An evaluation method and device for extreme natural weather emergency mechanism

Abstract

The application relates to an evaluation method and device of an extreme natural weather emergency mechanism, and relates to the field of power grid management. In the method, a first prediction accuracy of extreme natural weather is determined according to a meteorological log in the emergency mechanism to be evaluated, and a first score is determined according to the first prediction accuracy; a second prediction accuracy of power grid failure is determined according to a power grid state log in the emergency mechanism to be evaluated, and a second score is determined according to the second prediction accuracy; a processing capacity value is determined according to a fault response speed and a power supply recovery speed in processing a fault event, and a third score is determined according to the processing capacity value and an influence level of the extreme natural weather corresponding to the fault event; a fourth score is determined according to an opinion attitude on the processing situation of the fault event on a social media; and the first score, the second score, the third score and the fourth score are weighted and summed to obtain a total score for evaluating the emergency mechanism to be evaluated. The technical scheme provided by the application achieves the effect of comprehensively evaluating the emergency mechanism.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid management, and in particular to an evaluation method and device for an extreme natural weather emergency mechanism. BACKGROUND

[0002] In the field of power grid management, with the frequent occurrence of natural disasters and the increasing severity of extreme weather conditions, it is crucial to ensure the stable operation of the power system. As an important infrastructure in modern society, the safety of the power grid not only affects the daily life of residents and enterprises, but also directly affects the national economy and social stability. Therefore, establishing an effective emergency mechanism to cope with the stability of the power grid under extreme natural weather conditions is an important research topic at present.

[0003] Currently, the evaluation of the emergency mechanism usually adopts multiple means, such as historical data analysis, accuracy of fault prediction, etc. These means collect and analyze historical data to predict power grid failure under extreme natural weather conditions, and then take preventive measures. However, the existing emergency mechanism evaluation methods usually lack a comprehensive evaluation system to consider the influence of multiple factors, often leading to inaccurate evaluation of the emergency mechanism.

[0004] Therefore, how to construct an emergency mechanism evaluation method that can comprehensively consider multiple factors has become a problem to be solved. SUMMARY

[0005] The present application provides an evaluation method and device for an extreme natural weather emergency mechanism, which can comprehensively reflect the performance of the emergency mechanism in prediction, early warning, processing and feedback, etc. This comprehensive evaluation method provides a scientific decision basis for the power grid management platform, which helps to continuously optimize and improve the emergency mechanism, and improves the overall ability and level of the power grid in coping with extreme natural weather.

[0006] In a first aspect of the present application, an evaluation method for an extreme natural weather emergency mechanism is provided, applied to a power grid management platform, the evaluation method comprising:

[0007] Obtaining meteorological logs in the emergency mechanism to be evaluated, determining a first prediction accuracy of extreme natural weather according to the meteorological logs, and determining a first score according to the first prediction accuracy, the meteorological logs including daily actual meteorological data and meteorological prediction data within a preset time period, the extreme natural weather including temperature higher than a first temperature preset value or lower than a second temperature preset value, precipitation greater than a first precipitation preset value or less than a second precipitation preset value, wind power greater than a wind power preset value, and precipitation of a preset type;

[0008] obtaining a power grid state log in an emergency mechanism to be evaluated, determining a second prediction accuracy of a power grid failure according to the power grid state log, the power grid state log including daily working data of the power grid and power grid failure prediction data generated in combination with the meteorological log, and determining a second score according to the second prediction accuracy;

[0009] determining a processing capacity value according to a fault response speed and a power recovery speed in processing a fault event, determining an influence level of an extreme natural weather corresponding to the fault event, and determining a third score according to the processing capacity value and the influence level;

[0010] obtaining an opinion attitude on the processing of the fault event on a social media, and determining a fourth score according to the opinion attitude, the opinion attitude including positive, neutral and negative;

[0011] performing weighted summation on the first score, the second score, the third score and the fourth score to obtain a total score of the emergency mechanism to be evaluated, and evaluating the emergency mechanism to be evaluated according to the total score.

[0012] By adopting the above technical solution, the actual meteorological data in the meteorological log is compared with the meteorological prediction data in a preset time period, which can quantitatively evaluate the prediction accuracy (first score) of the emergency mechanism for the extreme natural weather. This helps to timely find and improve the prediction model, thereby improving the prediction accuracy of future extreme weather events and providing strong support for the power grid to take preventive measures in advance. By combining the meteorological log and the power grid state log, the second prediction accuracy (second score) of the power grid failure can be evaluated, which can reveal the effectiveness of the emergency mechanism in predicting power grid failures. This helps to identify potential power grid failure risks in advance, take preventive measures, and reduce the occurrence rate and impact range of power grid failures caused by extreme weather. By evaluating the fault response speed and the power recovery speed to determine the processing capacity value (third score), and combining the influence level of the extreme natural weather for comprehensive scoring, the efficiency and effectiveness of the emergency mechanism in responding to actual fault events can be intuitively reflected. This helps to find and improve the weak links in the processing process, improve the overall fault handling capacity, ensure the rapid recovery of power supply, and reduce social impact and economic losses. The opinion attitude (fourth score) on the processing of the fault event obtained from the social media reflects the attention to public concerns and satisfaction. This helps to understand the real views of the public on the power grid emergency response work, provides a social reference for the continuous improvement of the emergency mechanism, and enhances the public's trust and support for the power grid enterprise. By weighted summation to obtain the total score of the emergency mechanism and comprehensive evaluation, the performance of the emergency mechanism in prediction, early warning, processing and feedback can be comprehensively reflected. This comprehensive evaluation method provides a scientific decision-making basis for the power grid management platform, which helps to continuously optimize and improve the emergency mechanism and improve the overall ability and level of the power grid in response to extreme natural weather.

[0013] Optionally, the determining the first prediction accuracy of the extreme natural weather according to the weather log comprises:

[0014] determining a first sub-score according to a first difference between the predicted occurrence time of the extreme natural weather and the actual occurrence time of the extreme natural weather, determining a second sub-score according to a second difference between the predicted intensity of the extreme natural weather and the actual intensity of the extreme natural weather, and determining a third sub-score according to a difference between the predicted type of the extreme natural weather and the actual type of the extreme natural weather;

[0015] determining a sub-prediction accuracy of the first target prediction event according to the first sub-score, the second sub-score and the third sub-score, and obtaining the first prediction accuracy according to an average value of the sub-prediction accuracies of the plurality of first target prediction events.

[0016] By adopting the above technical solution, the prediction accuracy is refined into three dimensions of time, intensity and type (i.e. the first sub-score, the second sub-score and the third sub-score), which can more comprehensively and accurately measure the performance of the prediction model in the aspect of extreme natural weather prediction. This refined evaluation helps to find the advantages and disadvantages of the prediction model in different aspects, providing more targeted directions for model optimization. By calculating the time difference and the intensity difference to determine the sub-prediction accuracy, the deviation between the prediction and the actual situation can be quantified, thus more intuitively reflecting the accuracy of the prediction. This helps to motivate the relevant team to continuously optimize the prediction model, reduce prediction errors and improve prediction accuracy, providing more reliable basis for the early warning and prevention work of the power grid. By comparing the predicted type with the actual occurrence type to determine the third sub-score, the accuracy of the prediction model in identifying the type of extreme weather can be ensured. This is crucial for the targeted prevention and response measures of the power grid, because different types of extreme weather may have different impacts on the power grid and require different response strategies. By calculating the average value of the sub-prediction accuracies of the plurality of first target prediction events to obtain the first prediction accuracy, the evaluation results can be generalized from the individual to the general, making the evaluation results more representative and credible. This comprehensive evaluation method helps to reduce the influence of individual events on the overall evaluation results, improving the scientificity and fairness of the evaluation results.

[0017] Optionally, the determining the second prediction accuracy of the power grid failure according to the power grid state log comprises:

[0018] extracting a first feature related to the power grid failure from the weather log, the first feature including the occurrence time, intensity and duration of the extreme natural weather, and extracting a second feature reflecting the state of the power grid from the power grid state log, the second feature including the load change trend, device health status and historical failure mode;

[0019] inputting the first feature and the second feature into a preset fault prediction model to obtain power grid fault prediction data, the power grid fault prediction data including predicted occurrence time, predicted occurrence location, and predicted occurrence type;

[0020] determining the second prediction accuracy according to the power grid fault prediction data and actual fault data.

[0021] By adopting the above technical solution, the first feature related to the power grid fault (such as the occurrence time, intensity, and duration of extreme natural weather) is extracted from the meteorological log, and the second feature reflecting the power grid state (such as the load change trend, equipment health status, and historical fault pattern) is extracted from the power grid state log, realizing multi-dimensional and comprehensive consideration for power grid fault prediction. This comprehensive feature analysis method can more comprehensively capture various factors that may cause power grid faults, improving the accuracy of prediction. The extracted first feature and second feature are input into a preset fault prediction model to obtain power grid fault prediction data. This prediction model based on big data and machine learning algorithms can automatically learn the complex relationship between historical fault data and the current power grid state, thereby realizing accurate prediction of future power grid faults. This intelligent prediction method not only improves the prediction efficiency, but also reduces the influence of human intervention and subjective judgment. The power grid fault prediction data includes detailed information such as predicted occurrence time, predicted occurrence location, and predicted occurrence type. This accurate prediction result helps power grid management personnel to understand the specific situation of possible faults in advance, and to develop targeted preventive measures and emergency plans, thereby effectively reducing the impact of faults on power grid operation. By comparing the power grid fault prediction data with the actual fault data, the accuracy of the prediction model (i.e., the second prediction accuracy) can be quantitatively evaluated. This evaluation method helps to discover the deficiencies and biases in the prediction model in a timely manner, providing data support for the continuous optimization of the model. With the continuous optimization and iteration of the model, the prediction accuracy will be continuously improved, providing more reliable protection for the safe and stable operation of the power grid.

[0022] Optionally, determining the second prediction accuracy according to the power grid fault prediction data and actual fault data includes:

[0023] determining a fourth sub-score according to a third difference between the predicted occurrence time of the power grid fault and the actual occurrence time of the power grid fault, determining a fifth sub-score according to a fourth difference between the predicted occurrence location of the power grid fault and the actual occurrence location of the power grid fault, and determining a sixth sub-score according to the predicted occurrence type of the power grid fault and the actual occurrence type of the power grid fault;

[0024] determining the sub-prediction accuracy of the second target prediction event according to the fourth sub-score, the fifth sub-score, and the sixth sub-score, and performing weighted summation on the sub-prediction accuracy of the second target prediction event according to the predicted occurrence type of the power grid fault to obtain the second prediction accuracy.

[0025] By adopting the above technical solutions, the difference between the predicted occurrence time and the actual occurrence time of the power grid fault (third difference), the difference between the predicted location and the actual location (fourth difference), and the matching degree of the predicted type and the actual type are calculated respectively, realizing multi-dimensional evaluation of the prediction accuracy. This evaluation method can more comprehensively reflect the performance of the prediction model in various aspects, providing more detailed references for model optimization. Comparing key indicators such as prediction time, location and type with actual data can accurately quantify the accuracy of the prediction model in these aspects. This accurate evaluation method helps to reduce evaluation errors and improve the reliability of evaluation results. The second prediction accuracy is obtained by weighting and summing the sub-prediction accuracies of the multiple second target prediction events according to the power grid fault prediction type. This weighting and summing method takes into account the differences in the impact of different fault types on power grid operation, making the evaluation results more in line with actual situations and enhancing the pertinence and practicality of the evaluation. Through multi-dimensional and accurate evaluation of prediction accuracy, deficiencies and biases of the prediction model in different aspects can be found in a timely manner. This helps relevant personnel to optimize the prediction model targetedly, improve the prediction ability and accuracy of the model, and provide more reliable protection for the safe and stable operation of the power grid.

[0026] Optionally, the processing capacity value is determined according to the fault response speed and the power recovery speed of the fault event, comprising:

[0027] The first time of the fault occurrence, the second time of the maintenance personnel arriving at the scene to start processing the fault, and the third time of the power recovery are obtained;

[0028] The fault response speed is determined according to the first time and the second time, the power recovery speed is determined according to the second time and the third time, the fault response speed and the power recovery speed are weighted and summed to obtain the processing capacity value.

[0029] By adopting the above technical solutions, the key nodes such as the fault occurrence time, the maintenance personnel's on-site arrival time and the power restoration time are quantified, so that the response speed and the recovery ability of the power grid management platform in handling the fault event can be accurately evaluated. This quantitative evaluation method makes the processing capacity value objective and comparable, and provides a scientific basis for evaluating the emergency response ability of the power grid management platform. The fault response speed is one of the important indicators for evaluating the emergency response ability. By calculating the time difference from the fault occurrence to the maintenance personnel's on-site arrival, the response speed of the power grid management platform after receiving the fault report can be intuitively reflected. This evaluation method helps to motivate relevant personnel to improve the emergency response efficiency, reduce the fault handling time and reduce the impact of the fault on the power grid operation. The power restoration speed is an important indicator for evaluating the recovery ability of the power grid management platform. By calculating the time difference from the maintenance personnel's on-site arrival to the power restoration, the recovery speed and efficiency of the power grid management platform after handling the fault can be evaluated. This evaluation method helps the power grid management platform to optimize the fault handling process, improve the power restoration speed and ensure the power grid to resume normal operation as soon as possible. By weighted sum of the fault response speed and the power restoration speed, a comprehensive processing capacity value can be obtained. This value can comprehensively reflect the overall ability and level of the power grid management platform in handling the fault event. This comprehensive evaluation method helps the power grid management platform to fully understand its emergency response ability, find existing problems and deficiencies, and provide direction for subsequent improvement and promotion.

[0030] Optionally, the determining the influence level of the extreme natural weather corresponding to the fault event according to the processing capacity value and the influence level comprises:

[0031] determining the type and intensity of the extreme natural weather corresponding to the fault event, matching a preset influence level according to the type and intensity, and multiplying the preset influence level by the processing capacity value to obtain a third score.

[0032] By adopting the technical solution, the type and intensity of the extreme natural weather corresponding to the fault event are determined, and the preset influence level is matched, so that the precise evaluation of the influence of weather factors on the power grid fault can be realized. This evaluation method considers the different influences of different weather types and intensities on the operation of the power grid, making the evaluation result more in line with the actual situation. The third score is obtained by multiplying the processing capacity value and the influence level of the extreme natural weather, which comprehensively considers the actual capacity of the power grid management platform in processing the fault event and the influence of external weather factors. This comprehensive evaluation method helps to better understand the performance of the power grid management platform in extreme weather conditions, providing strong support for subsequent improvement and improvement. By evaluating the third score corresponding to different fault events, the power grid management platform can understand the types of extreme weather that have greater influence on the operation of the power grid and its own performance in handling these faults. This helps the power grid management platform to optimize resource allocation and invest more resources and efforts into preventing and responding to extreme weather types that have greater influence on the operation of the power grid, improving the overall response capability.

[0033] Optionally, the fourth score is determined according to the public opinion attitude of the handling of the fault event on the social media, and the fourth score includes:

[0034] The crawler technology or social media interface is used to capture social media data containing keywords of the fault event, the keywords including fault name, location, time, power supply enterprise name, repair, and recovery, and the social media data including posts, comments, and forwards.

[0035] The social media data is subjected to sentiment analysis to identify sentiment tendency and intensity, the sentiment tendency including positive, negative, and neutral, and the intensity including praise, satisfaction, recognition, criticism, dissatisfaction, and complaint.

[0036] The public opinion score of each content in the social media data is determined according to the sentiment tendency and intensity, and the fourth score is obtained by weighted average of all contents.

[0037] By adopting the above technical solutions, the crawler technology or social media interface can be used to quickly capture social media data related to the fault event, including posts, comments, forwards, etc. This method can reflect the public's views and attitudes towards the fault event and its handling in real time, providing valuable feedback information for the power grid management platform. Through sentiment analysis of social media data, the public's emotional tendency and intensity can be accurately identified. This analysis is not limited to simple positive, negative, and neutral classification, but further refined into specific emotions such as praise, satisfaction, recognition, criticism, dissatisfaction, and complaints. This detailed sentiment analysis helps the power grid management platform to better understand the public's true feelings and needs, improving the insight and precision of decision-making. According to the emotional tendency and intensity, the public opinion score of each social media content is determined, and the weighted average of all content is obtained as the fourth score. This quantitative evaluation method makes the public opinion attitude measurable and comparable, providing an objective evaluation standard for the power grid management platform. By comparing the fourth scores of different fault events, the public's satisfaction and recognition of different event handling can be intuitively understood. The determination process of the fourth score provides a clear direction for the power grid management platform to improve service quality. By analyzing the positive and negative factors in public opinion attitude, the power grid management platform can identify problems and shortcomings in the service process and develop targeted improvement measures accordingly. This helps to improve the service level of the power grid management platform and enhance the public's trust and satisfaction.

[0038] In a second aspect of the present application, an evaluation system for an extreme natural weather emergency mechanism is provided, comprising a weather module, a power grid module, a processing module, a public opinion module, and an evaluation module, wherein:

[0039] The weather module is configured to obtain meteorological logs in the emergency mechanism to be evaluated, determine a first prediction accuracy of extreme natural weather based on the meteorological logs, and determine a first score based on the first prediction accuracy. The meteorological logs include daily actual meteorological data and meteorological prediction data within a preset time period. The extreme natural weather includes temperature higher than a first temperature preset value or lower than a second temperature preset value, precipitation greater than a first precipitation preset value or less than a second precipitation preset value, wind power greater than a wind power preset value, and precipitation of a preset type.

[0040] The power grid module is configured to obtain power grid state logs in the emergency mechanism to be evaluated, determine a second prediction accuracy of power grid failure based on the power grid state logs, and determine a second score based on the second prediction accuracy. The power grid state logs include daily work data of the power grid and power grid failure prediction data generated in combination with the meteorological logs.

[0041] a processing module configured to determine a processing capability value according to a fault response speed and a power recovery speed of processing the fault event, determine an influence level of an extreme natural weather corresponding to the fault event, and determine a third score according to the processing capability value and the influence level;

[0042] an opinion module configured to obtain an opinion attitude on the processing of the fault event on a social media, and determine a fourth score according to the opinion attitude, the opinion attitude including positive, neutral and negative;

[0043] an evaluation module configured to perform weighted summation on the first score, the second score, the third score and the fourth score to obtain a total score of the emergency mechanism to be evaluated, and evaluate the emergency mechanism to be evaluated according to the total score.

[0044] In a third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to perform the method according to any one of the preceding aspects.

[0045] In a fourth aspect of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores instructions, when the instructions are executed, the method according to any one of the preceding aspects is performed.

[0046] In summary, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0047] 1. By obtaining and analyzing the actual meteorological data and the prediction data in the meteorological log, the first prediction accuracy of the extreme natural weather can be quantified, and a first score is given accordingly. This method helps to understand the performance of the emergency mechanism in predicting extreme weather, provides a scientific basis for preparing in advance, and thus reduces the loss caused by inaccurate prediction;

[0048] 2. By analyzing the power grid state log in combination with the meteorological log, especially the power grid fault prediction data, the fault prediction accuracy of the power grid under extreme weather can be evaluated. This helps to discover potential power grid fault risks in time, and the processing capability value is determined by quantifying the fault response speed and the power recovery speed, and the efficiency of the emergency mechanism is evaluated in combination with the influence level of the extreme natural weather. This not only directly reflects the efficiency of the emergency mechanism in processing specific fault events, but also provides data support for further optimizing the emergency response process;

[0049] 3. Collect public opinion attitudes towards the handling of the failure event through social media, and determine the fourth score based on this, making the evaluation process more comprehensive and objective. This method helps to understand the public's satisfaction and trust in power grid emergency management, and also encourages power grid management departments to respond more actively to public concerns and improve service quality;

[0050] 4. By weighting and summing the scores of the four aspects, the total score of the emergency mechanism is obtained, so as to realize the comprehensive and systematic evaluation of the emergency mechanism. This comprehensive evaluation method not only considers the technical factors (such as prediction accuracy and processing capacity), but also considers the social factors (such as public opinion attitude), which helps to find the advantages and disadvantages of the emergency mechanism and provides a clear direction for subsequent improvement and optimization. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 is a flowchart of the evaluation method of the extreme natural weather emergency mechanism disclosed in the embodiments of the present application;

[0052] Figure 2 is a module schematic diagram of the evaluation system of the extreme natural weather emergency mechanism disclosed in the embodiments of the present application;

[0053] Figure 3 is a structural schematic diagram of an electronic device disclosed in the embodiments of the present application.

[0054] REFERENCE SIGNS: 201, weather module; 202, power grid module; 203, processing module; 204, public opinion module; 205, evaluation module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0055] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the embodiments of the specification will be described clearly and completely below in conjunction with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all.

[0056] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent examples, illustrations or descriptions. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concept in a specific way.

[0057] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first", "second", etc. are used only for the purpose of description and should not be understood as indicating or implying relative importance or implying the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0058] The embodiment discloses an evaluation method of an extreme natural weather emergency mechanism, applied to a power grid management platform, Figure 1 is a flowchart of the evaluation method of the extreme natural weather emergency mechanism disclosed by the embodiment of the present application, as Figure 1 shown, the evaluation method comprises the following steps:

[0059] S110, acquiring a meteorological log in the emergency mechanism to be evaluated, determining a first prediction accuracy of the extreme natural weather according to the meteorological log, and determining a first score according to the first prediction accuracy, the meteorological log comprising daily actual meteorological data and meteorological prediction data within a preset time period, the extreme natural weather comprising temperature higher than a first temperature preset value or lower than a second temperature preset value, precipitation greater than a first precipitation preset value or less than a second precipitation preset value, wind power greater than a wind power preset value, and precipitation of a preset type;

[0060] The meteorological log of the region where the emergency mechanism to be evaluated is implemented is obtained. The daily actual meteorological data refers to the daily meteorological conditions recorded in the actual observation, including but not limited to specific numerical values such as temperature, precipitation, wind force, etc. These data are the basis for evaluating the accuracy of the prediction. The meteorological prediction data within a preset time period refers to the data obtained by predicting the meteorological conditions within a future preset time period based on various meteorological models and technical means. These data are used to compare with the actual data to evaluate the accuracy of the prediction. In order to evaluate the accuracy of the prediction, the meteorological conditions that are considered as extreme natural weather need to be clearly defined. According to the description, these meteorological conditions include: temperature higher than a first temperature preset value (such as 37℃) or lower than a second temperature preset value (such as 0℃), precipitation greater than a first precipitation preset value (such as 20mm / hour) or less than a second precipitation preset value (such as 20 days without precipitation), wind force greater than a wind force preset value (such as 12 levels), specific types of precipitation (such as freezing rain, hail). By using the collected meteorological log, especially by comparing the actual meteorological data with the prediction data, the prediction accuracy of extreme natural weather can be evaluated. Specifically, the prediction data is compared with the daily actual meteorological data item by item, and special attention is paid to whether the occurrence of extreme weather events is accurately predicted. According to the comparison result, the ratio of the number of accurate predictions to the total number of predictions is calculated as a quantitative indicator of the first prediction accuracy. Based on the first prediction accuracy, a score (first score) can be further determined to quantify and evaluate the performance of the emergency mechanism in predicting extreme natural weather. The determination of this score can be based on a preset scoring standard, such as: if the prediction accuracy is higher than a certain threshold, a higher score is given; if the prediction accuracy is lower, the score is correspondingly reduced. The specific calculation method and threshold of the score can be set according to the actual situation and evaluation requirements.

[0061] Optionally, the first prediction accuracy of extreme natural weather determined according to the meteorological log comprises:

[0062] determining a first sub-score according to a first difference between the predicted occurrence time of extreme natural weather and the actual occurrence time of extreme natural weather, determining a second sub-score according to a second difference between the predicted intensity of extreme natural weather and the actual intensity of extreme natural weather, and determining a third sub-score according to a difference between the predicted type of extreme natural weather and the actual type of extreme natural weather;

[0063] determining the sub-prediction accuracy of the first target prediction event according to the first sub-score, the second sub-score and the third sub-score, and obtaining the first prediction accuracy according to the average value of the sub-prediction accuracies of a plurality of first target prediction events.

[0064] Suppose a region is being evaluated for its prediction accuracy of extreme natural weather in the next week. The meteorological log of the region records the actual weather events that occurred as well as the predicted weather events. Three main types of extreme weather are of interest: high temperature, heavy rain, and strong wind.

[0065] Prediction 1 (High Temperature): The prediction was that the temperature would reach 38°C in the afternoon of the third day, but it actually occurred in the morning of the fourth day, with a temperature of 39°C. Prediction 2 (Heavy Rain): The prediction was that there would be heavy rain in the evening of the fifth day, and it actually occurred in the evening of the fifth day as well, but the predicted amount of precipitation was 100mm, while the actual amount was 120mm. Prediction 3 (Strong Wind): The prediction was that the wind would reach 8 levels in the afternoon of the sixth day, and it actually occurred in the afternoon of the sixth day as well, but the actual wind reached 9 levels. For the high temperature prediction, the time difference is one and a half days (from the afternoon of the third day to the morning of the fourth day), which, according to the scoring criteria, might result in a lower sub-score, such as 60 points (out of 100). The time difference for the heavy rain and strong wind predictions is 0, so both predictions have a sub-score of 100 for the time aspect. In the high temperature prediction, the actual temperature was 1°C higher than the predicted temperature, which might result in a sub-score close to 100, such as 95 points. In the heavy rain prediction, the actual amount of precipitation was 20mm more than the predicted amount, which might result in a slightly lower sub-score, such as 85 points. In the strong wind prediction, the actual wind was one level higher than the predicted wind, which might also result in a lower sub-score, such as 75 points. All predictions correctly predicted the type of extreme weather (high temperature, heavy rain, strong wind), so the sub-scores for the type matching aspect are all 100 points for the three predictions. For each prediction event, a combined sub-prediction accuracy score can be calculated. For example, for the high temperature prediction:

[0066] Sub-prediction accuracy = (time difference sub-score + intensity difference sub-score + type matching sub-score) / 3 = (60 + 95 + 100) / 3 = 85, and similarly, the sub-prediction accuracy for the heavy rain and strong wind predictions can be calculated. Finally, the average of the sub-prediction accuracies for all first target prediction events is taken to get the first prediction accuracy: First prediction accuracy = (high temperature sub-prediction accuracy + heavy rain sub-prediction accuracy + strong wind sub-prediction accuracy) / 3. Assuming the sub-prediction accuracies for heavy rain and strong wind are 88 and 80 respectively (hypothetical values based on the above logic), then the first prediction accuracy = (85 + 88 + 80) / 3 = 84.33.

[0067] The prediction accuracy of extreme natural weather is comprehensively evaluated through three different dimensions (time, intensity, and type). This multi-dimensional evaluation can more comprehensively reflect the performance of the prediction, as considering only one dimension (such as time or intensity) may overlook other key information, leading to biased evaluation results. By converting the differences between prediction and actual (time difference, intensity difference), and type matching into specific sub-scores, the embodiment of the invention realizes the fine quantification of prediction accuracy. This quantification makes the evaluation results more intuitive and comparable, and also provides specific improvement directions for subsequent prediction model optimization. By calculating the average of the sub-prediction accuracies of multiple first target prediction events to obtain the first prediction accuracy, the embodiment of the invention can effectively reduce the influence of individual extreme or abnormal events on the overall evaluation results, making the evaluation results more stable and reliable. By quantifying the evaluation of prediction accuracy, the performance of the prediction model in different aspects can be clearly seen. This provides valuable feedback for model developers, helping them to find the shortcomings of the model and make targeted optimization, further improving the accuracy and reliability of the prediction model.

[0068] In S120, the power grid state log in the to-be-evaluated emergency mechanism is obtained, the second prediction accuracy of the power grid fault is determined according to the power grid state log, and the second score is determined according to the second prediction accuracy. The power grid state log includes daily work data of the power grid and power grid fault prediction data generated in combination with the meteorological log;

[0069] The power grid state log is a detailed record generated in the daily operation of the power grid, including but not limited to key parameters such as voltage, current, power factor, load condition, and equipment operating state. In addition, it also includes power grid fault prediction data generated in combination with meteorological logs (such as temperature, humidity, wind speed, and rainfall). These data are usually automatically generated by the monitoring system and prediction model of the power grid and stored in the database. In order to evaluate, relevant log information needs to be extracted from these data sources. The daily work data of the power grid is analyzed in detail to understand the operating state, load change, and equipment health condition of the power grid at different time periods. These data reflect the actual operation of the power grid and potential risk points. The power grid fault prediction data generated based on the meteorological log is compared with the actual work data. The prediction data usually includes the prediction of the time, location, type, and severity of the possible power grid fault in the future period.

[0070] The difference between the predicted time of the fault occurrence and the actual time of the fault occurrence is evaluated to calculate an index of time accuracy. The type and location of the predicted fault are compared with the type and location of the actual fault to evaluate the accuracy of the prediction in terms of type and location. If the prediction data includes a prediction of the severity of the fault, the degree of agreement between the predicted severity and the actual severity also needs to be evaluated. The results of the above evaluations are combined to form a comprehensive evaluation of the accuracy of the power grid fault prediction. According to the evaluation results, a scoring standard is developed to convert the prediction accuracy into a specific score. The scoring standard can be weighted based on multiple dimensions such as time, type, location, severity, etc. According to the scoring standard, the prediction accuracy score of the power grid fault (i.e., the second score) is calculated. The second score reflects the effectiveness of the emergency mechanism in predicting power grid faults.

[0071] Optionally, the determining the second prediction accuracy of the power grid fault according to the power grid state log comprises:

[0072] extracting first features related to the power grid fault from the meteorological log, the first features including the occurrence time, intensity, and duration of extreme natural weather, and extracting second features reflecting the state of the power grid from the power grid state log, the second features including load change trends, equipment health conditions, and historical fault patterns;

[0073] inputting the first features and the second features into a preset fault prediction model to obtain power grid fault prediction data, the power grid fault prediction data including predicted occurrence time, predicted occurrence location, and predicted occurrence type;

[0074] determining the second prediction accuracy according to the power grid fault prediction data and actual fault data.

[0075] Identify and record the occurrence times of extreme natural weather events (such as storms, lightning, high temperatures, etc.) that could potentially impact the power grid from meteorological logs. These time points are key references for predicting when a power grid failure might occur. In addition to the occurrence times, the intensity and duration of these extreme natural weather events also need to be recorded. This information is crucial for assessing their potential impact on the power grid. Analyze the load data of the power grid to identify daily, weekly, monthly, or seasonal trends in load changes. Sharp changes in load can be a precursor to power grid failures. Extract health status information of critical equipment in the power grid through monitoring systems and maintenance records. Aging, damage, or abnormal operation of equipment can increase the risk of power grid failures. Review past power grid failure records to analyze the types, locations, causes, and correlations between them. These historical data help identify weak links in the power grid and common failure patterns. Input the extracted first and second features into a pre-set power grid failure prediction model. This model can be a complex machine learning or deep learning model that has been trained and optimized with a large amount of historical data. The model outputs predicted power grid failure data based on the input features. These data include predicted occurrence times, predicted occurrence locations, and predicted occurrence types. The predicted time can be a specific date and time point, or a time period; the predicted location can be a specific device or area in the power grid; and the predicted type refers to the specific nature of the failure (such as short circuit, open circuit, overload, etc.). Compare the predicted data with the actual data: compare the predicted occurrence times with the actual occurrence times, the predicted occurrence locations with the actual occurrence locations, and the predicted occurrence types with the actual occurrence types. Based on the comparison results, calculate a series of accuracy indicators to evaluate the accuracy of the prediction. These indicators may include the average or median value of the time difference, the location matching rate, the type matching rate, etc. In addition, more complex evaluation methods such as confusion matrix, ROC curve, etc. can be used to comprehensively evaluate the performance of the prediction model. Synthesize the various accuracy indicators to form a comprehensive evaluation of the accuracy of power grid failure prediction. This evaluation result reflects the effectiveness and reliability of the pre-set failure prediction model in predicting power grid failures.

[0076] By combining extreme natural weather information (such as occurrence time, intensity, and duration) from meteorological logs and specific state information (such as load change trends, equipment health, and historical failure patterns) from grid state logs, a more comprehensive consideration of various factors affecting grid failures can be achieved. This multi-source data fusion approach helps to improve the accuracy and reliability of grid failure prediction. Based on the predicted failure information, grid operators can more effectively allocate human, material, and financial resources to ensure rapid response and power restoration in the event of a failure. This helps to reduce failure handling costs and improve resource utilization efficiency. Accurate failure prediction data provides strong support for grid planning, construction, and operation. Based on these data, grid managers can make more scientific decisions, optimize grid structure, and improve the overall performance and disaster resistance of the grid.

[0077] Optionally, the second prediction accuracy is determined according to the grid failure prediction data and actual failure data, including:

[0078] A third difference value between the grid failure prediction occurrence time and the actual grid failure occurrence time is determined to obtain a fourth sub-score, a fourth difference value between the grid failure prediction location and the actual grid failure occurrence location is determined to obtain a fifth sub-score, and a sixth sub-score is determined according to the grid failure prediction type and the actual grid failure type.

[0079] The second target prediction event sub-prediction accuracy is determined according to the fourth sub-score, the fifth sub-score, and the sixth sub-score, and the second prediction accuracy is obtained by weighted summation of the second target prediction event sub-prediction accuracy according to the grid failure prediction type.

[0080] A difference between the predicted occurrence time of the power grid fault and the actual occurrence time of the power grid fault is calculated, which is referred to as a third difference. It reflects the accuracy of the prediction in time. According to the size of the third difference, a scoring standard can be set to determine a fourth sub-score. Generally speaking, the smaller the difference, the more accurate the predicted time, and the higher the fourth sub-score. A difference or distance between the predicted location of the power grid fault and the actual occurrence location of the power grid fault is calculated, which is referred to as a fourth difference. It reflects the accuracy of the prediction in spatial location. Similarly, according to the size of the fourth difference, a scoring standard can be set to determine a fifth sub-score. The smaller the difference, the more accurate the predicted location, and the higher the fifth sub-score. For the comparison of the predicted type of the power grid fault and the actual occurrence type of the power grid fault, if they are completely consistent, the highest sixth sub-score can be given; if they are partially consistent or inconsistent, the corresponding score can be given according to the specific circumstances. This score reflects the accuracy of the prediction in type identification. Based on the sub-scores of the three dimensions (the fourth sub-score, the fifth sub-score, and the sixth sub-score), the sub-prediction accuracy of each second target prediction event can be calculated. This is usually done by weighted averaging of the three sub-scores or according to other predetermined algorithms. Since different types of power grid faults may have different degrees of impact on the operation of the power grid, the sub-prediction accuracies of multiple second target prediction events can be weighted and summed according to the predicted type of the power grid fault when calculating the second prediction accuracy. This ensures that those fault types that have a greater impact on the operation of the power grid are given more attention in the evaluation of prediction accuracy. The result obtained by weighted summation is the second prediction accuracy, which comprehensively reflects the overall performance of the power grid fault prediction model in the three dimensions of time, location, and type.

[0081] By calculating the difference in each of the three dimensions of time, location, and type to determine the sub-scores (the fourth sub-score, the fifth sub-score, and the sixth sub-score), this method can more accurately reflect the deviation between the prediction and the actual situation. The evaluation of each dimension is independent, which helps to identify the performance of the prediction model in different aspects, thereby enabling more targeted optimization. Considering that different fault types may have different degrees of impact on the operation of the power grid, the weighted summation method is used to aggregate the sub-prediction accuracies of multiple second target prediction events, which can more reasonably reflect the overall prediction accuracy. This weighting method can be adjusted according to actual circumstances to better adapt to the needs of power grid operation. By comparing the predicted data with the actual data and calculating the second prediction accuracy, the shortcomings of the prediction model can be discovered in a timely manner. This feedback mechanism helps model developers to continuously optimize and improve the model, improving the reliability and accuracy of the prediction model.

[0082] S130, determining a processing capability value according to the fault response speed and the power recovery speed of processing the fault event, determining an influence level of the extreme natural weather corresponding to the fault event, and determining a third score according to the processing capability value and the influence level;

[0083] The fault response speed refers to the time interval from the occurrence of the fault event to the start of the countermeasures taken by the grid operator. A faster response speed generally means higher emergency response capability and shorter power outage time. Therefore, the fault response speed is an important indicator for measuring the processing capability of the grid. The power recovery speed refers to the time from the start of the fault to the recovery of normal power supply of the grid. The power recovery speed not only reflects the maintenance efficiency of the grid operator, but also directly relates to the power experience of the users. A faster power recovery speed can reduce the impact of power outage on users and improve user satisfaction. Based on the fault response speed and the power recovery speed, a processing capability value can be calculated. This value can be the weighted sum of the two speeds, or it can be some combination of their respective scores. The higher the processing capability value, the better the performance of the grid in responding to fault events. Extreme natural weather includes but is not limited to strong wind, heavy rain, lightning, hail, snowstorm and other extreme weather conditions. These weather conditions may cause damage to grid facilities, leading to the occurrence of fault events. According to the intensity, duration and actual impact of extreme natural weather on grid facilities, it can be divided into different influence levels. The higher the influence level, the greater the destructive power of extreme natural weather on the grid, and the higher the possibility and severity of fault events. After determining the processing capability value and the influence level of the extreme natural weather, these two factors can be combined for comprehensive evaluation. One possible method is to consider the processing capability value as a positive factor of the grid response capability, and consider the influence level as a negative factor. Through some algorithm (such as weighted sum, product method, etc.), these two factors are transformed into a comprehensive evaluation score, i.e. the third score. The third score reflects the overall performance of the grid in responding to fault events under specific extreme natural weather conditions. It not only considers the processing capability of the grid itself, but also considers the impact of external weather conditions on the operation of the grid. Therefore, the third score is a more comprehensive and objective evaluation indicator, which can provide valuable reference information for grid managers.

[0084] Optionally, the determination of the processing capability value according to the fault response speed and the power recovery speed of processing the fault event comprises:

[0085] The first time of the occurrence of the fault is obtained, the second time of the arrival of the maintenance personnel at the scene to start processing the fault is obtained, and the third time of the recovery of power supply is obtained;

[0086] The fault response speed is determined according to the first time and the second time, the power restoration speed is determined according to the second time and the third time, and the processing capacity value is obtained by weighted sum of the fault response speed and the power restoration speed.

[0087] The first time (time of fault occurrence): This refers to the time point when the fault event actually occurs. This time point marks the beginning of the fault event and is the starting point of all subsequent processing activities. The second time (time of maintenance personnel arrival): This refers to the time point when the power grid maintenance personnel arrive at the fault site and begin to handle the fault. The interval between this time point and the time of fault occurrence reflects the response speed of the power grid operator to the fault event. The third time (time of power restoration): This refers to the time point when the power grid restores normal power supply. The interval between this time point and the time of maintenance personnel arrival reflects the efficiency of the maintenance work and the speed of power restoration. Fault response speed: It can usually be obtained by calculating the difference between the second time and the first time. The smaller this difference, the faster the response speed of the power grid operator to the fault event. Power restoration speed: It can be obtained by calculating the difference between the third time and the second time. The smaller this difference, the higher the efficiency of the maintenance work and the faster the speed of power restoration.

[0088] Since the importance of fault response speed and power restoration speed may be different in evaluating the processing capacity of the power grid, it is necessary to perform weighted sum on them. The allocation of weights can be determined according to actual conditions and the needs of the power grid operator. For example, if the fault response speed is considered more important, it can be given a higher weight. The result of weighted sum is the processing capacity value. The processing capacity value comprehensively reflects the overall performance of the power grid in dealing with fault events, including response speed and power restoration speed. The higher the processing capacity value, the stronger the processing capacity of the power grid. By comparing the processing capacity values of different time periods, different regions or different power grids, the operation efficiency and emergency response capacity of the power grid can be evaluated. The processing capacity value can be used as a reference for the power grid manager to develop improvement measures, optimize resource allocation and improve emergency response capacity. At the same time, it can also be used as an important indicator for users to evaluate the service quality of the power grid.

[0089] By quantifying key time nodes in the fault handling process, such as the time of fault occurrence, the time of maintenance personnel arrival, and the time of power restoration, the evaluation of the power grid handling capacity becomes more objective and specific. This quantitative evaluation method helps to reduce the influence of subjective judgment and improve the accuracy and reliability of the evaluation results. Both the fault response speed and the power restoration speed are considered, which reflect the emergency response capability and maintenance recovery capability of the power grid after the fault occurs. By considering both aspects comprehensively, the overall performance of the power grid in fault handling can be evaluated more comprehensively. The fault response speed and the power restoration speed are weighted and summed to obtain the handling capacity value. This weighted sum method can adjust the weights according to the actual situation to reflect the importance of different dimensions in the evaluation. For example, in some cases, the power restoration speed may be more important, so it can be given a higher weight. This flexibility makes the evaluation results more in line with actual needs. By evaluating the handling capacity value of the power grid regularly or irregularly, the power grid managers can understand the performance of the power grid in fault handling in a timely manner and take improvement measures accordingly. This helps to improve the management efficiency of the power grid and reduce the impact of faults on the operation of the power grid.

[0090] Optionally, the determining the influence level of the extreme natural weather corresponding to the fault event according to the handling capacity value and the influence level comprises:

[0091] determining the type and intensity of the extreme natural weather corresponding to the fault event, matching a preset influence level according to the type and intensity, and multiplying the preset influence level by the handling capacity value to obtain the third score.

[0092] According to the experience of grid operators or industry standards, there is a preset extreme weather impact level table. In this table, different types of extreme weather and their different intensities correspond to different impact levels. For example, a strong storm with high intensity may be assigned a higher impact level, such as level 5 (assuming impact levels are represented by numbers 1-5, with 5 being the highest). According to the method described earlier, the first time of fault occurrence, the second time of maintenance personnel arriving at the scene, and the third time of power restoration are obtained. Through calculation, the fault response speed is X hours / minutes, and the power restoration speed is Y hours / minutes. Then, the two speeds are weighted and summed (assuming the weight of the fault response speed is 0.6 and the weight of the power restoration speed is 0.4), and the processing capacity value Z is obtained. The impact level is converted into a coefficient (for example, level 5 corresponds to a coefficient of 1.5, which can be set according to actual conditions), and then the coefficient is multiplied by the processing capacity value to obtain the third score. Third score = processing capacity value Z * impact level coefficient (1.5). For example, the processing capacity value Z is 80 (this is a hypothetical value, and the actual calculation will be based on specific data), and the impact level coefficient is 1.5, then: Third score = 80 * 1.5 = 120.

[0093] The embodiment of the present application not only considers the processing capacity of the power grid itself (i.e. fault response speed and power restoration speed), but also considers the impact of external extreme natural weather. By combining the two, the overall performance of the power grid under specific conditions can be more comprehensively evaluated. By determining the type and intensity of the extreme natural weather corresponding to the fault event and matching the preset impact level, the precise quantification of external factor influence can be achieved. This quantification method helps to reduce the uncertainty of subjective judgment and improve the accuracy and objectivity of the evaluation results. Multiplying the preset impact level by the processing capacity value to obtain the third score, this weighted multiplication method can reflect the degree of influence of external factors (extreme natural weather) on the processing capacity of the power grid. The higher the impact level, the greater the negative impact of external factors on the power grid, so the result after multiplication will also decrease accordingly, thus more accurately reflecting the actual performance of the power grid under specific conditions. By calculating the third score, the power grid managers can more clearly understand the performance of the power grid in response to different extreme natural weather conditions. This helps them make more scientific and reasonable decisions, such as optimizing resource allocation, strengthening equipment maintenance, and improving emergency response capabilities, to better cope with future possible fault events. The calculation result of the third score provides a quantifiable evaluation index for the power grid managers to evaluate the performance of the power grid in fault handling. By calculating the third score regularly or irregularly and comparing it with historical data, the power grid managers can timely find the shortcomings of the power grid in dealing with extreme natural weather and take corresponding improvement measures to continuously improve the reliability and stability of the power grid.

[0094] S140, obtaining public opinion attitude on the handling of the failure event on social media, determining a fourth score according to the public opinion attitude, the public opinion attitude including positive, neutral and negative;

[0095] Social media platforms, such as Weibo, Twitter, Facebook, etc., are important channels for public to express opinions and attitudes. By monitoring and collecting posts, comments and shared content related to the handling of a specific failure event on these platforms, a large amount of user feedback can be obtained. The collected social media data needs to be analyzed for sentiment to determine the public's attitude towards the handling of the failure event. These attitudes can usually be divided into positive, negative and neutral. Positive attitude: indicates that the public is satisfied with the handling result of the failure event, considers that the handling is timely and effective, or expresses appreciation for the responsibility and professionalism shown in the handling process. Neutral attitude: indicates that the public has no special emotional tendency towards the handling of the failure event, which may be due to lack of enough information to form a clear point of view, or considers that the handling is neither particularly good nor particularly bad. Negative attitude: indicates that the public is not satisfied with the handling result of the failure event, considers that the handling is not timely and effective, or criticizes and blames the problems in the handling process. According to the classified public opinion attitude, an evaluation score (fourth score) can be calculated to quantify the overall evaluation of the public on the handling of the failure event. The calculation method of this score can be designed according to actual needs, but usually the number, proportion and their respective weights of various attitude types are considered. For example, a higher score can be given to positive attitude, a lower score to negative attitude, and neutral attitude is adjusted according to its proportion in the whole. Through weighted summation or other statistical methods, a fourth score that comprehensively reflects the public's attitude can be obtained. The calculation result of the fourth score can provide valuable feedback for power grid managers. By understanding the public's views and attitudes towards the handling of the failure event, managers can evaluate whether their response measures are appropriate and whether there is room for improvement. At the same time, these information can also be used as an important reference for formulating similar event handling strategies in the future.

[0096] Optionally, the obtaining public opinion attitude on the handling of the failure event on social media, determining a fourth score according to the public opinion attitude includes:

[0097] Using crawler technology or social media interface to grab social media data containing keywords of the failure event, the keywords including failure name, location, time, power supply enterprise name, repair, recovery, the social media data including posts, comments, forwards;

[0098] Performing sentiment analysis on the social media data to identify sentiment tendency and intensity, the sentiment tendency including positive, negative and neutral, the intensity including praise, satisfaction, recognition, criticism, dissatisfaction, complaint;

[0099] According to the emotional tendency and intensity, determine the public opinion score of each piece of content in the social media data, and obtain the fourth score by weighted average of all contents.

[0100] Determine a series of keywords related to the fault event, such as "XX city power failure", "XX road power failure", "XX power supply company repair", "power restoration", etc. Use crawler technology or social media interface: select appropriate tools (such as Scrapy framework of Python, Twitter API, Weibo API, etc.), search and crawl related posts, comments and forwarding data on social media platforms (such as Weibo, WeChat, TikTok, Twitter, etc.) according to the above keywords. Remove irrelevant content such as advertisements and spam. Process the crawled text by removing duplicates, noise, converting to lowercase (if applicable), and unifying encoding. Select appropriate sentiment analysis tools: use natural language processing (NLP) libraries (such as NLTK, jieba segmentation + SnowNLP, Baidu AI open platform, etc.) to perform sentiment analysis on the preprocessed text. If positive sentiment words and phrases such as "quick repair", "service in place", "timely power restoration" are identified, the content is classified as positive attitude. If negative sentiment words and phrases such as "slow handling", "poor service", "long power outage time" are identified, the content is classified as negative attitude. If the content cannot be clearly classified as positive or negative, or the content itself is objective and has no emotional color, the content is classified as neutral attitude. At the same time, the emotional intensity of each piece of content is evaluated, for example, some praise may be light, while some complaints may be very strong. According to the emotional tendency and intensity, assign a public opinion score to each piece of social media content. For example, set the highest score for positive emotion as 5 points, neutral as 3 points, and the lowest score for negative emotion as 1 point (or adjust according to specific circumstances), and fine-tune according to the emotional intensity. Weighted average of all content public opinion scores to calculate the fourth score of the overall public opinion attitude on social media about the handling of this fault event. When weighted average, consider the exposure of each piece of content (such as likes and forwards) as a weight factor to more accurately reflect the overall trend of public opinion. For example, the fourth score of the handling of this fault event is calculated as 3.5 points (full score 5 points), indicating that the public has a certain positive view of the handling of the fault event, but there is still a certain degree of dissatisfaction and complaints.

[0101] By performing sentiment analysis on the scraped social media data, the sentiment orientation (positive, negative, neutral) and intensity (praise, satisfaction, recognition, criticism, dissatisfaction, complaint) of the public towards the handling of the fault event can be accurately identified. This sentiment analysis technology can deeply explore the real attitude and emotion of the public, providing a more objective and accurate basis for evaluation. According to the sentiment orientation and intensity, the public opinion score of each social media content is determined, and the weighted average of all contents is obtained to get the fourth score. This process realizes the quantitative evaluation of public opinion attitude. This quantitative evaluation method makes the evaluation result more scientific, objective and comparable, which helps the power grid managers to more accurately understand the public's view and attitude towards the handling of the fault event. By obtaining and analyzing the public opinion attitude on social media, power grid managers can more comprehensively understand the feedback and opinions of the public towards the handling of the fault event. This helps them to timely find problems, adjust strategies, optimize services, and better meet the needs and expectations of the public. At the same time, the fourth score as a comprehensive evaluation index can also provide decision support for power grid managers, helping them to make more scientific and reasonable decisions.

[0102] S150, the first score, the second score, the third score and the fourth score are weighted and summed to obtain a total score of the emergency mechanism to be evaluated, and the emergency mechanism to be evaluated is evaluated according to the total score.

[0103] The first score, the second score, the third score and the fourth score are given different weights in the evaluation process to reflect their respective importance in the overall evaluation. The allocation of weights can be adjusted according to actual conditions and evaluation goals. For example, if the evaluation focuses on emergency response speed and recovery ability, the weight of the third score may be relatively high. The total score is used to determine the pros and cons of the emergency mechanism to be evaluated.

[0104] The embodiment also discloses an evaluation system for an extreme natural weather emergency mechanism, Figure 2 is a module schematic diagram of the evaluation system for the extreme natural weather emergency mechanism disclosed by the embodiment of the present application, as Figure 2 shown, the evaluation system includes a weather module 201, a power grid module 202, a processing module 203, an opinion module 204 and an evaluation module 205, wherein:

[0105] The weather module 201 is configured to obtain a meteorological log in an emergency mechanism to be evaluated, determine a first prediction accuracy of extreme natural weather according to the meteorological log, and determine a first score according to the first prediction accuracy, the meteorological log comprising daily actual meteorological data and meteorological prediction data in a preset time period, and the extreme natural weather comprising temperature higher than a first temperature preset value or lower than a second temperature preset value, precipitation greater than a first precipitation preset value or less than a second precipitation preset value, wind power greater than a wind power preset value, and a preset type of precipitation;

[0106] The power grid module 202 is configured to obtain a power grid state log in an emergency mechanism to be evaluated, determine a second prediction accuracy of power grid failure according to the power grid state log, and determine a second score according to the second prediction accuracy, the power grid state log comprising daily working data of the power grid and power grid failure prediction data generated in combination with the meteorological log;

[0107] The processing module 203 is configured to determine a processing capacity value according to a fault response speed and a power supply recovery speed in processing a fault event, determine an influence level of extreme natural weather corresponding to the fault event, and determine a third score according to the processing capacity value and the influence level;

[0108] The public opinion module 204 is configured to obtain a public opinion attitude on the processing of the fault event on a social media, and determine a fourth score according to the public opinion attitude, the public opinion attitude comprising positive, neutral and negative;

[0109] The evaluation module 205 is configured to obtain a total score of the emergency mechanism to be evaluated by weighted sum of the first score, the second score, the third score and the fourth score, and evaluate the emergency mechanism to be evaluated according to the total score.

[0110] Optionally, the weather module 201 is configured to:

[0111] determine a first sub-score according to a first difference between a predicted occurrence time of extreme natural weather and an actual occurrence time of extreme natural weather, determine a second sub-score according to a second difference between a predicted intensity of extreme natural weather and an actual intensity of extreme natural weather, and determine a third sub-score according to a predicted type of extreme natural weather and an actual type of extreme natural weather;

[0112] determine a sub-prediction accuracy of a first target prediction event according to the first sub-score, the second sub-score and the third sub-score, and obtain the first prediction accuracy according to an average value of sub-prediction accuracies of a plurality of first target prediction events.

[0113] Optionally, the power grid module 202 is configured to:

[0114] extracting a first feature related to the power grid failure from the meteorological log, the first feature including occurrence time, intensity and duration of extreme natural weather, extracting a second feature reflecting power grid state from the power grid state log, the second feature including load change trend, device health status and historical failure mode;

[0115] inputting the first feature and the second feature into a preset failure prediction model to obtain power grid failure prediction data, the power grid failure prediction data including predicted occurrence time, predicted occurrence location and predicted occurrence type;

[0116] determining the second prediction accuracy according to the power grid failure prediction data and actual failure data.

[0117] Optionally, the power grid module 202 is configured to:

[0118] determining a fourth sub-score according to a third difference between the predicted occurrence time of the power grid failure and the actual occurrence time of the power grid failure, determining a fifth sub-score according to a fourth difference between the predicted occurrence location of the power grid failure and the actual occurrence location of the power grid failure, and determining a sixth sub-score according to a difference between the predicted occurrence type of the power grid failure and the actual occurrence type of the power grid failure;

[0119] determining a sub-prediction accuracy of a second target prediction event according to the fourth sub-score, the fifth sub-score and the sixth sub-score, and performing weighted summation on the sub-prediction accuracies of a plurality of second target prediction events according to the predicted occurrence type of the power grid failure to obtain the second prediction accuracy.

[0120] Optionally, the processing module 203 is configured to:

[0121] obtaining a first time of failure occurrence, a second time of repair personnel arriving at the scene to start processing the failure, and a third time of power recovery;

[0122] determining a failure response speed according to the first time and the second time, determining a power recovery speed according to the second time and the third time, and performing weighted summation on the failure response speed and the power recovery speed to obtain a processing capability value.

[0123] Optionally, the processing module 203 is configured to:

[0124] determining a type and intensity of extreme natural weather corresponding to the failure event, matching a preset influence level according to the type and intensity, and multiplying the preset influence level and the processing capability value to obtain a third score.

[0125] Optionally, the public opinion module 204 is configured to:

[0126] Utilizing a crawler technique or a social media interface, social media data containing keywords of the fault event are captured, the keywords including fault name, location, time, power supply enterprise name, repair, recovery, the social media data including posts, comments, forwards;

[0127] Performing sentiment analysis on the social media data to identify sentiment tendency and intensity, the sentiment tendency including positive, negative and neutral, the intensity including praise, satisfaction, recognition, criticism, dissatisfaction, complaint;

[0128] Determining an opinion score of each piece of content in the social media data according to the sentiment tendency and intensity, and obtaining the fourth score by weighted average of all the contents.

[0129] It should be noted that: the apparatus provided in the above embodiments, when realizing its functions, only takes the above-mentioned division of each functional module as an example, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0130] The embodiment also discloses an electronic device, referring to Figure 3 The electronic device can include: at least one processor 301, at least one communication bus 302, a user interface 303, a network interface 304, and at least one memory 305.

[0131] The communication bus 302 is used to realize the connection and communication between the components.

[0132] The user interface 303 can include a display screen (Display) and a camera (Camera), and the optional user interface 303 can also include a standard wired interface and a wireless interface.

[0133] The network interface 304 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0134] The processor 301 can include one or more processing cores. The processor 301 connects various parts within the server through various interfaces and lines, performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Alternatively, the processor 301 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interfaces, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be realized by a separate chip.

[0135] The memory 305 can include a random access memory (RAM) and a read-only memory (ROM). Alternatively, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 305 can also be at least one storage device located away from the aforementioned processor 301. As shown in the figure, the memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of the evaluation method of the extreme natural weather emergency mechanism. Figure 3 As shown in the figure, the memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of the evaluation method of the extreme natural weather emergency mechanism.

[0136] In Figure 3In the electronic device shown, the user interface 303 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 301 can be used to invoke an application program stored in the memory 305 and storing the evaluation method of the extreme natural weather emergency mechanism, which, when executed by one or more processors 301, causes the electronic device to perform the method of one or more of the above-described embodiments.

[0137] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0138] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0139] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic. The division of the units is only a logical function division. There can be another division manner for actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different parts can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical or other forms.

[0140] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0141] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0142] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory 305 and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory 305 includes: a U disk, a mobile hard disk, a magnetic or optical disk and various media that can store program codes.

[0143] The above is only exemplary embodiments of the present disclosure, which cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the disclosure. The present application is intended to cover any variations, uses or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the art that are not described in the present disclosure. The scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for evaluating an emergency mechanism for extreme natural weather, characterized by, The evaluation method is applied to a power grid management platform and comprises the following steps: obtaining meteorological logs in an emergency mechanism to be evaluated, determining a first prediction accuracy of extreme natural weather according to the meteorological logs, and determining a first score according to the first prediction accuracy, wherein the meteorological logs comprise daily actual meteorological data and meteorological prediction data in a preset time period, and the extreme natural weather comprises temperature higher than a first temperature preset value or lower than a second temperature preset value, precipitation greater than a first precipitation preset value or less than a second precipitation preset value, wind power greater than a wind power preset value, and precipitation of a preset type; obtaining power grid state logs in the emergency mechanism to be evaluated, determining a second prediction accuracy of power grid failure according to the power grid state logs, and determining a second score according to the second prediction accuracy, wherein the power grid state logs comprise daily working data of the power grid and power grid failure prediction data generated in combination with the meteorological logs; determining a processing capacity value according to a fault response speed and a power supply recovery speed in processing a fault event, determining an influence level of extreme natural weather corresponding to the fault event, and determining a third score according to the processing capacity value and the influence level; obtaining public opinion attitudes on the processing of the fault event on a social media, and determining a fourth score according to the public opinion attitudes, wherein the public opinion attitudes comprise positive, neutral, and negative; performing weighted summation on the first score, the second score, the third score, and the fourth score to obtain a total score of the emergency mechanism to be evaluated, and evaluating the emergency mechanism to be evaluated according to the total score, the first prediction accuracy of extreme natural weather according to the meteorological logs comprises: determining a first sub-score according to a first difference between a predicted occurrence time of extreme natural weather and an actual occurrence time of extreme natural weather, determining a second sub-score according to a second difference between a predicted intensity of extreme natural weather and an actual intensity of extreme natural weather, and determining a third sub-score according to a predicted type of extreme natural weather and an actual occurrence type of extreme natural weather; determining a sub-prediction accuracy of a first target prediction event according to the first sub-score, the second sub-score, and the third sub-score, and obtaining the first prediction accuracy according to an average value of sub-prediction accuracies of a plurality of first target prediction events, the second prediction accuracy of power grid failure according to the power grid state logs comprises: extracting first features related to power grid failure from the meteorological logs, wherein the first features comprise occurrence time, intensity, and duration of extreme natural weather, and extracting second features reflecting power grid state from the power grid state logs, wherein the second features comprise load change trend, equipment health status, and historical failure mode; inputting the first features and the second features into a preset failure prediction model to obtain power grid failure prediction data, wherein the power grid failure prediction data comprises predicted occurrence time, predicted occurrence location, and predicted occurrence type; determining the second prediction accuracy according to the power grid failure prediction data and actual failure data.

2. The method of claim 1, wherein, the second prediction accuracy according to the power grid failure prediction data and actual failure data comprises: determine a fourth sub-score according to a third difference value between a predicted occurrence time of the power grid fault and an actual occurrence time of the power grid fault, determine a fifth sub-score according to a fourth difference value between a predicted location of the power grid fault and an actual occurrence location of the power grid fault, and determine a sixth sub-score according to a predicted type of the power grid fault and an actual occurrence type of the power grid fault; determine a sub-prediction accuracy of a second target prediction event according to the fourth sub-score, the fifth sub-score, and the sixth sub-score, and perform a weighted summation on the sub-prediction accuracies of a plurality of the second target prediction events according to the predicted types of the power grid faults to obtain a second prediction accuracy.

3. The assessment method for extreme natural weather emergency mechanisms according to claim 1, characterized in that, The determining of the processing capability value according to the fault response speed and the power recovery speed in processing the fault event includes: obtaining a first time of the fault occurrence, a second time of a repair personnel arriving at a scene to start processing the fault, and a third time of the power recovery; determining a fault response speed according to the first time and the second time, determining a power recovery speed according to the second time and the third time, and performing a weighted summation on the fault response speed and the power recovery speed to obtain the processing capability value.

4. The method of claim 3, wherein the extreme natural weather emergency mechanism is a hurricane. The determining of the influence level of the extreme natural weather corresponding to the fault event and the determining of the third score according to the processing capability value and the influence level include: determining a type and intensity of the extreme natural weather corresponding to the fault event, matching a preset influence level according to the type and intensity, and multiplying the preset influence level and the processing capability value to obtain the third score.

5. The evaluation method for extreme natural weather emergency mechanisms according to claim 1, characterized in that, The obtaining of the public opinion attitude on the processing situation of the fault event on the social media and the determining of the fourth score according to the public opinion attitude include: using a crawler technology or a social media interface to capture social media data containing a keyword of the fault event, the keyword including a fault name, a location, a time, a power supply enterprise name, a repair, and a recovery, the social media data including posts, comments, and forwards; performing sentiment analysis on the social media data to identify sentiment tendencies and intensities, the sentiment tendencies including positive, negative, and neutral, and the intensities including praise, satisfaction, recognition, criticism, dissatisfaction, and complaint; determining a public opinion score of each content in the social media data according to the sentiment tendencies and intensities, and performing a weighted average on all the contents to obtain the fourth score.

6. An evaluation system of extreme natural weather emergency mechanism, characterized in that, The system includes a weather module, a power grid module, a processing module, a public opinion module, and an evaluation module, wherein: the weather module is configured to obtain a meteorological log in a to-be-evaluated emergency mechanism, determine a first prediction accuracy of extreme natural weather according to the meteorological log, and determine a first score according to the first prediction accuracy, the meteorological log including daily actual meteorological data and meteorological prediction data in a preset time period, and the extreme natural weather including a temperature higher than a first temperature preset value or lower than a second temperature preset value, a precipitation greater than a first precipitation preset value or less than a second precipitation preset value, a wind power greater than a wind power preset value, and a preset type of precipitation. a power grid module configured to obtain a power grid state log in an emergency mechanism to be evaluated, determine a second prediction accuracy of a power grid failure according to the power grid state log, and determine a second score according to the second prediction accuracy, the power grid state log including daily operation data of a power grid and power grid failure prediction data generated in combination with the weather log; a processing module configured to determine a processing capability value according to a fault response speed and a power supply recovery speed in processing a fault event, determine an influence level of an extreme natural weather corresponding to the fault event, and determine a third score according to the processing capability value and the influence level; an opinion module configured to obtain an opinion attitude on the processing of the fault event on a social media, and determine a fourth score according to the opinion attitude, the opinion attitude including positive, neutral and negative; an evaluation module configured to perform weighted summation on the first score, the second score, the third score and the fourth score to obtain a total score of the emergency mechanism to be evaluated, and evaluate the emergency mechanism to be evaluated according to the total score, the weather module is configured to: determine a first sub-score according to a first difference between a predicted occurrence time of an extreme natural weather and an actual occurrence time of the extreme natural weather, determine a second sub-score according to a second difference between a predicted intensity of the extreme natural weather and an actual intensity of the extreme natural weather, and determine a third sub-score according to a predicted type of the extreme natural weather and an actual type of the extreme natural weather; determine a sub-prediction accuracy of a first target prediction event according to the first sub-score, the second sub-score and the third sub-score, and obtain a first prediction accuracy according to an average value of sub-prediction accuracies of a plurality of the first target prediction events, the power grid module is configured to: extract a first feature related to a power grid failure from the weather log, the first feature including an occurrence time, an intensity and a duration of an extreme natural weather, and extract a second feature reflecting a power grid state from the power grid state log, the second feature including a load change trend, a device health status and a historical failure mode; input the first feature and the second feature into a preset failure prediction model to obtain power grid failure prediction data, the power grid failure prediction data including a predicted occurrence time, a predicted occurrence location and a predicted occurrence type; determine the second prediction accuracy according to the power grid failure prediction data and actual failure data.

7. An electronic device, comprising: The electronic device includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to enable the electronic device to perform the method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions which, when executed, perform the method of any one of claims 1-5.

Images