Intervention scheme recommendation method and system based on comprehensive weight emergency capability evaluation

Abstract

The invention relates to the technical field of enterprise emergency capability assessment, and provides an intervention scheme recommendation method and system based on comprehensive weight emergency capability assessment, and the method comprises the steps: determining an evaluation index; power grid enterprise emergency management and control related data are obtained, the value range of evaluation indexes is calculated, a matter element extension evaluation model is constructed, and the correlation degree of each evaluation index with respect to different grades is calculated; performing expert scoring on each evaluation index by adopting a link ratio scoring method to obtain a subjective weight; carrying out information entropy calculation on the evaluation indexes by adopting an entropy weight method to obtain objective weights; and fusing the subjective weight and the objective weight by using a Lagrange multiplier method based on a minimum identification information principle to obtain a comprehensive weight of the evaluation index, and obtaining an evaluation result of the emergency capability of the power grid enterprise. According to the method, subjective and objective weight calculation methods are creatively fused, and a matter-element extension model is introduced, so that quantitative evaluation and dynamic adaptive adjustment of the emergency capacity of the power grid enterprise are realized, and scientificity and universality of an evaluation result are improved.

Description

Technical Field

[0001] This invention relates to the technical field of enterprise emergency response capability assessment, specifically to a method and system for recommending intervention schemes based on comprehensive weighted emergency response capability assessment. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] In recent years, frequent extreme weather events have led to an increase in power system accidents, causing serious social impacts and economic losses. Due to the characteristics of the power system, such as strong synchronization between transmission and consumption, complex operational structure, and rapid risk propagation, emergencies are unpredictable and highly impactful. Against this backdrop, enhancing the emergency management capabilities of power grid companies has become a core means of ensuring power supply security. Scientifically assessing the emergency response capabilities of power grid companies not only helps identify emergency shortcomings, optimize resource allocation, and streamline management mechanisms, but also effectively improves the power system's resilience and recovery capabilities, making it a key measure to enhance energy security.

[0004] Existing methods for assessing power grid emergency response capabilities are primarily based on traditional experience-based judgments and hierarchical scoring systems. While they propose an indicator framework covering the entire process from prevention to early warning, response, and recovery, significant shortcomings remain in weight allocation and the evaluation process. On one hand, existing methods use fixed scoring weights, failing to dynamically adjust according to the scale and risk exposure of different regional power grids, making it difficult to reflect individualized response needs. On the other hand, the evaluation process heavily relies on on-site verification by experts, leading to high costs, low efficiency, and susceptibility to subjective expert judgment, thus reducing the objectivity and generalizability of the evaluation results. Because the evaluation process lacks unified standards and the results heavily depend on subjective judgment, the evaluation results often fail to accurately and comprehensively reflect the emergency response capabilities of power grid companies at different stages. This lack of objectivity directly impacts the quality of subsequent emergency response plan recommendations, making it difficult for the generated response strategies to align with the company's actual handling capabilities and resource allocation. Especially in situations where emergencies develop rapidly and response time is limited, traditional recommendation methods based on fixed templates or experience rules are difficult to adjust strategies in a timely manner. They cannot dynamically optimize response paths based on factors such as the company's current available resources and response link efficiency, resulting in decision-making delays, response lags, and even secondary risks, affecting the stable operation of the power grid system and public safety. Summary of the Invention

[0005] To address the aforementioned issues, this invention proposes a method and system for recommending intervention plans based on comprehensive weighted emergency response capability assessment. It innovatively integrates subjective and objective weight calculation methods and introduces a matter-element extension model, enabling quantitative evaluation and dynamic adaptive adjustment of power grid enterprises' emergency response capabilities. This enhances the scientific rigor and universality of the evaluation results, thereby improving the accuracy of emergency response plan recommendations.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: One or more embodiments provide a method for recommending intervention programs based on comprehensive weighted emergency response capability assessment, including the following steps: Construct an evaluation index system for the emergency response capabilities of power grid enterprises and determine the evaluation indicators; Acquire relevant data on emergency management and control of power grid enterprises, calculate the value range of evaluation indicators, construct a matter-element extension evaluation model, determine the classical domain and the node domain, and calculate the correlation degree of each evaluation indicator with respect to different levels; The chain-comparison scoring method was used to assign expert scores to each evaluation indicator, and subjective weights were obtained. The information entropy of the evaluation indicators is calculated using the entropy weight method to obtain objective weights. Based on the principle of minimum discriminative information and using the Lagrange multiplier method, subjective weights and objective weights are integrated to obtain the comprehensive weight of the evaluation index. The comprehensive correlation degree is calculated based on the comprehensive weight and correlation degree to obtain the evaluation results of the emergency response capability of power grid enterprises. Combined with the characteristics of emergency scenarios, corresponding intervention plans are generated and recommended. One or more embodiments provide an intervention program recommendation system based on comprehensive weighted emergency response capability assessment, including: The evaluation system construction module is configured to build an evaluation index system for the emergency response capabilities of power grid enterprises and determine the evaluation indicators. The correlation calculation module is configured to acquire relevant data on emergency management and control of power grid enterprises, calculate the value range of evaluation indicators, construct a matter-element extension evaluation model, determine the classical domain and the section domain, and calculate the correlation of each evaluation indicator with respect to different levels. The subjective weight calculation module is configured to use the year-on-year scoring method to conduct expert scoring on each evaluation indicator to obtain the subjective weight. The objective weight calculation module is configured to use the entropy weight method to calculate the information entropy of the evaluation indicators to obtain the objective weights. The comprehensive weight calculation module is configured to integrate subjective and objective weights based on the principle of minimum discriminative information and using the Lagrange multiplier method to obtain the comprehensive weight of the evaluation index. The solution recommendation module is configured to calculate the comprehensive correlation degree based on the comprehensive weight and correlation degree to obtain the evaluation results of the power grid enterprise's emergency response capability, and generate and recommend corresponding intervention solutions in combination with the characteristics of the emergency scenario.

[0007] An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the steps in the above-described method for recommending intervention plans based on comprehensive weighted emergency response capability assessment.

[0008] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the steps in the above-described method for recommending intervention plans based on comprehensive weighted emergency response capability assessment.

[0009] Compared with the prior art, the beneficial effects of the present invention are as follows: This implementation method effectively overcomes the subjectivity of expert judgment in traditional methods by introducing a subjective and objective weight fusion mechanism in the evaluation method, while enhancing the sensitivity of the evaluation system to changes in actual data. On the one hand, by combining the chain-linked scoring method and the entropy weight method, subjective and objective weights are constructed and fused, overcoming the lack of flexibility caused by the fixed weight configuration in traditional methods. This enables adaptive adjustment to the characteristics of different regional power grids (such as scale and risk exposure), thereby improving the applicability and accuracy of the model in different scenarios. On the other hand, the evaluation mechanism that integrates subjective and objective information significantly reduces the reliance on on-site verification by experts, alleviating the manual burden of the evaluation work, reducing costs, and improving efficiency. In addition, the matter-element extension evaluation model achieves precise identification of the enterprise's emergency response capability status by quantifying the correlation between various indicators and multi-level standards, enhancing the objectivity, stability, and generalizability of the evaluation results. This provides a clear decision-making basis for subsequent optimization of emergency resource allocation and adjustment of management mechanisms, and recommendation of appropriate intervention schemes, thereby improving the resilience and responsiveness of the overall power system.

[0010] The advantages of the present invention, as well as its additional advantages, will be described in detail in the following specific embodiments. Attached Figure Description

[0011] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute a limitation thereof.

[0012] Figure 1 This is a flowchart of the enterprise emergency response capability evaluation method of Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of the power grid enterprise emergency response capability evaluation index system according to Embodiment 1 of the present invention; Figure 3 This is a correlation diagram between the secondary evaluation indicators and each risk level in a practical application case of Embodiment 1 of the present invention; Figure 4This is a correlation diagram between primary indicators and various risk levels in a practical application case of Embodiment 1 of the present invention. Detailed Implementation

[0013] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0014] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0015] It should be noted that the terminology used herein is for describing particular embodiments only and is not intended to limit the exemplary embodiments of the present invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof. It should be noted that, without conflict, the various embodiments and features within those embodiments can be combined with each other. The embodiments will now be described in detail with reference to the accompanying drawings.

[0016] Example 1 In one or more of the technical solutions disclosed in the embodiments, such as Figures 1 to 4 As shown, a recommended intervention plan based on comprehensive weighted emergency response capacity assessment includes the following steps: Step 1: Construct an evaluation index system for the emergency response capabilities of power grid enterprises and determine the evaluation indicators; Step 2: Obtain relevant data on emergency management and control of power grid enterprises, calculate the value range of evaluation indicators, construct a matter-element extension evaluation model, determine the classical domain and the node domain, and calculate the correlation degree of each evaluation indicator with respect to different levels; Step 3: Use the chain-linked scoring method to conduct expert scoring of the evaluation indicators and obtain subjective weights; Step 4: Calculate the information entropy of each evaluation index using the entropy weight method to obtain the objective weight; Step 5: Based on the principle of minimum discriminative information and using the Lagrange multiplier method, the subjective weights and objective weights are integrated to obtain the comprehensive weights of the evaluation indicators. Step 6: Calculate the comprehensive correlation degree based on the comprehensive weight and correlation degree to obtain the evaluation results of the power grid enterprise's emergency response capability. Combined with the characteristics of the emergency scenario, generate and recommend corresponding intervention plans.

[0017] This implementation method first constructs an evaluation index system for the emergency response capabilities of power grid enterprises based on the four stages of "prevention-early warning-response-recovery," ensuring coverage of key dimensions such as emergency preparedness, information analysis, emergency response, resource allocation, and recovery capabilities. By constructing a matter-element extension model, each evaluation index is abstracted into a matter element, and its corresponding classical domain (representing the standard range for different evaluation levels) and section domain (representing the specific value range of the sample to be evaluated) are clearly defined for subsequent correlation calculations. The chain-linked scoring method is used to collect subjective scores from experts for each index, forming an expert scoring matrix, and subjective weights are calculated accordingly. Simultaneously, the entropy weight method is used to perform information entropy analysis on the objective data of the indicators to extract objective weights. Next, the principle of minimum discriminative information is introduced and combined with the Lagrange multiplier method to optimize the weight fusion process, achieving a balance between consistency and difference between subjective and objective weights, ultimately obtaining a comprehensive weight. Finally, the comprehensive weight of each index is weighted and summed with its correlation to each level to obtain the comprehensive correlation degree, which is used to determine the enterprise's emergency response capability level, achieving a scientific evaluation of the power grid enterprise's emergency response capabilities.

[0018] This implementation method effectively overcomes the subjectivity of expert judgment in traditional methods by introducing a subjective and objective weight fusion mechanism in the evaluation method, while enhancing the sensitivity of the evaluation system to changes in actual data. On the one hand, by combining the chain-linked scoring method and the entropy weight method, subjective and objective weights are constructed and fused, overcoming the lack of flexibility caused by the fixed weight configuration in traditional methods. This enables adaptive adjustment to the characteristics of different regional power grids (such as scale and risk exposure), thereby improving the applicability and accuracy of the model in different scenarios. On the other hand, the evaluation mechanism that integrates subjective and objective information significantly reduces the reliance on on-site verification by experts, alleviates the manual burden of the evaluation work, reduces costs, and improves efficiency. In addition, the matter-element extension evaluation model achieves precise identification of the enterprise's emergency response capability status by quantifying the correlation between each indicator and multi-level standards, enhancing the objectivity, stability, and generalizability of the evaluation results. This provides a clear decision-making basis for subsequent optimization of emergency resource allocation and adjustment of management mechanisms, thereby improving the resilience and responsiveness of the overall power system.

[0019] In step 1, the evaluation index system for the emergency response capabilities of power grid enterprises includes multiple evaluation indicators for four stages: prevention and emergency preparedness, monitoring and early warning, emergency response and rescue, and post-disaster recovery and reconstruction. The evaluation index system for the emergency response capabilities of power grid enterprises is based on the entire process of power grid enterprises responding to emergencies and is divided into four phases: prevention and emergency preparedness, monitoring and early warning, emergency response and rescue, and post-event recovery and reconstruction. Each phase has multiple specific evaluation indicators to systematically assess the capability level of power grid enterprises in different emergency situations.

[0020] Specifically, such as Figure 2 As shown, the evaluation index system constructed in this embodiment includes 4 primary indicators and 16 secondary indicators; The primary indicators include prevention and emergency preparedness indicator B1, monitoring and early warning indicator B2, and emergency response and rescue indicator B3. Prevention and emergency preparedness indicator B1 is used to quantify the risk prevention and resource preparation status of power grid companies before the occurrence of emergencies, including secondary indicators: emergency planning and implementation indicator C. 11 Emergency response plan system indicator C 12 Emergency training and drill indicators C 13 Emergency response team indicator C 14 and emergency support capability indicator C 15 Five key capabilities.

[0021] Monitoring and early warning indicator B2 is used to represent an enterprise's risk identification and early warning mechanisms before and after the occurrence of emergencies, including secondary indicators: monitoring and early warning capability indicator C. 21 Event monitoring indicator C 22 and early warning management indicators C 23 Three aspects.

[0022] Emergency Response and Rescue Indicator B3 is used to assess a company's ability to respond to and coordinate rescue efforts during an accident, including secondary indicators: Pre-accident Handling Indicator C. 31 Emergency Command Indicators C 32 Information reporting indicator C 33 Public opinion guidance indicator C 34 and adjustment and termination indicators C 35 Five dimensions.

[0023] Post-incident recovery and reconstruction indicator B4 is used to assess the effectiveness of the response to the aftermath of an accident and the recovery status of the power grid system. It includes secondary indicators: Post-incident handling indicator C. 41 Emergency response evaluation index C 42 and recovery and reconstruction indicator C 43 Three aspects.

[0024] In step 2, based on relevant emergency management data of the power grid enterprise, the value range of the corresponding evaluation indicators is calculated, including: Step 201: Obtain emergency planning documents, contingency plan system documents, drill records, and other related materials, and calculate evaluation index C. 11 To evaluation index C 15 The initial value; Step 202: Obtain monitoring system data and early warning records for power grid operation, and calculate evaluation index C. 21 To evaluation index C 23 The range of values ​​for; Data from power grid operation monitoring systems can be obtained by connecting to the SCADA system of power system enterprises, including: Real-time operating parameters of the power grid, such as voltage, current, and frequency, can be collected and transmitted to the dispatch center of the SCADA system in real time through intelligent power sensors, current transformers (CTs), voltage transformers (PTs), and frequency acquisition units installed on transmission lines and substations.

[0025] The status of equipment in operation in a substation, such as switches, circuit breakers, and bus load, can be collected through actual intelligent switch status acquisition modules, intelligent circuit breaker monitoring terminals, and online bus load monitoring systems. Load rate, temperature, vibration, and partial discharge monitoring values ​​of power transmission and transformation lines; Fault records and early warning logs for critical nodes in the power grid, such as main lines and areas with concentrated heavy loads; Environmental monitoring data, such as wind speed, snow and ice pressure, number of lightning strikes, and temperature / humidity changes, as well as meteorological data that affects the safe operation of transmission lines; meteorological data can be collected in real time through the meteorological bureau's public data interface or meteorological monitoring devices deployed along the transmission lines; Among them, SCADA (Supervisory Control and Data Acquisition) is a core automation platform widely used in power systems for real-time monitoring, control, and data acquisition of power grid equipment.

[0026] Step 203: Obtain emergency response process records, command and dispatch logs, and media response materials, and determine evaluation indicator C. 31 To evaluation index C 35 The initial range of values; Step 204: Obtain the post-accident assessment report and power grid system recovery report, and determine the evaluation index C. 41 To evaluation index C 43 The range of values ​​for; Step 2 involves constructing a matter-element extension evaluation model, determining the classical domain and the node domain, and calculating the correlation degree of each evaluation index with respect to different levels. This includes the following steps: The specific steps include determining the matter element and its matrix, quantitatively describing the characteristics of the matter element and calculating the correlation function, determining the index weights, and calculating the comprehensive correlation degree.

[0027] Step 21: Determining the Classical Domain: Construct the classical domain based on the value range corresponding to the indicator characteristics of the object to be evaluated at each level; Classical Domain Matrix Represented as: (1); In the formula, (j=1,2,3,4) represents the evaluation level; (i=1,2,…,n) are the evaluation indicators; Evaluation indicators i In the corresponding evaluation level The corresponding threshold range. The above together constitutes the classical domain of the matter-element extension evaluation model.

[0028] Step 22, Determining the Section Domain: Construct the section domain based on the maximum range of values ​​for the corresponding indicator characteristics of the object to be evaluated; The domain is the maximum range of possible values ​​for a given feature. (This refers to the domain of a matter-element extension evaluation model.) It can be represented as: (2); In the formula, D represents the set of all security levels; Indicators acceptable range of values .

[0029] The object to be evaluated is defined by representing the data or analysis results from the on-site investigation of the object to be evaluated using object elements. Q i ( i =1,2,…, n The matter-element matrix of ) can be represented as: (3); In the formula, Represents the i-th element to be evaluated; The element to be evaluated is... Evaluation indicators The actual measured value, that is, the specific value of the evaluation index within the evaluation time interval.

[0030] Step 22, Correlation Calculation: Based on the distance relationship between the feature values ​​of each evaluation indicator of the object to be evaluated and the classical domains under different evaluation levels, a correlation function is constructed to calculate the correlation degree of the evaluation indicators with respect to different levels. The closer the feature value of an evaluation indicator is to the classical domain of a certain level, the higher its correlation degree with that level.

[0031] The key to matter-element extension evaluation is establishing correlation functions and calculating correlation degrees. The correlation degree of each evaluated object with respect to each level is calculated. The calculation formula is: (4); (5); In the formula, Represents the i-th object to be evaluated The correlation function; For point to the classical domain interval The distance is given by the subscript i, where i is the i-th evaluation indicator, j is the j-th evaluation level, including low risk, general risk, relatively high risk, and major risk; and k is the k-th object to be evaluated. For point To the section interval The distance; and Evaluation metrics for classical domain and section domain, respectively The corresponding threshold range; and The rating levels are respectively Evaluation Indicators The lower and upper limits of the corresponding threshold range; and Evaluation indicators under section D The lower and upper limits of the corresponding threshold range.

[0032] Furthermore, to facilitate the comparison of the correlation between the actual measured values ​​of each evaluation indicator and the correlation between each level, the calculated correlation needs to be standardized to obtain the standardized correlation. The calculation formula is as follows: (6); Considering the weighting coefficients of each feature, the standardized correlation degree and the weighting coefficients are combined to form the comprehensive correlation degree, and its calculation formula is as follows: (7); in, This represents the overall weight value; The above completes the calculation of the correlation degree. The comprehensive correlation degree calculated according to formula (7) can be directly used to determine the level to which the evaluation object belongs. If the comprehensive correlation degree reaches the maximum value under a certain level, then the evaluation object belongs to that level. This method not only effectively avoids the problems of information overlap and subjective assumptions in traditional evaluation, but also improves the scientificity and credibility of the evaluation results through quantitative means, which meets the dual requirements of accuracy and objectivity in modern decision analysis.

[0033] To improve the accuracy of the evaluation, this embodiment adopts a combined weighting strategy that integrates the month-on-month scoring method and the entropy weight method. The month-on-month scoring method reflects the dynamic changes in the relative importance of indicators, while the entropy weight method objectively mines the information distribution of the data itself, thereby effectively balancing the influence of subjective experience and objective data.

[0034] In step 3, the chain-linked scoring method is used to conduct expert scoring on each evaluation indicator to obtain subjective weights, including the following steps: Step 31: Construct an initial table. Fill the first column of the initial table with the n evaluation indicators whose weights need to be determined, and number them in the order of D1 to Dn, as shown in Table 1. Table 1. Weighting determined using the chain-linked scoring method;

[0035] Step 32: Based on expert experience, compare the importance of adjacent indicators in the first column of the initial table, and use the obtained score as a provisional coefficient Xi to fill in the second column of the initial table; Specifically, based on expert experience, the importance of adjacent evaluation indicators in column 1 of Table 1 is compared from top to bottom, and the resulting score is recorded as a provisional coefficient Xi (i=1~n, representing the i-th evaluation indicator), which is added to column 2. Xi represents the ratio of the importance of Di and Di+1.

[0036] Step 33: Correct the provisional coefficient Xi in column 2 of the initial table, and record the result as the correction coefficient Yi, and fill it into column 3 of the initial table; the correction coefficient is determined starting from the last object, and its correction coefficient is set to 1; then the correction coefficient of each evaluation object is calculated in reverse order: the correction coefficient of each evaluation object is equal to the correction coefficient of the next object multiplied by the provisional coefficient in column 2 of the initial table corresponding to that object; and so on, until the correction coefficient of all objects is calculated; The specific correction method is explained below: The correction factor for the last object Yn is set to 1; Then, the previous term is calculated recursively, using the following recursive formula: ; ; By analogy, the correction coefficients can be calculated.

[0037] Step 34: Normalize the correction coefficient Yi, and fill the result as the weight in column 4 of the initial table. The weight in column 4 is the subjective weight. The correction coefficient Yi in column 3 is normalized, and the result is denoted as the weight. Enter the information in column 4. The normalized equation is: (8); Step 4 involves calculating the information entropy of the evaluation indicators using the entropy weight method to obtain objective weights. This method includes the following steps: Step 41: Construct an indicator value matrix based on the original scores of each object to be evaluated on each evaluation indicator. And standardize the process; Construct a judgment matrix for the nth evaluation index ci of m evaluated items, based on the numerical matrix of the power grid enterprise emergency response capability evaluation index system. Standardize the data, and set... For each evaluation index value The standardized result is calculated using the following formula: (9); In the formula, Represents the th element in the normalized matrix K. l The element in row i-th column; and They are the Kth l The maximum and minimum values ​​of the row elements.

[0038] Step 42: For the standardized index value matrix, calculate the information entropy di for each evaluation index. The calculation formula is as follows: (10); (11); in, This represents the normalized weight of the i-th column in the standardized index value matrix; Step 43: Based on the obtained information entropy, calculate the entropy weight bi of the evaluation index ci, i.e., the objective weight; The formula for calculating entropy weights is: (12); Step 5, based on the principle of minimum discriminative information and using the Lagrange multiplier method, integrates the subjective weights and the objective weights to obtain the comprehensive weights of the evaluation indicators. This method includes the following steps: Step 51: With the goal of making the combined weight ei as close as possible to the subjective weight ai obtained by the chain ratio scoring method and the objective weight bi obtained by the entropy weight method, the objective function is established using the principle of minimum discriminative information: (13); Step 52: Solve the constructed objective function using the Lagrange multiplier method to obtain the comprehensive weight value. for: (14); Based on the obtained comprehensive weight Formula 7 is used to synthesize the standardized correlation degree and weight coefficients into a comprehensive correlation degree, enabling a comprehensive assessment and ranking of the emergency response capabilities of the evaluated entities, such as power grid enterprises. This allows for accurate identification of their relative strengths and weaknesses within a multi-dimensional indicator system, providing a scientific basis for decision-making. By introducing the optimal combination of weights, not only is the subjective initiative of expert experience taken into account, but the objective characteristics of data-driven approaches are also integrated, effectively improving the rationality and robustness of the evaluation results.

[0039] Furthermore, based on the matter-element extension model, combined with a pre-set indicator system and comprehensive weights, the comprehensive correlation of the enterprise in four primary dimensions, namely "risk perception capability", "material allocation capability", "response linkage capability" and "recovery execution capability", is calculated, and finally a profile of the enterprise's emergency response capability is formed.

[0040] Step 6, based on the comprehensive correlation of an enterprise's emergency response capabilities, recommends relevant emergency intervention plans, including the following steps: Step 61: Construct a strategy library for intervention plans. The strategy library contains a variety of typical intervention measures, the target scenarios of each intervention measure, and the mapping relationship of the comprehensive correlation between the corresponding implementation plans of the implementing enterprises. Step 62: Obtain the characteristics of the current emergency scenario and select appropriate intervention measures based on the constructed strategy library; Specifically, a similarity matching algorithm is used to calculate the matching degree between the current accident scenario (e.g., a typhoon causing damage to the main network in a certain area) and the target scenario in the strategy library, and the most relevant set of intervention strategies is selected from the strategy library; Step 63: Based on the intervention measures, determine the comprehensive relevance of the corresponding implementation plan of the implementing enterprise, and select enterprises that meet the comprehensive relevance under the first-level dimension to implement the corresponding intervention plan.

[0041] For example, when the system identifies that a power grid company's "material allocation capability" correlation is below a threshold, it automatically triggers the corresponding "cross-regional emergency material support" plan in the strategy library, selecting companies with the top 30% overall correlation in this dimension as support providers and generating collaborative dispatch instructions. Simultaneously, by combining real-time traffic, inventory, and disaster spread prediction data, it dynamically optimizes transportation routes and allocation ratios to ensure accurate resource delivery. Finally, a closed-loop feedback mechanism evaluates the intervention effect, continuously iterating and optimizing the mapping relationships in the strategy library to improve the overall intelligent decision-making level of emergency response.

[0042] To illustrate the effectiveness of the evaluation method in this embodiment, it is applied to a real-world case for analysis. 1) Establish classical domains and section domains and determine the object elements to be evaluated; Based on the suggestions of experts and professionals, the classic domain for scoring each primary evaluation indicator of the emergency response capability of power grid enterprises is divided into four levels: "low risk" [90,100], "general risk" [80,90], "relatively high risk" [70,80], and "major risk" [0,70], with a domain of [0,100].

[0043] Experts were invited to assign importance numbers based on standards and specifications such as the "Evaluation Specification for Emergency Response Capability Building of Power Grid Enterprises" (DL / T 1920—2018) and their own experience, ensuring the authority and professionalism of the numbering order.

[0044] 2) Determine the entropy weights for each evaluation indicator; The weights of each secondary indicator for evaluating the emergency response capability of power grid enterprises are derived from formulas (8) to (14), as shown in Table 2.

[0045] Table 2. Weights of evaluation indicators using the month-on-month scoring method and entropy weight method, and comprehensive weights;

[0046] 3.3 Calculate the correlation degree; The higher the correlation value of each indicator's risk level, the higher the membership degree. Using formulas (4) to (5), the correlation degree between each secondary indicator and each risk level can be obtained, see... Figure 3 .

[0047] Depend on Figure 3 It can be seen that the emergency response capability evaluation indicators of power grid enterprises are between low risk and general risk, and most of them are low risk.

[0048] The comprehensive weight of each primary evaluation indicator is determined based on the weight of the secondary evaluation indicators, and the correlation between the primary indicators and each risk level is calculated according to formulas (4) to (5). Figure 4 As shown in the figure, prevention and emergency preparedness, emergency response and rescue are classified as low-risk; detection and early warning, and post-disaster recovery and reconstruction are classified as moderate-risk.

[0049] Similarly, a similar evaluation can be made on emergency response and rescue, as well as post-disaster recovery and reconstruction.

[0050] To verify the effectiveness and reliability of the proposed method for assessing enterprise emergency response capabilities, the common comprehensive index method and fuzzy comprehensive evaluation method were used to analyze and compare the same case. The evaluation results of different methods are shown in Table 3.

[0051] Table 3 Comparison of results from different evaluation methods;

[0052] Both the comprehensive index method and the fuzzy comprehensive evaluation method are existing methods. As shown in Table 3, the evaluation results of the three different evaluation methods for the same case are not the same. The overall evaluation result of the method studied in this technology and the fuzzy comprehensive evaluation method is general risk, while the evaluation result of the comprehensive index method is low risk. At the same time, the risk levels corresponding to different evaluation indicators also have certain differences. Taking the risk level of post-disaster recovery and reconstruction as an example, the risk level of the comprehensive index method and the fuzzy comprehensive evaluation method is low risk, while the evaluation level of the method proposed in this technology is general risk. The reason is that the comprehensive index method relies entirely on subjective weighting in the evaluation process, and its excessive reliance on experience leads to a lower evaluation risk level; while the fuzzy comprehensive evaluation method also has obvious defects. The determination of the weights of each evaluation indicator using expert weighting method and data survey method is too subjective, resulting in randomness in the evaluation results. The method of this embodiment combines both subjective and objective aspects to comprehensively determine the weights of risk indicators, thereby enhancing the credibility of the evaluation results of the emergency response capabilities of power grid enterprises.

[0053] This embodiment integrates a subjective and objective weighting mechanism (comparative scoring method and entropy weighting method), which improves the rationality and credibility of the evaluation weights. At the same time, it uses the matter-element extension model to determine the multi-level correlation, avoiding the "critical fuzziness" problem in traditional fuzzy classification methods. The evaluation results have good discrimination, explanatory power and practical value.

[0054] Example 2 Based on Example 1, this example provides an intervention plan recommendation system based on comprehensive weighted emergency response capability assessment, including: The evaluation system construction module is configured to build an evaluation index system for the emergency response capabilities of power grid enterprises and determine the evaluation indicators. The correlation calculation module is configured to acquire relevant data on emergency management and control of power grid enterprises, calculate the value range of evaluation indicators, construct a matter-element extension evaluation model, determine the classical domain and the section domain, and calculate the correlation of each evaluation indicator with respect to different levels. The subjective weight calculation module is configured to use the year-on-year scoring method to conduct expert scoring on each evaluation indicator to obtain the subjective weight. The objective weight calculation module is configured to use the entropy weight method to calculate the information entropy of the evaluation indicators to obtain the objective weights. The comprehensive weight calculation module is configured to integrate subjective and objective weights based on the principle of minimum discriminative information and using the Lagrange multiplier method to obtain the comprehensive weight of the evaluation index. The solution recommendation module is configured to calculate the comprehensive correlation degree based on the comprehensive weight and correlation degree to obtain the evaluation results of the power grid enterprise's emergency response capability, and generate and recommend corresponding intervention solutions in combination with the characteristics of the emergency scenario.

[0055] It should be noted that each module in this embodiment corresponds one-to-one with each step in embodiment 1, and their specific implementation process is the same, so it will not be repeated here.

[0056] Example 3 Based on Embodiment 1, this embodiment provides an electronic device, including a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, they complete the steps in the intervention plan recommendation method based on comprehensive weighted emergency response capability assessment described in Embodiment 1.

[0057] Example 4 Based on Embodiment 1, this embodiment provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, they complete the steps in the intervention plan recommendation method based on comprehensive weighted emergency response capability assessment described in Embodiment 1.

[0058] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0059] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for recommending intervention plans based on comprehensive weighted emergency response capacity assessment, characterized in that: Includes the following steps: Construct an evaluation index system for the emergency response capabilities of power grid enterprises and determine the evaluation indicators; Acquire relevant data on emergency management and control of power grid enterprises, calculate the value range of evaluation indicators, construct a matter-element extension evaluation model, determine the classical domain and the node domain, and calculate the correlation degree of each evaluation indicator with respect to different levels; The chain-comparison scoring method was used to assign expert scores to each evaluation indicator, and subjective weights were obtained. The information entropy of the evaluation indicators is calculated using the entropy weight method to obtain objective weights. Based on the principle of minimum discriminative information and using the Lagrange multiplier method, subjective weights and objective weights are integrated to obtain the comprehensive weight of the evaluation index. The comprehensive correlation degree is calculated based on the comprehensive weight and correlation degree to obtain the evaluation results of the emergency response capability of power grid enterprises. Combined with the characteristics of emergency scenarios, corresponding intervention plans are generated and recommended.

2. The intervention plan recommendation method based on comprehensive weighted emergency response capability assessment as described in claim 1, characterized in that: The evaluation index system for the emergency response capabilities of power grid enterprises includes multiple evaluation indicators for four stages: prevention and emergency preparedness, monitoring and early warning, emergency response and rescue, and post-disaster recovery and reconstruction.

3. The intervention plan recommendation method based on comprehensive weighted emergency response capability assessment as described in claim 1, characterized in that: The method for constructing a matter-element extension evaluation model, determining the classical domain and the node domain, and calculating the correlation degree of each evaluation index with respect to different levels includes the following steps: Based on the value range of the indicator characteristics of the object to be evaluated at each level, a classical domain is constructed. Based on the maximum range of values ​​for the corresponding indicator characteristics of the object to be evaluated, construct the section domain; Based on the distance relationship between the characteristic values ​​of various evaluation indicators of the object to be evaluated and the classical domain under different evaluation levels, a correlation function is constructed to calculate the correlation degree of the evaluation indicators with respect to different levels.

4. The intervention plan recommendation method based on comprehensive weighted emergency response capability assessment as described in claim 1, characterized in that: The evaluation indicators were scored by experts using a year-over-year scoring method to obtain subjective weights, including the following steps: Construct an initial table and fill the first column of the n evaluation indicators whose weights need to be determined. Based on expert experience, the importance of adjacent indicators in the first column of the initial table is compared, and the resulting score is used as a provisional coefficient Xj and filled into the second column of the initial table. The provisional coefficient Xj in column 2 of the initial table is corrected, and the result is recorded as the correction coefficient Yj and filled into column 3 of the initial table; The correction coefficient Yj is normalized, and the result is used as the weight in column 4 of the initial table. The weight in column 4 is the subjective weight.

5. The intervention plan recommendation method based on comprehensive weighted emergency response capability assessment as described in claim 1, characterized in that: The method for calculating the information entropy of the evaluation index using the entropy weight method to obtain the objective weight includes the following steps: Based on the original scores of each object to be evaluated on each evaluation indicator, an indicator value matrix is ​​constructed and then standardized. For the standardized index value matrix, calculate the information entropy of each evaluation index; Based on the obtained information entropy, the entropy weights of the evaluation indicators are calculated, i.e., the objective weights.

6. The intervention plan recommendation method based on comprehensive weighted emergency response capability assessment as described in claim 1, characterized in that: A method for fusing subjective weights and objective weights to obtain the comprehensive weights of the evaluation index based on the principle of minimum discriminative information and using the Lagrange multiplier method includes the following steps: So that the combined weights Subjective weights obtained by the chain-linked scoring method Objective weights obtained by the entropy weight method Using the principle of minimum discriminative information as the objective, a target function is established based on the closest approximation. The objective function is solved using the Lagrange multiplier method to obtain the comprehensive weight value.

7. The intervention plan recommendation method based on comprehensive weighted emergency response capability assessment as described in claim 6, characterized in that: Using the principle of minimum discriminative information, the objective function is established as follows: ； in, Indicates the combined weight value. Indicates subjective weighting. Indicates objective weight.

8. An intervention plan recommendation system based on comprehensive weighted emergency response capability assessment, characterized in that: include: The evaluation system construction module is configured to construct an evaluation index system for the emergency response capabilities of power grid enterprises and determine the evaluation indicators. The correlation calculation module is configured to acquire relevant data on emergency management and control of power grid enterprises, calculate the value range of evaluation indicators, construct a matter-element extension evaluation model, determine the classical domain and the section domain, and calculate the correlation of each evaluation indicator with respect to different levels. The subjective weight calculation module is configured to use the chain-linked scoring method to conduct expert scoring on each evaluation indicator to obtain the subjective weight. The objective weight calculation module is configured to use the entropy weight method to calculate the information entropy of the evaluation indicators to obtain the objective weights. The comprehensive weight calculation module is configured to integrate subjective and objective weights based on the principle of minimum discriminative information and using the Lagrange multiplier method to obtain the comprehensive weight of the evaluation index. The solution recommendation module is configured to calculate the comprehensive correlation degree based on the comprehensive weight and correlation degree to obtain the evaluation results of the power grid enterprise's emergency response capability, and generate and recommend corresponding intervention solutions in combination with the characteristics of the emergency scenario.

9. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the steps in the intervention program recommendation method based on comprehensive weighted emergency response capability assessment as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, complete the steps in the intervention plan recommendation method based on comprehensive weighted emergency response capability assessment as described in any one of claims 1-7.

Images