Method and device for determining risk level of power supply enterprise, and computer equipment

Abstract

The invention relates to a risk level determination method and device of a power supply enterprise and computer equipment. The method comprises the steps of obtaining power operation data of a power supply enterprise, determining an index original value of the power supply enterprise under risk assessment indexes of multiple dimensions according to the power operation data, and mapping the index original value into a corresponding index risk value based on data distribution characteristics of the index original value, and performing weighted operation processing on the corresponding index risk value by adopting the index weight parameter corresponding to each risk assessment index to obtain a weighted risk value corresponding to each risk assessment index, and fusing the weighted risk values corresponding to the risk assessment indexes of multiple dimensions to obtain a target risk value of the power supply enterprise. And determining an enterprise risk level matched with the target risk value based on a preset relationship between the risk value and the risk level. By adopting the method, comprehensive risk assessment can be performed on the power production safety of the power supply enterprise by fusing multi-dimensional indexes, and the risk assessment accuracy is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power production safety management, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for determining the risk level of a power supply enterprise. Background Art

[0002] With the development of smart grids and the advancement of digital transformation, grid management platforms have accumulated massive amounts of operational data from power supply companies, including equipment status, violation records, and hidden danger records. However, existing enterprise risk assessment methods for power supply companies primarily rely on static checklists, expert judgment, or single-dimensional data analysis. These methods are unable to address the systemic risks associated with the multi-factor coupling of power operations, leading to prone to assessment errors. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining the risk level of a power supply enterprise that can improve the accuracy in order to address the above technical problems.

[0004] In a first aspect, the present application provides a method for determining the risk level of a power supply enterprise, which is used for early warning of accident risks at the operation site of the power supply enterprise, including:

[0005] Obtain power operation data from power supply companies;

[0006] Determining, based on the power operation data, original values ​​of risk assessment indicators of the power supply enterprise under multiple dimensions, and mapping the original values ​​of the indicators to corresponding risk values ​​of the indicators based on data distribution characteristics of the original values ​​of the indicators, wherein the risk assessment indicators are determined based on accident-causing events of power safety accidents of the power supply enterprise;

[0007] Performing weighted calculation processing on the corresponding indicator risk value using the indicator weight parameter corresponding to each of the risk assessment indicators to obtain the weighted risk value corresponding to each of the risk assessment indicators, wherein the indicator weight parameter is determined based on the event weight parameter of the accident-causing event associated with the risk assessment indicator, and the event weight parameter is used to characterize the structural importance of the accident-causing event in the power safety accident tree of the power supply enterprise;

[0008] The target risk value of the power supply enterprise is obtained by integrating the weighted risk values ​​of multiple dimensions, and the enterprise risk level that matches the target risk value is determined based on the relationship between the preset risk value and the risk level.

[0009] In one embodiment, determining the original values ​​of the indicators of the power supply enterprise under the risk assessment indicators of multiple dimensions based on the power operation data, and mapping the original values ​​of the indicators to corresponding indicator risk values ​​based on the data distribution characteristics of the original values ​​of the indicators, includes:

[0010] The power operation data is processed by respectively using the calculation method corresponding to each of the risk assessment indicators to obtain the original value of the indicator of the power supply enterprise under each of the risk assessment indicators;

[0011] Determine the segmentation interval corresponding to the original value of the indicator according to the mean and standard deviation of the original value of each risk assessment indicator;

[0012] The indicator original value is converted into a corresponding indicator risk value according to the relationship between the original value corresponding to the segmented interval and the risk value.

[0013] In one embodiment, determining the segmented interval corresponding to the original value of the indicator according to the mean and standard deviation of the original value of each risk assessment indicator includes:

[0014] The difference between the mean and standard deviation of the original values ​​of the indicator and the sum of the mean and standard deviation of the original values ​​of the indicator are used to divide the corresponding left tail extreme value interval, normal fluctuation interval and right tail extension interval;

[0015] Comparing the original value of each risk assessment indicator with the difference between the mean and the standard deviation and the sum of the mean and the standard deviation;

[0016] Based on the comparison result of the original value of the indicator, a segmented interval corresponding to the original value of the indicator is determined from the left tail extreme value interval, the normal fluctuation interval and the right tail extension interval.

[0017] In one embodiment, converting the original indicator value into the corresponding indicator risk value according to the relationship between the original value corresponding to the segmented interval and the risk value includes:

[0018] In the case where the segmented interval is the left tail extreme value interval, the original value of the indicator and the difference between the mean and the standard deviation are processed by using a direct proportional transformation relationship corresponding to the left tail extreme value interval to obtain a corresponding indicator risk value;

[0019] In the case where the segmented interval is the normal fluctuation interval, the original value of the indicator and the difference between the mean and the standard deviation are processed by using a first linear interpolation relationship corresponding to the normal fluctuation interval to obtain a corresponding indicator risk value;

[0020] When the segmented interval is the right-tail extension interval, the second linear interpolation relationship corresponding to the right-tail extension interval is used to perform calculation processing on the original value of the indicator and the sum of the mean and the standard deviation to obtain the corresponding indicator risk value.

[0021] In one embodiment, the method for determining the indicator weight parameter includes:

[0022] Obtaining an event weight parameter of the accident-causing event and the number of associated indicators of the accident-causing event;

[0023] Distributing the event weight parameter of the accident-causing event equally to each risk assessment indicator associated with the accident-causing event according to the number of associated indicators, and obtaining a weight distribution value of each risk assessment indicator relative to the accident-causing event;

[0024] The weight distribution values ​​of the risk assessment indicators are accumulated respectively to obtain the indicator weight parameters corresponding to the risk assessment indicators.

[0025] In one embodiment, the method for determining the event weight parameter includes:

[0026] Acquire historical accident samples and construct a power safety accident tree corresponding to the historical accident samples;

[0027] Determining the target cut set where the accident-causing event is located from the minimum cut set corresponding to the power safety accident tree;

[0028] determining a structural importance coefficient of the accident-causing event according to the total number of the target cut sets and the total number of the minimum cut sets;

[0029] Determine the top event of the power safety accident tree where the accident causation event is located, and determine the top event weight parameter according to the occurrence frequency of the top event;

[0030] The top event weight parameter and the structure importance coefficient are used to perform calculation processing to obtain the event weight parameter of the accident-causing event.

[0031] Secondly, the present application also provides a risk level determination device for a power supply enterprise, which is used for early warning of accident risks at the operation site of the power supply enterprise; comprising:

[0032] Data acquisition module, used to obtain power operation data of power supply enterprises;

[0033] An indicator determination module, configured to determine, based on the power operation data, original values ​​of the indicators of the power supply enterprise under risk assessment indicators of multiple dimensions, and map the original values ​​of the indicators to corresponding indicator risk values ​​based on data distribution characteristics of the original values ​​of the indicators, wherein the risk assessment indicators are determined based on accident-causing events of power safety accidents of the power supply enterprise;

[0034] An indicator weighting module is used to perform weighted calculation processing on the corresponding indicator risk value using the indicator weight parameter corresponding to each of the risk assessment indicators to obtain the weighted risk value corresponding to each of the risk assessment indicators, wherein the indicator weight parameter is determined based on the event weight parameter of the accident-causing event associated with the risk assessment indicator, and the event weight parameter is used to characterize the structural importance coefficient of the accident-causing event in the power safety accident tree of the power supply enterprise;

[0035] The level determination module is used to integrate the weighted risk values ​​of multiple dimensions to obtain the target risk value of the power supply enterprise, and determine the enterprise risk level that matches the target risk value based on the relationship between the preset risk value and the risk level.

[0036] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method for determining the risk level of a power supply enterprise as described in any one of the embodiments of the first aspect.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining the risk level of a power supply enterprise as described in any one of the embodiments of the first aspect.

[0038] In a fifth aspect, the present application further provides a computer program product, comprising a computer program that, when executed by a processor, implements the method for determining the risk level of a power supply enterprise as described in any one of the embodiments of the first aspect.

[0039] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for determining the risk level of a power supply enterprise obtain the power operation data of the power supply enterprise, determine the original values ​​of the indicators of the power supply enterprise under the risk assessment indicators of multiple dimensions based on the power operation data, and map the original values ​​of the indicators to corresponding indicator risk values ​​based on the data distribution characteristics of the original values ​​of the indicators. The indicator weight parameters corresponding to each risk assessment indicator are used to perform weighted operation processing on the corresponding indicator risk values ​​to obtain the weighted risk values ​​corresponding to each risk assessment indicator. The weighted risk values ​​corresponding to the risk assessment indicators of multiple dimensions are integrated to obtain the target risk value of the power supply enterprise. Based on the relationship between the preset risk value and the risk level, the enterprise risk level matching the target risk value is determined. This method can not only integrate multi-dimensional indicators (such as risk assessment indicators under the dimensions of people, objects, environment, and management) to conduct a comprehensive risk assessment of the power production safety of the power supply enterprise, thereby improving the comprehensiveness of the risk assessment, but also can obtain the risk value of each indicator based on the data distribution characteristics of the original values ​​of each indicator, so as to facilitate the subsequent cross-scale risk value integration and improve the calculation accuracy of the target risk value. In addition, since the risk assessment indicators used in the above-mentioned method for determining the risk level of power supply enterprises are determined based on the accident-causing events of power safety accidents in power supply enterprises, the causal mapping between indicators and events can also be used to improve the objectivity and scientific nature of risk assessment indicators, thereby helping to improve the accuracy of subsequent enterprise risk level determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 This is an application environment diagram of a method for determining a risk level for a power supply enterprise in one embodiment;

[0042] Figure 2 1 is a flow chart of a method for determining a risk level of a power supply enterprise in one embodiment;

[0043] Figure 3 A schematic diagram of a process for converting an indicator risk value in one embodiment;

[0044] Figure 4 Schematic diagram of a flow chart of a step of determining a segmented interval in one embodiment;

[0045] Figure 5 A schematic flow chart of the steps for determining the indicator risk value in one embodiment;

[0046] Figure 6 A flowchart of the indicator weight parameter determination step in one embodiment;

[0047] Figure 7 Schematic diagram of a flow chart of the event weight parameter determination step in one embodiment;

[0048] Figure 8 is a flow chart of a method for determining a risk level of a power supply enterprise in another embodiment;

[0049] Figure 9 Schematic diagram of a power safety fault tree in one embodiment;

[0050] Figure 10 is a structural block diagram of a risk level determination device 1000 for a power supply enterprise in one embodiment;

[0051] Figure 11 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0053] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0054] The risk level determination method for power supply enterprises provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104 or placed on the cloud or other network servers.

[0055] For example, server 104 can obtain power operation data from a power supply enterprise through terminal 102. Server 104 can store risk assessment logic for multiple risk assessment indicators. The risk assessment indicators are determined based on the causal events of power safety accidents at the power supply enterprise. Server 104 executes the risk assessment logic for each risk assessment indicator to perform computations on the power operation data, obtaining the original values ​​of the indicators under the multiple risk assessment indicators for the power supply enterprise. Based on the data distribution characteristics of the original indicator values, the original indicator values ​​are mapped to corresponding indicator risk values. Server 104 can store indicator weight parameters corresponding to each risk assessment indicator. The indicator weight parameters can be determined based on the event weight parameters of the causal events associated with the risk assessment indicators. The event weight parameters can be used to represent the structural importance of the causal events in the power supply enterprise's power safety accident tree. Server 104 can use the indicator weight parameters corresponding to each risk assessment indicator to perform weighted computations on the corresponding indicator risk values ​​to obtain weighted risk values ​​corresponding to each risk assessment indicator. Server 104 can also store preset relationships between risk values ​​and risk levels. Server 104 can integrate the weighted risk values ​​of the power supply enterprise under various risk assessment indicators to obtain the target risk value of the power supply enterprise, and combine the relationship between the preset risk value and the risk level to determine the risk level corresponding to the target risk value as the enterprise risk level to which the current power supply enterprise belongs.

[0056] Terminal 102 may include, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart TVs, smart car devices, and projectors. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Head-mounted devices may include virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, and the like. Server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0057] In an exemplary embodiment, Figure 2 As shown, a method for determining the risk level of a power supply enterprise is provided, and the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S202 to S208.

[0058] Step S202: Acquire power operation data of the power supply enterprise.

[0059] Among them, power supply enterprises can be used to represent all enterprises engaged in power production, transmission, sales or services, for example, they can include power generation enterprises, transmission enterprises, distribution enterprises, etc.

[0060] Power operation data may include but is not limited to equipment status data, violation record data, hidden danger ledger data, etc. of the power supply company.

[0061] For example, the server may obtain the power operation data of the power supply enterprise at predetermined intervals (e.g., weekly, monthly, or annually). Alternatively, in some embodiments, the power operation data may be data obtained through statistics, monitoring, and research on the power operation status of the power supply enterprise provided by the power grid management platform, thereby facilitating the fusion analysis of multi-source heterogeneous data for the power supply enterprise.

[0062] Step S204 , determining the original values ​​of the indicators of the power supply enterprise under the risk assessment indicators of multiple dimensions based on the power operation data, and mapping the original values ​​of the indicators to corresponding indicator risk values ​​based on the data distribution characteristics of the original values ​​of the indicators.

[0063] Among them, risk assessment indicators can be constructed based on the four dimensions of operational standardization, safety management and control, equipment operation and maintenance, and resource allocation to form a quantitative evaluation system for power production safety. Each risk assessment indicator can be anchored to a unique dimension and reflect the effectiveness of a specific management element. For example, the indicator of tools not being inspected beyond the expiration date can be used to expose loopholes in the execution of tool inspection cycles. The indicator of the incidence of abnormal operations can be used to verify the interference effect of damaged tools. Risk assessment indicators can be targeted at accident causes and have plasticity of management actions. For example, the occupational health examination indicator can directly correspond to employee physical and mental events. The hazard control completion indicator can be linked to the rectification and acceptance of management actions such as non-standard scaffolding construction and hanging basket failure.

[0064] The indicator risk value can be used to quantitatively evaluate the power operation data of power supply enterprises under the risk assessment indicators from the perspective of power safety production.

[0065] The data distribution characteristics can be used to characterize the distribution of the original values ​​of the indicators corresponding to each risk assessment indicator within a plurality of preset segmentation intervals.

[0066] For example, the server may store risk assessment logic for risk assessment indicators across multiple dimensions. The power operation data corresponding to each risk assessment indicator is processed according to the risk assessment logic for each risk assessment indicator to obtain the original indicator value for each risk assessment indicator for the power supply enterprise. Based on the data distribution characteristics of the original indicator values, the segmented intervals within the overall indicator original value for each risk assessment indicator are determined. The original indicator values ​​are processed using a mapping relationship corresponding to the segmented intervals to obtain the corresponding indicator risk value.

[0067] Optionally, in some embodiments, the risk assessment index may include a ratio-type index. The risk assessment logic of the ratio-type index may be a logic that calculates the ratio of the numerator (the amount of specific abnormal events or the amount of specific compliance events) to the denominator (the total amount or the base number). The risk assessment logic of the ratio-type index is used to quantify the frequency of event occurrence or the intensity of resource allocation. Ratio-type indicators may include non-standard operation indicators, operation violation indicators, and the like. The indicator risk value corresponding to the unplanned operation indicator can be obtained by aggregating and calculating the violation events such as failure to start work in time and excessive construction period, dividing it by the total number of operations of the power supply enterprise and multiplying it by the number of types of violation events, and can be used as a quantitative value to strengthen risk characterization. The indicator risk value corresponding to the operation violation indicator can be obtained by calculating the inverse relationship between the total amount of operations and the number of violations, and can be used to reversely measure the safety management and control effectiveness of the enterprise's operations.

[0068] Optionally, in some embodiments, the risk assessment indicators may include direct-value indicators. The risk assessment logic of direct-value indicators may be a logic that directly takes values ​​based on the pre-calculated results of the power grid enterprise-level management platform (i.e., the power grid management platform). The power grid management platform can pre-process the power operation data of the power supply enterprise through its built-in calculation rules, including data cleaning, logic verification, and ratio calculation, and then store the pre-processed power operation data as data processed in the subsequent risk level determination process. The significant advantage of direct-value indicators lies in the standardization of business rules - the power grid management platform realizes data integration of the entire business process based on the "Power Grid Security Supervision Data Interface Specification", and the calculation rules built into the power grid management platform are certified by industry standards, ensuring that the power operation data output by the power grid management platform is immediately usable, significantly reducing manual calculation costs and error rates, and providing "zero-latency" data support for real-time supervision and dynamic decision-making.

[0069] Optionally, in some embodiments, risk assessment indicators may include composite indicators. The risk assessment logic for composite indicators may be calculated by focusing on the pain points of power production management in power supply enterprises. By correlating the physical meanings of indicator elements, these indicators better align with the actual needs of power grid operation and maintenance. For example, composite indicators may include overall human resource allocation indicators and safety and regulatory personnel allocation indicators. The risk assessment logic for the overall human resource allocation indicator may be based on calculating the ratio of the number of employees to the length of medium-voltage distribution network lines. This ratio directly reflects the per capita operation and maintenance load and intuitively quantifies the degree of alignment between human resources and asset size. Industry practice has established mature threshold criteria for determining this ratio, making it easier for power supply enterprises (such as grassroots units) to quickly identify staffing gaps. The risk assessment logic for the safety and regulatory personnel allocation indicator may be based on the dynamic characteristics of the total number of operations and calculating the ratio of the number of safety and regulatory personnel to the total number of operations. This ratio directly represents the density of regulatory resources per unit of operation, directly echoing the practical management principle that "greater operations lead to higher regulatory demands," providing an actionable quantitative basis for the flexible deployment of safety and regulatory resources.

[0070] In step S206, the indicator weight parameters corresponding to the risk assessment indicators are respectively used to perform weighted calculation processing on the corresponding indicator risk values ​​to obtain the weighted risk values ​​corresponding to the risk assessment indicators.

[0071] The indicator weight parameter can be determined based on the event weight parameter of the accident-causing event associated with the risk assessment indicator. Optionally, in some embodiments, the risk assessment indicator can be a precise, quantitative indicator derived by classifying the accident-causing events of power safety accidents into corresponding dimensions (including any of the four dimensions of operational standardization, safety management and control, equipment operation and maintenance, and resource allocation), deconstructing the implicit management elements (such as periodic inspection, scrap management, abnormal intervention, and other actionable management actions). In other words, the accident-causing events associated with the risk assessment indicator are used to represent the accident-causing events used as the basis for deducing the risk assessment indicator.

[0072] The event weight parameter can be used to characterize the structural importance of the accident-causing event in the power safety fault tree. The structural importance can be used to assess the contribution of the accident-causing event to the top event of the power safety fault tree in which it is located.

[0073] Optionally, in some implementations, a power safety accident tree can be constructed by performing a fault tree analysis (FTA) on the power safety accident. The power safety accident tree is simplified to obtain a minimum cut set of the power safety accident tree. Each minimum cut set can be used to represent a minimum combination of causal events that constitute the power safety accident. Events in the minimum cut set are used as the accident causal events. Using the minimum cut sets containing the accident causal events, the structural importance coefficient of the accident causal event in the power safety accident tree can be calculated.

[0074] For example, the server may pre-store indicator weight parameters corresponding to various risk assessment indicators. For each risk assessment indicator, the following operations are performed: the indicator weight parameter corresponding to the current risk assessment indicator is used to perform a weighted operation on the indicator risk value corresponding to the current risk assessment indicator; the product of the indicator weight parameter and the indicator risk value is used as the weighted risk value corresponding to the current risk assessment indicator, thereby obtaining the weighted risk value corresponding to each risk assessment indicator.

[0075] Step S208: The weighted risk values ​​of multiple dimensions are integrated to obtain the target risk value of the power supply enterprise, and based on the relationship between the preset risk value and the risk level, the enterprise risk level that matches the target risk value is determined.

[0076] For example, the server may pre-store the relationship between risk values ​​and risk levels. The weighted risk values ​​of the power supply enterprise under each risk assessment indicator are accumulated to obtain a sum of the weighted risk values. This sum of the weighted risk values ​​is used as the target risk value of the power supply enterprise. Based on the preset relationship between risk values ​​and risk levels, the risk level corresponding to the current target risk value is retrieved and used as the enterprise risk level to which the current power supply enterprise belongs.

[0077] Optionally, in some implementation methods, the power supply enterprise may subsequently formulate corresponding risk prevention and control measures based on the enterprise risk level, strengthen the monitoring and early warning of key indicators with higher weighted risk values, optimize the resource allocation of the power supply enterprise, thereby enhancing the risk response capability of the power supply enterprise and ensuring the stable operation and sustainable development of the power supply enterprise.

[0078] In the above-mentioned method for determining the risk level of the power supply enterprise, the power operation data of the power supply enterprise is obtained, and the original values ​​of the indicators of the power supply enterprise under the risk assessment indicators of multiple dimensions are determined according to the power operation data, and the original values ​​of the indicators are mapped to the corresponding indicator risk values ​​based on the data distribution characteristics of the original values ​​of the indicators. The indicator weight parameters corresponding to each risk assessment indicator are respectively used to perform weighted operation processing on the corresponding indicator risk values ​​to obtain the weighted risk values ​​corresponding to each risk assessment indicator, and the weighted risk values ​​corresponding to the risk assessment indicators of multiple dimensions are integrated to obtain the target risk value of the power supply enterprise. Based on the relationship between the preset risk value and the risk level, the enterprise risk level matching the target risk value is determined. This method can not only integrate multi-dimensional indicators (such as risk assessment indicators under the dimensions of people, objects, environment, and management) to conduct a comprehensive risk assessment on the power production safety of the power supply enterprise and improve the comprehensiveness of the risk assessment, but also can obtain the risk value of each indicator based on the data distribution characteristics of the original values ​​of each indicator, so as to facilitate the subsequent cross-scale risk value fusion and improve the calculation accuracy of the target risk value.

[0079] In addition, since the risk level determination method of the above-mentioned power supply enterprise determines the event weight parameters of the accident-causing events according to the structural importance of the accident-causing events in the power safety accident tree, and determines the indicator weight parameters of the risk assessment indicators according to the event weight parameters of the accident-causing events associated with the risk assessment indicators, it is possible to construct a causal relationship between the accident-causing events and the risk assessment indicators based on the accident tree analysis method, which helps to form a closed-loop logic of accident consistent causes-management measures-indicators, thereby improving the objectivity and reliability of the risk assessment indicators, so that the risk assessment indicators can accurately reflect the key risk factors that lead to power safety accidents.

[0080] Optionally, in some implementations, certain power operation data of power supply companies may change due to factors such as weather, environment, and management practices. For example, the risk of falls from heights at power supply companies may increase dramatically during inclement weather. Therefore, the server can dynamically and adaptively adjust the weighting parameters of corresponding risk assessment indicators based on real-time power operation data (such as operating environment monitoring data and hidden danger rectification rates) to update the company's risk level, thereby improving the accuracy and timeliness of the power supply company's risk level determination method.

[0081] In an exemplary embodiment, Figure 3 As shown, step S204 includes steps S302 to S306.

[0082] In step S302 , the power operation data is processed using the calculation method corresponding to each risk assessment indicator to obtain the original value of the indicator under each risk assessment indicator of the power supply enterprise.

[0083] For example, the server may store risk assessment logic corresponding to each risk assessment indicator. Referring to the calculation methods in the risk assessment logic for ratio-based indicators, direct-valued indicators, and composite indicators provided in the above embodiments, the power operation data corresponding to the risk assessment indicator is processed, and the resulting value is used as the original value of the indicator under the current risk assessment indicator, thereby obtaining the original value of the indicator under each risk assessment indicator of the power supply enterprise.

[0084] Step S304: determining the segmentation interval corresponding to the original value of each risk assessment indicator according to the mean and standard deviation of the original value of the indicator.

[0085] The mean can be used to reflect the typical level of the original value of the indicator, that is, the central trend of the original value of the indicator under each risk assessment indicator. Optionally, in some embodiments, the mean can be calculated using the following formula:

[0086] ,

[0087] Among them, the dataset It can represent a collection of original values ​​of risk assessment indicators in multiple dimensions. It can represent the original value of the indicator corresponding to the nth risk assessment indicator. It can represent the mean of the original value of the indicator. Can be expressed as a data set Function of the mean.

[0088] The standard deviation can be used to measure the original value of each risk assessment indicator around the mean. The fluctuation range, that is, the degree of dispersion of the original values ​​of the indicators under the risk assessment indicators of multiple dimensions. Optionally, in some embodiments, the standard deviation can be calculated by the following formula:

[0089] ,

[0090] Among them, the dataset Same meaning as above. It can express the standard deviation of the original value of the indicator. Can be used to represent a dataset A function of the variance of .

[0091] The mean and standard deviation together constitute the basic parameters for describing the data distribution of the original values ​​of indicators. According to the central limit theorem, when the sample size of the original values ​​of indicators is large enough (that is, when the number of risk assessment indicators is large enough), the original values ​​of most indicators will approach the normal distribution. Principle (about 68.27% of the original value of the indicator will fall within The principle of ( ) provides probabilistic support for the segmentation of intervals and becomes the theoretical benchmark for defining the main fluctuation range of the original value of the indicator.

[0092] For example, the server can obtain the total number of original values ​​of indicators under each risk assessment indicator, as well as the sum of the original values ​​of indicators under each risk assessment indicator. The ratio of the sum of the original values ​​of indicators under each risk assessment indicator to the total number of original values ​​of indicators is calculated as the mean of the original values ​​of the indicators. The square of the difference between the original value of the indicator under each risk assessment indicator and the mean is calculated, the squared value is accumulated, and then divided by the total number of original values ​​of the indicator to obtain the standard deviation of the original value of the indicator. The mean and standard deviation are used to calculate the boundary points of the segmented interval. Based on the size relationship between the original value of the indicator and the boundary point, the segmented interval corresponding to the original value of the indicator is determined.

[0093] Step S306: Convert the original value of the indicator into the corresponding risk value of the indicator according to the relationship between the original value corresponding to the segmented interval and the risk value.

[0094] For example, the server may store the relationship between the original value and the risk value corresponding to each segmented interval. Based on the segmented interval corresponding to the original value of the indicator, the original value of the indicator is processed using the relationship between the corresponding original value and the risk value to obtain the indicator risk value corresponding to the original value of the indicator.

[0095] In this embodiment, the power operation data is processed by respectively using the operation method corresponding to each risk assessment indicator to obtain the original value of the indicator of the power supply enterprise under each risk assessment indicator; the segmentation interval corresponding to the original value of the indicator is determined according to the mean and standard deviation of the original value of the indicator under each risk assessment indicator; according to the relationship between the original value corresponding to the segmentation interval and the risk value, the original value of the indicator is converted into the corresponding indicator risk value, which can use statistical laws to improve the objectivity of the division of the segmentation interval and map the measured original value of the indicator to an ordered risk level space, thereby helping to improve the accuracy of the enterprise risk level subsequently determined based on the indicator risk value.

[0096] In an exemplary embodiment, Figure 4 As shown, step S304 includes the following steps S402 to S406. Among them:

[0097] Step S402: using the difference between the mean and standard deviation of the original values ​​of the indicator and the sum of the mean and standard deviation of the original values ​​of the indicator, the corresponding left-tail extreme value interval, normal fluctuation interval and right-tail extension interval are divided.

[0098] Among them, the left-tail extreme value interval can be used to represent the extreme value interval whose value is significantly lower than the original value of the normal index. In general, the lower bound of the left-tail extreme value interval is 0, and the upper bound is the statistical critical value. , thus forming a quantitative definition of abnormally low values. The setting of the left-tail extreme value interval combined with the indicator attributes can reflect the coupling of statistical laws and indicator semantics.

[0099] The normal fluctuation interval can be used to represent the range covering the original value of the normal indicator, reflecting the typical range of variation of the original indicator value in historical observations. The division of the normal fluctuation interval not only conforms to the probability distribution characteristics under the law of large numbers, but also provides an objective "normal state" reference system for risk assessment of power supply enterprises.

[0100] The right-tail extension interval can be set based on expert opinions. For example, the theoretical maximum value M specified by the expert can be introduced as the upper boundary point for construction. The right-tail extension interval can be used to solve the problem of missing extreme values ​​caused by relying solely on historical data. The determination of the maximum value M is based on domain knowledge and industry norms, which is a necessary supplement to the limitations of statistical methods. The right-tail extension interval can reflect the organic combination of empirical knowledge and data-driven in the risk assessment system of this application.

[0101] For example, the server can calculate the difference between the mean and standard deviation of the original value of the indicator and the sum of the mean and standard deviation. The server can use 0 as the lower boundary point and the difference between the mean and standard deviation of the original value of the indicator as the upper boundary point of the left tail extreme value interval, and define the left tail extreme value interval as The difference between the original mean and standard deviation of the indicator is used as the lower boundary point, and the sum of the original mean and standard deviation of the indicator is used as the upper boundary point. The normal fluctuation range is defined as The sum of the mean and standard deviation of the original value of the indicator is used as the lower boundary point, and the preset value M is used as the upper boundary point. The right tail extension interval is defined as .

[0102] Step S404 : comparing the original value of each risk assessment indicator with the difference between the mean and the standard deviation, and the sum of the mean and the standard deviation.

[0103] Step S406 , based on the comparison result of the original value of the indicator, a segmented interval corresponding to the original value of the indicator is determined from the left tail extreme value interval, the normal fluctuation interval, and the right tail extension interval.

[0104] For example, the server can compare the size relationship between the original value of the indicator under each risk assessment indicator and the difference between the mean and standard deviation corresponding to the original value of the indicator, as well as the size relationship between the original value of the indicator under each risk assessment indicator and the sum of the mean and standard deviation corresponding to the original value of the indicator. The left-tail extreme value interval is used as the segmented interval corresponding to the original value of the indicator that is less than the difference between the mean and the standard deviation. The normal fluctuation interval is used as the segmented interval corresponding to the original value of the indicator that is greater than or equal to the difference between the mean and the standard deviation and less than the sum of the mean and the standard deviation. The right-tail extension interval is used as the segmented interval corresponding to the original value of the indicator that is greater than the sum of the mean and the standard deviation.

[0105] In this embodiment, based on the statistical distribution characteristics of the original values ​​of the indicators under each risk assessment indicator, a three-level interval division system is constructed using the mean and standard deviation to obtain the left tail extreme value interval, the normal fluctuation interval and the right tail extension interval, thereby determining the segmented interval corresponding to the measured original value of the indicator, which can achieve the synergy between statistical laws and expert knowledge: using 3 The introduction of the principle ensures the objectivity of the division of the normal fluctuation range. The addition of the expert-specified value M solves the problem of the adaptability of statistical methods to field-specific extreme values. The two together constitute the "data-driven-knowledge-constrained" double-round extreme value assignment. Its theoretical applicability is based on two premises: first, the original value data of the indicator has a unimodal distribution feature (normal distribution or approximate normal distribution) to ensure 3 The first is the validity of the principle; the second is the existence of a clear physical or logical zero point (the lower limit of the original value of the indicator is 0) and the theoretical upper limit M of the original value of the indicator agreed by experts to define the complete indicator definition domain.

[0106] Furthermore, from a methodological perspective, the segmented interval determination method provided in this embodiment breaks through the either-or limitations of traditional value assignment methods. It avoids the mechanical processing of extreme values ​​by purely data-driven methods (such as the entropy weight method) while correcting the arbitrariness of purely subjective methods (such as the Delphi method). This provides a replicable theoretical paradigm for solving the common problem of "cross-scale conversion of evaluation indicators." The segmented determination method provided in this embodiment can be further expanded by combining fuzzy set theory or Bayesian inference to meet applications in non-normally distributed data and uncertain scenarios.

[0107] In an exemplary embodiment, Figure 5 As shown, step S306 may include the following steps S502 to S508. Among them:

[0108] Step S502: determine the segmentation interval corresponding to the original value of the current indicator.

[0109] Exemplarily, the server may perform the following operation S504 when determining that the segmented interval is a left-tail extreme value interval; perform the operation S506 when determining that the segmented interval is a normal fluctuation interval; and perform the operation S508 when determining that the segmented interval is a right-tail extension interval.

[0110] Step S504: Using the proportional transformation relationship corresponding to the left tail extreme value interval, the original value of the indicator and the difference between the mean and the standard deviation are processed to obtain the corresponding indicator risk value.

[0111] Exemplarily, the risk domain corresponding to the left-tail extreme value interval can be an acceptable risk domain. Based on the logic that the smaller the original value of the indicator, the lower the risk value of the indicator, the server can use the positive proportional transformation relationship corresponding to the left-tail extreme value interval to perform calculations on the original value of the indicator to obtain the corresponding risk value of the indicator. Among them, the positive proportional transformation relationship can be used to reflect the risk attenuation characteristics of the extreme effective state between the original value of the indicator in the left-tail extreme value interval and the corresponding risk value of the indicator. Optionally, in some embodiments, the following positive proportional transformation relationship can be used to convert the left-tail extreme value interval into The original value of the indicator in the range is mapped to the value range in The risk value of the indicator within:

[0112] ,

[0113] Among them, x represents the original value of the indicator, y represents the risk value of the indicator, It represents the difference between the mean and standard deviation of the indicator risk value.

[0114] Step S506 , using a first linear interpolation relationship corresponding to the normal fluctuation range to perform calculations on the original value of the indicator and the difference between the mean and the standard deviation to obtain a corresponding indicator risk value.

[0115] For example, the risk domain corresponding to the normal fluctuation range may be a low risk domain, and the normal fluctuation range may cover 6 Full range. The server can use the first linear interpolation relationship corresponding to the normal fluctuation interval to calculate the difference between the original value of the indicator and the mean and standard deviation of the original value of the indicator to obtain the corresponding indicator risk value. Among them, the first linear interpolation relationship can reflect the slight difference in the risk level of the original value of the indicator within the normal fluctuation interval, which is consistent with the risk assessment assumption that "the risk in the normal range is negligible". Optionally, in some embodiments, the following first linear interpolation relationship can be used to convert the normal fluctuation interval into The indicator risk value within the range is mapped to the value range The risk value of the indicator within:

[0116] ,

[0117] Among them, x represents the original value of the indicator, y represents the risk value of the indicator, It represents the difference between the mean and standard deviation of the indicator risk value. Indicates the length of the normal fluctuation interval.

[0118] Step S508: Using the second linear interpolation relationship corresponding to the right tail extension interval, the original value of the indicator and the sum of the mean and the standard deviation are processed to obtain the corresponding indicator risk value.

[0119] Exemplarily, the risk domain corresponding to the right-tail extension interval may be a medium-high risk domain. The server may use the second linear interpolation relationship corresponding to the right-tail extension interval to perform calculations on the original value of the indicator in the right-tail extension interval and the sum of the mean and standard deviation corresponding to the original value of the indicator to obtain the corresponding indicator risk value. Among them, the second linear interpolation relationship can reflect the acceleration effect of the risk between the original value of the indicator in the right-tail extension interval and the corresponding indicator risk value as the indicator value increases, which is consistent with the theoretical logic of "abnormal values ​​induce high risks" in risk assessment. Optionally, in some embodiments, the server may use the following second linear interpolation relationship to convert the right-tail extension interval into The original value of the indicator in the range is mapped to the value range in The risk value of the indicator within:

[0120] ,

[0121] Among them, x represents the original value of the indicator, y represents the risk value of the indicator, and M is the maximum value of the original value of the indicator. The sum of the mean and standard deviation corresponding to the original value of the indicator. In extreme cases where the original value of the indicator exceeds the maximum value M, M is used instead of the original value of the indicator for calculation.

[0122] Optionally, in some embodiments, the server may construct a piecewise function corresponding to the original value X of the indicator using the left tail extreme value interval and its corresponding direct proportional relationship, the normal fluctuation interval and its corresponding first linear interpolation relationship, the right tail extension interval and its corresponding second linear interpolation relationship .

[0123] Optionally, in some implementations, the server may divide the risk assessment indicators into positive indicators and negative indicators.

[0124] Among them, the larger the original value of the indicator corresponding to the negative indicator, the higher the risk. For negative indicators: the server can directly use the piecewise function corresponding to the original value X of the indicator. Map the raw value of the indicator to For example, if the risk assessment indicator A is a negative indicator and its corresponding original value is X, the server can use the piecewise function The corresponding indicator risk value is calculated according to the following formula:

[0125] ,

[0126] Wherein, RA represents the indicator risk value of the risk assessment indicator A which is a negative indicator. The original value of the risk assessment index A is obtained through the piecewise function The result obtained after calculation.

[0127] The positive indicator is essentially a risk health value. That is, the larger the original value of the positive indicator, the better the operation and the lower the risk of safety accidents. For example, if risk assessment indicator B is a positive indicator, the server can calculate the corresponding indicator risk value in the following way:

[0128] ,

[0129] Wherein, RB represents the indicator risk value of the risk assessment indicator B which is a positive indicator. The original value of the risk assessment index B is obtained through the piecewise function The result obtained after calculation.

[0130] In this embodiment, by using the calculation logic corresponding to the segmented intervals to map the original value of the indicator to the indicator risk value, the relationship between the indicator value and the risk of power safety accidents can be reflected, thereby improving the reliability of the indicator risk value.

[0131] In an exemplary embodiment, Figure 6 As shown, a method for determining the indicator weight parameter is also provided, including the following steps S602 to S606.

[0132] Step S602: Obtain the event weight parameter of the accident-causing event and the number of associated indicators of the accident-causing event.

[0133] For example, the server may obtain the event weight parameter of the accident-causing event and all risk assessment indicators associated with the accident-causing event from a local database or a data communication network, and count the number of risk assessment indicators associated with the accident-causing event to obtain the number of associated indicators of the accident-causing event.

[0134] Step S604 : Distribute the event weight parameter of the accident-causing event to each risk assessment indicator associated with the accident-causing event according to the number of associated indicators, and obtain a weight distribution value of each risk assessment indicator relative to the accident-causing event.

[0135] For example, the server may calculate the ratio of the event weight parameter of the accident-causing event to the number of associated indicators as the weight distribution value of each risk assessment indicator associated with the accident-causing event. , the server can set its event weight parameter Evenly distribute to all risk assessment indicators associated with the accident causal events. association If there are risk assessment indicators, the server can calculate the weight distribution value according to the following method:

[0136] ,

[0137] in, Can indicate the event that caused the accident Associated risk assessment indicators ( , Accident-causing events The collection of all risk assessment indicators associated with the accident causal events The weight distribution value obtained at . Can indicate the event that caused the accident The event weight parameter. Can indicate the event that caused the accident The number of associated indicators.

[0138] Step S606 , accumulating the weight distribution values ​​of the risk assessment indicators to obtain the indicator weight parameters corresponding to the risk assessment indicators.

[0139] For example, the server may perform the following operations for each risk assessment indicator: cumulatively add the weighted values ​​of the current risk assessment indicator relative to all the accident-causing events associated with it, and use the sum of the weighted values ​​of all the accident-causing events associated with the current risk assessment indicator as the indicator weight parameter corresponding to the current risk assessment indicator. Traverse the collection of all associated accident-causing events , calculate the indicator weight parameters according to the following method:

[0140] ,

[0141] in, Can represent risk assessment indicators The indicator weight parameter. Can represent risk assessment indicators The collection of all associated incident causal events Any one of the accident-causing events. Can represent risk assessment indicators Relative to accident-causing events The weight distribution value of . Can indicate the event that caused the accident The event weight parameter. Can indicate the event that caused the accident The number of associated indicators.

[0142] Optionally, in some implementations, the server may further perform matrix operations according to the following formula to implement the operations of steps S604 to S606 above:

[0143] ,

[0144] in, Represents the indicator weight vector composed of the indicator weight parameters of the risk assessment indicators. express dimensional correlation matrix, m represents the total number of accident-causing events, n represents the total number of risk assessment indicators, and w represents the event weight vector composed of the event weight parameters of the accident-causing events.

[0145] If the risk assessment indicator Related to the accident causation event , then the elements in the incidence matrix C Can represent risk assessment indicators Relative to accident-causing events The weight distribution value of . Can indicate the event that caused the accident The number of associated indicators.

[0146] In this embodiment, by following the principle of distribution fairness (assuming that the risk assessment indicators associated with the same accident-causing event contribute equally to the accident-causing event to achieve equivalent equal distribution of event weight parameters) and the principle of aggregation integrity (integrating the weight distribution values ​​of all accident-causing events associated with the risk assessment indicator and accumulating them to obtain the final indicator weight parameter of the risk assessment indicator) during the weight distribution process, not only can the indicator weight deviation caused by subjective preference be effectively avoided, but also the normalization condition can be strictly satisfied in the weight transfer process ( , that is, the indicator weight parameters of n risk assessment indicators The cumulative value is 1, and the event weight parameter of m accident-causing events is The cumulative value of is 1), achieving complete mapping and conservation of the total weight between the accident causal event layer and the risk assessment indicator layer.

[0147] In an exemplary embodiment, Figure 7As shown, a method for calculating the event weight parameter is also provided, including the following steps S702 to S710.

[0148] Step S702: Obtain historical accident samples and construct a power safety accident tree corresponding to the historical accident samples.

[0149] Among them, historical accident samples can be used to characterize samples of power operation data extracted from high-frequency or high-loss power safety accidents that have occurred.

[0150] For example, the server can retrieve historical accident samples from a local database or data network. An accident tree analysis is performed on these historical accident samples. Based on deductive reasoning logic and a top-down fault decomposition strategy, the system analyzes intermediate events (triggering conditions) layer by layer, starting from the top event (accident type). Ultimately, the causal event is located and a power safety accident tree corresponding to the historical accident sample is constructed. Deductive reasoning logic constructs an accident causal network using Boolean logic gates, quantitatively revealing the correlation paths between various risk factors and providing data support for subsequent risk classification management and safety measure formulation.

[0151] For example, the server can use "electric shock casualties of power supply company personnel" as the top event and determine that the direct causes of "electric shock casualties of power supply company personnel" include: the occurrence of electric shock danger and the failure to correct the danger. Moreover, these two events must occur at the same time for the top event "electric shock casualties of power supply company personnel" to occur. At this time, the event "occurrence of electric shock danger" and the event "failure to correct the danger" can be connected using the AND gate. Similarly, if any one of the multiple direct cause events that cause the top event will cause the top event, then the direct cause events corresponding to the top event can be connected using the OR gate.

[0152] Optionally, in some embodiments, multiple power safety accident trees can be constructed, such as electric shock accident trees, height fall accident trees, object strike accident trees, mechanical injury accident trees, collapse injury accident trees, vehicle injury accident trees, explosion and fire accident trees, poisoning and suffocation accident trees, scalding accident trees, and lightning strike accident trees.

[0153] Step S704: determining a target cut set where the accident-causing event is located from the minimum cut set corresponding to the power safety accident tree.

[0154] The minimal cut set can be used to represent the minimum set of events that are the direct cause of the top event. That is, when all events in the minimal cut set occur simultaneously, the top event is guaranteed to occur. However, if any event is removed from the minimal cut set, the set can no longer cause the top event to occur.

[0155] For example, the server can simplify the power safety accident tree according to the top event, determine the minimum cut set of the power safety accident tree, and obtain the minimum cut set including the accident causative event as the target cut set where the accident causative event is located.

[0156] For example, the minimum cut set corresponding to the top event "electric shock casualties of power supply enterprise personnel" can include cut set 1 {unqualified grounding system, lack of safety knowledge of employees, equipment insulation failure and leakage, working under the influence of alcohol, leakage protection device failure, damaged insulation tools}, cut set 2 {unqualified grounding system, physical and mental reasons of employees, equipment insulation failure and leakage, working under the influence of alcohol, leakage protection device failure, damaged insulation tools}, and cut set 3 {unqualified grounding system, lack of safety awareness of employees, equipment insulation failure and leakage, working under the influence of alcohol, leakage protection device failure, damaged insulation tools}. Then, the target cut set where the accident-causing event "unqualified grounding system" is located includes cut set 1, cut set 2, and cut set 3, and the target cut set where the accident-causing event "lack of safety knowledge of employees" is located is cut set 1.

[0157] Step S706 : determining the structural importance coefficient of the accident-causing event according to the total number of target cut sets and the total number of minimum cut sets.

[0158] For example, the server may calculate the ratio of the total number of target cut sets containing the accident causal events to the total number of minimum cut sets of the power safety accident tree as the structural importance coefficient of the accident causal events in the power safety accident tree.

[0159] Step S708 : determining the top event of the power safety accident tree where the accident causative event is located, and determining a weight parameter of the top event according to the occurrence frequency of the top event.

[0160] For example, the server can determine the number of occurrences of the top event of the power safety accident tree where the accident-causing event is located, as well as the total number of accidents corresponding to the historical accident samples. The ratio of the number of occurrences of the top event to the total number of accidents is calculated to obtain the frequency of occurrence of the top event. Optionally, in some embodiments, the frequency of occurrence of the top event can be directly used as the weight parameter of the top event. Alternatively, in other embodiments, based on the pre-stored mapping relationship between the frequency of occurrence and the weight parameter (the higher the frequency, the higher the corresponding weight parameter), the weight parameter corresponding to the frequency of occurrence of the top event can be determined as the weight parameter of the top event.

[0161] In step S710 , the top event weight parameter and the structure importance coefficient are used to perform calculation processing to obtain the event weight parameter of the accident-causing event.

[0162] For example, the server may multiply the structural importance coefficient of the accident-causing event by the top event weight parameter of the top event of the power safety accident tree where the accident-causing event is located, to obtain a modified importance coefficient of the accident-causing event relative to the current power safety accident tree. If there is only one power safety accident tree where the accident-causing event is located, the modified importance coefficient may be used as the event weight parameter of the accident-causing event. If there are multiple power safety accident trees where the accident-causing event is located, the sum of the modified importance coefficients of the accident-causing event relative to each power safety accident tree may be used as the event weight parameter of the accident-causing event.

[0163] In this embodiment, the initial structural importance coefficient of the accident-causing event is calculated by using the minimum cut set, and then the structural importance coefficient is corrected in combination with the top event weight parameter to obtain the true importance as the event weight parameter of the accident-causing event. This can comprehensively consider the ranking of the accident-causing event in the power safety accident tree, the frequency of occurrence of the top event of the power safety accident tree where the accident-causing event is located, and the repeated occurrence of the accident-causing event in multiple power safety accident trees, thereby improving the accuracy of determining the event weight parameter.

[0164] In an exemplary embodiment, Figure 8 As shown, a method for determining the risk level of a power supply enterprise is also provided, including the following steps S802 to S812.

[0165] Step S802: Acquire power operation data of the power supply enterprise.

[0166] In step S804, the power operation data is processed using the calculation method corresponding to each risk assessment indicator to obtain the original value of the power supply enterprise under each risk assessment indicator.

[0167] Step S806: Determine the segmentation interval corresponding to the original value of each risk assessment indicator according to the mean and standard deviation of the original value of the indicator.

[0168] Step S808: Convert the original value of the indicator into the corresponding risk value of the indicator according to the relationship between the original value corresponding to the segmented interval and the risk value.

[0169] Step S810 , performing weighted calculation processing on the corresponding indicator risk value using the indicator weight parameter corresponding to each risk assessment indicator to obtain the weighted risk value corresponding to each risk assessment indicator.

[0170] Step S812: The weighted risk values ​​of multiple dimensions are integrated to obtain the target risk value of the power supply enterprise, and based on the relationship between the preset risk value and the risk level, the enterprise risk level that matches the target risk value is determined.

[0171] Alternatively, in some embodiments, Figure 9 The figure provides a schematic diagram of a power safety fault tree, including top event 930, event 951, event 953, accident-causing event 971, accident-causing event 973, accident-causing event 975, and accident-causing event 977. The simultaneous occurrence of event 951 and event 953 will result in top event 930. Therefore, an AND gate can be used to connect event 951 and event 953. The occurrence of either accident-causing event 971 or accident-causing event 973 will result in event 951. Therefore, a NOT gate can be used to connect accident-causing event 971 and accident-causing event 973. Only when accident-causing event 971 and accident-causing event 973 occur simultaneously will event 953. Therefore, an AND gate can be used to connect accident-causing event 971 and accident-causing event 973.

[0172] right Figure 9 By simplifying the power safety accident tree shown in the figure, we can get its minimum cut set including: {event 951, accident-causing event 971}, {event 951, accident-causing event 973}, {event 953, accident-causing event 975, accident-causing event 977}. Thus, we can get the accident-causing event 971 in Figure 9 The structural importance coefficient in the power safety accident tree shown is one third.

[0173] Optionally, in some embodiments, the server can also classify and aggregate accident-causing events based on the four-dimensional system of "people-things-environment-management". Among them, the personnel safety capability dimension can focus on events related to behavior, awareness, and skill management. For example, human events such as failure to follow procedures and working under the influence of alcohol correspond to accident-causing events such as the safety learning index and the serious violation index. The equipment reliability dimension can cover events related to equipment, tools, and protective facilities. For example, equipment events such as equipment insulation failure and hanging basket failure correspond to accident-causing events such as the timely rate of hidden danger control and the index of equipment running with hidden dangers. The environmental risk control dimension can target events related to work scenarios and natural conditions. For example, environmental events such as night work and complex geology correspond to accident-causing events such as the medium- and high-risk work index and the work preparation index. The management and supervision effectiveness dimension can control events related to systems, processes, and execution. For example, management events such as the lack of dedicated supervision and failure to rectify hidden dangers correspond to accident-causing events such as the inspection coverage rate and the timely rate of violation rectification. This forms a four-dimensional indicator system covering all factors. Each dimension achieves classified control and quantitative monitoring of accident causes through mapping typical events with corresponding indicators (such as the accident-causing event "failure to follow procedures" → the risk assessment indicator "Safety Learning Index").

[0174] Optionally, in some implementations, the server can also perform logical closed-loop verification on the constructed indicator system to ensure that each risk assessment indicator is anchored to at least one accident-causing event, achieving full coverage of accident-causing events and establishing a complete closed-loop "accident cause → management action → quantitative indicator" system. For example, the accident-causing event of exposed, unprotected live parts of equipment can be transformed into quantitative risk assessment indicators such as the index of operating equipment with hidden dangers and the timely rate of hidden danger remediation through the management action of hidden danger rectification. This forms a management closed loop from problem identification (exposed equipment) to action implementation (rectification) to quantification of results (index reduction). This achieves verifiability and traceability from accident cause to management effectiveness.

[0175] Optionally, in some embodiments, the server can also perform systematic verification of the indicator system. For example, the server can calculate the coverage rate of risk assessment indicators for accident-causing events using a matrix mapping table (which stores the correlation between risk assessment indicators and accident-causing events). The server can use Pearson correlation analysis to calculate the correlation coefficient between the risk assessment indicators and the power safety accident rate, ensuring that the correlation coefficients are all greater than a preset threshold (e.g., 0.65). The server can use factor analysis to extract the common factors of the risk assessment indicators in each dimension, calculate the degree of deviation of the risk assessment indicators in each dimension from the sphericity assumption (no correlation between variables), and obtain the cumulative variance contribution rate. Structural Equation Modeling (SEM) can then be used to verify the causal path of the indicator system. The server can formulate corresponding corrective measures based on the enterprise risk level and pilot them in power supply enterprises. After the pilot, power operation data collected from the pilot operation can be used to recalculate the indicator risk value. When the change in the indicator risk value matches the change in the power safety accident rate, the causal relationship of "indicator improvement → accident reduction" can be verified.

[0176] In this embodiment, by deducing the cause of the accident based on the accident tree analysis, and through the mapping of "accident cause → management action → quantitative indicator", a causal closed-loop indicator is constructed (such as the causal closed-loop mapping of the accident cause event "damage to insulating tools" → the risk assessment indicator "index of expired tools and equipment not submitted for inspection"). This can ensure the scientific and standard risks of the indicators and solve the problem that the existing risk assessment methods (such as the hierarchical analysis method and the expert scoring method) rely on subjective experience to select indicators and fail to establish a scientific mapping relationship with the cause of the accident, resulting in insufficient representativeness of the indicators and the inability to accurately reflect the causal missing of key risk factors (such as the lack of correlation between "equipment insulation failure" and "timely rate of hidden danger control").

[0177] In this embodiment, the initial weights of accident-causing events are calculated by using the structural importance of the minimum cut set of the power safety accident tree, and then the event weight parameters of the accident-causing events are obtained by correction based on the frequency of occurrence of the top event. This can achieve dynamic adjustment of the weights, improve the adaptability of the risk level determination method, and solve the problem that traditional risk assessment methods (such as the hierarchical analysis method) use fixed weights and cannot be dynamically adjusted to match risk evolution (such as the surge in the risk of falling from heights caused by seasonal work peaks), resulting in risk assessment results lagging behind actual risk changes.

[0178] In this embodiment, by integrating the four-dimensional data of people (safety learning index), objects (index of equipment operating with hidden dangers), environment (night operation index), and management (inspection coverage rate), a multi-dimensional collaborative evaluation of risk assessment indicators is conducted. This can systematically quantify the comprehensive risk and solve the problem that existing risk assessment methods focus on a single dimension (such as only analyzing violation data or equipment defects) and have difficulty in identifying multi-factor coupling risks (such as the superimposed effect of "night operation + personnel fatigue").

[0179] In this embodiment, by utilizing the quantitative association between risk assessment indicators and accident-causing events, accurate mapping from data to risk warnings can be achieved, solving the problem that existing risk assessment methods integrate multi-source data but only perform statistical display (such as ranking the number of violations) and fail to use quantitative models to explore the deep association between data and risks (such as failing to map "overdue inspection of tools" as a leading indicator of mechanical injury accidents).

[0180] In summary, by adopting the risk level determination method for power supply enterprises provided in the above embodiments, those skilled in the art can solve the three core problems of causal loss, static evaluation, and dimensional limitation in the prior art, thereby improving the accuracy and timeliness of enterprise risk assessment.

[0181] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

[0182] Based on the same inventive concept, the embodiments of the present application also provide a device for determining the risk level of a power supply enterprise, which is used to implement the above-mentioned method for determining the risk level of a power supply enterprise. The implementation solution provided by this device is similar to the implementation solution described in the above-mentioned method. Therefore, the specific limitations in the embodiments of one or more devices for determining the risk level of a power supply enterprise provided below can be found in the above-mentioned limitations on the method for determining the risk level of a power supply enterprise, and will not be repeated here.

[0183] In an exemplary embodiment, Figure 10 As shown, a risk level determination device 1000 for a power supply enterprise is provided, which is used for early warning of accident risks at the operation site of the power supply enterprise, including: a data acquisition module 1002, an indicator determination module 1004, an indicator weighting module 1006 and a level determination module 1008, wherein:

[0184] The data acquisition module 1002 is used to acquire the power operation data of the power supply enterprise.

[0185] The indicator determination module 1004 is used to determine the original values ​​of the indicators of the power supply enterprise under the risk assessment indicators of multiple dimensions based on the power operation data, and map the original values ​​of the indicators to corresponding indicator risk values ​​based on the data distribution characteristics of the original values ​​of the indicators. The risk assessment indicators are determined based on the accident-causing events of the power safety accidents of the power supply enterprise.

[0186] The indicator weighting module 1006 is used to perform weighted operation processing on the corresponding indicator risk value using the indicator weight parameters corresponding to each risk assessment indicator to obtain the weighted risk value corresponding to each risk assessment indicator. The indicator weight parameters are determined based on the event weight parameters of the accident-causing event associated with the risk assessment indicator. The event weight parameters are used to characterize the structural importance of the accident-causing event in the power safety accident tree of the power supply enterprise.

[0187] The level determination module 1008 is used to integrate the weighted risk values ​​of multiple dimensions to obtain the target risk value of the power supply enterprise, and determine the enterprise risk level that matches the target risk value based on the relationship between the preset risk value and the risk level.

[0188] In an exemplary embodiment, the indicator determination module 1004 includes: an original value determination unit, which is used to perform calculations on the power operation data using the calculation methods corresponding to each risk assessment indicator to obtain the original value of the indicator of the power supply enterprise under each risk assessment indicator; an interval determination unit, which is used to determine the segmented interval corresponding to the original value of the indicator based on the mean and standard deviation of the original value of the indicator under each risk assessment indicator; an indicator conversion unit, which is used to convert the original value of the indicator into the corresponding indicator risk value based on the relationship between the original value corresponding to the segmented interval and the risk value.

[0189] In an exemplary embodiment, the interval determination unit is also used to use the difference between the mean and standard deviation of the original value of the indicator and the sum of the mean and standard deviation of the original value of the indicator to divide the corresponding left-tail extreme value interval, normal fluctuation interval and right-tail extension interval; compare the original value of the indicator under each risk assessment indicator with the difference between the mean and standard deviation and the sum of the mean and standard deviation; based on the comparison result of the original value of the indicator, determine the segmented interval corresponding to the original value of the indicator from the left-tail extreme value interval, normal fluctuation interval and right-tail extension interval.

[0190] In an exemplary embodiment, the indicator conversion unit is also used to, when the segmented interval is a left-tail extreme value interval, use the direct proportional transformation relationship corresponding to the left-tail extreme value interval to perform calculation processing on the original value of the indicator and the difference between the mean and the standard deviation to obtain the corresponding indicator risk value; when the segmented interval is a normal fluctuation interval, use the first linear interpolation relationship corresponding to the normal fluctuation interval to perform calculation processing on the original value of the indicator and the difference between the mean and the standard deviation to obtain the corresponding indicator risk value; when the segmented interval is a right-tail extension interval, use the second linear interpolation relationship corresponding to the right-tail extension interval to perform calculation processing on the original value of the indicator and the sum of the mean and the standard deviation to obtain the corresponding indicator risk value.

[0191] In an exemplary embodiment, the risk level determination device 1000 of the power supply enterprise includes an indicator weight determination module, which is used to obtain the event weight parameters of the accident-causing event and the number of associated indicators of the accident-causing event; according to the number of associated indicators, the event weight parameters of the accident-causing event are evenly distributed to each risk assessment indicator associated with the accident-causing event to obtain the weight distribution value of each risk assessment indicator relative to the accident-causing event; the weight distribution values ​​of each risk assessment indicator are accumulated respectively to obtain the indicator weight parameters corresponding to each risk assessment indicator.

[0192] In an exemplary embodiment, the risk level determination device 1000 of the power supply enterprise includes an event weight determination module, which is used to obtain historical accident samples and construct a power safety accident tree corresponding to the historical accident samples; determine the target cut set where the accident-causing event is located from the minimum cut set corresponding to the power safety accident tree; determine the structural importance coefficient of the accident-causing event based on the total number of target cut sets and the total number of minimum cut sets; determine the top event of the power safety accident tree where the accident-causing event is located, and determine the top event weight parameter based on the occurrence frequency of the top event; use the top event weight parameter and the structural importance coefficient to perform calculation processing to obtain the event weight parameter of the accident-causing event.

[0193] Each module in the power supply enterprise risk level determination device 1000 can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0194] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 11 As shown. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store power operation data, indicator risk values, indicator weight parameters, weighted risk values, enterprise risk levels, etc. The I / O 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 via a network connection. When the computer program is executed by the processor, it implements a method for determining the risk level of a power supply enterprise.

[0195] Those skilled in the art will understand that Figure 11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0196] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0197] In an exemplary 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 steps in the above-mentioned method embodiments are implemented.

[0198] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0199] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the 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 above-mentioned embodiments. In particular, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of a non-volatile memory and a volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0200] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0201] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for determining the risk level of a power supply enterprise, characterized in that: Used for accident risk warning at power supply enterprise operation sites; The method comprises: Obtain power operation data from power supply companies; Determining original values ​​of risk assessment indicators of the power supply enterprise under multiple dimensions based on the power operation data, and mapping the original values ​​of the indicators to corresponding risk values ​​of the indicators based on data distribution characteristics of the original values ​​of the indicators, wherein the risk assessment indicators are determined based on accident-causing events of power safety accidents of the power supply enterprise; Performing weighted calculations on the corresponding indicator risk values ​​using the indicator weight parameters corresponding to each of the risk assessment indicators to obtain weighted risk values ​​corresponding to each of the risk assessment indicators, wherein the indicator weight parameters are determined based on the event weight parameters of the accident-causing events associated with the risk assessment indicators, and the event weight parameters are used to characterize the structural importance of the accident-causing events in the power safety accident tree of the power supply enterprise; The target risk value of the power supply enterprise is obtained by integrating the weighted risk values ​​of multiple dimensions, and the enterprise risk level that matches the target risk value is determined based on the relationship between the preset risk value and the risk level.

2. The method according to claim 1, characterized in that The determining, based on the power operation data, the original values ​​of the indicators of the power supply enterprise under the risk assessment indicators of multiple dimensions, and mapping the original values ​​of the indicators to corresponding indicator risk values ​​based on data distribution characteristics of the original values ​​of the indicators, includes: The power operation data is processed by respectively using the calculation method corresponding to each of the risk assessment indicators to obtain the original value of the indicator of the power supply enterprise under each of the risk assessment indicators; Determine the segmentation interval corresponding to the original value of the indicator according to the mean and standard deviation of the original value of each risk assessment indicator; The indicator original value is converted into a corresponding indicator risk value according to the relationship between the original value corresponding to the segmented interval and the risk value.

3. The method according to claim 2, characterized in that Determining the segmented intervals corresponding to the original values ​​of the indicators according to the mean and standard deviation of the original values ​​of the indicators under each of the risk assessment indicators includes: The difference between the mean and standard deviation of the original values ​​of the indicator and the sum of the mean and standard deviation of the original values ​​of the indicator are used to divide the corresponding left tail extreme value interval, normal fluctuation interval and right tail extension interval; Comparing the original value of each risk assessment indicator with the difference between the mean and the standard deviation and the sum of the mean and the standard deviation; Based on the comparison result of the original value of the indicator, a segmented interval corresponding to the original value of the indicator is determined from the left tail extreme value interval, the normal fluctuation interval and the right tail extension interval.

4. The method according to claim 3, characterized in that The converting the original value of the indicator into the corresponding risk value of the indicator according to the relationship between the original value corresponding to the segmented interval and the risk value includes: In the case where the segmented interval is the left tail extreme value interval, the original value of the indicator and the difference between the mean and the standard deviation are processed by using a direct proportional transformation relationship corresponding to the left tail extreme value interval to obtain a corresponding indicator risk value; In the case where the segmented interval is the normal fluctuation interval, the original value of the indicator and the difference between the mean and the standard deviation are processed by using a first linear interpolation relationship corresponding to the normal fluctuation interval to obtain a corresponding indicator risk value; When the segmented interval is the right-tail extension interval, the second linear interpolation relationship corresponding to the right-tail extension interval is used to perform calculation processing on the original value of the indicator and the sum of the mean and the standard deviation to obtain the corresponding indicator risk value.

5. The method according to any one of claims 1 to 4, characterized in that The method for determining the indicator weight parameter includes: Obtaining an event weight parameter of the accident-causing event and the number of associated indicators of the accident-causing event; Distributing the event weight parameter of the accident-causing event equally to each risk assessment indicator associated with the accident-causing event according to the number of associated indicators, and obtaining a weight distribution value of each risk assessment indicator relative to the accident-causing event; The weight distribution values ​​of the risk assessment indicators are accumulated respectively to obtain the indicator weight parameters corresponding to the risk assessment indicators.

6. The method according to claim 5, characterized in that The method for determining the event weight parameter includes: Acquire historical accident samples and construct a power safety accident tree corresponding to the historical accident samples; Determining the target cut set where the accident-causing event is located from the minimum cut set corresponding to the power safety accident tree; determining a structural importance coefficient of the accident-causing event according to the total number of the target cut sets and the total number of the minimum cut sets; Determine the top event of the power safety accident tree where the accident causation event is located, and determine the top event weight parameter according to the occurrence frequency of the top event; The top event weight parameter and the structure importance coefficient are used to perform calculation processing to obtain the event weight parameter of the accident-causing event.

7. A risk level determination device for a power supply enterprise, characterized in that: Used for accident risk warning at power supply enterprise operation sites; The device comprises: Data acquisition module, used to obtain power operation data of power supply enterprises; An indicator determination module, configured to determine, based on the power operation data, original values ​​of the indicators of the power supply enterprise under multiple dimensions of risk assessment indicators, and map the original values ​​of the indicators to corresponding indicator risk values ​​based on data distribution characteristics of the original values ​​of the indicators, wherein the risk assessment indicators are determined based on accident-causing events of power safety accidents of the power supply enterprise; An indicator weighting module is used to perform weighted calculation processing on the corresponding indicator risk value using the indicator weight parameter corresponding to each of the risk assessment indicators to obtain the weighted risk value corresponding to each of the risk assessment indicators, wherein the indicator weight parameter is determined based on the event weight parameter of the accident-causing event associated with the risk assessment indicator, and the event weight parameter is used to characterize the structural importance of the accident-causing event in the power safety accident tree of the power supply enterprise; The level determination module is used to integrate the weighted risk values ​​of multiple dimensions to obtain the target risk value of the power supply enterprise, and determine the enterprise risk level that matches the target risk value based on the relationship between the preset risk value and the risk level.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: 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 a 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 a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images