Method and system for realizing dynamic intelligent evaluation of electric power project

Abstract

The embodiment of the invention provides a method and a system for realizing dynamic intelligent evaluation of an electric power project. The method comprises the following steps: acquiring historical electric power project related data, and carrying out fusion processing; establishing a post-evaluation model of single-project dynamic tracking and a post-evaluation model of multi-project dynamic tracking; an analytic hierarchy process or a triangular fuzzy comprehensive evaluation method is adopted to determine the index weight of each index of the project in the post-evaluation model of single-project dynamic tracking, and an advantage and inferior solution distance method is adopted to determine the index weight of each index of the project in the post-evaluation model of multi-project dynamic tracking; dynamically updating a corresponding index weight according to the real-time feedback data; and performing dynamic intelligent evaluation on the electric power project through the post-evaluation model of single-project dynamic tracking and the post-evaluation model of multi-project dynamic tracking. According to the invention, the electric power project data can be effectively integrated, and the dynamic tracking evaluation of the electric power project is realized by using artificial intelligence and data fusion technologies.

Description

Technical Field

[0001] The present invention relates to the technical field of power project management, and in particular to a method and system for realizing dynamic intelligent evaluation of power projects. Background Art

[0002] In the field of power construction, post-project evaluation is a key link to ensure project quality and continuous improvement. Traditional post-evaluation methods for power projects mainly rely on "static" indicators, which are evaluated once after the project is completed and cannot dynamically reflect the changes and performance of the project during operation. This method has many limitations, such as troublesome fund-raising, high human resource consumption, and difficulty in real-time and dynamic evaluation of projects. With the increasing complexity of power systems and the sharp increase in data volume, traditional post-evaluation methods can no longer meet the needs of modern power project management.

[0003] In the era of big data, the power system has accumulated a huge amount of data, which contains detailed information on all stages of the project from planning, construction to operation. However, the utilization rate of this data is currently low, and its potential value has not been fully utilized. How to effectively integrate this data and use artificial intelligence and data fusion technology to achieve dynamic tracking and evaluation of power projects is an urgent problem to be solved in the current power project management field. Summary of the invention

[0004] The embodiment of the present invention provides a method and system for realizing dynamic intelligent evaluation of power projects, which can effectively integrate power project data and realize dynamic tracking evaluation of power projects by using artificial intelligence and data fusion technology.

[0005] In a first aspect, the present application provides a method for realizing dynamic intelligent evaluation of power projects, comprising: Obtain historical power project-related data and integrate them through automatic matching algorithms; According to the fused power project related data, a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model are established; Adopting the analytic hierarchy process or triangular fuzzy comprehensive evaluation method to determine the weights of various indicators in the post-evaluation model of dynamic tracking of a single project, and adopting the superior and inferior solution distance method to determine the weights of various indicators in the post-evaluation model of dynamic tracking of multiple projects; Respectively obtain real-time feedback data of the indicator weights of various indicators of the project in the post-evaluation model of the dynamic tracking of a single project and the post-evaluation model of the dynamic tracking of multiple projects, and dynamically update the corresponding indicator weights according to the real-time feedback data; Based on the dynamically updated indicator weights, dynamic intelligent evaluation of power projects is carried out through the post-evaluation model of single project dynamic tracking and the post-evaluation model of multiple projects dynamic tracking.

[0006] In one embodiment, the obtaining of historical power project related data and fusing the historical power project related data through an automatic matching algorithm includes: Adjust the system data format of different power systems and obtain historical power project related data from different power systems; Classify historical power project-related data, extract target key fields, and use them as the basis for data matching; Obtain the degree of consistency between the target key fields of different power systems, perform data matching based on the degree of consistency, and obtain data matching results; According to the data matching result, the historical power project related data are fused.

[0007] In one embodiment, the types of project indicators in the post-evaluation model for dynamic tracking of a single project and the post-evaluation model for dynamic tracking of multiple projects include at least: process evaluation indicators, project effect evaluation indicators, environmental impact evaluation indicators and sustainability evaluation indicators, wherein each indicator includes indicators at the preset criterion layer, primary indicators and secondary indicators.

[0008] In one embodiment, the use of the analytic hierarchy process or the triangular fuzzy comprehensive evaluation method to determine the indicator weights for various indicators of the project in the post-evaluation model of the dynamic tracking of a single project includes: Adopting analytic hierarchy process or triangular fuzzy comprehensive evaluation method to obtain real-time evaluation data of three-level indicators; According to the real-time evaluation data of the three-level indicators, the hierarchical membership of each data is calculated; According to the hierarchical affiliation of each data item, starting from the third-level indicators, the real-time evaluation data of the second-level indicators, the first-level indicators and the criterion-level indicators are determined step by step until the real-time evaluation data of the target level is determined; According to the real-time evaluation data of the target level, the indicator weights for various indicators of the project in the post-evaluation model of dynamic tracking of a single project are obtained.

[0009] In one embodiment, the method of using the superior and inferior solution distance method to determine the indicator weights for various indicators of the project in the post-evaluation model of dynamic tracking of multiple projects includes: In the case where there is at least one power project, obtaining project annual and real-time evaluation data corresponding to each power project; Based on the project year, the same project in the same year and the same project in different years are determined separately; The superiority and inferiority solution distance method is used to obtain the superiority and inferiority results of the post-evaluation of the same project in the same year and the same project in different years, and the superiority and inferiority results of the post-evaluation of the same project in different years are integrated; Based on the post-evaluation results of the same project in the same year and the integrated post-evaluation results of the same project in different years, the indicator weights for various project indicators in the post-evaluation model for dynamic tracking of multiple projects are determined.

[0010] In one embodiment, after integrating the post-evaluation results corresponding to the same project in different years, the method further includes: According to the post-evaluation results of the same project in different years after integration, the indicator weight of each project is obtained, and the projects are ranked according to the indicator weight to determine at least one of the top n projects; According to the indicator weight corresponding to at least one of the top n projects in the ranking, the indicator weight for each indicator of the project in the post-evaluation model of dynamic tracking of the single project is updated.

[0011] In one embodiment, dynamically updating the corresponding indicator weight according to the real-time feedback data includes: Obtain adjustment information on the number of similar projects and project priorities based on feedback from post-evaluators; The corresponding indicator weights of each project are dynamically updated based on the feedback adjustment information on the number of similar projects and the adjustment information on project priorities.

[0012] In one embodiment, before obtaining the data year and real-time evaluation data corresponding to each power project, the method further includes: At least one power project is classified and screened according to preset required comparison types, wherein the required comparison types include project year, project region and project attributes.

[0013] In a second aspect, the present application also provides a system for realizing dynamic intelligent evaluation of power projects, including: The data acquisition and processing module is used to acquire historical power project related data and integrate the historical power project related data through an automatic matching algorithm; A model building module is used to establish a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model based on the fused power project related data; An indicator weight determination module is used to determine the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of a single project by using a hierarchical analysis method or a triangular fuzzy comprehensive evaluation method, and to determine the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of multiple projects by using a superior and inferior solution distance method; An indicator weight updating module is used to obtain real-time feedback data of the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of a single project and a post-evaluation model for dynamic tracking of multiple projects, and dynamically update the corresponding indicator weights according to the real-time feedback data; The dynamic intelligent evaluation module is used to perform dynamic intelligent evaluation of power projects based on dynamically updated indicator weights through a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model.

[0014] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0015] The above-mentioned method and system for realizing dynamic intelligent evaluation of power projects, firstly, by acquiring historical power project-related data and using automatic matching algorithm for fusion processing, can effectively integrate the massive data of power projects from planning, construction to operation. Based on the fused data, a post-evaluation model for dynamic tracking of a single project and a post-evaluation model for dynamic tracking of multiple projects are established. The single-project model focuses on in-depth analysis and tracking of changes in various indicators of a single power project during operation, such as project cost control, quality assurance, and schedule. It can monitor the key performance indicators of the project in real time and timely discover potential problems based on the changing trends of these indicators. The multi-project model comprehensively evaluates and compares multiple power projects from a macro perspective. It can help managers understand the performance differences between different projects and identify projects with excellent performance and projects that need improvement. The hierarchical analysis method or triangular fuzzy comprehensive evaluation method is used to determine the indicator weights in the single-project model. These methods can fully consider the experience and knowledge of experts and the characteristics of the data itself. This method not only ensures the scientific nature of the evaluation, but also takes into account the flexibility of actual operation. For the multi-project model, the superior and inferior solution distance method is used to determine the indicator weights. This method dynamically adjusts the weights by calculating the distance between each project indicator and the ideal optimal solution and the worst solution. It can better reflect the relative position and competitiveness of the project in the group. More importantly, the application can obtain real-time feedback data and dynamically update the indicator weights based on these data. This means that the evaluation model is not static, but can adjust itself as the project operation changes. Based on the dynamically updated indicator weights, the present invention realizes dynamic intelligent evaluation of power projects through the post-evaluation model of dynamic tracking of single projects and multiple projects. This evaluation method has the following significant advantages: Compared with the traditional one-time evaluation method of static indicators, the dynamic intelligent evaluation of the present invention can reflect the changes of the project in real time during operation. It no longer relies on retrospective analysis after the completion of the project, but through real-time monitoring and evaluation, it not only covers all stages of the project, but also deeply analyzes the key indicators of the project, discovers problems in time and provides solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 An application environment diagram of a method for implementing dynamic intelligent evaluation of power projects in one embodiment; Figure 2 A schematic diagram of a flow chart of a method for implementing dynamic intelligent evaluation of power projects in one embodiment; Figure 3 A schematic flow chart of a method for implementing dynamic intelligent evaluation of power projects in another embodiment; Figure 4 A schematic flow chart of a method for implementing dynamic intelligent evaluation of power projects in yet another embodiment; Figure 5 A structural block diagram of a system for implementing dynamic intelligent evaluation of power projects in one embodiment; Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] The method for realizing dynamic intelligent evaluation of power projects provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0020] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0021] In an exemplary embodiment, Figure 2 As shown in the figure, a method for realizing dynamic intelligent evaluation of power projects is provided. Figure 1 The server in the example is used to illustrate, including the following steps S202 to S210. Among them: Step S202, obtaining historical power project related data, and fusing the historical power project related data through an automatic matching algorithm.

[0022] Specifically, by completing system integration from the full-service data center, it is possible to obtain the power project planning and management platform, unified video surveillance platform, video image information of projects under construction and put into production, equipment ledger information, equipment operation information, etc. The data types of power project-related data include substation data and line data. Substation data covers information such as substation name, voltage level, main transformer number, and affiliated unit; line data includes information such as starting power station, terminal power station, line name, and voltage level. The automatic matching algorithm is divided into substation data automatic matching algorithm and line data automatic matching algorithm. The two are similar in process and include modules such as data extraction, key data screening, data format adjustment, data precise matching, data fuzzy matching, and abnormal data analysis.

[0023] After obtaining historical power project related data, the automatic matching algorithm is used to process these data. For data that can be accurately matched, they are directly integrated together; for data that requires fuzzy matching, manual review or further processing is performed according to the matching degree and prompts; for abnormal data, the reasons are analyzed and corresponding measures are taken, such as data correction and supplementation, to finally achieve data fusion. The power project data that has been cleaned, sorted and integrated has higher accuracy and consistency, and can better reflect the actual situation of the power project.

[0024] Step S204, establishing a post-evaluation model for dynamic tracking of a single project and a post-evaluation model for dynamic tracking of multiple projects based on the fused power project related data.

[0025] Specifically, for a single power project, based on the fused project-related data, a single project dynamic tracking post-evaluation model is constructed that can post-evaluate the project in real time and dynamically. The purpose is to achieve continuous tracking and evaluation of various indicators at all stages of the project life cycle, timely discover problems in project operation, and provide a basis for project improvement and subsequent decision-making on similar projects.

[0026] The integrated data includes the decision-making basis and design data in the project planning stage, the construction progress, quality control, investment completion status and other data during the construction process, as well as the operation data after the project is put into operation, such as equipment operating status, power output, failure rate, etc.

[0027] For example, in process evaluation, indicators include preliminary decision evaluation, construction preparation, project construction management, etc.; in project effect and benefit evaluation, indicators include technical level, project implementation effect, project capital benefit, etc. Indicators include both static indicators, such as project decision basis, project planning storage status, etc., and dynamic indicators, such as project planning consistency rate, feasibility study consistency rate, etc. Dynamic indicators will change over time and with changes in project operation.

[0028] The post-evaluation model for dynamic tracking of a single project can dynamically calculate and score various indicators based on the project data obtained in real time. For example, for dynamic indicators, as the project operation data is updated, such as changes in the equipment operation status, fluctuations in power output, etc., the model will automatically recalculate the indicator score to reflect the actual operation status of the project at different time points. At the same time, the model can set up an early warning mechanism. When the score of certain indicators is lower than the preset threshold or there is an abnormal change, an early warning will be issued in time to remind relevant personnel to pay attention and take measures.

[0029] Application scenario: In the operation and management of power projects, project managers can grasp the operation status and benefits of the project in real time through the single project dynamic tracking and post-evaluation model. For example, in the early stage of project commissioning, focus on the commissioning and failure rate indicators of the equipment to promptly discover and solve equipment problems.

[0030] For multiple power projects, a multi-project dynamic tracking and post-evaluation model is established based on the fusion-processed data of each project. The purpose is to find out the differences and commonalities between projects through horizontal comparison and comprehensive analysis of multiple projects, summarize the lessons learned from project operation, and provide more comprehensive and valuable decision-making support for the planning, construction and management of power projects.

[0031] The integrated data includes not only the detailed data of a single project, but also the integration and standardization of similar data of multiple projects. For example, the construction investment data and operation benefit data of different projects at the same stage are summarized and compared to form a comprehensive data set of multiple projects. At the same time, considering the construction background of different projects, regional differences and other factors, the data also needs to be classified and labeled so as to conduct targeted analysis in the model.

[0032] On the basis of the single project post-evaluation index system, select important indicators suitable for multi-project comparison. These indicators should have strong comparability and be able to reflect the common characteristics and key performance of the projects. The differences in the numerical values ​​of indicators of different projects need to be standardized to eliminate the influence of dimensions and data size. For example, the dimensionless method is used to convert the indicator data of each project into relative values ​​or standardized scores, so that the indicators of different projects can be compared under the same standard.

[0033] The post-evaluation model for dynamic tracking of multiple projects can dynamically track the post-evaluation results of multiple projects. As time goes by and project data is updated, the evaluation indicators and comprehensive scores of each project are regularly recalculated to reflect the overall operation trend and changes of the project group. In addition, the model also has the function of self-feedback learning. According to the results of the post-evaluation of multiple projects, the weights and evaluation strategies of individual projects are revised and optimized, forming a closed-loop feedback mechanism to continuously improve the scientificity and adaptability of the evaluation model.

[0034] Application scenarios: In project management decisions, the multi-project dynamic tracking and post-evaluation model can provide a reference for project planning. By comprehensively evaluating and comparing power projects of different types and regions, successful project cases and lessons learned from failures can be identified, providing a basis for the site selection, scale determination, and technology selection of new projects.

[0035] Step S206, using the hierarchical analysis method or the triangular fuzzy comprehensive evaluation method to determine the indicator weights for each project indicator in the post-evaluation model of single project dynamic tracking, and using the superior and inferior solution distance method to determine the indicator weights for each project indicator in the post-evaluation model of multi-project dynamic tracking.

[0036] Specifically, the determination of indicator weights in the post-evaluation model of dynamic tracking of a single project: 1. Analytical Hierarchy Process (AHP): The analytic hierarchy process is a commonly used multi-criteria decision-making method that determines the indicator weights by constructing a judgment matrix and performing consistency tests.

[0037] Construct a hierarchical model: divide the post-evaluation indicators into the criteria layer, primary indicators, secondary indicators, etc. For example, the criteria layer is the comprehensive results of the project post-evaluation, and the primary indicators include process evaluation, project effect and benefit evaluation, environmental and social impact evaluation, sustainability evaluation, etc.

[0038] Construct a judgment matrix: Compare the indicators at each level in pairs to construct a judgment matrix. The comparison is done on a 1-9 scale, where 1 means that the two indicators are equally important, and 9 means that one indicator is significantly more important than the other.

[0039] Consistency test: Calculate the maximum eigenvalue (λmax) and consistency index (CI) of the judgment matrix, and perform a consistency ratio (CR) test. If CR < 0.1, the consistency of the judgment matrix is ​​considered acceptable.

[0040] Calculate weights: Calculate the weights of each indicator by using the arithmetic mean method, geometric mean method, or maximum eigenvalue method. For example, when using the maximum eigenvalue method, find the eigenvector corresponding to the maximum eigenvalue of the judgment matrix and normalize it to obtain the weight.

[0041] Example: Assume that there are three secondary indicators in the process evaluation: preliminary decision evaluation, construction preparation, and project construction management. The judgment matrix constructed by expert scoring is as follows: Early Decision Construction preparation Project construction Early Decision 1 3 2 Construction preparation 1 / 3 1 1 / 2 Project construction 1 / 2 2 1 Calculate the maximum eigenvalue λmax and consistency index CI for consistency check. If passed, calculate the weights, assuming the weights are 0.4, 0.3, and 0.3 respectively.

[0042] 2. Triangular fuzzy comprehensive evaluation method: The triangular fuzzy comprehensive evaluation method constructs a fuzzy judgment matrix and a fuzzy evaluation factor matrix and uses triangular fuzzy numbers to deal with the uncertainty of indicator weights.

[0043] Constructing a fuzzy judgment matrix: Similar to the AHP method, but using triangular fuzzy numbers (a, b, c) to represent the experts' judgments on the relative importance of indicators. For example, (1, 1, 1) means that two indicators are equally important, and (3, 5, 7) means that one indicator is significantly more important than the other. Constructing a fuzzy evaluation factor matrix: Combining the fuzzy judgment matrices of multiple experts to obtain a fuzzy evaluation factor matrix. Processing the fuzzy evaluation factor matrix to obtain an adjusted judgment matrix. Calculate the weight of each indicator through the operation of triangular fuzzy numbers. The weight calculation method can refer to the method in the AHP method, but use the median of the triangular fuzzy number for calculation.

[0044] Example: Assume that there are two secondary indicators in the evaluation of project effects and benefits: technical level and project implementation effect. The fuzzy judgment matrix given by the experts is as follows: Technical Level Project implementation effect Technical Level （1，1，1） （3，5，7） Project implementation effect （1 / 7，1 / 5，1 / 3） （1，1，1） Through calculation and adjustment, the weight of each indicator is obtained. It is assumed that the weights are 0.6 and 0.4 respectively.

[0045] Determination of indicator weights in the post-evaluation model of multi-project dynamic tracking: The TOPSIS method determines the relative proximity of each item by calculating the distance between each item indicator and the ideal solution and the negative ideal solution, thereby determining the indicator weight. Standardize the indicator data of each item to eliminate the influence of dimension and data size. For example, the standardization method of extremely large indicators is used to convert all indicators into dimensionless relative values. In the standardized data, the best value (maximum value) and the worst value (minimum value) of each indicator are determined to form the ideal solution and the negative ideal solution. Calculate the Euclidean distance of each item to the ideal solution and the negative ideal solution.

[0046] By formula Calculate the relative proximity of each item, where is the distance between the project and the ideal solution, is the distance between the project and the negative ideal solution.

[0047] Determine weights: Determine the weights of each indicator based on relative proximity. The weights can be obtained by normalizing the relative proximity, or adjusted through expert scoring or historical data.

[0048] Example: Assume that in a multi-project post-evaluation, there are two projects A and B, and two secondary indicators: technical level and project implementation effect. The standardized data are as follows: project Technical Level Project implementation effect A 0.8 0.7 B 0.6 0.9 The ideal solution is (1,1) and the negative ideal solution is (0,0). Calculate the distance between each item and the ideal solution and the negative ideal solution: D A+ =0.36, D A- =1.06; D B+ =0.45, D B- =1.08.

[0049] The relative proximity of project A and project B is calculated to be 0.74 and 0.7 respectively. The weight of each indicator is determined based on the relative proximity. It is assumed that the weights are 0.55 and 0.45 respectively.

[0050] Step S208, respectively obtaining real-time feedback data of the indicator weights of various indicators of the project in the post-evaluation model of the single-project dynamic tracking and the post-evaluation model of the multi-project dynamic tracking, and dynamically updating the corresponding indicator weights according to the real-time feedback data.

[0051] Specifically, real-time feedback data mainly comes from real-time operation data in the system, including equipment operation status, power output, failure rate, investment completion, etc. These data are transmitted to the post-evaluation system in real time through automatic matching algorithms and data fusion technology.

[0052] According to the real-time feedback data, the indicator weights can be adjusted dynamically. The following methods can be used: Weight adjustment based on data changes: If the real-time data of an indicator changes significantly, it indicates that the impact of the indicator on the project may increase, and the weight of the indicator is increased accordingly. For example, if the failure rate of a project suddenly increases significantly, the weight of the failure rate indicator is increased to reflect its greater impact on project operations.

[0053] Weight adjustment based on expert feedback: Indicator weights are adjusted based on the experience and judgment of experts. Experts can make suggestions for weight adjustment based on the actual operation of the project and industry experience, and the post-evaluation system dynamically updates the weights based on these suggestions.

[0054] Weight adjustment based on model self-learning: Use machine learning algorithms, such as neural networks or decision trees, to analyze historical and real-time data and automatically adjust indicator weights. The model learns the changing patterns of data and predicts changes in the importance of indicators, thereby dynamically updating weights.

[0055] Update frequency: Determine the weight update cycle based on the project's operating characteristics and data update frequency. For key indicators, weights can be updated in real time or daily; for relatively stable indicators, they can be updated weekly or monthly. For example, for equipment operating status indicators, since their data changes frequently, weights can be updated in real time; and for project investment benefit indicators, since their changes are relatively slow, they can be updated monthly.

[0056] Step S210 , based on the dynamically updated indicator weights, a dynamic intelligent evaluation is performed on the power project through a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model.

[0057] Specifically, the post-evaluation model of single-project dynamic tracking performs dynamic evaluation: First, obtain project operation data from the system in real time, including equipment operation status, power output, failure rate, etc. Perform data cleaning, format conversion and outlier processing to ensure data accuracy and availability.

[0058] Dynamic index calculation: Calculate the current value of each dynamic index based on real-time data. For example, calculate the maximum load rate of the transformer, the average load rate of the line, etc.

[0059] Static indicator confirmation: For static indicators, such as project decision-making basis, project planning inventory status, etc., confirmation is carried out through system files or manual judgment.

[0060] Use the dynamically updated indicator weights to weight each indicator. For example, if the weight of the failure rate indicator increases, its influence in the total score will also increase accordingly. Use the fuzzy comprehensive evaluation method to comprehensively calculate the weighted scores of each indicator to obtain the comprehensive evaluation results of the project. The specific steps are as follows: Determine the fuzzy evaluation factor set: take each indicator as the evaluation factor set.

[0061] Determine the comment set for fuzzy evaluation: Set the comment set, such as "excellent", "good", "average", and "not up to standard".

[0062] Establish fuzzy sets of factor importance: Construct fuzzy sets based on dynamic weights.

[0063] The membership of each indicator forms an evaluation matrix. Through fuzzy operation, the comprehensive evaluation results of the project are obtained. The comprehensive evaluation results are displayed in the form of charts, reports, etc., so that decision makers can intuitively understand the project operation status. According to the evaluation results, diagnose problems in project operation and put forward improvement suggestions. Feedback the evaluation results to project managers to adjust the project operation strategy in a timely manner.

[0064] Post-evaluation model for dynamic tracking of multiple projects for dynamic evaluation: Obtain the operating data of each project from the system in real time, including equipment operating status, power output, failure rate, etc. Perform data cleaning, format conversion and outlier processing to ensure data accuracy and availability.

[0065] Dynamic indicator calculation: Calculate the current value of each dynamic indicator based on real-time data. For example, calculate the average failure rate and average load rate of multiple projects.

[0066] Static indicator confirmation: For static indicators, such as project decision-making basis, project planning warehousing status, etc., confirmation is carried out through system files or manual judgment.

[0067] Use the dynamically updated indicator weights to weight each indicator. For example, if the weight of the failure rate indicator increases, its influence in the total score will also increase accordingly. Distance between good and bad solutions: Use the distance between good and bad solutions to conduct a comprehensive evaluation of multiple projects. The specific steps are as follows: Standardize the indicator data of each project to eliminate the influence of dimension and data size. In the standardized data, determine the optimal value (maximum value) and the worst value (minimum value) of each indicator to form the ideal solution and the negative ideal solution. Calculate the Euclidean distance of each project from the ideal solution and the negative ideal solution.

[0068] According to the relative proximity, multiple projects are sorted and compared to obtain comprehensive evaluation results. The comprehensive evaluation results are displayed in the form of charts, reports, etc., so that decision makers can intuitively understand the operation status and performance differences of each project. According to the evaluation results, problems in project operation are diagnosed and improvement suggestions are put forward. The evaluation results are fed back to project managers to adjust project operation strategies in a timely manner and optimize resource allocation.

[0069] In the above-mentioned method for realizing dynamic intelligent evaluation of power projects, by obtaining historical power project-related data and using automatic matching algorithms for fusion processing, the massive data of power projects from planning, construction to operation can be effectively integrated. Based on the fused data, a post-evaluation model for dynamic tracking of a single project and a post-evaluation model for dynamic tracking of multiple projects were established. The single-project model focuses on in-depth analysis and tracking of changes in various indicators of a single power project during operation, such as project cost control, quality assurance, and schedule scheduling. It can monitor the key performance indicators (KPIs) of the project in real time and timely discover potential problems based on the changing trends of these indicators. The multi-project model comprehensively evaluates and compares multiple power projects from a macro perspective. It can help managers understand the performance differences between different projects and identify projects with outstanding performance and projects that need improvement. The hierarchical analysis method or triangular fuzzy comprehensive evaluation method is used to determine the indicator weights in the single-project model. For the multi-project model, the superior and inferior solution distance method is used to determine the indicator weights. This method dynamically adjusts the weights by calculating the distance between each project indicator and the ideal optimal solution and the worst solution. It can better reflect the relative position and competitiveness of the project in the group. More importantly, the present application can obtain real-time feedback data and dynamically update the indicator weights based on these data. This means that the evaluation model is not static, but can adjust itself as the project operation changes. Based on the dynamically updated indicator weights, the present invention realizes dynamic intelligent evaluation of power projects through the post-evaluation model of single-project and multi-project dynamic tracking.

[0070] In an exemplary embodiment, historical power project related data is obtained, and the historical power project related data is fused and processed by an automatic matching algorithm, including: Adjust the system data format of different power systems and obtain historical power project related data from different power systems; Classify historical power project-related data, extract target key fields, and use them as the basis for data matching; Obtain the degree of consistency between the target key fields of different power systems, perform data matching based on the degree of consistency, and obtain data matching results; Based on the data matching results, historical power project related data are fused and processed.

[0071] Specifically, standardize the data formats of different systems to ensure data consistency. For example, standardize the date format to YYYY-MM-DD, standardize the voltage level to kV, etc. Remove duplicate records, correct erroneous data, fill in missing values, etc. to ensure data accuracy and completeness.

[0072] Data categories include: Basic project information: project name, project number, voltage level, construction location, etc.

[0073] Construction phase data: data from the preliminary decision-making, design, construction, acceptance and other stages.

[0074] Operation phase data: equipment operating status, power output, failure rate, maintenance records, etc.

[0075] Benefit data: return on investment, operating costs, economic benefits, etc.

[0076] The key fields to be extracted include: Project Name: Used to identify and match projects.

[0077] Project Number: Unique project identifier.

[0078] Voltage level: such as 110kV, 220kV, etc.

[0079] Construction location: The geographical location of the project.

[0080] Commissioning time: the time when the project is officially put into operation.

[0081] Device ID: used to identify a specific device.

[0082] Equipment type: such as transformer, line, etc.

[0083] Operating status: The current operating status of the device, such as normal, faulty, etc.

[0084] Obtaining the degree of match of key fields includes: Exact match: Perform an exact match on key fields, such as project number, equipment number, etc. If the fields are exactly the same, the match is considered successful.

[0085] Fuzzy matching: For some fields that may have errors, such as project name, construction location, etc., fuzzy matching can be performed. You can use a string similarity algorithm (such as Levenshtein distance) to calculate the similarity of the field, and set a threshold (such as 80% similarity) to determine whether the match is successful.

[0086] Combine the results of exact matching and fuzzy matching to make a comprehensive judgment. For example, if the project number and equipment number match exactly, but there is a slight difference in the project name, it can be considered a successful match.

[0087] Integrate the successfully matched data into a unified data set. Ensure the consistency and completeness of the data. Manually review and supplement the unmatched data. For example, if the operating status of a certain device is recorded in the PMS system but missing in the EMS system, the data can be supplemented manually. Verify the merged data to ensure the accuracy and consistency of the data. You can use data verification rules, such as checking the range and format of the data.

[0088] In this embodiment, through the above steps, historical power project related data can be effectively obtained and fused to provide high-quality data support for subsequent dynamic intelligent evaluation.

[0089] In an exemplary embodiment, the types of project indicators in the post-evaluation model of single-project dynamic tracking and the post-evaluation model of multiple-project dynamic tracking include at least: process evaluation indicators, project effect evaluation indicators, environmental impact evaluation indicators and sustainability evaluation indicators, wherein each indicator includes preset criterion layer indicators, primary indicators and secondary indicators.

[0090] Specifically, 1. Process evaluation indicators: 1.1 Criteria level indicators: Project process evaluation: Evaluate the management quality and execution effectiveness of each stage of the project from planning to implementation.

[0091] 1.2 First-level indicators: Preliminary decision-making evaluation: evaluate the scientificity and rationality of the project in the planning and decision-making stages. Construction preparation: evaluate the preparatory work of the project before construction, including design, bidding, contract signing, etc. Project construction management: evaluate the management quality of the project during the construction process, including safety, quality, progress and investment control. Project completion acceptance: evaluate the completion quality and compliance of the project during the completion acceptance stage. Start-up and commissioning: evaluate the operation of the project during the startup and commissioning stages.

[0092] 1.3 Secondary indicators: Preliminary decision evaluation; construction preparation; project construction management; project completion acceptance; start-up and commissioning status.

[0093] 2. Project effect evaluation indicators: 2.1 Criteria level indicators: Project effect and benefit evaluation: Evaluate the effect and economic benefits of the project during the operation phase.

[0094] 2.2 First-level indicators: Technical level: evaluate the overall technical level of the project. Project implementation effect: evaluate the actual operation effect of the project. Project financial benefits: evaluate the economic benefits of the project.

[0095] 2.3 Secondary indicators: Technical level; project implementation effect; project financial benefits.

[0096] 3. Environmental impact assessment indicators: 3.1 Criteria level indicators: Environmental and Social Impact Assessment: Assess the impact of a project on the environment and society.

[0097] 3.2 First-level indicators: Environmental compliance evaluation: Evaluate the project's performance in terms of environmental compliance.

[0098] Environmental management capability evaluation: Evaluate the environmental management capability of the project.

[0099] 3.3 Secondary indicators: Environmental compliance assessment: Soil and Water Conservation: Evaluate the project’s performance in soil and water conservation.

[0100] Revegetation: Evaluate the project's performance in revegetation.

[0101] Electromagnetic Interference: Evaluate the project's performance with respect to electromagnetic interference.

[0102] Environmental management capability evaluation: Environmental impact assessment approval: Evaluate the approval status of the environmental impact assessment report.

[0103] Completion of environmental protection acceptance: Evaluate the completion of environmental protection acceptance.

[0104] Implementation of environmental protection measures: Evaluate the implementation of environmental protection measures.

[0105] 4. Sustainability evaluation indicators: 4.1 Criteria level indicators: Project Sustainability Evaluation: Evaluate the sustainability of the project.

[0106] 4.2 First-level indicators: Project sustainability: Assess the project's ability to operate sustainably.

[0107] Project contribution to enterprise development: Evaluate the project's contribution to enterprise development.

[0108] 4.3 Secondary indicators: Project sustainability; project development contribution.

[0109] In this embodiment, through the above steps, the power project can be effectively and dynamically intelligently evaluated to ensure the scientificity, accuracy and timeliness of the evaluation results, thus providing strong support for the management and decision-making of the power project.

[0110] In an exemplary embodiment, Figure 3 As shown, the hierarchical analysis method or triangular fuzzy comprehensive evaluation method is used to determine the indicator weights of various indicators in the post-evaluation model of dynamic tracking of a single project, including: Step S302, using the analytic hierarchy process or the triangular fuzzy comprehensive evaluation method to obtain real-time evaluation data of the three-level indicators; Step S304, calculating and obtaining the hierarchical membership of each data item according to the real-time evaluation data of the three-level indicators; Step S306, based on the hierarchical membership of each data item, starting from the third-level indicator, the real-time evaluation data of the second-level indicator, the first-level indicator and the criterion-level indicator are determined step by step until the real-time evaluation data of the target level is determined; Step S308, obtaining the indicator weights for various indicators of the project in the post-evaluation model of dynamic tracking of the single project according to the real-time evaluation data of the target level.

[0111] Specifically, real-time acquisition of project operation data, including equipment operation status, power output, failure rate, etc. Data cleaning, format conversion and outlier processing are performed to ensure data accuracy and availability. Real-time data of the three-level indicators are extracted, such as the maximum load rate of the transformer, the average load rate of the line, the failure rate, etc. Static indicators are confirmed, such as the basis for project decision-making, the status of project planning and storage, etc. The three-level indicators are used as the evaluation factor set, and a comment set is set, such as "excellent", "good", "medium", and "not up to standard", which is expressed as a fuzzy set. Based on the real-time data, the degree of membership of each three-level indicator to each comment is calculated to form a fuzzy evaluation matrix.

[0112] For each secondary indicator, the comprehensive membership is calculated based on the membership of the third-level indicators it contains. For each first-level indicator, the comprehensive membership is calculated based on the membership of the second-level indicators it contains. For the criterion layer indicators, the comprehensive membership is calculated based on the membership of the first-level indicators it contains. The weight of each indicator is calculated by the arithmetic mean method, the geometric mean method or the maximum eigenvalue method. For example, when using the maximum eigenvalue method, the eigenvector corresponding to the maximum eigenvalue of the judgment matrix is ​​solved and normalized to obtain the weight.

[0113] In an exemplary embodiment, Figure 4 As shown in the figure, the superior and inferior solution distance method is used to determine the indicator weights for various indicators of the project in the post-evaluation model of dynamic tracking of multiple projects, including: Step S402, when there is at least one power project, obtaining project annual and real-time evaluation data corresponding to each power project; Step S404, based on the project year, respectively determining the same project in the same year and the same project in different years; Step S406, using the good and bad solution distance method, respectively obtain the post-evaluation good and bad results corresponding to the same project in the same year and the same project in different years, and integrate the post-evaluation good and bad results corresponding to the same project in different years; Step S408, based on the post-evaluation results of the same project in the same year and the integrated post-evaluation results of the same project in different years, determine the indicator weights for various indicators in the post-evaluation model for dynamic tracking of multiple projects.

[0114] Specifically, the operating data of each power project is obtained from the system in real time, including equipment operating status, power output, failure rate, etc. Data cleaning, format conversion and outlier processing are performed to ensure data accuracy and availability.

[0115] Extract annual data for each project, such as 2020, 2021, etc. Extract real-time evaluation data for each project, including real-time data of three-level indicators, such as the maximum load rate of the transformer, the average load rate of the line, the failure rate, etc.

[0116] Filter out all projects in the same year (e.g. 2021) to ensure that the projects are compared over the same time period. For example, both Project A and Project B are evaluated in 2021.

[0117] Filter out the same projects from different years to ensure that these projects are compared over different time periods. For example, Project A has evaluation data in both 2020 and 2021.

[0118] The superiority and inferiority solution distance method is used to obtain the superiority and inferiority results of the post-evaluation of the same project in the same year and the same project in different years, and the superiority and inferiority results of the post-evaluation of the same project in different years are integrated: Standardize the project data of the same year to eliminate the influence of dimension and data size. In the standardized data, determine the optimal value (maximum value) and the worst value (minimum value) of each indicator to form the ideal solution and the negative ideal solution. Calculate the Euclidean distance between each project and the ideal solution and the negative ideal solution, and calculate the relative proximity of each project. According to the relative proximity, sort and compare the projects of the same year to obtain the post-evaluation results.

[0119] Standardize the project data of different years to eliminate the influence of dimension and data size. In the standardized data, determine the optimal value (maximum value) and the worst value (minimum value) of each indicator to form the ideal solution and the negative ideal solution. Calculate the Euclidean distance between each project and the ideal solution and the negative ideal solution, and calculate the relative proximity of each project. According to the relative proximity, sort and compare the projects of different years to obtain the post-evaluation results. Integrate the post-evaluation results of different years, for example, calculate the average relative proximity of different years, or perform trend analysis.

[0120] Determine the comprehensive evaluation results of each project based on the post-evaluation results of the same year. Determine the comprehensive evaluation results of each project based on the post-evaluation results of different years after integration. Dynamically adjust the indicator weights based on the comprehensive evaluation results. The following methods can be used: Weight adjustment based on data changes: If an indicator changes significantly in the project of the same year or different years, it indicates that the impact of the indicator on the project may increase, and the weight of the indicator should be increased accordingly.

[0121] Weight adjustment based on project group analysis: By analyzing the comprehensive evaluation results of multiple projects, find out the commonalities and differences between projects and adjust the indicator weights. For example, if the failure rate of multiple projects generally increases, increase the weight of the failure rate indicator.

[0122] Weight adjustment based on feedback learning: Use machine learning algorithms, such as neural networks or decision trees, to analyze historical and real-time data and automatically adjust indicator weights. The model learns the changing patterns of data and predicts changes in the importance of indicators, thereby dynamically updating weights.

[0123] In an exemplary embodiment, after integrating the post-evaluation results corresponding to the same project in different years, the following is further included: According to the post-evaluation results of the same project in different years after integration, the indicator weight of each project is obtained, and the projects are ranked according to the indicator weight to determine at least one of the top n projects; According to the indicator weight corresponding to at least one of the top n projects in the ranking, the indicator weight for each indicator of the project in the post-evaluation model of dynamic tracking of the single project is updated.

[0124] Specifically, the weighted sum method can be used to calculate the score of each project according to the determined indicator weight. According to the ranking results, select the top n projects with the highest scores. For example, select the top 3 projects. For the top n ranked projects, calculate the average weight of each indicator. For example, for the top 3 projects, calculate the average of the weight of each indicator. Use the calculated average weight as the new indicator weight to update the indicator weights for each indicator of the project in the post-evaluation model of dynamic tracking of the single project.

[0125] In this embodiment, through the above steps, the indicator weights for various indicators of the project in the post-evaluation model of dynamic tracking of multiple projects can be effectively determined, and the indicator weights for various indicators of the project in the post-evaluation model of dynamic tracking of a single project can be updated according to the indicator weights corresponding to at least one of the top n projects in the ranking, thereby ensuring the scientificity, accuracy and timeliness of the evaluation results, and providing strong support for the management and decision-making of power projects.

[0126] In an exemplary embodiment, dynamically updating corresponding indicator weights according to real-time feedback data includes: Obtain adjustment information on the number of similar projects and project priorities based on feedback from post-evaluators; The corresponding indicator weights of each project are dynamically updated based on the feedback adjustment information on the number of similar projects and the adjustment information on project priorities.

[0127] Specifically, the quantity information of similar projects is collected from the post-evaluation system. Similar projects refer to projects operating under the same or similar conditions, such as projects in the same region, the same voltage level, and the same functional category. The post-evaluation personnel can manually input or automatically count the number of similar projects through the system. Collect project priority information from the post-evaluation system. Project priority can be adjusted based on the importance and urgency of the project. Post-evaluation personnel can manually adjust project priorities, such as raising the priority of an important project or lowering the priority of a minor project.

[0128] If the number of similar projects increases, it means that the representativeness of such projects has increased, and the indicator weight of such projects can be appropriately increased. For example, if the number of similar projects in a certain region increases from 10 to 20, the indicator weight of the projects in that region can be increased. If the priority of a project increases, the indicator weight of the project can be appropriately increased; if the priority decreases, the indicator weight of the project can be appropriately reduced. Combined with the adjustment of the number of similar projects and the adjustment of project priorities, the indicator weights of each project are comprehensively updated.

[0129] For example, for a certain project, if the number of similar projects increases and the project priority improves, the weights can be adjusted comprehensively: the weight after the number of similar projects is adjusted: 0.6; the weight after the project priority is adjusted: 0.9; the comprehensive weight: take the larger value of the two, that is, 0.9.

[0130] In this embodiment, through the above steps, the indicator weights of each project can be effectively and dynamically updated according to the real-time feedback data, ensuring that the post-evaluation model can adapt to changes in project operation and feedback from post-evaluators, thereby improving the scientificity and accuracy of the evaluation results.

[0131] In an exemplary embodiment, before obtaining the data year and real-time evaluation data corresponding to each power project, the method further includes: At least one power project is classified and screened according to preset required comparison types, wherein the required comparison types include project year, project region and project attributes.

[0132] Specifically, the required comparison types include: Project Year: Classified according to the project's commissioning year or evaluation year.

[0133] Project region: classified according to the geographical location of the project, such as province, city, etc.

[0134] Project attributes: Classify according to project functions, voltage levels, project types and other attributes.

[0135] 1. Project year screening: Get the commissioning year or evaluation year of each project from the system. Based on the preset project year, screen out projects in a specific year. For example, screen out projects commissioned in 2020 and 2021.

[0136] 2. Project area screening: Get the geographical location information of each project from the system, such as province, city, etc. According to the preset project area, filter out projects in a specific area. For example, filter out all projects located in a certain province.

[0137] 3. Project attribute screening: Get the attribute information of each project such as function, voltage level, project type, etc. from the system. According to the preset project attributes, screen out projects with specific attributes. For example, screen out all 110kV substation projects.

[0138] In this embodiment, through the above steps, the power projects can be effectively classified and screened, ensuring that the annual and real-time evaluation data subsequently obtained are targeted and representative, providing a solid foundation for the subsequent dynamic intelligent evaluation.

[0139] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0140] Based on the same inventive concept, the embodiment of the present application also provides a system for realizing the method for realizing the dynamic intelligent evaluation of power projects involved in the above-mentioned method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more system embodiments for realizing the dynamic intelligent evaluation of power projects provided below can refer to the limitations of the method for realizing the dynamic intelligent evaluation of power projects above, and will not be repeated here.

[0141] In an exemplary embodiment, Figure 5 As shown, a system for realizing dynamic intelligent evaluation of power projects is provided, comprising: The data acquisition and processing module 502 is used to acquire historical power project related data and perform fusion processing on the historical power project related data through an automatic matching algorithm; A model building module 504 is used to build a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model based on the fused power project related data; The indicator weight determination module 506 is used to determine the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of a single project by using a hierarchical analysis method or a triangular fuzzy comprehensive evaluation method, and to determine the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of multiple projects by using a superior and inferior solution distance method; The indicator weight updating module 508 is used to obtain the real-time feedback data of the indicator weights of various indicators of the project in the post-evaluation model of the single-project dynamic tracking and the post-evaluation model of the multi-project dynamic tracking, and dynamically update the corresponding indicator weights according to the real-time feedback data; The dynamic intelligent evaluation module 510 is used to perform dynamic intelligent evaluation on power projects based on dynamically updated indicator weights through a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model.

[0142] Each module in the system for realizing dynamic intelligent evaluation of power projects can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0143] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical power project related data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for realizing dynamic intelligent evaluation of power projects is implemented.

[0144] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0145] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above method when executing the computer program.

[0146] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0147] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0148] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0149] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0150] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0151] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for realizing dynamic intelligent evaluation of power projects, characterized in that: include: Obtain historical power project-related data and integrate them through automatic matching algorithms; According to the fused power project related data, a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model are established; Adopting the analytic hierarchy process or triangular fuzzy comprehensive evaluation method to determine the weights of various indicators in the post-evaluation model of dynamic tracking of a single project, and adopting the superior and inferior solution distance method to determine the weights of various indicators in the post-evaluation model of dynamic tracking of multiple projects; Respectively obtain real-time feedback data of the indicator weights of various indicators of the project in the post-evaluation model of the dynamic tracking of a single project and the post-evaluation model of the dynamic tracking of multiple projects, and dynamically update the corresponding indicator weights according to the real-time feedback data; Based on the dynamically updated indicator weights, dynamic intelligent evaluation of power projects is carried out through the post-evaluation model of single project dynamic tracking and the post-evaluation model of multiple projects dynamic tracking.

2. The method according to claim 1, characterized in that The obtaining of historical power project related data and fusing the historical power project related data through an automatic matching algorithm includes: Adjust the system data format of different power systems and obtain historical power project related data from different power systems; Classify historical power project-related data, extract target key fields, and use them as the basis for data matching; Obtain the degree of consistency between the target key fields of different power systems, perform data matching based on the degree of consistency, and obtain data matching results; According to the data matching result, the historical power project related data are fused.

3. The method according to claim 1, characterized in that: The types of project indicators in the post-evaluation model for dynamic tracking of a single project and the post-evaluation model for dynamic tracking of multiple projects include at least: process evaluation indicators, project effect evaluation indicators, environmental impact evaluation indicators and sustainability evaluation indicators, wherein each indicator includes indicators at the preset criterion layer, primary indicators and secondary indicators.

4. The method according to claim 3, characterized in that The method of using the analytic hierarchy process or the triangular fuzzy comprehensive evaluation method to determine the weights of various indicators of the project in the post-evaluation model of the dynamic tracking of a single project includes: Adopting analytic hierarchy process or triangular fuzzy comprehensive evaluation method to obtain real-time evaluation data of three-level indicators; According to the real-time evaluation data of the three-level indicators, the hierarchical membership of each data is calculated; According to the hierarchical affiliation of each data item, starting from the third-level indicators, the real-time evaluation data of the second-level indicators, the first-level indicators and the criterion-level indicators are determined step by step until the real-time evaluation data of the target level is determined; According to the real-time evaluation data of the target level, the indicator weights for various indicators of the project in the post-evaluation model of dynamic tracking of a single project are obtained.

5. The method according to claim 4, characterized in that The method of distance between superior and inferior solutions is used to determine the weights of various indicators of the project in the post-evaluation model of dynamic tracking of multiple projects, including: In the case where there is at least one power project, obtaining project annual and real-time evaluation data corresponding to each power project; Based on the project year, the same project in the same year and the same project in different years are determined separately; The superiority and inferiority solution distance method is used to obtain the superiority and inferiority results of the post-evaluation of the same project in the same year and the same project in different years, and the superiority and inferiority results of the post-evaluation of the same project in different years are integrated; Based on the post-evaluation results of the same project in the same year and the integrated post-evaluation results of the same project in different years, the indicator weights for various project indicators in the post-evaluation model for dynamic tracking of multiple projects are determined.

6. The method according to claim 5, characterized in that After the integration of the post-evaluation results corresponding to the same project in different years, it also includes: According to the post-evaluation results of the same project in different years after integration, the indicator weight of each project is obtained, and the projects are ranked according to the indicator weight to determine at least one of the top n projects; According to the indicator weight corresponding to at least one of the top n projects in the ranking, the indicator weight for each indicator of the project in the post-evaluation model of dynamic tracking of the single project is updated.

7. The method according to claim 5, characterized in that The dynamically updating corresponding indicator weights according to the real-time feedback data includes: Obtain adjustment information on the number of similar projects and project priorities based on feedback from post-evaluators; The corresponding indicator weights of each project are dynamically updated based on the feedback adjustment information on the number of similar projects and the adjustment information on project priorities.

8. The method according to claim 5, characterized in that Before obtaining the annual data and real-time evaluation data corresponding to each power project, it also includes: At least one power project is classified and screened according to preset required comparison types, wherein the required comparison types include project year, project region and project attributes.

9. A system for realizing dynamic intelligent evaluation of power projects, characterized in that: include: The data acquisition and processing module is used to acquire historical power project related data and integrate the historical power project related data through an automatic matching algorithm; A model building module is used to establish a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model based on the fused power project related data; An indicator weight determination module is used to determine the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of a single project by using a hierarchical analysis method or a triangular fuzzy comprehensive evaluation method, and to determine the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of multiple projects by using a superior and inferior solution distance method; An indicator weight updating module is used to obtain real-time feedback data of the indicator weights of various indicators of a project in a post-evaluation model for dynamic tracking of a single project and a post-evaluation model for dynamic tracking of multiple projects, and dynamically update the corresponding indicator weights according to the real-time feedback data; The dynamic intelligent evaluation module is used to perform dynamic intelligent evaluation of power projects based on dynamically updated indicator weights through a single-project dynamic tracking post-evaluation model and a multi-project dynamic tracking post-evaluation model.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images