to receive optimized investment strategy suggestions from the investment decision support module, the strategy suggestions include specific investment projects, fund allocation, expected returns and risk assessment content;

[0054] Industry trend analysis unit: connected to the strategy receiving unit, used to receive the latest industry trend data from the cross-domain data fusion module, the industry trend data includes information on power demand growth forecast, technology advancement direction and changes in market competition pattern, and specifically identifies trend change factors that potentially affect the current investment strategy by performing trend analysis on the industry trend data, and generates trend adjustment suggestions;

[0055] Policy change analysis unit: used to receive the latest policy change data from the cross-domain data fusion module, including new regulations, environmental protection requirements and energy transformation policies issued by the government, analyze the latest policy change data, evaluate its impact on the current investment strategy, and generate policy adjustment suggestions;

[0056] Strategy adjustment unit: connected with the industry trend analysis unit and the policy change analysis unit, used to integrate the trend adjustment suggestions and policy adjustment suggestions with the original investment strategy suggestions. The strategy adjustment unit applies a dynamic optimization algorithm to adjust the investment strategy in real time and generate an updated power grid investment strategy.

[0057] Strategy feedback unit: used to feed back the updated power grid investment strategy to the comprehensive evaluation index generation module. Specifically, the adjusted strategy is used as new input data for the comprehensive evaluation index generation module to recalculate the power grid investment benefit index to achieve continuous improvement.

[0058] Optionally, the user interaction module includes a policy receiving unit, a data visualization unit, a user input unit, a report generating unit and a user notification unit; wherein:

[0059] Strategy receiving unit: used to receive the updated power grid investment policy from the strategy dynamic update module for users to view and operate;

[0060] Data visualization unit: connected to the strategy receiving unit, used to visualize the updated power grid investment strategy and display the indicators in the investment strategy in the form of charts, graphs and reports according to different user needs;

[0061] User input unit: used to allow the user to perform interactive operations according to the displayed investment strategy, and the user input unit includes a parameter adjustment interface and a feedback submission interface;

[0062] Report generation unit: connected to the data visualization unit and the user input unit, used to generate a detailed power grid investment recommendation report, which includes an investment strategy summary, detailed analysis, user adjustment suggestions and potential risk assessment;

[0063] User notification unit: used to send notifications to users to remind them that new investment strategies have been updated or new investment reports have been generated. Notification methods include email, SMS or system message notifications.

[0064] Beneficial effects of the present invention:

[0065] The present invention can significantly improve the accuracy and efficiency of power grid investment decisions by integrating real-time data from multiple fields, including market trends, policy changes, environmental impacts and social feedback. The platform realizes dynamic adjustment of power grid investment strategies to ensure that investment decisions can respond to the latest changes in the market and policies in a timely manner, thereby maximizing investment returns and reducing potential risks. In addition, by applying advanced data analysis and predictive models, the platform can provide in-depth insights to help decision makers identify and exploit market opportunities while effectively avoiding risks.

[0066] The present invention enables different user groups (including grid operators, investors and policy makers) to access, evaluate and adjust grid investment strategies in real time by providing intuitive data visualization and interactive interfaces. This open interactive method not only enhances the transparency of the decision-making process, but also encourages the participation of a wider range of stakeholders, thereby improving the comprehensiveness and democracy of decision-making. Overall, the implementation of this platform will promote the optimization of grid investment strategies, enhance the scientific nature and real-time nature of investment decisions, and is of great significance to the future sustainable development of the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 A schematic diagram of a dynamic power grid investment benefit evaluation and consulting platform according to an embodiment of the present invention;

[0069] Figure 2 Schematic diagram of a policy dynamic update module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0071] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0072] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0073] like Figure 1-Figure 2 As shown in the figure, the dynamic power grid investment benefit evaluation and consulting platform includes a cross-domain data fusion module, a real-time intelligent analysis module, a comprehensive evaluation index generation module, an investment decision support module, a strategy dynamic update module and a user interaction module; among which:

[0074] Cross-domain data fusion module: used to collect heterogeneous data from grid operations, finance, environmental impact and social feedback, and standardize them into a unified format data set through data cleaning and preprocessing technology, which serves as the basic input data for other modules in the platform;

[0075] Real-time intelligent analysis module: receives data sets from the cross-domain data fusion module, uses a prediction model based on machine learning to dynamically analyze real-time data, generates intermediate data including power grid investment benefit evaluation, and provides it to the comprehensive evaluation index generation module for further analysis;

[0076] Comprehensive evaluation index generation module: obtains intermediate data from the real-time intelligent analysis module, combines historical data and industry standards, applies multi-dimensional evaluation algorithms, generates comprehensive power grid investment benefit indicators, which cover economic benefits, environmental impact, social responsibility and technological innovation, and feeds back to the investment decision support module;

[0077] Investment decision support module: receives the power grid investment benefit indicators provided by the comprehensive evaluation index generation module, combines market forecasts and policy change data, uses decision support algorithms, and generates optimized investment strategy recommendations. This strategy recommendation will be sent back to the strategy dynamic update module so that it can be adjusted according to the latest analysis results;

[0078] Strategy dynamic update module: Receives strategy suggestions from the investment decision support module, and dynamically adjusts the power grid investment strategy based on the latest industry trends and policy change data provided by the cross-domain data fusion module, and feeds back the updated strategy to the comprehensive evaluation index generation module for continuous improvement;

[0079] User interaction module: Based on the investment strategy output by the strategy dynamic update module, the module displays the latest grid investment recommendations to users and collects user feedback data. The user feedback data will enter the system again through the cross-domain data fusion module as a reference for future data analysis and strategy optimization.

[0080] The cross-domain data fusion module includes a data acquisition unit, a data cleaning unit and a data preprocessing unit; among which:

[0081] Data acquisition unit: used to extract heterogeneous data from the power grid operation system, financial management system, environmental monitoring equipment and social feedback system. The heterogeneous data include power load data, financial statement data, environmental pollutant emission data and user satisfaction survey data. Each type of data is collected through an independent interface and stored in the preliminary data warehouse;

[0082] Data cleaning unit: connected to the data acquisition unit, used to clean the data in the preliminary data warehouse. The cleaning process includes removing abnormal values, filling missing data, correcting inconsistent data formats, and eliminating duplicate data. The clean data generated after data cleaning is transmitted to the data preprocessing unit;

[0083] Data preprocessing unit: used to standardize clean data. Standardization includes converting heterogeneous data from different sources into a unified format according to a predetermined data model to make it conform to the general data structure requirements of the platform, and forming a data set in a unified format after standardization. The data is stored in the standardized data warehouse of the cross-domain data fusion module for use by subsequent modules. Through the collaborative work of the above units, the cross-domain data fusion module can effectively collect and process various heterogeneous data to ensure consistent and high-quality data input for subsequent analysis and evaluation.

[0084] The real-time intelligent analysis module includes a data input unit, a model training unit, a real-time analysis unit, and an intermediate data storage unit; wherein:

[0085] Data input unit: used to receive standardized data sets from the cross-domain data fusion module. The data sets include cleaned and pre-processed power grid operation data, financial data, environmental impact data, and social feedback data. The data input unit transmits the received data to the model training unit and the real-time analysis unit.

[0086] Model training unit: connected to the data input unit, trains the data set based on the random forest model. The model training unit uses the historical data set, generates multiple decision tree models through multiple random sampling and decision tree construction, and forms the final prediction model by integrating the prediction results of each decision tree. The model can process high-dimensional data and heterogeneous data, improve the accuracy and stability of the prediction, and the trained random forest model is stored in the model library for the real-time analysis unit to call;

[0087] Real-time analysis unit: connected to the model training unit and the data input unit, responsible for calling the trained random forest model to dynamically analyze the received real-time data. By applying the random forest model to each new input data for evaluation, intermediate data containing the investment benefits of the power grid are generated. The intermediate data includes multiple indicators such as investment return prediction, risk assessment, and environmental impact assessment. The generated intermediate data is stored in the intermediate data storage unit and transmitted to the comprehensive evaluation index generation module for further analysis;

[0088] Intermediate data storage unit: connected to the real-time analysis unit, used to store the intermediate data generated by the real-time analysis unit to ensure the integrity and consistency of the data before transmission to subsequent modules; through the cooperation of the above units, the real-time intelligent analysis module can effectively use the random forest model to perform efficient and accurate dynamic analysis of real-time data, generate intermediate data for power grid investment benefit evaluation, and ensure the system's prediction ability and response speed.

[0089] The training of the data set based on the random forest model in the model training unit includes:

[0090] Historical data set preparation: Receive standardized historical data sets from the data input unit. The data sets include power grid operation data, financial data, environmental impact data, and social feedback data. The data sets are divided into training sets and validation sets. The training sets are used to build the random forest model, and the validation sets are used to evaluate the prediction performance of the model.

[0091] Multiple random sampling: The model training unit performs multiple random sampling (Bootstrap sampling) on ​​the data in the training set. Each sampling generates a new subset. The size of each subset is the same as the original training set, but each subset may contain repeated data points. Assuming that the training set contains N samples, the probability of each sampling is: Among them, x i represents the i-th sample extracted from the original training set, P(x i ) is the probability of drawing the sample;

[0092] Decision tree model construction: For each subset generated by random sampling, a decision tree model is constructed using the decision tree algorithm. The decision tree creates branch nodes by recursively splitting the data space. Each branch node selects a feature A and its threshold to maximize the information gain or Gini coefficient. The information gain calculation formula is: Among them, IG(T, A) represents the information gain when selecting feature A in data set T, H(T) is the entropy of data set T, V is the set of possible values ​​of feature A, T v is the subset divided according to the value v of feature A;

[0093] Generation of multiple decision tree models: Multiple decision tree models are generated by repeating random sampling and decision tree model construction. Each decision tree model corresponds to a subset sampled from the training set. If M random samplings are performed, M decision tree models are generated.

[0094] Prediction results of the comprehensive decision tree: For given input data, the model training unit inputs it into all M decision tree models to obtain the prediction results of each decision tree. For classification problems, the final prediction result is determined by voting, that is, the category with the most occurrences is selected as the final prediction result; for regression problems, the final prediction result is the average of the prediction values ​​of all decision trees;

[0095] The final prediction formula for the classification problem is: in, is the final prediction result, c represents the possible category, y i is the prediction result of the i-th decision tree model, I(·) is the indicator function, if y i =c, then I(y i =c) = 1; otherwise I(y i =c)=0; Indicates the number of times category c appears in M ​​prediction results, argmax c Indicates that the category c that maximizes the above formula is selected as the final prediction result

[0096] The final prediction formula for the regression problem is: in, is the final prediction result, y i is the prediction result of the i-th decision tree model; through the above steps, the model training unit generates multiple decision tree models by using multiple random sampling and decision tree construction, and forms the final random forest prediction model by integrating the prediction results of each decision tree, thereby improving the accuracy and robustness of the model.

[0097] The comprehensive evaluation index generation module includes an intermediate data receiving unit, a historical data fusion unit, an industry standard reference unit, a multi-dimensional evaluation algorithm unit and an evaluation result generation unit; wherein:

[0098] Intermediate data receiving unit: used to receive intermediate data generated by the real-time intelligent analysis module. The intermediate data includes preliminary evaluation results of multiple dimensions such as investment return prediction, risk assessment, and environmental impact assessment. The intermediate data receiving unit transmits this data to the historical data fusion unit and the evaluation algorithm unit.

[0099] Historical data fusion unit: connected to the intermediate data receiving unit, used to extract historical data related to the intermediate data from the system's historical database. The historical data includes past power grid investment performance data, environmental impact history records, and social feedback historical trends. The historical data fusion unit generates an extended data set with historical references by comparing and fusing the historical data with the received intermediate data.

[0100] Industry standard reference unit: connected to the historical data fusion unit, used to compare the extended data set with industry standards. Industry standards include best practice indicators for power grid investment, national or regional environmental protection regulations and standards, and technical specifications for the power industry. By scaling the extended data set, the data meets industry standard requirements in different dimensions.

[0101] Multi-dimensional evaluation algorithm unit: connected to the industry standard reference unit, used to apply the multi-dimensional evaluation algorithm to conduct a comprehensive analysis of the scaled data. The multi-dimensional evaluation algorithm uses the analytic hierarchy process (AHP) for analysis, and the formula is: Among them, A is the evaluation result, λ k is the weight of the kth level, r k is the comprehensive evaluation value of the kth level, and m is the total number of evaluation levels;

[0102] Evaluation result generation unit: connected to the multi-dimensional evaluation algorithm unit, used to integrate the evaluation results generated by the multi-dimensional evaluation algorithm unit, and finally generate a comprehensive power grid investment benefit index, which covers multiple dimensions of economic benefits, environmental impact, social responsibility and technological innovation, and transmits the generated comprehensive evaluation index to the investment decision support module for further decision analysis; through the cooperation of the above units, the comprehensive evaluation index generation module can effectively combine real-time intermediate data, historical data and industry standards, and apply a multi-dimensional evaluation algorithm to generate a comprehensive power grid investment benefit index, providing the system with an accurate and comprehensive basis for investment benefit evaluation.

[0103] Industry standard reference units include:

[0104] Industry standard matching steps: first receive the extended data set, which contains the intermediate data with historical references from the historical data fusion unit; then match the data of each dimension with the corresponding industry standards, which include economic benefit standards, environmental impact standards, social responsibility standards, and technological innovation standards; for each data dimension, the matched industry standard value is recorded as S i , where i is the index of the data dimension;

[0105] Difference calculation steps: For each data point in the extended data set, calculate its difference with the industry standard. Let the data point in the extended data set be d i , the corresponding industry standard value is S i , then the difference value Δ i The calculation formula is: i =d i -S i , where Δ i Represents data point d i Compared with the industry standard value S i The difference between

[0106] Standardization step: For the difference value Δ i , and standardize it so that it is within the predetermined range, so as to uniformly process the data of each dimension; the standardization formula is: Among them, v i is the standardized value, min(Δ i ) and max(Δ i ) are the current data dimensions Δ i The minimum and maximum difference values ​​of

[0107] Scaling step: The standardized value v i Scaling is performed to make each data dimension meet the industry standard requirements. Scaling adjusts the data points so that their relative positions within the standardized range meet the preset industry standards. The scaled data points are recorded as r i , and its calculation formula is: Among them, r i are the scaled data points, is the average of industry standard values;

[0108] Scaling result generation step: Combine the scaled results of all dimensions to generate a scaled extended data set, and pass the data set to the multidimensional evaluation algorithm unit for further analysis; through the above steps, the industry standard reference unit can effectively scale the extended data set to ensure that all data dimensions meet the corresponding industry standard requirements and provide unified format input data for subsequent multidimensional evaluation algorithms.

[0109] The investment decision support module includes a comprehensive evaluation receiving unit, a market data fusion unit, a decision support algorithm unit, and a strategy suggestion generation unit; among which:

[0110] Comprehensive evaluation receiving unit: used to receive the power grid investment benefit indicators from the comprehensive evaluation indicator generation module. The indicators cover multiple dimensions such as economic benefits, environmental impact, social responsibility and technological innovation. The comprehensive evaluation receiving unit transmits these indicators to the decision support algorithm unit and the market data fusion unit.

[0111] Market data fusion unit: connected to the comprehensive evaluation receiving unit, used to receive and process market forecast data and policy change data. Market forecast data includes future power demand, energy price trends and industry competition. Policy change data includes national or regional power industry policy adjustments, new environmental protection regulations and energy transformation policies. The market data fusion unit also includes fusing the received data with comprehensive evaluation indicators to generate an extended investment decision data set.

[0112] Decision support algorithm unit: connected with the market data fusion unit, applying decision support algorithms to analyze the expanded investment decision data set. The decision support algorithms include multi-objective optimization algorithms and linear programming algorithms.

[0113] Strategy recommendation generation unit: used to format the final optimized investment strategy solution generated by the linear programming algorithm and generate an investment strategy recommendation report, which includes specific investment projects, capital allocation, expected returns and risk assessment, and pass this report to the strategy dynamic update module; through the cooperation of the above units, the investment decision support module can effectively combine comprehensive evaluation indicators, market forecast data and policy change data, and apply decision support algorithms to generate optimized power grid investment strategy recommendations, providing power grid companies with scientific and comprehensive investment decision-making basis.

[0114] The decision support algorithm unit specifically includes:

[0115] Objective function definition: First, define the corresponding objective function for each power grid investment benefit indicator, specifically setting x as the investment strategy variable vector, f j (x) is the objective function of the jth dimension, where j = 1, 2, ..., m, and m is the total number of objective dimensions; then the form of each objective function is: Among them, a ij is the contribution coefficient of the i-th investment strategy variable to the j-th target dimension, x i is the i-th investment strategy variable, n is the total number of investment strategy variables;

[0116] Pareto frontier analysis: Apply multi-objective optimization algorithms to find non-inferior solutions in all objective dimensions through Pareto frontier analysis. The Pareto frontier is defined as the sum of all objective functions f j (x) cannot be optimized without degrading other objective functions. The optimization goal is to maximize each objective function: maxf j (x) for j = 1, 2, ..., m, the Pareto frontier solution set contains all non-inferior solutions, forming a preliminary optimal solution set;

[0117] Linear objective function setting: For each solution in the Pareto frontier solution set, a linear programming algorithm is applied for optimization, and the objective function is set to minimize the investment cost. The objective function is: minc T x, where c is the cost coefficient vector and x is the investment strategy variable vector;

[0118] Constraint setting: When solving linear programming problems, a set of constraints needs to be set in combination with market data and policy change data. The constraints are set as: Ax≤b, where A is the constraint coefficient matrix, x is the investment strategy variable vector, and b is the constraint vector;

[0119] Linear programming solution: Through the linear programming algorithm, the investment strategy solution that minimizes the objective function under the above constraints is solved. The formula is: * =argmin x (c T x)subject to Ax≤b, where x * To find the optimal investment strategy solution;

[0120] Result integration: The optimal investment strategy solution obtained by solving the linear programming is compared with the preliminary solution set obtained by the multi-objective optimization step, and the solution with the best performance in each dimension is selected as the final investment strategy plan. The final optimized investment strategy is integrated and a comprehensive report is generated, which is passed to the strategy recommendation generation unit for further processing and output.

[0121] The strategy dynamic update module includes a strategy receiving unit, an industry trend analysis unit, a policy change analysis unit, a strategy adjustment unit and a strategy feedback unit; wherein:

[0122] Strategy receiving unit: used to receive optimized investment strategy suggestions from the investment decision support module. The strategy suggestions include specific investment projects, fund allocation, expected returns and risk assessment content. The strategy receiving unit transmits the received strategy suggestions to the industry trend analysis unit and the policy change analysis unit for dynamic adjustment;

[0123] Industry trend analysis unit: connected to the strategy receiving unit, used to receive the latest industry trend data from the cross-domain data fusion module. The industry trend data includes information on power demand growth forecasts, technological progress directions, and changes in the market competition landscape. Specifically, by performing trend analysis on the industry trend data, it identifies trend change factors that potentially affect the current investment strategy and generates trend adjustment suggestions;

[0124] The industry trend analysis unit specifically includes:

[0125] Data trend analysis: The industry trend analysis unit first receives the latest industry trend data from the cross-domain data fusion module. For each type of trend data, such as power demand growth forecast, technology advancement direction and market competition pattern changes, the analysis unit applies the time series analysis method to predict the data trend. The formula for time series analysis is: t =α+βt+∈ t , where y t is the trend data corresponding to time point t, α is the constant term, β is the slope of the trend term, t is the time variable, ∈ t is the random error term. Through regression analysis, the slope β of the trend term is calculated to identify the growth or decline trend of the data.

[0126] Identification of trend change factors: After determining the trend, the analysis unit evaluates the potential impact of these trend changes on the current investment strategy and sets a threshold T. When the trend change rate β exceeds the threshold T, it is considered that the trend change has a significant impact on the investment strategy;

[0127] Generate trend adjustment suggestions: Generate corresponding adjustment suggestions based on the identified trend change factors. For example, if the growth rate of electricity demand exceeds expectations, it is recommended to increase investment in grid expansion projects. The specific form of the adjustment suggestion depends on the nature and impact of the trend change factors.

[0128] Policy change analysis unit: used to receive the latest policy change data from the cross-domain data fusion module. The policy change data includes new regulations, environmental protection requirements and energy transformation policies issued by the government. By analyzing the latest policy change data, it evaluates its impact on the current investment strategy and generates policy adjustment suggestions;

[0129] The policy change analysis unit specifically includes:

[0130] Policy analysis: First, receive the latest policy change data from the cross-domain data fusion module. For each policy, analyze its impact on the areas related to power grid investment. Set the policy impact function as P(x), where x is the investment strategy variable. Analyze the direct impact of each policy on the investment strategy. The formula is as follows: in, is the sensitivity coefficient of the policy to the investment strategy variable x, Δx is the change in the strategy variable caused by the policy change;

[0131] Assessing policy impact: The analysis unit accumulates and weights the policy impact function to assess the comprehensive impact of overall policy changes on the current investment strategy. The weight is set as w j , the comprehensive evaluation formula of policy impact is: Where m is the total number of policy changes, P total (x) is the total impact of policy changes on investment strategies;

[0132] Generate policy adjustment recommendations: Generate corresponding policy adjustment recommendations based on the policy impact assessment results. For example, if a new environmental regulation significantly raises emission standards, it is recommended to adjust the investment ratio in clean energy projects. The specific form of the adjustment recommendation is determined based on the nature and impact of the policy change.

[0133] Strategy adjustment unit: connected with the industry trend analysis unit and the policy change analysis unit, used to integrate the trend adjustment suggestions and policy adjustment suggestions with the original investment strategy suggestions. The strategy adjustment unit applies a dynamic optimization algorithm to adjust the investment strategy in real time and generate an updated power grid investment strategy.

[0134] The policy adjustment unit specifically includes:

[0135] Comprehensive analysis of adjustment suggestions: Comprehensively analyze the trends and policy adjustment suggestions received, evaluate the relative importance and urgency of each suggestion, and set the adjustment factor as α j represents the weight of the jth recommendation, where j indexes the total number of trends and policy adjustment recommendations. The weights are determined based on the expected impact of the recommendation and the original goal of the policy;

[0136] Analysis of original investment strategy: The strategy adjustment unit considers the original investment strategy recommendations and analyzes the performance and limitations of the current investment strategy. Each investment decision in the original strategy i It needs to be re-evaluated based on the new adjustment proposal, where i represents the index of the investment strategy variable;

[0137] Application of dynamic optimization algorithm: Apply dynamic optimization algorithm to adjust the strategy in real time. The algorithm combines the analysis results of trend analysis, policy adjustment suggestions and original strategy to perform the following calculations:

[0138] Among them, x i,new is the adjusted investment decision for the ith item, Δx ij The recommended adjustment amount for the i-th investment strategy for the j-th recommendation;

[0139] Generate updated investment strategy: Based on the above calculation results, generate an updated grid investment strategy. The updated strategy needs to meet all industry standards and policy requirements and be optimized to improve the overall investment benefits. The final optimization objective function can be expressed as: Among them, w i is the weight of the i-th investment strategy, ROI i (x i,new ) is the adjusted return on investment.

[0140] Strategy feedback unit: used to feed back the updated power grid investment strategy to the comprehensive evaluation index generation module. Specifically, the adjusted strategy is used as new input data for the comprehensive evaluation index generation module to recalculate the power grid investment benefit index to achieve continuous improvement. The feedback process includes formatting and data transmission of the strategy results. Through the cooperation of the above units, the strategy dynamic update module can effectively combine the latest industry trends and policy change data, adjust the power grid investment strategy in real time, and input the updated strategy into the comprehensive evaluation index generation module through the feedback mechanism, thereby achieving continuous optimization and improvement of the power grid investment strategy.

[0141] The user interaction module includes a strategy receiving unit, a data visualization unit, a user input unit, a report generating unit and a user notification unit; wherein:

[0142] Strategy receiving unit: used to receive the updated power grid investment policy from the strategy dynamic update module. This unit ensures that all the latest investment strategy data can be delivered to the user interaction interface in a timely manner for users to view and operate;

[0143] Data visualization unit: connected to the strategy receiving unit, used to visualize the updated power grid investment strategy, and display the indicators in the investment strategy (such as capital allocation, expected return, risk assessment, etc.) in the form of charts, graphs and reports according to different user needs; the data visualization unit helps users intuitively understand the core content of the investment strategy through graphics, which is convenient for decision-making;

[0144] User input unit: used to allow users to interact with the displayed investment strategy. Users can provide feedback on the investment strategy, adjust parameters or simulate the strategy through this unit. The user input unit includes a parameter adjustment interface and a feedback submission interface. The parameter adjustment interface allows users to modify strategy parameters in the interface, such as adjusting the capital allocation ratio and viewing the impact of different adjustments on expected returns. The feedback submission interface allows users to submit feedback suggestions on the current strategy, and the feedback data will be transmitted to the strategy dynamic update module for further optimization.

[0145] Report generation unit: connected to the data visualization unit and the user input unit, used to generate detailed power grid investment recommendation reports. The report generation unit integrates the user input and system output data to generate customized reports. The report content includes investment strategy summary, detailed analysis, user adjustment suggestions and potential risk assessment. The generated report can be exported to PDF or other common file formats for users to save and share;

[0146] User notification unit: used to send notifications to users to remind them that new investment strategies have been updated or new investment reports have been generated. Notification methods include email, SMS or system message notifications.

[0147] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0148] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Dynamic power grid investment benefit evaluation and consulting platform, characterized by: It includes cross-domain data fusion module, real-time intelligent analysis module, comprehensive evaluation index generation module, investment decision support module, strategy dynamic update module and user interaction module; among which: Cross-domain data fusion module: used to collect heterogeneous data from grid operations, finance, environmental impact and social feedback, and standardize them into a unified format through data cleaning and preprocessing technology; Real-time intelligent analysis module: receives data sets from the cross-domain data fusion module, uses a prediction model based on machine learning to dynamically analyze real-time data, generates intermediate data including power grid investment benefit evaluation, and provides it to the comprehensive evaluation index generation module; Comprehensive evaluation index generation module: obtains intermediate data from the real-time intelligent analysis module, combines historical data and industry standards, applies multi-dimensional evaluation algorithms, and generates comprehensive power grid investment benefit indicators; Investment decision support module: receives the power grid investment benefit indicators provided by the comprehensive evaluation index generation module, combines market forecasts and policy change data, uses decision support algorithms, and generates optimized investment strategy recommendations; Strategy dynamic update module: Receives strategy suggestions from the investment decision support module, and dynamically adjusts the power grid investment strategy based on the latest industry trends and policy change data provided by the cross-domain data fusion module, and feeds back the updated strategy to the comprehensive evaluation index generation module for continuous improvement; User interaction module: Based on the investment strategy output by the strategy dynamic update module, it presents the latest power grid investment recommendations to users.

2. The dynamic power grid investment benefit evaluation and consulting platform according to claim 1 is characterized in that: The cross-domain data fusion module includes a data acquisition unit, a data cleaning unit and a data preprocessing unit; wherein: Data collection unit: used to extract heterogeneous data from the power grid operation system, financial management system, environmental monitoring equipment and social feedback system, respectively. The heterogeneous data includes power load data, financial statement data, environmental pollutant emission data and user satisfaction survey data. Each type of data is collected through an independent interface and stored in a preliminary data warehouse; Data cleaning unit: connected to the data acquisition unit, used to clean the data in the preliminary data warehouse, the cleaning process includes removing abnormal values, filling missing data, correcting the problem of inconsistent data format and eliminating duplicate data. The clean data generated after data cleaning is transmitted to the data preprocessing unit; Data preprocessing unit: used to perform standardization processing on clean data, which includes converting heterogeneous data from different sources into a unified format according to a predetermined data model to make it conform to the general data structure requirements of the platform, and forming the standardized data into a data set in a unified format and storing it in the standardized data warehouse of the cross-domain data fusion module.

3. The dynamic power grid investment benefit evaluation and consulting platform according to claim 1 is characterized in that: The real-time intelligent analysis module includes a data input unit, a model training unit, a real-time analysis unit and an intermediate data storage unit; wherein: Data input unit: used to receive standardized data sets from the cross-domain data fusion module, the data sets including cleaned and pre-processed power grid operation data, financial data, environmental impact data and social feedback data; Model training unit: connected to the data input unit, training the data set based on the random forest model. The model training unit uses the historical data set to generate multiple decision tree models through multiple random sampling and decision tree construction, and forms the final prediction model by integrating the prediction results of each decision tree. The trained random forest model is stored in the model library for the real-time analysis unit to call; Real-time analysis unit: connected to the model training unit and the data input unit, responsible for calling the trained random forest model to dynamically analyze the received real-time data, and generating intermediate data containing the investment benefits of the power grid by applying the random forest model to evaluate each new input data. The intermediate data includes multiple indicators such as investment return prediction, risk assessment, and environmental impact assessment; Intermediate data storage unit: connected to the real-time analysis unit, used to store the intermediate data generated by the real-time analysis unit.

4. The dynamic power grid investment benefit evaluation and consulting platform according to claim 3 is characterized in that: The model training unit comprises: Historical data set preparation: receiving a standardized historical data set from a data input unit, the data set including power grid operation data, financial data, environmental impact data, and social feedback data, and dividing the data set into a training set and a validation set, wherein the training set is used to build a random forest model, and the validation set is used to evaluate the prediction performance of the model; Multiple random sampling: The model training unit performs multiple random samplings on the data in the training set. Each sampling generates a new subset. The size of each subset is the same as the original training set. Assuming that the training set contains N samples, the probability of each sampling is: Among them, x i represents the i-th sample extracted from the original training set, P(x i ) is the probability of drawing the sample; Decision tree model construction: For each subset generated by random sampling, a decision tree model is constructed using the decision tree algorithm. The decision tree creates branch nodes by recursively splitting the data space. Each branch node selects a feature A and its threshold to maximize the information gain. The calculation formula for information gain is: Among them, IG(T, A) represents the information gain when selecting feature A in data set T, H(T) is the entropy of data set T, V is the set of possible values ​​of feature A, T v is the subset divided according to the value v of feature A; Generation of multiple decision tree models: Multiple decision tree models are generated by repeating random sampling and decision tree model construction. Each decision tree model corresponds to a subset sampled from the training set. If M random samplings are performed, M decision tree models are generated. Prediction results of the comprehensive decision tree: For given input data, the model training unit inputs it into all M decision tree models to obtain the prediction results of each decision tree. Specifically for classification problems, the final prediction result is determined by voting, that is, the category with the most occurrences is selected as the final prediction result; for regression problems, the final prediction result is the average of the prediction values ​​of all decision trees.

5. The dynamic power grid investment benefit evaluation and consulting platform according to claim 1 is characterized in that: The comprehensive evaluation index generation module includes an intermediate data receiving unit, a historical data fusion unit, an industry standard reference unit, a multi-dimensional evaluation algorithm unit and an evaluation result generation unit; wherein: Intermediate data receiving unit: used to receive intermediate data generated by the real-time intelligent analysis module, wherein the intermediate data includes preliminary evaluation results of multiple dimensions such as investment return prediction, risk evaluation, and environmental impact evaluation; Historical data fusion unit: connected to the intermediate data receiving unit, used to extract historical data related to the intermediate data from the system's historical database, the historical data including past power grid investment performance data, environmental impact history records, and social feedback historical trends. The historical data fusion unit generates an extended data set with historical references by comparing and fusing the historical data with the received intermediate data; Industry standard reference unit: connected to the historical data fusion unit, used to compare the extended data set with industry standards, including best practice indicators for power grid investment, national or regional environmental protection regulations and standards, and technical specifications for the power industry. By scaling the extended data set, the data meets the industry standard requirements in different dimensions. Multi-dimensional evaluation algorithm unit: connected to the industry standard reference unit, used to apply the multi-dimensional evaluation algorithm to conduct a comprehensive analysis on the scaled data. The multi-dimensional evaluation algorithm adopts the hierarchical analysis method for analysis, and the formula is: Among them, A is the evaluation result, λ k is the weight of the kth level, r k is the comprehensive evaluation value of the kth level, and m is the total number of evaluation levels; Evaluation result generation unit: connected to the multi-dimensional evaluation algorithm unit, used to integrate the evaluation results generated by the multi-dimensional evaluation algorithm unit, and finally generate a comprehensive power grid investment benefit index, which covers multiple dimensions of economic benefits, environmental impact, social responsibility and technological innovation, and transmits the generated comprehensive evaluation index to the investment decision support module.

6. The dynamic power grid investment benefit evaluation and consulting platform according to claim 5 is characterized in that: The industry standard reference units include: Industry standard matching step: first receive the extended data set, which contains the intermediate data with historical references from the historical data fusion unit; then match the data of each dimension with the corresponding industry standards, which include economic benefit standards, environmental impact standards, social responsibility standards and technological innovation standards; for each data dimension, the matched industry standard value is recorded as S i , where i is the index of the data dimension; Difference calculation steps: For each data point in the extended data set, calculate its difference with the industry standard. Let the data point in the extended data set be d i , the corresponding industry standard value is S i , then the difference value Δ i The calculation formula is: i =d i -S i , where Δ i Represents data point d i Compared with the industry standard value S i The difference between Standardization step: For the difference value Δ i , standardize it so that it is within the predetermined range, so as to uniformly process the data of each dimension; Scaling step: The standardized value v i Scaling is performed to ensure that each data dimension meets the industry standard requirements. Scaling adjusts the data points so that their relative positions within the standardized range meet the preset industry standards. Scaling result generation step: combining the scaling results of all dimensions to generate a scaled extended data set.

7. The dynamic power grid investment benefit evaluation and consulting platform according to claim 1 is characterized in that: The investment decision support module includes a comprehensive evaluation receiving unit, a market data fusion unit, a decision support algorithm unit and a strategy suggestion generating unit; wherein: Comprehensive evaluation receiving unit: used to receive the power grid investment benefit index from the comprehensive evaluation index generating module; Market data fusion unit: connected to the comprehensive evaluation receiving unit, used to receive and process market forecast data and policy change data. Market forecast data includes future power demand, energy price trends and industry competition. Policy change data includes national or regional power industry policy adjustments, new environmental protection regulations and energy transformation policies. The market data fusion unit also includes fusing the received data with comprehensive evaluation indicators to generate an extended investment decision data set. Decision support algorithm unit: connected to the market data fusion unit, applying decision support algorithms to analyze the expanded investment decision data set, the decision support algorithms including multi-objective optimization algorithms and linear programming algorithms; Strategy recommendation generation unit: used to format the final optimized investment strategy solution generated by the linear programming algorithm and generate an investment strategy recommendation report, which includes specific investment projects, capital allocation, expected returns and risk assessment.

8. The dynamic power grid investment benefit evaluation and consulting platform according to claim 7 is characterized in that: The decision support algorithm unit specifically includes: Objective function definition: First, define the corresponding objective function for each power grid investment benefit indicator, specifically setting x as the investment strategy variable vector, f j (x) is the objective function of the jth dimension, where j = 1, 2, ..., m, and m is the total number of objective dimensions; then the form of each objective function is: Among them, a ij is the contribution coefficient of the i-th investment strategy variable to the j-th target dimension, x i is the i-th investment strategy variable, n is the total number of investment strategy variables; Pareto frontier analysis: Apply multi-objective optimization algorithms to find non-inferior solutions in all objective dimensions through Pareto frontier analysis. The Pareto frontier is defined as the sum of all objective functions f j (x) A set of solutions that cannot be optimized without degrading other objective functions; Linear objective function setting: For each solution in the Pareto frontier solution set, a linear programming algorithm is applied for optimization, and the objective function is set to minimize the investment cost; Constraint setting: When solving linear programming problems, a set of constraints needs to be set based on market data and policy change data; Linear programming solution: Use the linear programming algorithm to solve the investment strategy solution that minimizes the objective function under the above constraints; Result integration: Compare the optimal investment strategy solution obtained by linear programming with the preliminary solution set obtained in the multi-objective optimization step, select the solution with the best performance in each dimension as the final investment strategy plan, and integrate the final optimized investment strategy to generate a comprehensive report.

9. The dynamic power grid investment benefit evaluation and consulting platform according to claim 1 is characterized in that: The strategy dynamic update module includes a strategy receiving unit, an industry trend analysis unit, a policy change analysis unit, a strategy adjustment unit and a strategy feedback unit; wherein: Strategy receiving unit: used to receive optimized investment strategy suggestions from the investment decision support module, the strategy suggestions include specific investment projects, fund allocation, expected returns and risk assessment content; Industry trend analysis unit: connected to the strategy receiving unit, used to receive the latest industry trend data from the cross-domain data fusion module, the industry trend data includes information on power demand growth forecast, technology advancement direction and changes in market competition pattern, and specifically identifies trend change factors that potentially affect the current investment strategy by performing trend analysis on the industry trend data, and generates trend adjustment suggestions; Policy change analysis unit: used to receive the latest policy change data from the cross-domain data fusion module, including new regulations, environmental protection requirements and energy transformation policies issued by the government, analyze the latest policy change data, evaluate its impact on the current investment strategy, and generate policy adjustment suggestions; Strategy adjustment unit: connected with the industry trend analysis unit and the policy change analysis unit, used to integrate the trend adjustment suggestions and policy adjustment suggestions with the original investment strategy suggestions. The strategy adjustment unit applies a dynamic optimization algorithm to adjust the investment strategy in real time and generate an updated power grid investment strategy. Strategy feedback unit: used to feed back the updated power grid investment strategy to the comprehensive evaluation index generation module. Specifically, the adjusted strategy is used as new input data for the comprehensive evaluation index generation module to recalculate the power grid investment benefit index to achieve continuous improvement.

10. The dynamic power grid investment benefit evaluation and consulting platform according to claim 1, characterized in that: The user interaction module includes a policy receiving unit, a data visualization unit, a user input unit, a report generating unit and a user notification unit; wherein: Strategy receiving unit: used to receive the updated power grid investment policy from the strategy dynamic update module for users to view and operate; Data visualization unit: connected to the strategy receiving unit, used to visualize the updated power grid investment strategy and display the indicators in the investment strategy in the form of charts, graphs and reports according to different user needs; User input unit: used to allow the user to perform interactive operations according to the displayed investment strategy, and the user input unit includes a parameter adjustment interface and a feedback submission interface; Report generation unit: connected to the data visualization unit and the user input unit, used to generate a detailed power grid investment recommendation report, which includes an investment strategy summary, detailed analysis, user adjustment suggestions and potential risk assessment; User notification unit: used to send notifications to users to remind them that new investment strategies have been updated or new investment reports have been generated. Notification methods include email, SMS or system message notifications.

Images