Risk assessment method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a risk assessment method and device, computer equipment, a storage medium and a program product. The method comprises the steps of obtaining a target power risk event in power risk events occurring in a power system and a corresponding evaluation index model; the evaluation index model is constructed by hierarchical structures of evaluation indexes of different levels; and evaluating the target power risk event according to the evaluation index model to obtain an evaluation result. The evaluation index model is constructed by the hierarchical structures of the evaluation indexes of different levels, so that a more comprehensive and accurate evaluation index model can be constructed based on the hierarchical structures of the evaluation indexes of different levels; therefore, the target electric power risk event in the electric power operation can be comprehensively and multi-dimensionally evaluated according to the more comprehensive and accurate evaluation index model, so that the comprehensiveness, accuracy and credibility of personal risk evaluation in the electric power operation process can be improved.

Description

Technical Field

[0001] This application relates to the technical field of power safety, and particularly to a risk assessment method, device, computer device, storage medium, and program product. Background Art

[0002] With the continuous expansion of the power grid scale, the power grid operation scenarios are becoming increasingly complex, resulting in more and more difficulties and challenges for technicians in actual operations, and thus personal risk events may occur. Therefore, it is necessary to evaluate the risk events in power operations in advance to guide power units at all levels to do a good job in personal safety control.

[0003] However, the traditional risk assessment method has the problem of low assessment accuracy. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a risk assessment method, device, computer device, storage medium, and program product that can improve the assessment accuracy of the risk assessment method.

[0005] In a first aspect, this application provides a risk assessment method, including:

[0006] Obtain a target power risk event in the power risk events that occur in the power system, and the corresponding evaluation index model; the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels;

[0007] Evaluate the target power risk event according to the evaluation index model to obtain an evaluation result.

[0008] In one embodiment, the evaluating the target power risk event according to the evaluation index model to obtain an evaluation result includes:

[0009] Input the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain the evaluation result; the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

[0010] In one embodiment, the method further includes:

[0011] Obtain the event tree information corresponding to the power risk events that occur in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information;

[0012] Determine the evaluation index model according to the event tree information.

[0013] In one embodiment, the evaluation of the target power risk event according to the evaluation index model to obtain an evaluation result includes:

[0014] Extract evaluation indexes at all levels from the evaluation index model, and generate an index scoring table according to the evaluation indexes at all levels;

[0015] Display the index scoring table on the current interface, and in response to the user's evaluation operation on the index scoring table, obtain a scoring result according to the evaluation operation;

[0016] Evaluate the target power risk event according to the scoring result to obtain the evaluation result.

[0017] In one embodiment, the evaluation of the target power risk event according to the scoring result to obtain the evaluation result includes:

[0018] Perform a consistency test on the judgment matrix corresponding to the scoring result to obtain a test result;

[0019] In the case where the test result indicates that the test passes, determine the weight vector of the evaluation indexes at all levels according to the judgment matrix;

[0020] Multiply the weight vectors of the evaluation indexes at all levels to obtain the evaluation result.

[0021] In one embodiment, the method further includes:

[0022] Return to execute the step of obtaining the target power risk event among the power risk events occurring in the power system until the evaluation of all basic events in the power risk events is completed to obtain the target evaluation result.

[0023] In a second aspect, the present application further provides a risk assessment device, including:

[0024] An acquisition module, configured to acquire a target power risk event among the power risk events occurring in the power system, and a corresponding evaluation index model; the evaluation index model is constructed by a hierarchical structure of evaluation indexes at different levels;

[0025] An evaluation module, configured to evaluate the target power risk event according to the evaluation index model to obtain an evaluation result.

[0026] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method in any one of the embodiments in the first aspect when executing the computer program.

[0027] Fourthly, the present application also provides a computer-readable storage medium. On the computer-readable storage medium, a computer program is stored, and when the computer program is executed by a processor, the steps of the method in any one of the embodiments of the first aspect are implemented.

[0028] Fifthly, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the embodiments of the first aspect are implemented.

[0029] For the above risk assessment method, device, computer device, storage medium and program product, a target power risk event in the power risk events occurring in the power system is obtained, as well as the corresponding evaluation index model; the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels; the target power risk event is evaluated according to the evaluation index model to obtain an evaluation result. Since the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels, the embodiments of the present application can determine the hierarchical structure of evaluation indexes at different levels from multiple aspects such as human factors, material factors, environmental factors, and management factors, and construct a more comprehensive and accurate evaluation index model, so that the target power risk event in power operation can be comprehensively and multi-dimensionally evaluated according to the more comprehensive and accurate evaluation index model, and thus the comprehensiveness, accuracy and credibility of personal risk assessment in the power operation process can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required to be used in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is an application environment diagram of the risk assessment method in an embodiment;

[0032] Figure 2 It is a flowchart of the risk assessment method in an embodiment;

[0033] Figure 3 It is a structural diagram of a fault tree in an embodiment;

[0034] Figure 4 It is a flowchart of the evaluation steps in an embodiment;

[0035] Figure 5 It is a schematic diagram of a hierarchical structure model in an embodiment;

[0036] Figure 6 Schematic diagram of an index scoring table in an embodiment;

[0037] Figure 7 Schematic diagram of an index scoring table in another embodiment;

[0038] Figure 8 Schematic diagram of an evaluation result obtained by using the analytic hierarchy process in an embodiment;

[0039] Figure 9 Schematic diagram of an evaluation result obtained by using a preset risk assessment model in an embodiment;

[0040] Figure 10 Schematic flow chart of a risk assessment method in another embodiment;

[0041] Figure 11 Structural block diagram of a risk assessment device in an embodiment. Detailed implementation manners

[0042] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion.

[0044] In the description of the embodiments of this application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of this application, "a plurality of" means more than two, unless otherwise specifically defined.

[0045] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment may be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0046] With the continuous expansion of the power grid scale, the power grid operation scenarios are becoming increasingly complex, covering multiple aspects such as emergency repair, inspection and experiment, and daily maintenance. Each link requires technical personnel to execute, resulting in more and more difficulties and challenges for technical personnel in actual operation. For example, the operation area is vast, the tasks are cumbersome, and there are many participants, while the on-site supervision human resources are relatively scarce. In addition, some technical personnel lack safety awareness and have a weak safety concept, and even become accustomed to potential operation hazards. These factors together contribute to the frequent occurrence of violation behaviors, which may lead to accidental accidents in severe cases, directly endangering the lives of operation personnel, and thus may occur personal risk events. Therefore, it is necessary to evaluate the risk events in power operations in advance to guide power units at all levels to do a good job in personal safety control.

[0047] However, due to the bottleneck constraints in the links of information transmission, acquisition, and utilization, the traditional risk assessment method can only evaluate the risk events in power operations based on limited local information, resulting in incomplete risk understanding, poor timeliness, and difficulty in truly achieving advanced pre-control. Therefore, the traditional risk assessment method has the problem of low assessment accuracy.

[0048] After introducing the background technology of the risk assessment method provided by the embodiments of the present application as above, below, the implementation environment involved in the risk assessment method provided by the embodiments of the present application will be briefly described. The risk assessment method provided by the embodiments of the present application can be applied to, for example Figure 1In the computer device shown. The computer device can be a terminal, or it can also be a server. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements a risk assessment method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0049] Those skilled in the art can understand that Figure 1 The structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. A specific terminal may include more or fewer components than those shown in the figure, or combine some components, or have a different component arrangement.

[0050] In one embodiment, as Figure 2 shown, a risk assessment method is provided. Taking the method applied to the computer device in Figure 1 as an example for illustration, it includes the following steps:

[0051] S201, obtain the target power risk event in the power risk events occurring in the power system, and the corresponding evaluation index model; the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels.

[0052] Among them, the target power risk event refers to at least one power risk event among multiple power risk events. The evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels, and the evaluation indexes are predetermined based on the power risk events occurring in the power system.

[0053] In the embodiments of the present application, optionally, the computer device may obtain the target power risk event in the power risk events occurring in the power system in real time; or, the computer device may also obtain the target power risk event in the power risk events occurring in the power system from a database or a power grid management platform. In addition, the computer device may pre-obtain multiple evaluation indicators, and classify and summarize the above-mentioned multiple evaluation indicators into five aspects based on theoretical knowledge such as safety behavior science, psychology, and accident causation theory: human factors, equipment condition, material use, operation method, and environmental conditions, which is abbreviated as the "human-machine-material-method-environment method". Thus, the computer device may classify multiple evaluation indicators based on the classification result (i.e., combining the factors of people, objects, environment, and management), obtain evaluation indicators at different levels, and then construct an evaluation indicator model according to the hierarchical structure of the evaluation indicators at different levels, that is, obtain a three-layer indicator system for characterizing personal risks, laying a foundation for realizing accurate personal risk assessment and control. Of course, the embodiments of the present application do not limit the specific implementation manners of obtaining the target power risk event and the evaluation indicator model.

[0054] Exemplarily, the multiple evaluation indicators may include, but are not limited to, evaluation indicators at least at three levels / hierarchies. For example, it may at least include first-level indicators, second-level indicators, and third-level indicators. Among them, the first-level indicators may include, but are not limited to, the on-site operation personal safety status index, the overall personal accident risk index; the second-level indicators may include, but are not limited to, the personnel basic index, the environmental basic index, the material basic index, the operation and maintenance management index, the operation management index, the professional violation index, the violation investigation and punishment efficiency index, the accident and incident management index, the personal accident management index, the safety risk system rating index, the average violation index; the third-level indicators, that is, the basic indicators, may include, but are not limited to, indicators such as personnel, environment, material, operation, violation, risk, hidden danger, accident and incident, violation quantity, and employee quantity for which specific basic data can be directly obtained. For example, if it is known that the second-level indicator includes the average violation index, the third-level indicators corresponding to this second-level indicator are the violation quantity and the employee quantity, because: the average violation index can be determined based on the violation quantity and the employee quantity.

[0055] Further, among the secondary indicators: the personnel basic index may include but is not limited to the overall human resource allocation index, the employee certification rate index, the occupational health examination index, the regular inspection index of tools and equipment, the signing index of the work safety responsibility letter; the environmental basic index may include but is not limited to the terrain index, the rainfall index, the high temperature index, the low temperature index, the dryness index; the material basic index may include but is not limited to the power supply area index, the proportion index of medium-voltage distribution network insulated lines, the proportion index of medium-voltage distribution network cables, the effective coverage rate index of distribution automation, the reliability management tolerance index, the transferable power supply index of the distribution network; the operation and maintenance management index may include but is not limited to the medium-voltage line operation and maintenance management index, the distribution transformer operation and maintenance management index, the timely index of emergency defects, the completion index of hidden danger treatment, the timely index of hidden danger treatment; the operation management index may include but is not limited to the accurate index of operation plan, the month-on-month accurate index of operation plan, the operation risk distribution index, the month-on-month operation risk distribution index, the operation type distribution index, the month-on-month operation type distribution index, the operation video access index, the supervision coverage index of medium- and high-risk operations, the month-on-month supervision coverage index of medium- and high-risk operations; the professional violation index may include but is not limited to the violation level distribution index, the month-on-month violation level distribution index, the operation violation index, the month-on-month operation violation index, the average violation index, the month-on-month average violation index, the repeated index of serious violations, the month-on-month repeated index of serious violations; the violation investigation efficiency index includes the safety supervision personnel allocation index, the serious violation investigation efficiency index, the month-on-month serious violation investigation efficiency index, the violation investigation efficiency index, the month-on-month violation investigation efficiency index, the violation closed-loop rectification index, the month-on-month violation closed-loop rectification index; the accident and incident management index includes the annual accident and incident management index, the accident and incident management index within the preset number of years, the accident and incident index caused by repeated reasons; the personal accident management index may include but is not limited to the historical personal accident management index; the safety and risk management system rating index includes the operation risk assessment index. Based on this, the embodiments of the present application can determine multiple more detailed indexes included in the secondary indicators, so that the evaluation indicators in the evaluation index model can cover dimensions such as personnel allocation, operation volume, power supply area, operation violation situation, hidden danger investigation situation, asset scale, etc., making the evaluation indicators more comprehensive, so as to further improve the accuracy and reliability of the personal risk evaluation results in electric power operations.

[0056] S202, evaluate the target power risk event according to the evaluation index model to obtain an evaluation result.

[0057] In an embodiment of the present application, optionally, the computer device may evaluate the target power risk event according to the evaluation index model and a preset machine learning model to obtain an evaluation result; or, the computer device may also directly evaluate the target power risk event according to the evaluation index model to obtain an evaluation result. Of course, the specific implementation manner of the evaluation in the embodiments of the present application is not limited. Among them, the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

[0058] In the above risk assessment method, the target power risk event in the power risk events occurring in the power system and the corresponding evaluation index model are obtained; the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels; the target power risk event is evaluated according to the evaluation index model to obtain an evaluation result. Since the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels, the embodiments of the present application can determine the hierarchical structure of evaluation indexes at different levels from multiple aspects such as human factors, material factors, environmental factors, and management factors, and construct a more comprehensive and accurate evaluation index model, so that the target power risk event in power operations can be comprehensively and multi-dimensionally evaluated according to the more comprehensive and accurate evaluation index model, thus improving the comprehensiveness, accuracy, and credibility of the personal risk assessment in the power operation process.

[0059] In one embodiment, an implementation manner for determining the evaluation index model is provided, that is, the above risk assessment method further includes:

[0060] Obtain the event tree information corresponding to the power risk event occurring in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information.

[0061] Determine the evaluation index model according to the event tree information.

[0062] In an embodiment of the present application, the computer device may input the power accident report corresponding to the power system into a preset large language model for feature extraction to obtain accident information, so as to construct an accident tree of the power risk event according to the accident information. Among them, the accident information includes the key accident features in the power accident report, and the accident tree includes a top event, intermediate events, and basic events in a tree structure. The basic events correspond to the tertiary indicators, that is, each basic event comes from the indicators determined by screening the primary indicators, secondary indicators, and tertiary indicators step by step and associated with each intermediate event under the top event. Exemplarily, as shown in Figure 3 shown, Figure 3 is a schematic structural diagram of an accident tree in an embodiment.

[0063] Exemplarily, the construction process of the accident tree can be as follows: The computer device can determine the target power risk event as the top event, and determine each intermediate event that can be included under the top event according to the accident information, as well as determine the basic events that cause each intermediate event under the top event. After determining the top event, intermediate events, and basic events, the computer device can use logic gates to associate the basic events, intermediate events, and top event to obtain an accident tree with a hierarchical structure. In addition, the computer device can also identify the critical path of the target power risk event through machine learning and adjust the constructed accident tree according to the critical path, so as to obtain a more accurate accident tree.

[0064] In addition, the computer device can also obtain the specific values corresponding to the third-level indicators from the power accident reports and / or databases corresponding to the power system. For example, the specific values corresponding to the third-level indicators can include, but are not limited to, the specific values of weather and geography that can be obtained externally; the basic indicator data of problems found in inspections, checks, and supervision; the relevant basic indicator data obtained from the construction operation plan including risk level, operation method, number of operators, construction content, and safety measures, etc.

[0065] Thus, the computer device can determine the event tree information corresponding to the power risk event that occurs in the power system according to the accident tree of the power risk event and the specific values corresponding to the third-level indicators. Among them, the event tree information includes first-level event information, second-level event information, and third-level event information. The first-level event information corresponds to the top event, the second-level event information corresponds to the intermediate event, and the third-level event information corresponds to the basic event. After that, the computer device can determine the specific information in the hierarchical structure of the evaluation indicators at different levels according to the event tree information, so as to obtain an evaluation indicator model including the specific information in the hierarchical structure.

[0066] Among them, the main advantages of constructing the accident tree are as follows: First, quantitatively evaluate each key factor affecting the occurrence of accidents such as personnel, equipment, environment, and management, and comprehensively control the risk points; Second, refine each node of the accident tree according to the indicator system to more accurately describe the event occurrence conditions and scenarios; Third, the indicator system can be used as the knowledge basis for constructing the accident tree, reducing the dependence on expert experience and improving the objectivity of analysis; Based on the evaluation indicators and accident tree at all levels, formulate more scientific and comprehensive risk prevention and emergency response measures.

[0067] Among them, the training and usage process of the large language model is as follows: (1) Pre-training: Through pre-training on a large-scale corpus, the large language model has learned rich language representations and context understanding capabilities. Therefore, the large language model can understand complex text inputs and extract key information. (2) Text embedding: The large language model can convert the text in the power accident report into embedding vectors in numerical form. The above embedding vectors capture the semantic features of words, phrases, and sentences and can express the key information in the text. (3) Context understanding: By understanding the entire text content, even if this information is distributed in different parts of the document, the large language model can identify important elements in the accident report, such as causes, results, conditions, etc. (4) Data preprocessing: Clean the data in the power accident report, including removing useless information, correcting typos, unifying terms, etc., to improve the processing effect of the model. (5) Feature extraction task definition: Define the tasks for the types of information extracted from the power accident report. For example, it can be named entity recognition (NER) to label the key entities in the accident report (such as equipment names, operation errors, etc.), or text classification to classify the accident types. (6) Model selection and adjustment: Select a suitable pre-trained language model and fine-tune it according to the specific task. For example, use the BERT (Bidirectional Encoder Representation from Transformers) model for entity recognition or use GPT-3 (General Pre-trained Transformer-3) to generate causal relationship descriptions of accidents. (7) Model training: Train the model using the labeled accident report data. If it is for fine-tuning, less data may be required; if training some parts of the model from scratch, more data is needed. (8) Information extraction: Apply the model to new accident reports to automatically identify and extract information such as accident causes, results, involved personnel, and equipment. (9) Result integration and evaluation: Integrate the extracted information into fault tree analysis or other risk management tools.

[0068] Based on this, using large language models for feature extraction can significantly improve the efficiency and accuracy of data processing. Especially when dealing with a large amount of unstructured text data, large language models can help quickly and accurately extract valuable information from power accident reports, providing support for risk analysis and accident prevention. Therefore, applying large language models to power personal risk assessment, first, can efficiently process a large amount of data; second, can automatically extract key information from a large number of accident reports, reducing the need for manual analysis, especially in the power industry with a large and complex amount of data; third, can enhance the accuracy and consistency of data; fourth, can ensure that the information obtained from power accident reports is more accurate and error-free through automatic extraction, avoiding human errors and improving the consistency of data processing; fifth, can reveal deep-seated risk factors, helping to uncover risk factors and patterns hidden behind complex data, especially those factors that may be overlooked during manual analysis; sixth, can conduct comprehensive risk identification and assessment: by analyzing the causes and consequences of accidents in detail and comprehensively, provide a comprehensive risk assessment for power enterprises, supporting better risk management decisions; seventh, can optimize risk management strategies: utilize the data extracted from power accident reports to optimize existing risk management strategies, such as adjusting maintenance plans and safety training by identifying common or major fault causes; eighth, can improve the effectiveness of prevention and response measures: based on a detailed analysis of accident factors, formulate or improve prevention measures and emergency response plans, reducing the probability of future accidents and improving the ability to handle accidents; ninth, can support compliance and standardization requirements: ensure that risk management activities comply with industry safety standards and regulatory requirements, and support compliance certification and audits by providing detailed accident analysis reports.

[0069] In this embodiment, natural language processing technology can be used to automatically extract accident information and its causal relationships from power accident reports by using a large language model, thereby constructing an accident tree of power risk events, that is, it can clearly show in the form of a tree diagram each basic event and its logical relationship for the occurrence of the top event, and can, starting from the top-level undesired event, through the causal association relationship between logical gates and basic events, trace and analyze various causes leading to the occurrence of this top event. Furthermore, it can automatically and accurately obtain the event tree information corresponding to the power risk events occurring in the power system, and determine an accurate evaluation index model based on the event tree information.

[0070] In one embodiment, an implementation method for evaluating a target power risk event is provided, that is, "evaluating the target power risk event according to the evaluation index model in S202 above to obtain an evaluation result", including:

[0071] Input the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain an evaluation result; the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

[0072] In the embodiments of this application, the computer device can pre-determine a preset risk assessment model. Among them, the preset risk assessment model can be any machine learning model. For example: (1) Classification model: Classification algorithms, such as support vector machine (SVM, Support Vector Machine), random forest, gradient boosting machine (GBM, Gradient Boosting Machine), and neural network, etc., can be used to predict the occurrence probability of basic events or directly predict the occurrence of top events. The above models can learn fault patterns based on historical accident data and then be used for real-time accident prediction. (2) Cluster analysis: Cluster algorithms, such as K-means or DBSCAN (Density-Based Spatial Clustering of Applications with Noise), etc., can be used to identify similar accident patterns or accident behaviors, and are applicable to scenarios where it is necessary to understand how accidents occur without clear labels, which can help identify potential accident paths or weak links in the power system. (3) Association rule learning: Association rule learning algorithms, such as Apriori and FP-growth (Frequent Pattern Growth) algorithms, etc., can be used to discover the correlation and dependency relationships between basic events. It can reveal which components' accidents often occur simultaneously, which helps to build a more accurate accident tree model. (4) Reinforcement learning: Reinforcement learning can be used to dynamically optimize the accident tree structure, especially in scenarios where the power system configuration changes frequently or real-time adjustment of accident response strategies is required. Through the reward mechanism, the model can learn how to adjust the accident tree to minimize the impact of accidents. (5) Deep learning: Deep learning models, such as convolutional neural network (CNN, Convolutional Neural Networks) and recurrent neural network (RNN, Recurrent Neural Network), etc., due to their powerful feature extraction and sequence data processing capabilities, can be used for accident prediction and pattern recognition of complex systems.

[0073] Thus, the computer device can input the evaluation index model and the target power risk event into a preset risk assessment model for evaluation, and then obtain the evaluation result of the target power risk event. Exemplarily, the computer device can input the basic events and the target power risk event in the evaluation index model into the preset risk assessment model for evaluation, and then obtain the probabilities of occurrence of the basic events. Therefore, according to the probabilities of occurrence of the basic events and the relationship of the logic gates in the fault tree, the probabilities of occurrence of the intermediate events and the top event can be determined. Among them, the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event. For example, the evaluation result can refer to the probability of occurrence of the target power risk event.

[0074] In this embodiment, the evaluation index model and the target power risk event can be input into a preset risk assessment model for evaluation to obtain the evaluation result. Then, through automatic evaluation by combining the fault tree model predicted by machine learning and the large language model, the accuracy and efficiency of accident prediction and evaluation can be improved.

[0075] In one embodiment, an implementation method for evaluating a target power risk event is provided, that is, "evaluating the target power risk event according to the evaluation index model to obtain the evaluation result" in S202 above, as Figure 4 shown, including:

[0076] S301, extract evaluation indexes at all levels from the evaluation index model, and generate an index scoring table according to the evaluation indexes at all levels.

[0077] In the embodiment of the present application, the computer device can extract evaluation indexes at all levels from the evaluation index model, and establish a hierarchical structure model according to the extracted evaluation indexes at all levels. Exemplarily, combined with Figure 5 shown, Figure 5 is a schematic diagram of the hierarchical structure model in one embodiment. Among them, the hierarchical structure model includes a general target layer, an intermediate layer, and an index layer. Under the general target layer, there are several intermediate layers. Under each intermediate layer, there are several index layers respectively. Each index layer includes several basic indexes. Specifically, the first-level indexes can be filled into the general target layer, the second-level indexes can be filled into each intermediate layer, and the third-level indexes (i.e., basic indexes) can be filled into each index layer.

[0078] Thus, the computer device can automatically generate an index scoring table according to the evaluation indexes at all levels. Exemplarily, combined with Figure 6 and Figure 7 shown, Figure 6 is a schematic diagram of the index scoring table in one embodiment. Figure 6 It is a comparison scoring table of each second-level index and other second-level indexes; Figure 7It is a schematic diagram of an index scoring table in another embodiment. Figure 6 It is a comparison scoring table between each third-level index and other third-level indexes. Among them, the index scoring table is used to quantify the relative importance of one index to another index by using integers from 1 to 9. The larger the value, the more important the index; the reciprocals 1 / 2 to 1 / 9 indicate that the other index is relatively more important to this index.

[0079] S302. Display the index scoring table on the current interface, and in response to the user's evaluation operation on the index scoring table, obtain the scoring result according to the evaluation operation.

[0080] In the embodiment of the present application, the computer device can pre-determine the comparison basis. For example, the comparison basis can be: if index i is equally important compared to index j, it can be quantified as 1; if index i is slightly more important compared to index j, it can be quantified as 3; if index i is relatively more important compared to index j, it can be quantified as 5; if index i is very important compared to index j, it can be quantified as 7; if index i is extremely important compared to index j, it can be quantified as 9; in addition, if index i is "higher than equally important but lower than slightly more important" compared to index j, it can be quantified as 2. Then, the computer device can display the index scoring table and the comparison basis on the current interface. Thus, the user can perform an evaluation operation on the index scoring table according to the comparison basis on the current interface. Furthermore, the computer device can respond to the user's evaluation operation on the index scoring table and obtain the scoring result according to the evaluation operation. Exemplarily, as shown in Table 1 below, Table 1 is a schematic table of the scoring result in one embodiment. Among them, each value in the scoring result represents the comparison result of the relative importance of the two indexes output by the evaluation operation.

[0081] Table 1

[0082]

[0083] S303. Evaluate the target power risk event according to the scoring result to obtain the evaluation result.

[0084] In the embodiment of the present application, the computer device can evaluate the target power risk event according to the scoring result to obtain the evaluation result. In one embodiment, S303 includes:

[0085] Perform a consistency test on the judgment matrix corresponding to the scoring result to obtain the test result.

[0086] In the case where the test result indicates that the test passes, determine the weight vector of the evaluation indexes at each level according to the judgment matrix.

[0087] Multiply the weight vectors of the evaluation indexes at each level to obtain the evaluation result.

[0088] In the embodiments of the present application, the computer device may convert the scoring result into a matrix form, and thus obtain a judgment matrix corresponding to the scoring result. Therefore, the consistency test can be performed according to the judgment matrix corresponding to the scoring result to obtain a test result. Exemplarily, the computer device may respectively solve the matrix order n, the maximum eigenvalue λ and the corresponding eigenvector w of the judgment matrix, and thus, the consistency test formula of formula (1) below can be used for the consistency test:

[0089] , (1)

[0090] where CI is the consistency index, RI is the known average random consistency index, and CR is the consistency ratio.

[0091] Therefore, the computer device may determine whether the consistency index CI calculated by the above formula (1) is less than a preset threshold. If the consistency index CI is less than the preset threshold, it means that the test result indicates that the test passes. At this time, that is, when the test result indicates that the test passes, the computer device may determine the weight vector of each level of evaluation indicators layer by layer according to the judgment matrix and the eigenvector w, and thus determine the weight vector of each level relative to other levels. Therefore, the computer device may multiply the weight vectors of each level of evaluation indicators to obtain an evaluation result. For example, the evaluation result may represent the weight vector corresponding to the evaluation indicator.

[0092] In this embodiment, the evaluation indicators of each level are extracted from the evaluation indicator model, and an indicator scoring table is generated according to the evaluation indicators of each level; the indicator scoring table is displayed on the current interface, and in response to the user's evaluation operation on the indicator scoring table, and the scoring result is obtained according to the evaluation operation; the target power risk event is evaluated according to the scoring result to obtain an evaluation result. In this way, through the analytic hierarchy process, the various index factors causing risks can be compared and analyzed to measure the influence degree of different evaluation indicators, and automated, hierarchical and systematic evaluation and analysis can be realized.

[0093] In one embodiment, an implementation manner for evaluating all power risk events is provided, that is, the above risk assessment method further includes:

[0094] Return to the step of executing to obtain the target power risk event in the power risk events occurring in the power system until all basic events in the power risk events are evaluated to obtain a target evaluation result.

[0095] In the embodiments of the present application, after determining the evaluation result corresponding to the target power risk event, the computer device may return to execute the step of obtaining the target power risk event among the power risk events occurring in the power system. That is to say, the computer device may re-obtain a new target power risk event among the power risk events occurring in the power system, reconstruct the evaluation index model corresponding to the new target power risk event, and evaluate the target power risk event according to the new evaluation index model to obtain a new evaluation result corresponding to the new target power risk event. In this way, until all basic events in the power risk events are evaluated, the target evaluation results corresponding to all basic events can be obtained.

[0096] Exemplarily, as shown in combination with Figure 8 and Figure 9 shown, Figure 8 is a schematic diagram of the evaluation result obtained by using the analytic hierarchy process in an embodiment, Figure 9 is a schematic diagram of the evaluation result obtained by using a preset risk assessment model in an embodiment. By comparing the results of the two methods, it can be found that although there are numerical differences, the overall trends are consistent, indicating that the above two methods can effectively evaluate the personal risk events in the power system.

[0097] In this embodiment, by returning to execute the step of obtaining the target power risk event among the power risk events occurring in the power system, until all basic events in the power risk events are evaluated, all power risk events can be evaluated, and the target evaluation results of all power risk events can be obtained.

[0098] In an alternative embodiment, as shown in Figure 10 shown, a risk assessment method is provided, which is applied to a computer device and includes:

[0099] S20, obtaining the target power risk event among the power risk events occurring in the power system;

[0100] S21, obtaining the event tree information corresponding to the power risk events occurring in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information;

[0101] S22, determining an evaluation index model according to the event tree information; the evaluation index model is constructed by the hierarchical structure of evaluation indexes at different levels;

[0102] S23, inputting the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain an evaluation result; the evaluation result is used to represent the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

[0103] Alternatively, in S24, extract the evaluation indicators at all levels from the evaluation index model, and generate an index scoring table according to the evaluation indicators at all levels;

[0104] In S25, display the index scoring table on the current interface, and in response to the user's evaluation operation on the index scoring table, obtain the scoring result according to the evaluation operation;

[0105] In S26, perform a consistency test according to the judgment matrix corresponding to the scoring result to obtain the test result;

[0106] In S27, when the test result indicates that the test passes, determine the weight vector of the evaluation indicators at all levels according to the judgment matrix;

[0107] In S28, multiply the weight vectors of the evaluation indicators at all levels to obtain the evaluation result;

[0108] In S29, return to the step of executing to obtain the target power risk event among the power risk events occurring in the power system until all basic events in the power risk events are evaluated to obtain the target evaluation result.

[0109] In the above risk assessment method, obtain the target power risk event among the power risk events occurring in the power system, and the corresponding evaluation index model; the evaluation index model is constructed by the hierarchical structure of evaluation indicators at different levels; evaluate the target power risk event according to the evaluation index model to obtain the evaluation result. Since the evaluation index model is constructed by the hierarchical structure of evaluation indicators at different levels, the embodiments of the present application can determine the hierarchical structure of evaluation indicators at different levels from multiple aspects such as human factors, material factors, environmental factors, and management factors, and construct a more comprehensive and accurate evaluation index model. Therefore, the target power risk event in power operations can be comprehensively and multi-dimensionally evaluated according to the more comprehensive and accurate evaluation index model, which can improve the comprehensiveness, accuracy, and credibility of personal risk assessment in the power operation process. Through the above method, it helps power enterprises achieve high-level risk management and prevention goals, thereby protecting employees' safety, ensuring the operation of equipment, reducing economic losses, and enhancing the public's confidence in the safety management of the power industry, and can significantly improve the quality and efficiency of accident analysis, which is of great significance to the long-term development of power operations.

[0110] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0111] Based on the same inventive concept, an embodiment of the present application also provides a risk assessment device for implementing the above-mentioned risk assessment method. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the risk assessment device provided below can refer to the limitations on the risk assessment method in the above text, and will not be repeated here.

[0112] In an exemplary embodiment, as Figure 11 shown, a risk assessment device is provided, including: an acquisition module 31 and an evaluation module 32, where:

[0113] The acquisition module 31 is used to acquire a target power risk event in the power risk events occurring in the power system, and the corresponding evaluation index model; the evaluation index model is constructed by a hierarchical structure of evaluation indexes at different levels.

[0114] The evaluation module 32 is used to evaluate the target power risk event according to the evaluation index model to obtain an evaluation result.

[0115] In one of the embodiments, the evaluation module 32 includes:

[0116] The first evaluation unit is used to input the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain an evaluation result; the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

[0117] In one of the embodiments, the above-mentioned risk assessment device further includes:

[0118] The event tree information acquisition module is used to acquire the event tree information corresponding to the power risk event occurring in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information;

[0119] A determination module, configured to determine an evaluation index model according to event tree information.

[0120] In one embodiment, the evaluation module 32 includes:

[0121] A generation unit, configured to extract evaluation indexes at all levels from the evaluation index model, and generate an index score table according to the evaluation indexes at all levels;

[0122] A scoring unit, configured to display the index score table on the current interface, and in response to a user's evaluation operation on the index score table, and obtain a scoring result according to the evaluation operation;

[0123] A second evaluation unit, configured to evaluate a target power risk event according to the scoring result to obtain an evaluation result.

[0124] In one embodiment, the second evaluation unit is specifically configured to:

[0125] Perform a consistency test according to the judgment matrix corresponding to the scoring result to obtain a test result;

[0126] In the case where the test result indicates that the test is passed, determine the weight vector of the evaluation indexes at all levels according to the judgment matrix;

[0127] Multiply the weight vectors of the evaluation indexes at all levels to obtain an evaluation result.

[0128] In one embodiment, the above risk assessment device further includes:

[0129] A third evaluation module, configured to return to execute the step of obtaining the target power risk event in the power risk events occurring in the power system until all basic events in the power risk events are evaluated to obtain a target evaluation result.

[0130] Each module in the above risk assessment device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0131] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 1As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a risk assessment method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0132] Those skilled in the art can understand that Figure 1 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0133] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0134] Obtain the target power risk event in the power risk events occurring in the power system, and the corresponding evaluation index model; the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels;

[0135] Evaluate the target power risk event according to the evaluation index model to obtain an evaluation result.

[0136] In an embodiment, when evaluating the target power risk event according to the evaluation index model to obtain an evaluation result, the processor also implements the following steps when executing the computer program:

[0137] Input the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain an evaluation result; the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

[0138] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0139] Obtain the event tree information corresponding to the power risk event that occurs in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information;

[0140] Determine the evaluation index model according to the event tree information.

[0141] In one embodiment, when the processor executes the computer program to evaluate the target power risk event to obtain an evaluation result, the following steps are further implemented:

[0142] Extract the evaluation indexes at all levels from the evaluation index model, and generate an index scoring table according to the evaluation indexes at all levels;

[0143] Display the index scoring table on the current interface, and in response to the user's evaluation operation on the index scoring table, obtain the scoring result according to the evaluation operation;

[0144] Evaluate the target power risk event according to the scoring result to obtain an evaluation result.

[0145] In one embodiment, when the processor executes the computer program to evaluate the target power risk event to obtain an evaluation result, the following steps are further implemented:

[0146] Perform a consistency test according to the judgment matrix corresponding to the scoring result to obtain a test result;

[0147] In the case where the test result indicates that the test passes, determine the weight vector of the evaluation indexes at all levels according to the judgment matrix;

[0148] Multiply the weight vectors of the evaluation indexes at all levels to obtain an evaluation result.

[0149] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0150] Return to execute the step of obtaining the target power risk event in the power risk events that occur in the power system until the evaluation of all basic events in the power risk event is completed to obtain the target evaluation result.

[0151] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0152] Obtain a target power risk event in the power risk events occurring in the power system, and the corresponding evaluation index model; the evaluation index model is constructed from the hierarchical structure of evaluation indexes at different levels;

[0153] Evaluate the target power risk event according to the evaluation index model to obtain an evaluation result.

[0154] In one embodiment, when the computer program is executed by a processor to evaluate the target power risk event to obtain an evaluation result, the following steps are further implemented:

[0155] Input the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain an evaluation result; the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

[0156] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0157] Obtain the event tree information corresponding to the power risk event occurring in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information;

[0158] Determine the evaluation index model according to the event tree information.

[0159] In one embodiment, when the computer program is executed by a processor to evaluate the target power risk event to obtain an evaluation result, the following steps are further implemented:

[0160] Extract the evaluation indexes at each level from the evaluation index model, and generate an index score table according to the evaluation indexes at each level;

[0161] Display the index score table on the current interface, and in response to the user's evaluation operation on the index score table, and obtain a scoring result according to the evaluation operation;

[0162] Evaluate the target power risk event according to the scoring result to obtain an evaluation result.

[0163] In one embodiment, when the computer program is executed by a processor to evaluate the target power risk event to obtain an evaluation result, the following steps are further implemented:

[0164] Perform a consistency test on the judgment matrix corresponding to the scoring result to obtain a test result;

[0165] In the case where the test result indicates that the test passes, determine the weight vector of the evaluation indexes at each level according to the judgment matrix;

[0166] Multiply the weight vectors of the evaluation indicators at all levels to obtain the evaluation result.

[0167] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0168] Return to execute the step of obtaining the target power risk event among the power risk events occurring in the power system until all the basic events in the power risk events are evaluated to obtain the target evaluation result.

[0169] In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor, implements the following steps:

[0170] Obtain the target power risk event among the power risk events occurring in the power system, and the corresponding evaluation index model; the evaluation index model is constructed from the hierarchical structure of evaluation indicators at different levels;

[0171] Evaluate the target power risk event according to the evaluation index model to obtain the evaluation result.

[0172] In one embodiment, when evaluating the target power risk event according to the evaluation index model to obtain the evaluation result, when the computer program is executed by a processor, the following steps are further implemented:

[0173] Input the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain the evaluation result; the evaluation result is used to characterize the influence degree of each evaluation indicator included in the evaluation index model in the target power risk event.

[0174] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0175] Obtain the event tree information corresponding to the power risk event occurring in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information;

[0176] Determine the evaluation index model according to the event tree information.

[0177] In one embodiment, when evaluating the target power risk event according to the evaluation index model to obtain the evaluation result, when the computer program is executed by a processor, the following steps are further implemented:

[0178] Extract the evaluation indicators at all levels from the evaluation index model, and generate an index score table according to the evaluation indicators at all levels;

[0179] Display the index score table on the current interface, and respond to the user's evaluation operation on the index score table, and obtain the scoring result according to the evaluation operation;

[0180] Evaluate the target power risk event according to the scoring result to obtain the evaluation result.

[0181] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: when evaluating the target power risk event according to the scoring result to obtain the evaluation result

[0182] Perform a consistency test on the judgment matrix corresponding to the scoring result to obtain the test result;

[0183] In the case where the test result indicates that the test passes, determine the weight vector of the evaluation indicators at each level according to the judgment matrix;

[0184] Multiply the weight vectors of the evaluation indicators at each level to obtain the evaluation result.

[0185] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0186] Return to execute the step of obtaining the target power risk event in the power risk events occurring in the power system until all the basic events in the power risk events are evaluated to obtain the target evaluation result.

[0187] It should be noted that the user information (including but not limited to information related to users in the power system, user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0188] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0189] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0190] The above embodiments only illustrate several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A risk assessment method, characterized in that, The method includes: Obtaining a target power risk event among the power risk events occurring in the power system, and a corresponding evaluation index model; the evaluation index model is constructed from a hierarchical structure of evaluation indexes at different levels; Evaluating the target power risk event according to the evaluation index model to obtain an evaluation result.

2. The method according to claim 1, characterized in that, The evaluating the target power risk event according to the evaluation index model to obtain an evaluation result includes: Inputting the evaluation index model and the target power risk event into a preset risk assessment model for evaluation to obtain the evaluation result; the evaluation result is used to characterize the influence degree of each evaluation index included in the evaluation index model in the target power risk event.

3. The method according to claim 1, characterized in that The method further includes: Obtaining event tree information corresponding to the power risk events occurring in the power system; the event tree information includes primary event information, secondary event information, and tertiary event information; Determining the evaluation index model according to the event tree information.

4. The method according to claim 1, wherein The evaluating the target power risk event according to the evaluation index model to obtain an evaluation result includes: Extracting evaluation indexes at all levels from the evaluation index model, and generating an index scoring table according to the evaluation indexes at all levels; Displaying the index scoring table on the current interface, and in response to a user's evaluation operation on the index scoring table, and obtaining a scoring result according to the evaluation operation; Evaluating the target power risk event according to the scoring result to obtain the evaluation result.

5. The method according to claim 4, characterized in that, The evaluating the target power risk event according to the scoring result to obtain the evaluation result includes: Performing a consistency test on the judgment matrix corresponding to the scoring result to obtain a test result; When the test result indicates that the test passes, determining a weight vector of the evaluation indexes at all levels according to the judgment matrix; Multiplying the weight vectors of the evaluation indexes at all levels to obtain the evaluation result.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Returning to execute the step of obtaining the target power risk event among the power risk events occurring in the power system until all basic events in the power risk event are evaluated to obtain a target evaluation result.

7. A risk assessment device, characterized in that, The device includes: An obtaining module, configured to obtain a target power risk event among the power risk events occurring in the power system, and a corresponding evaluation index model; the evaluation index model is constructed from a hierarchical structure of evaluation indexes at different levels; An evaluating module, configured to evaluate the target power risk event according to the evaluation index model to obtain an evaluation result.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images