Method, device and equipment for identifying periodic characteristics of personal risk in power scenarios

Abstract

The present application relates to a method for identifying a personal risk characteristic cycle in an electric power scenario, and relates to the field of electric power technology, including: determining the accident energy importance of historical accident samples; obtaining risk factor data sampled under a target risk factor of the historical accident samples; determining the accident energy value of the historical accident samples under the target risk factor according to the accident energy importance, risk factor data, accident occurrence time, and the personal risk characteristic cycle to be identified of the target risk factor; selecting a target number of target historical accident samples, and determining the average accident energy value according to the accident energy value of each target historical accident sample under the target risk factor; determining the risk value of the power supply enterprise according to the average accident energy value; taking the maximum risk value as the target and the convergence of the average accident energy value as the constraint condition, constructing a personal risk characteristic cycle identification model to obtain the personal risk characteristic cycle. The use of this method can improve the accuracy of the personal risk characteristic cycle.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device and equipment for periodic identification of personal risk characteristics in electric power scenarios. Background Art

[0002] The power industry is a basic lifeline industry of a country. Therefore, it is of great significance to ensure the safety of power production. Although the overall level of safety management in the power industry has been greatly improved with the increasing attention paid to power production safety management, safety accidents and incidents still occur from time to time. Therefore, it is urgent to adopt technical means to explore the laws of power production risks so that targeted control measures can be specified to reduce the occurrence of safety accidents. In recent years, with the digital and intelligent transformation of power grids, the information management platform of power supply companies has accumulated a large amount of power production safety data for analysis. For the personal risk assessment of power supply companies, the identification of personal risk characteristic cycles can realize the dynamic update of risk data, thereby identifying the personal risks of power supply companies in real time, and formulating control measures in time to prevent accidents.

[0003] In traditional technologies, the personal risk characteristic cycle is basically mapped to the frequency domain by Fourier transform and Hilbert-Huang transform to the risk factor data in the information management platform, and the personal risk characteristic cycle of the risk factor is determined by analyzing the main frequency component and the inverse relationship between the cycle and the frequency. Alternatively, the change characteristics of the risk factor data are extracted by using the time series analysis method, which is used as the personal risk characteristic cycle of the risk factor. However, these traditional personal risk characteristic cycle identification methods all focus on the risk factor data itself. For power personal risk, it is far from enough to analyze the risk factor data itself to obtain the change cycle. The personal risk characteristic cycle obtained by such analysis cannot effectively reflect the personal risk characteristics contained in the massive data of the information management platform, and the accuracy of the obtained personal risk characteristic cycle is low, which makes it impossible to accurately identify the personal risks of power supply enterprises in real time based on the personal risk characteristic cycle, and formulate control measures in time, so as to effectively prevent accidents. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device and equipment for identifying personal risk characteristic cycles in power scenarios that can improve the accuracy of personal risk characteristic cycles in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for identifying a periodicity of personal risk characteristics in an electric power scenario, the method comprising:

[0006] Identify multiple historical accident samples of power supply companies;

[0007] For each of the historical accident samples, determining the accident energy importance of the historical accident sample according to the accident type and number of casualties of the historical accident sample;

[0008] Acquire risk factor data sampled under a target risk factor of the historical accident sample; the target risk factor is any one of a plurality of risk factors of the historical accident sample;

[0009] Determine the accident energy value of the historical accident sample under the target risk factor according to the accident energy importance, the risk factor data, the accident occurrence time of the historical accident sample and the personal risk characteristic period to be identified of the target risk factor;

[0010] Selecting a target number of target historical accident samples to be determined from the multiple historical accident samples, and determining an average accident energy value of the target number of target historical accident samples under the target risk factor according to the accident energy value of each of the target historical accident samples under the target risk factor;

[0011] Determine the risk value of the power supply enterprise according to the average accident energy values ​​of the target historical accident samples of the target number under the multiple risk factors;

[0012] Taking the maximum risk value as the goal and the convergence of the average accident energy values ​​of the multiple risk factors as the constraint condition, a personal risk characteristic period identification model is constructed;

[0013] Solve the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of each of the multiple risk factors.

[0014] In a second aspect, the present application provides a device for identifying a periodicity of personal risk characteristics in an electric power scenario, the device comprising:

[0015] A determination module is used to determine a plurality of historical accident samples of a power supply enterprise; for each of the historical accident samples, the accident energy importance of the historical accident sample is determined according to the accident type and number of casualties of the historical accident sample;

[0016] An acquisition module, used to acquire risk factor data sampled under a target risk factor of the historical accident sample; the target risk factor is any one of a plurality of risk factors of the historical accident sample;

[0017] The determination module is also used to determine the accident energy value of the historical accident sample under the target risk factor according to the accident energy importance, the risk factor data, the accident occurrence time of the historical accident sample and the personal risk characteristic period to be identified of the target risk factor; select a target number of target historical accident samples to be determined from the multiple historical accident samples, and determine the average accident energy value of the target historical accident samples of the target number under the target risk factor according to the accident energy value of each of the target historical accident samples under the target risk factor; determine the risk value of the power supply enterprise according to the average accident energy value of the target historical accident samples of the target number under the multiple risk factors;

[0018] A construction module, for constructing a personal risk characteristic period identification model with the maximum risk value as the goal and the convergence of the average accident energy values ​​of the respective risk factors as the constraint condition;

[0019] A solution module is used to solve the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycle of each of the multiple risk factors.

[0020] In a third aspect, the present application provides a computer device including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the method embodiments of the present application are implemented.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the method embodiments of the present application.

[0022] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the steps in the method embodiments of the present application when the computer program is executed by a processor.

[0023] The above-mentioned method, device and equipment for identifying the periodicity of personal risk characteristics in the power scenario are as follows: by determining multiple historical accident samples of the power supply enterprise; for each historical accident sample, according to the accident type and number of casualties of the historical accident sample, determining the accident energy importance of the historical accident sample; obtaining the risk factor data sampled under the target risk factor of the historical accident sample; the target risk factor is any one of the multiple risk factors of the historical accident sample; according to the accident energy importance, risk factor data, the accident occurrence time of the historical accident sample and the personal risk characteristic period to be identified of the target risk factor, determining the accident energy value of the historical accident sample under the target risk factor; A target number of target historical accident samples to be determined is selected from multiple historical accident samples, and the average accident energy value of the target number of target historical accident samples under the target risk factor is determined according to the accident energy value of each target historical accident sample under the target risk factor; the risk value of the power supply enterprise is determined according to the average accident energy value of the target number of target historical accident samples under multiple risk factors; a personal risk characteristic cycle identification model is constructed with the maximum risk value as the goal and the convergence of the average accident energy values ​​under multiple risk factors as the constraint condition; the personal risk characteristic cycle identification model is solved to obtain the personal risk characteristic cycles of multiple risk factors. Compared with the traditional personal risk characteristic cycle identification method, the present application defines the accident energy importance of historical accident samples by the accident type and number of casualties of historical accident samples, and maps the accident energy value of historical accident samples based on the accident occurrence time of historical accident samples, and constructs a personal risk characteristic cycle identification model based on the mapped accident energy value, and solves the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of multiple risk factors. In this way, in the process of identifying the personal risk characteristic cycle, in addition to paying attention to the risk factor data itself, we also pay attention to other data such as the accident type, number of casualties, and accident time of historical accident samples accumulated in the information management platform. We can deeply explore the personal risk characteristics contained in the massive data of the information management platform and improve the accuracy of the personal risk characteristic cycle. Therefore, we can accurately identify the personal risks of power supply enterprises based on more accurate personal risk characteristic cycles, and formulate control measures in a timely manner, so as to effectively prevent accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is an application environment diagram of a method for identifying a periodicity of personal risk characteristics in an electric power scenario in an embodiment;

[0025] Figure 2 It is a flowchart of a method for identifying a periodicity of personal risk characteristics in an electric power scenario in one embodiment;

[0026] Figure 3A schematic diagram of the membership functions of accident type, number of casualties and accident energy importance in one embodiment;

[0027] Figure 4 Schematic diagram of a process for selecting target historical accident samples in one embodiment;

[0028] Figure 5 It is a structural block diagram of a device for identifying a periodicity of personal risk characteristics in an electric power scenario in one embodiment;

[0029] Figure 6 is an internal structure diagram of a computer device in one embodiment;

[0030] FIG. 7 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] The method for identifying the characteristic period of personal risk in power scenarios provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can be set up separately and can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other servers. Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptops, smart phones, tablet computers, vehicle-mounted terminals, intelligent voice interaction devices, aircraft, smart home appliances and portable wearable devices. Smart home appliances can be smart speakers, smart TVs and smart air conditioners. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, cloud security, host security and other network security services, CDN, and basic cloud computing services such as big data and artificial intelligence platforms. The terminal 102 and the server 104 can be directly or indirectly connected by wired or wireless communication, and this application is not limited here.

[0033] The server 104 may determine multiple historical accident samples of the power supply enterprise; for each historical accident sample, determine the accident energy importance of the historical accident sample according to the accident type and number of casualties of the historical accident sample. The server 104 may obtain the risk factor data sampled under the target risk factor of the historical accident sample; the target risk factor is any one of the multiple risk factors of the historical accident sample; determine the accident energy value of the historical accident sample under the target risk factor according to the accident energy importance, risk factor data, the accident occurrence time of the historical accident sample and the personal risk characteristic period to be identified of the target risk factor. The server 104 may select a target number of target historical accident samples to be determined from multiple historical accident samples, and determine the average accident energy value of the target number of target historical accident samples under the target risk factor according to the accident energy value of each target historical accident sample under the target risk factor; determine the risk value of the power supply enterprise according to the average accident energy value of the target number of target historical accident samples under multiple risk factors. The server 104 can construct a personal risk characteristic cycle identification model with the maximum risk value as the goal and the convergence of the average accident energy values ​​under multiple risk factors as the constraint condition; and solve the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of the multiple risk factors.

[0034] It is understood that the server 104 may periodically send the personal risk characteristics of the plurality of risk factors to the terminal 102 for further processing, and this embodiment does not limit this. It is understood that Figure 1 The application scenarios are only for illustration and are not limited to this.

[0035] In one embodiment, Figure 2 As shown, a method for identifying a characteristic period of personal risk in an electric power scenario is provided. The method can be applied to a computer device, which can be a terminal or a server. That is, the method can be executed by the terminal or the server alone, or can be implemented through interaction between the terminal and the server. This embodiment is described by taking the method applied to a computer device as an example, and includes the following steps:

[0036] Step 202: determine a plurality of historical accident samples of the power supply enterprise.

[0037] Among them, historical accident samples refer to accidents that occurred in power supply companies within a historical period.

[0038] Step 204: for each historical accident sample, determine the accident energy importance of the historical accident sample according to the accident type and number of casualties of the historical accident sample.

[0039] In one embodiment, for each historical accident sample, the computer device may use the accident type and number of casualties of the historical accident sample as inputs of a fuzzy function to output the accident energy importance of the historical accident sample.

[0040] In one embodiment, Figure 3 As shown, the fuzzy domain of accident type is {(minor injury, PS), (serious injury, PM), (death, PB)}, the fuzzy domain of casualty degree is {(1~2, PS), (3~4, PM), (5~6, PB)}, and the fuzzy domain of accident energy importance is {(0.2, PSS), (0.4, PS), (0.6, PM), (0.8, PB), (1.0, PBB)}. For each historical accident sample, the computer device can use the accident type and number of casualties of the historical accident sample as the input of the fuzzy function to output the accident energy importance of the historical accident sample.

[0041] Step 206, obtaining risk factor data sampled under the target risk factor of the historical accident sample; the target risk factor is any one of the multiple risk factors of the historical accident sample.

[0042] In one embodiment, the multiple risk factors of the historical accident samples may include at least one of violation, error, personnel configuration, operation configuration, line insulation ratio, risky operation, etc.

[0043] Step 208, determining the accident energy value of the historical accident sample under the target risk factor according to the accident energy importance, risk factor data, the accident occurrence time of the historical accident sample and the personal risk characteristic period to be identified of the target risk factor.

[0044] It is understandable that the period of personal risk characteristics to be identified is an unknown quantity to be determined.

[0045] In one embodiment, the computer device may map the accident energy importance, risk factor data, accident occurrence time of historical accident samples, and the personal risk characteristic period to be identified of the target risk factor into energy values ​​according to a preset mapping strategy, and obtain the accident energy value of the historical accident sample under the target risk factor. It can be understood that the accident energy value of a historical accident sample under the target risk factor can reflect the degree of influence of the risk factor data under the target risk factor on the historical accident sample, and the accident energy value is positively correlated with the degree of influence. It can be understood that the greater the accident energy value of a historical accident sample under the target risk factor, the greater the degree of influence of the risk factor data under the target risk factor on the historical accident sample, that is, the greater the probability of causing the occurrence of an accident. Conversely, the lower the accident energy value of a historical accident sample under the target risk factor, the lower the degree of influence of the risk factor data under the target risk factor on the historical accident sample, that is, the smaller the probability of causing the occurrence of an accident.

[0046] Step 210, selecting a target number of target historical accident samples to be determined from multiple historical accident samples, and determining the average accident energy value of the target number of target historical accident samples under the target risk factor based on the accident energy value of each target historical accident sample under the target risk factor.

[0047] It is understandable that the number of targets to be determined is an unknown number to be determined.

[0048] In one embodiment, the computer device may randomly select a target number of target historical accident samples to be determined from a plurality of historical accident samples.

[0049] In one embodiment, Figure 4 As shown, the computer device may be deployed with an information management platform of a power supply enterprise, and the information management platform may accumulate a large amount of power safety production data for analysis, such as risk factor data under various risk factors. It can be understood that each risk factor may lead to an accident. The computer device may select a target number of target historical accident samples to be determined from multiple historical accident samples (i.e., accident 1, accident 2, ..., accident N) according to the respective accident occurrence times of the multiple historical accident samples (i.e., time section 1, time section 2, ..., time section N).

[0050] Step 212, determining the risk value of the power supply enterprise according to the average accident energy values ​​of the target number of historical accident samples under multiple risk factors.

[0051] Among them, the risk value of the power supply enterprise is used to characterize the risk of incidents occurring in the power supply enterprise.

[0052] In one embodiment, the computer device may determine the risk value of the power supply enterprise according to the sum of the average accident energy values ​​of a target number of target historical accident samples under multiple risk factors.

[0053] Step 214, with the maximum risk value as the goal and the convergence of the average accident energy values ​​of each of the multiple risk factors as the constraint condition, construct a personal risk characteristic period identification model.

[0054] Step 216, solving the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of each of the multiple risk factors.

[0055] In one embodiment, the computer device can solve the personal risk characteristic cycle identification model through the gray wolf optimization algorithm model to obtain the personal risk characteristic cycles of each of the multiple risk factors. It can be understood that in addition to obtaining the personal risk characteristic cycles of each of the multiple risk factors, solving the personal risk characteristic cycle identification model can also obtain the specific value of the target quantity to be determined in this application.

[0056] In the above-mentioned method for identifying the personal risk characteristic cycle in the power scenario, multiple historical accident samples of the power supply enterprise are determined; for each historical accident sample, the accident energy importance of the historical accident sample is determined according to the accident type and number of casualties of the historical accident sample; the risk factor data sampled under the target risk factor of the historical accident sample is obtained; the target risk factor is any one of the multiple risk factors of the historical accident sample; according to the accident energy importance, risk factor data, the accident occurrence time of the historical accident sample and the personal risk characteristic cycle to be identified of the target risk factor, the accident energy value of the historical accident sample under the target risk factor is determined; from multiple A target number of target historical accident samples to be determined is selected from the historical accident samples, and the average accident energy value of the target number of target historical accident samples under the target risk factor is determined according to the accident energy value of each target historical accident sample under the target risk factor; the risk value of the power supply enterprise is determined according to the average accident energy value of the target number of target historical accident samples under multiple risk factors; a personal risk characteristic cycle identification model is constructed with the maximum risk value as the goal and the convergence of the average accident energy values ​​under multiple risk factors as the constraint condition; the personal risk characteristic cycle identification model is solved to obtain the personal risk characteristic cycles of multiple risk factors. Compared with the traditional personal risk characteristic cycle identification method, the present application defines the accident energy importance of historical accident samples by the accident type and number of casualties of historical accident samples, and maps the accident energy value of historical accident samples based on the accident occurrence time of historical accident samples, and constructs a personal risk characteristic cycle identification model based on the mapped accident energy value, and solves the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of multiple risk factors. In this way, in the process of identifying the personal risk characteristic cycle, in addition to paying attention to the risk factor data itself, we also pay attention to other data such as the accident type, number of casualties, and accident time of historical accident samples accumulated in the information management platform. We can deeply explore the personal risk characteristics contained in the massive data of the information management platform and improve the accuracy of the personal risk characteristic cycle. Therefore, we can accurately identify the personal risks of power supply enterprises based on more accurate personal risk characteristic cycles, and formulate control measures in a timely manner, so as to effectively prevent accidents.

[0057] In one embodiment, the accident energy value of the historical accident sample under the target risk factor is determined according to the accident energy importance, risk factor data, the accident occurrence time of the historical accident sample, and the personal risk characteristic period to be identified of the target risk factor, including:

[0058] ;

[0059] in, represents the energy importance of the accident, represents the accident time of the historical accident sample, represents the target risk factor, represents the period of personal risk characteristics to be identified for the target risk factor, Indicates the target risk factor The risk factor data obtained by downsampling, It represents the accident energy value of historical accident samples under the target risk factor. In this way, the accuracy of the accident energy value can be improved, and thus the accuracy of the personal risk characteristic cycle can be further improved.

[0060] In one embodiment, with the maximum risk value as the goal and the convergence of the average accident energy values ​​of multiple risk factors as the constraint condition, a personal risk characteristic period identification model is constructed, including:

[0061] ;

[0062] in, represents a set of multiple risk factors of historical accident samples, represents a set of multiple historical accident samples of power supply enterprises, represents a set consisting of a target number of target historical accident samples, Indicates The weight of historical accident samples, represents the number of targets to be determined for the target historical accident sample, represents the convergence parameter, represents the risk value, represents the average accident energy value, max represents the maximum value, and st. represents the constraint condition. In this way, the accuracy of the personal risk characteristic cycle can be further improved.

[0063] In one embodiment, a personal risk characteristic cycle identification model is solved to obtain the personal risk characteristic cycles of multiple risk factors, including: determining an original gray wolf optimization algorithm model; initializing the original gray wolf optimization algorithm model based on the personal risk characteristic cycle identification model to obtain the original gray wolf population of the original gray wolf optimization algorithm model; obtaining a target gray wolf population based on the original gray wolf population of the original gray wolf optimization algorithm model; the original gray wolf population represents the original solution space; a gray wolf in the original gray wolf population represents a candidate personal risk characteristic cycle in the original solution space; the distance between the positions of any two gray wolves in the target gray wolf population in the original solution space is less than a preset microhabitat radius; the target gray wolf population represents the target solution space; a gray wolf in the target gray wolf population represents a candidate personal risk characteristic cycle in the target solution space; based on the target gray wolf population, a target gray wolf optimization algorithm model is constructed; solving the personal risk characteristic cycle identification model through the target gray wolf optimization algorithm model to obtain the personal risk characteristic cycles of multiple risk factors.

[0064] In one embodiment, the fitness of each gray wolf in the target gray wolf population is determined according to the position of each gray wolf in the target gray wolf population of the target gray wolf optimization algorithm model in the target solution space, and the personal risk characteristic cycle identification model is solved directly based on the fitness of each gray wolf in the target gray wolf population to obtain the personal risk characteristic cycles of each of the multiple risk factors.

[0065] In the above embodiment, by introducing the microhabitat radius in the process of solving the original gray wolf optimization algorithm model, the original gray wolf population of the original gray wolf optimization algorithm model is further optimized, and the human risk characteristic cycle identification model is solved by the optimized target gray wolf optimization algorithm model, the accuracy of the personal risk characteristic cycle can be further improved.

[0066] In one embodiment, a personal risk characteristic cycle identification model is solved through a target gray wolf optimization algorithm model to obtain the personal risk characteristic cycles of multiple risk factors, including: determining the original fitness of each gray wolves in the target gray wolf population according to the position of each gray wolves in the target gray wolf population of the target gray wolf optimization algorithm model in the target solution space; for each gray wolf in the target gray wolf population, determining the target fitness of the gray wolf according to the original fitness of the gray wolf, the radius of the microhabitat, and the position of the gray wolf in the original solution space, respectively, and the distance between the position of each gray wolf in the original gray wolf population in the original solution space; according to the target fitness of each gray wolf in the target gray wolf population, iteratively adjusting the position of each gray wolf in the target gray wolf population in the target solution space until the iteration stop condition is met, thereby obtaining the personal risk characteristic cycles of multiple risk factors.

[0067] In the above embodiment, the target fitness of the gray wolves is obtained by optimizing the original fitness of each gray wolf in the target gray wolf population, and the position of each gray wolf in the target gray wolf population in the target solution space is iteratively adjusted according to the target fitness of each gray wolf in the target gray wolf population, so as to further improve the accuracy of the human risk characteristic cycle finally obtained.

[0068] In one embodiment, for each gray wolf in the target gray wolf population, the target fitness of the gray wolf is determined according to the original fitness of the gray wolf, the radius of the niche, and the distance between the position of the gray wolf in the original solution space and the position of each gray wolf in the original gray wolf population in the original solution space, including:

[0069] ;

[0070] ;

[0071] in, represents the number of gray wolves in the original gray wolf population, Gray wolf The original fitness of Gray wolf With the Gray Wolf The distance between the positions in the original solution space, represents the radius of the microhabitat, represents the preset shape parameters, represents a shared function, Gray wolf In this way, the accuracy of the target fitness can be improved, thereby further improving the accuracy of the final personal risk feature cycle.

[0072] In one embodiment, for each gray wolf in the target gray wolf population in each round of iteration, the position of the gray wolf adjusted based on this round of iteration is corrected according to a preset mutation formula; if the target fitness of the gray wolf determined based on the corrected position of the gray wolf is better than the target fitness of the gray wolf determined based on the adjusted position of the gray wolf in this round of iteration, the corrected position of the gray wolf is used as the position of the gray wolf in the next round of iteration.

[0073] In one embodiment, the computer device can determine the original fitness of each gray wolf in the target gray wolf population according to the position of each gray wolf in the target gray wolf population of the target gray wolf optimization algorithm model in the target solution space; for each gray wolf in the target gray wolf population, determine the target fitness of the gray wolf according to the original fitness of the gray wolf, the radius of the microhabitat, and the position of the gray wolf in the original solution space, respectively, and the distance between the position of each gray wolf in the original gray wolf population in the original solution space; according to the target fitness of each gray wolf in the target gray wolf population, iteratively adjust the position of each gray wolf in the target gray wolf population in the target solution space. For each gray wolf in the target gray wolf population in each round of iteration, according to the preset mutation formula, correct the position of the gray wolf adjusted based on this round of iteration; if the target fitness of the gray wolf determined based on the corrected position of the gray wolf is better than the target fitness of the gray wolf determined based on the position of the gray wolf adjusted based on this round of iteration, then the corrected position of the gray wolf is used as the position of the gray wolf in the next round of iteration, so as to continue iterative execution until the iteration stop condition is met, and the personal risk characteristic cycle of each of the multiple risk factors is obtained. In this way, by adding mutation technology to correct the position of the gray wolf during the iterative optimization process, we can escape from the local optimal solution, thereby further improving the accuracy of the final personal risk characteristic cycle.

[0074] In one embodiment, the mutation formula is expressed as:

[0075] ;

[0076] in, Represents the gray wolf based on this round of iteration adjustment location, represents the preset variation weight coefficient, Gray wolf Corrected position. In this way, the accuracy of the gray wolf's corrected position can be further improved, thereby further improving the accuracy of the final obtained personal risk characteristic cycle.

[0077] It should be understood that, although each step in the flow chart of the above-mentioned embodiments is shown in order, these steps are not necessarily performed in order. Unless there is a clear explanation in this article, the execution of these steps does not have strict order restrictions, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the above-mentioned embodiments may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in order, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0078] In one embodiment, Figure 5As shown, a device 500 for identifying a period of personal risk characteristics in an electric power scenario is provided, and the device specifically includes:

[0079] The determination module 502 is used to determine a plurality of historical accident samples of the power supply enterprise; for each historical accident sample, the accident energy importance of the historical accident sample is determined according to the accident type and number of casualties of the historical accident sample.

[0080] The acquisition module 504 is used to acquire risk factor data sampled under a target risk factor of the historical accident sample; the target risk factor is any one of the multiple risk factors of the historical accident sample.

[0081] The determination module 502 is also used to determine the accident energy value of the historical accident samples under the target risk factor based on the accident energy importance, risk factor data, the accident occurrence time of the historical accident samples and the personal risk characteristic period to be identified of the target risk factor; select a target number of target historical accident samples to be determined from multiple historical accident samples, and determine the average accident energy value of the target number of target historical accident samples under the target risk factor based on the accident energy value of each target historical accident sample under the target risk factor; determine the risk value of the power supply enterprise based on the average accident energy value of the target number of target historical accident samples under multiple risk factors.

[0082] The construction module 506 is used to construct a personal risk characteristic period identification model with the maximum risk value as the goal and the convergence of the average accident energy values ​​of each of the multiple risk factors as the constraint condition.

[0083] The solving module 508 is used to solve the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of each of the multiple risk factors.

[0084] In one embodiment, the determination module 502 is further configured to perform calculation according to the following formula:

[0085] ;

[0086] in, represents the energy importance of the accident, represents the accident time of the historical accident sample, represents the target risk factor, represents the period of personal risk characteristics to be identified for the target risk factor, Indicates the target risk factor The risk factor data obtained by downsampling, Represents the accident energy value of historical accident samples under the target risk factor.

[0087] In one embodiment, the construction module 506 is further configured to perform calculation according to the following formula:

[0088] ;

[0089] in, represents a set of multiple risk factors of historical accident samples, represents a set of multiple historical accident samples of power supply enterprises, represents a set consisting of a target number of target historical accident samples, Indicates The weight of historical accident samples, represents the number of targets to be determined for the target historical accident sample, represents the convergence parameter, represents the risk value, represents the average accident energy value, max represents the maximum value, and st. represents the constraint condition.

[0090] In one embodiment, the solution module 508 is also used to determine the original gray wolf optimization algorithm model; based on the personal risk characteristic cycle identification model, the original gray wolf optimization algorithm model is initialized to obtain the original gray wolf population of the original gray wolf optimization algorithm model; based on the original gray wolf population of the original gray wolf optimization algorithm model, the target gray wolf population is obtained; the original gray wolf population represents the original solution space; a gray wolf in the original gray wolf population represents a candidate personal risk characteristic cycle in the original solution space; the distance between the positions of any two gray wolves in the target gray wolf population in the original solution space is less than a preset microhabitat radius; the target gray wolf population represents the target solution space; a gray wolf in the target gray wolf population represents a candidate personal risk characteristic cycle in the target solution space; based on the target gray wolf population, a target gray wolf optimization algorithm model is constructed; through the target gray wolf optimization algorithm model, the personal risk characteristic cycle identification model is solved to obtain the personal risk characteristic cycles of multiple risk factors.

[0091] In one embodiment, the solution module 508 is also used to determine the original fitness of each gray wolf in the target gray wolf population according to the position of each gray wolf in the target gray wolf population of the target gray wolf optimization algorithm model in the target solution space; for each gray wolf in the target gray wolf population, determine the target fitness of the gray wolf according to the original fitness of the gray wolf, the radius of the microhabitat, and the position of the gray wolf in the original solution space, respectively, and the distance between the position of each gray wolf in the original gray wolf population in the original solution space; according to the target fitness of each gray wolf in the target gray wolf population, iteratively adjust the position of each gray wolf in the target gray wolf population in the target solution space until the iteration stop condition is met to obtain the personal risk characteristic cycle of each of the multiple risk factors.

[0092] In one embodiment, the solution module 508 is further configured to perform calculation according to the following formula:

[0093] ;

[0094] ;

[0095] in, represents the number of gray wolves in the original gray wolf population, Gray wolf The original fitness of Gray wolf With the Gray Wolf The distance between the positions in the original solution space, represents the radius of the microhabitat, represents the preset shape parameters, represents a shared function, Gray wolf Target fitness.

[0096] In one embodiment, for each gray wolf in the target gray wolf population in each round of iteration, the position of the gray wolf adjusted based on this round of iteration is corrected according to a preset mutation formula; if the target fitness of the gray wolf determined based on the corrected position of the gray wolf is better than the target fitness of the gray wolf determined based on the adjusted position of the gray wolf in this round of iteration, the corrected position of the gray wolf is used as the position of the gray wolf in the next round of iteration.

[0097] In one embodiment, the mutation formula is expressed as:

[0098] ;

[0099] in, Represents the gray wolf based on this round of iteration adjustment location, represents the preset variation weight coefficient, Gray wolf Corrected position.

[0100] The above-mentioned personal risk characteristic cycle identification device in the power scenario determines multiple historical accident samples of the power supply enterprise; for each historical accident sample, according to the accident type and number of casualties of the historical accident sample, determines the accident energy importance of the historical accident sample; obtains the risk factor data sampled under the target risk factor of the historical accident sample; the target risk factor is any one of the multiple risk factors of the historical accident sample; according to the accident energy importance, risk factor data, the accident occurrence time of the historical accident sample and the personal risk characteristic cycle to be identified of the target risk factor, determines the accident energy value of the historical accident sample under the target risk factor; from multiple A target number of target historical accident samples to be determined is selected from the historical accident samples, and the average accident energy value of the target number of target historical accident samples under the target risk factor is determined according to the accident energy value of each target historical accident sample under the target risk factor; the risk value of the power supply enterprise is determined according to the average accident energy value of the target number of target historical accident samples under multiple risk factors; a personal risk characteristic cycle identification model is constructed with the maximum risk value as the goal and the convergence of the average accident energy values ​​under multiple risk factors as the constraint condition; the personal risk characteristic cycle identification model is solved to obtain the personal risk characteristic cycles of multiple risk factors. Compared with the traditional personal risk characteristic cycle identification method, the present application defines the accident energy importance of historical accident samples by the accident type and number of casualties of historical accident samples, and maps the accident energy value of historical accident samples based on the accident occurrence time of historical accident samples, and constructs a personal risk characteristic cycle identification model based on the mapped accident energy value, and solves the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of multiple risk factors. In this way, in the process of identifying the personal risk characteristic cycle, in addition to paying attention to the risk factor data itself, we also pay attention to other data such as the accident type, number of casualties, and accident time of historical accident samples accumulated in the information management platform. We can deeply explore the personal risk characteristics contained in the massive data of the information management platform and improve the accuracy of the personal risk characteristic cycle. Therefore, we can accurately identify the personal risks of power supply enterprises based on more accurate personal risk characteristic cycles, and formulate control measures in a timely manner, so as to effectively prevent accidents.

[0101] Each module in the above-mentioned device for identifying personal risk characteristics period in the power scenario can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0102] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for identifying a periodicity of personal risk characteristics in an electric power scenario is implemented.

[0103] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for identifying a periodicity of personal risk characteristics in an electric power scenario is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0104] Those skilled in the art will understand that Figure 6The structure shown in FIG. 7 is merely a block diagram of a partial 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 arrangement of components.

[0105] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0106] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0107] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0108] 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 laws, regulations and standards of relevant countries and regions.

[0109] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0110] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0111] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for identifying the characteristic period of personal risk in power scenarios, characterized in that: The method comprises: Identify multiple historical accident samples of power supply companies; For each of the historical accident samples, determining the accident energy importance of the historical accident sample according to the accident type and number of casualties of the historical accident sample; Acquire risk factor data sampled under a target risk factor of the historical accident sample; the target risk factor is any one of a plurality of risk factors of the historical accident sample; ； in, represents the energy importance of the accident, represents the time of occurrence of the historical accident sample, represents the target risk factor, represents the personal risk characteristic period to be identified of the target risk factor, Indicates the target risk factors The risk factor data obtained by downsampling, represents the accident energy value of the historical accident sample under the target risk factor; the accident energy value of the historical accident sample under the target risk factor is used to reflect the degree of influence of the risk factor data under the target risk factor on the historical accident sample; Selecting a target number of target historical accident samples to be determined from the multiple historical accident samples, and determining an average accident energy value of the target number of target historical accident samples under the target risk factor according to the accident energy value of each of the target historical accident samples under the target risk factor; Determine the risk value of the power supply enterprise according to the average accident energy values ​​of the target historical accident samples of the target number under the multiple risk factors; ； in, represents a set of multiple risk factors of the historical accident samples, represents a set consisting of multiple historical accident samples of the power supply enterprise, represents a set consisting of the target number of target historical accident samples, Indicates The weight of the historical accident samples, represents the target number to be determined for the target historical accident sample, represents the convergence parameter, represents the risk value, represents the average accident energy value, max represents the maximum value, and st. represents the constraint condition; Solve the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of each of the multiple risk factors.

2. The method according to claim 1, characterized in that The step of solving the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of the respective risk factors includes: Determine the original gray wolf optimization algorithm model; Based on the personal risk characteristic period identification model, the original gray wolf optimization algorithm model is initialized to obtain the original gray wolf population of the original gray wolf optimization algorithm model; According to the original gray wolf population of the original gray wolf optimization algorithm model, a target gray wolf population is obtained; the original gray wolf population represents the original solution space; a gray wolf in the original gray wolf population represents a candidate personal risk characteristic cycle in the original solution space; the distance between the positions of any two gray wolves in the target gray wolf population in the original solution space is less than a preset microhabitat radius; the target gray wolf population represents the target solution space; a gray wolf in the target gray wolf population represents a candidate personal risk characteristic cycle in the target solution space; According to the target gray wolf population, construct a target gray wolf optimization algorithm model; The target grey wolf optimization algorithm model is used to solve the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycles of each of the multiple risk factors.

3. The method according to claim 2, characterized in that The method of solving the personal risk characteristic cycle identification model through the target grey wolf optimization algorithm model to obtain the personal risk characteristic cycles of the respective risk factors includes: Determine the original fitness of each gray wolf in the target gray wolf population according to the position of each gray wolf in the target solution space of the target gray wolf optimization algorithm model; For each gray wolf in the target gray wolf population, determine the target fitness of the gray wolf according to the original fitness of the gray wolf, the radius of the niche, and the distance between the position of the gray wolf in the original solution space and the position of each gray wolf in the original gray wolf population in the original solution space; According to the target fitness of each gray wolf in the target gray wolf population, the position of each gray wolf in the target gray wolf population in the target solution space is iteratively adjusted until an iteration stop condition is met, thereby obtaining the personal risk characteristic cycle of each of the multiple risk factors.

4. The method according to claim 3, characterized in that The method of determining the target fitness of each gray wolf in the target gray wolf population according to the original fitness of the gray wolf, the radius of the niche, and the distance between the position of the gray wolf in the original solution space and the position of each gray wolf in the original gray wolf population in the original solution space comprises: ； ； in, represents the number of gray wolves in the original gray wolf population, Represents the gray wolf The original fitness of Gray wolf With the Gray Wolf The distance between the positions in the original solution space, represents the radius of the microhabitat, represents the preset shape parameters, represents a shared function, Represents the gray wolf Target fitness.

5. The method according to claim 3, characterized in that: For each gray wolf in the target gray wolf population in each round of iteration, the position of the gray wolf adjusted based on the current round of iteration is corrected according to a preset mutation formula; If the target fitness of the gray wolf determined based on the revised position of the gray wolf is better than the target fitness of the gray wolf determined based on the position of the gray wolf adjusted in this round of iteration, the revised position of the gray wolf will be used as the position of the gray wolf in the next round of iteration.

6. The method according to claim 5, characterized in that The variation formula is expressed as: ； in, Indicates the gray wolf after the current round of iteration adjustment location, represents the preset variation weight coefficient, Represents the gray wolf Corrected position.

7. A device for identifying personal risk characteristics in power scenarios, characterized in that: The device comprises: A determination module is used to determine a plurality of historical accident samples of a power supply enterprise; for each of the historical accident samples, the accident energy importance of the historical accident sample is determined according to the accident type and number of casualties of the historical accident sample; An acquisition module, used to acquire risk factor data sampled under a target risk factor of the historical accident sample; the target risk factor is any one of a plurality of risk factors of the historical accident sample; The determination module is also used to calculate ; in, represents the energy importance of the accident, represents the time of occurrence of the historical accident sample, represents the target risk factor, represents the personal risk characteristic period to be identified of the target risk factor, Indicates the target risk factors The risk factor data obtained by downsampling, Represents the accident energy value of the historical accident sample under the target risk factor; the accident energy value of the historical accident sample under the target risk factor is used to reflect the degree of influence of the risk factor data under the target risk factor on the historical accident sample; the determination module is also used to select a target number of target historical accident samples to be determined from the multiple historical accident samples, and determine the average accident energy value of the target historical accident samples of the target number under the target risk factor according to the accident energy value of each of the target historical accident samples under the target risk factor; determine the risk value of the power supply enterprise according to the average accident energy values ​​of the target historical accident samples of the target number under the multiple risk factors; Building blocks for building ; in, represents a set of multiple risk factors of the historical accident samples, represents a set consisting of multiple historical accident samples of the power supply enterprise, represents a set consisting of the target number of target historical accident samples, Indicates The weight of the historical accident samples, represents the target number to be determined for the target historical accident sample, represents the convergence parameter, represents the risk value, represents the average accident energy value, max represents the maximum value, and st. represents the constraint condition; A solution module is used to solve the personal risk characteristic cycle identification model to obtain the personal risk characteristic cycle of each of the multiple risk factors.

8. The device according to claim 7, characterized in that The solution module is also used to determine the original gray wolf optimization algorithm model; based on the personal risk characteristic period identification model, the original gray wolf optimization algorithm model is initialized to obtain the original gray wolf population of the original gray wolf optimization algorithm model; according to the original gray wolf population of the original gray wolf optimization algorithm model, a target gray wolf population is obtained; The original gray wolf population represents the original solution space; a gray wolf in the original gray wolf population represents a candidate personal risk characteristic cycle in the original solution space; The distance between the positions of any two gray wolves in the target gray wolf population in the original solution space is less than the preset microhabitat radius; the target gray wolf population represents the target solution space; a gray wolf in the target gray wolf population represents a candidate personal risk characteristic cycle in the target solution space; According to the target gray wolf population, a target gray wolf optimization algorithm model is constructed; through the target gray wolf optimization algorithm model, the personal risk characteristic cycle identification model is solved to obtain the personal risk characteristic cycle of each of the multiple risk factors.

9. The device according to claim 8, characterized in that The solution module is also used to determine the original fitness of each gray wolf in the target gray wolf population according to the position of each gray wolf in the target gray wolf population of the target gray wolf optimization algorithm model in the target solution space; For each gray wolf in the target gray wolf population, determine the target fitness of the gray wolf according to the original fitness of the gray wolf, the radius of the niche, and the distance between the position of the gray wolf in the original solution space and the position of each gray wolf in the original gray wolf population in the original solution space; According to the target fitness of each gray wolf in the target gray wolf population, the position of each gray wolf in the target gray wolf population in the target solution space is iteratively adjusted until an iteration stop condition is met, thereby obtaining the personal risk characteristic cycle of each of the multiple risk factors.

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

Images