Risk early warning method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a risk early warning method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: acquiring current link data of each link of a power grid industrial chain; wherein the current link data of each link comprises index data of each risk index corresponding to the link; inputting the current link data of each link into a risk early warning model to obtain risk information of the power grid industrial chain output by the risk early warning model based on the model parameters and the current link data of each link; wherein the model parameters comprise association relationships among the links; and carrying out risk early warning on the power grid industry chain according to the risk information. By adopting the method, risk early warning can be accurately made.

Description

Technical Field

[0001] The present application relates to the field of electric power engineering technology, and in particular to a risk early warning method, device, computer equipment, storage medium and program product. Background Art

[0002] With the growing demand for electricity and the continuous expansion of the power grid, the power grid industry chain is facing increasingly severe security challenges. As a key national infrastructure, the stable operation of the power grid is crucial to national security, economic development and social stability.

[0003] However, the risk warning systems currently used in the power grid industry chain security system all have problems such as single data and low warning accuracy.

[0004] Therefore, it is crucial to detect security risks in the power grid industry chain in advance and issue early warnings. Summary of the invention

[0005] Based on this, it is necessary to provide a risk warning method, device, computer equipment, storage medium and program product to address the above technical issues, which can accurately make risk warnings.

[0006] In a first aspect, the present application provides a risk early warning method, the method comprising:

[0007] Obtaining current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0008] Input the current link data of each link into the risk warning model, and obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0009] Based on risk information, risk warnings are issued for the power grid industry chain.

[0010] In one embodiment, obtaining current link data of each link of the power grid industry chain includes:

[0011] For each link of the power grid industry chain, the original data of each data source of the link is obtained; from each original data, the initial data of each key risk indicator corresponding to the link is extracted; the extracted initial data of each key risk indicator is integrated to obtain the indicator data of each key risk indicator corresponding to the link.

[0012] In one embodiment, the extracted initial data of each key risk indicator are fused to obtain the indicator data of each key risk indicator corresponding to the link, including:

[0013] The initial data of each key risk indicator is processed in a unified manner; wherein the unified processing includes at least one of unified processing of timestamps, unified processing of measurement units, and unified processing of coding methods; data cleaning is performed on each initial data after the unified processing; each initial data after data cleaning is integrated to obtain indicator data of each key risk indicator corresponding to the link.

[0014] In one embodiment, it includes:

[0015] Obtain historical link data of the link; wherein the historical link data includes indicator data of each candidate risk indicator corresponding to the link; based on the historical link data and the target data of the link evaluation indicator corresponding to the link, calculate the correlation between each candidate risk indicator corresponding to the link and the link evaluation indicator to obtain the correlation value corresponding to each candidate risk indicator; based on the correlation value corresponding to each candidate risk indicator, select each key risk indicator corresponding to the link from each candidate risk indicator.

[0016] In one embodiment, it includes:

[0017] For each link, the historical link data of the link is processed by dimensionality reduction, and the features of the historical link data after dimensionality reduction are extracted to obtain the link features corresponding to the link; based on the features of each link, the correlation analysis is performed on each link to obtain the correlation relationship between the links.

[0018] In one embodiment, it includes:

[0019] Based on the risk information, determine the risk links in each link and the initial risk level corresponding to the risk links; determine the target risk level based on the initial risk level and the impact level of the risk link in the power grid industry chain; based on the target risk level, conduct risk warning for the power grid industry chain.

[0020] In a second aspect, the present application also provides a risk warning device, the device comprising:

[0021] An acquisition module is used to acquire current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0022] The information determination module is used to input the current link data of each link into the risk warning model to obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0023] The early warning module is used to issue risk warnings to the power grid industry chain based on risk information.

[0024] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0025] Obtaining current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0026] Input the current link data of each link into the risk warning model, and obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0027] Based on risk information, risk warnings are issued for the power grid industry chain.

[0028] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0029] Obtaining current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0030] Input the current link data of each link into the risk warning model, and obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0031] Based on risk information, risk warnings are issued for the power grid industry chain.

[0032] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0033] Obtaining current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0034] Input the current link data of each link into the risk warning model, and obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0035] Based on risk information, risk warnings are issued for the power grid industry chain.

[0036] The above-mentioned risk warning method, device, computer equipment, storage medium and program product, by obtaining the indicator data of each risk indicator corresponding to each link of the power grid industry chain, provide a data basis for accurate risk warning; further, the indicator data of each risk indicator corresponding to each link is input into the risk warning model including the correlation between each link, and the risk information of the power grid industry chain is obtained, taking into account the influence relationship between each link in the power grid industry chain; then, the risk warning of the power grid industry chain can be carried out according to the risk information. This scheme prepares the conditions for fully analyzing the potential relationship between the indicator data by obtaining the indicator data of each risk indicator corresponding to each link; furthermore, by considering the correlation between each link, it lays the foundation for obtaining accurate risk information; finally, by introducing the risk warning model, the indicator data of each risk indicator corresponding to each link is objectively analyzed, so as to make accurate risk warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] FIG1 is an application environment diagram of a risk warning method provided in an embodiment of the present application;

[0039] FIG2 is a schematic diagram of a risk warning process provided in an embodiment of the present application;

[0040] FIG3 is a schematic diagram of a process for obtaining current link data provided in an embodiment of the present application;

[0041] FIG4 is a schematic diagram of a process for determining key risk indicators provided in an embodiment of the present application;

[0042] FIG5 is a structural block diagram of a risk warning device provided in an embodiment of the present application;

[0043] FIG. 6 is an internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] 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.

[0045] The risk warning method provided in the embodiment of the present application can be applied in the application environment shown in FIG. 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system 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 network servers. The server 104 can obtain the current link data of each link of the power grid industry chain from the data storage system, and input the obtained data into the risk warning model, and the risk warning model is calculated and analyzed based on the model parameters and the current link data of each link, and the risk information of the power grid industry chain is obtained; then, according to the risk information, a risk warning for the power grid industry chain can be generated; further, the risk warning can be output through the terminal 102. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0046] In an exemplary embodiment, as shown in FIG2 , a risk warning method is provided, which is described by taking the method applied to the server 104 in FIG1 as an example, and may include the following steps:

[0047] S201, obtaining current link data of each link of the power grid industry chain.

[0048] Among them, the power grid industry chain can include power generation, transformation, transmission, distribution and power consumption; the current link data of each link includes the indicator data of each key risk indicator corresponding to the link; key risk indicators can be used to monitor indicators of loss events occurring in each link of the power grid industry chain, such as the proportion of renewable energy power generation, power generation cost, transformation efficiency, transmission loss, distribution network stability and electricity fee recovery rate.

[0049] For example, the current link data of each link in the power grid industry chain can be collected and integrated through multiple channels such as power companies, power departments, statistical databases and industry research institutions, and the integrated current link data of each link in the power grid industry chain can be stored in the data storage system in the server 104; furthermore, the server 104 can obtain the current link data of each link in the power grid industry chain in real time.

[0050] S202, inputting the current link data of each link into the risk warning model, and obtaining the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link.

[0051] Among them, the risk warning model can be obtained by training the model parameters through genetic algorithm based on historical link data and K-fold cross-validation method; the model parameters can include but are not limited to the correlation between each link; the risk information can include but is not limited to risk indicators, risk types, risk links, initial risk levels corresponding to risk links and measures corresponding to risk links.

[0052] Optionally, risk types may include but are not limited to upstream risks, midstream and downstream risks, natural disaster risks, and network security risks; appropriate risk warning models may be selected based on the characteristics of the power grid industry chain and the risk types. For example, models based on machine learning or statistics may be used, such as support vector machines, neural networks, decision trees, etc.; data at risk links may also be quantitatively evaluated, and the initial risk level corresponding to the risk link may be determined based on the scores of the quantitative evaluation.

[0053] Exemplarily, the current link data of each link can be used as the input of the risk warning model, and the risk warning model can calculate and analyze the current link data of each link in combination with the correlation between the links to determine the relatively abnormal current link data in each link; further, based on the relatively abnormal current link data in each link, the risk link and the initial risk level corresponding to the risk link and other information can be determined; further, based on the risk link and the initial risk level corresponding to the risk link and other information, the risk information of the power grid industry chain can be determined.

[0054] S203, based on the risk information, conduct risk warning for the power grid industry chain.

[0055] Among them, risk warning may include but is not limited to information such as warning level, warning type, warning link and warning measures.

[0056] Optionally, the warning types may include but are not limited to equipment warnings, operation warnings, management warnings, supply chain warnings and other warnings.

[0057] Exemplarily, the warning link and warning type and other information can be determined based on the risk link in the risk information. The warning level and other information can also be determined based on the initial risk level corresponding to the risk link in the risk information. The warning measures and other information can also be determined based on the measures and warning links corresponding to the risk link in the risk information. Furthermore, risk warnings can be conducted on the power grid industry chain based on information such as the warning link, warning type, warning level and warning measures to reduce the possibility and impact of risks.

[0058] The above-mentioned risk warning method, by obtaining the indicator data of each risk indicator corresponding to each link of the power grid industry chain, provides a data basis for accurate risk warning; further, the indicator data of each risk indicator corresponding to each link is input into the risk warning model including the correlation between each link, and the risk information of the power grid industry chain is obtained, taking into account the influence relationship between each link in the power grid industry chain; then, the risk warning of the power grid industry chain can be carried out according to the risk information. This scheme prepares the conditions for fully analyzing the potential relationship between the indicator data by obtaining the indicator data of each risk indicator corresponding to each link; furthermore, by considering the correlation between each link, it lays the foundation for obtaining accurate risk information; finally, by introducing the risk warning model, the indicator data of each risk indicator corresponding to each link is objectively analyzed, so as to make accurate risk warning.

[0059] Based on the above embodiment, the present embodiment of the application explains the above embodiment S201 in detail. Specifically, the process of obtaining the current link data in the present embodiment of the application, as shown in FIG3, specifically includes the following steps:

[0060] S301, for each link of the power grid industry chain, original data from each data source of the link is obtained.

[0061] Among them, the original data can represent the data of each link of the power grid industry chain collected from various data sources, such as power generation efficiency, power generation, transformation efficiency, transformation capacity, transmission capacity, distribution capacity, distribution loss and power load.

[0062] For example, the original data of each link of the power grid industry chain can be collected and integrated through multiple channels such as power companies, power departments, statistical databases, industry research institutions and third parties, and the integrated original data of each link of the power grid industry chain can be stored in the data storage system in the server 104; thus, the server 104 can obtain the original data in real time.

[0063] S302, extracting the initial data of each key risk indicator corresponding to each link from each original data.

[0064] The initial data may represent data of key risk indicators in various links of the power grid industry chain collected from various data sources.

[0065] It should be noted that each original data includes data on risk indicators in each link of the power grid industry chain collected from various data sources, that is, each original data includes not only data on key risk indicators, but also a lot of data that are not closely related to the risks of the power grid industry chain.

[0066] Exemplarily, the original data may be denoised using a K-Means clustering algorithm; further, based on the key risk indicators corresponding to each link, data corresponding to each key risk indicator, i.e., initial data, may be extracted from the original data after denoising.

[0067] S303, integrating the extracted initial data of each key risk indicator to obtain indicator data of each key risk indicator corresponding to the link.

[0068] One feasible method is to uniformly process the initial data of each key risk indicator; perform data cleaning on each initial data after the uniform processing; and fuse each initial data after the data cleaning to obtain the indicator data of each key risk indicator corresponding to the link.

[0069] The unified processing may include but is not limited to at least one of unified processing of timestamps, unified processing of measurement units and unified processing of encoding methods.

[0070] Exemplarily, a timestamp can be extracted from the initial data of each key risk indicator, and the format (such as year, month, day, hour, minute, second, etc.) and time zone of each initial data can be clarified; further, the timestamp of the initial data of each key risk indicator can be converted into a unified time format and time zone through a programming language or a data processing tool; and, the measurement unit corresponding to each initial data can be clarified, and the measurement unit corresponding to each initial data can be unified through a conversion formula; and, the encoding method corresponding to each initial data can be clarified, and the encoding method of the initial data of each key risk indicator can be unified through a programming language or a data processing tool; further, the unified initial data can be fused based on a fusion algorithm (such as pixel-level fusion, feature-level fusion, and decision-level fusion methods), and the indicator data of each key risk indicator corresponding to the link can be obtained.

[0071] Optionally, the initial data of each key risk indicator may be fused through Kalman filtering.

[0072] Another possible implementation method is to directly input the initial data of each key risk indicator into the fusion model, and the fusion model will fuse the initial data of each key risk indicator and obtain the indicator data of each key risk indicator corresponding to each link. The fusion model can be based on any of the following types: pixel-level fusion, feature-level fusion, and decision-level fusion, and can be implemented by corresponding fusion algorithms, such as algebraic method, wavelet transform, Bayesian estimation, neural network, etc.

[0073] In the embodiment of the present application, the accuracy of the indicator data of each key risk indicator is ensured by performing unified processing and cleaning operations on the data, laying the foundation for accurate risk warning.

[0074] Based on the above embodiment, the present application embodiment explains the above embodiment S201 in detail. Specifically, the process of determining key risk indicators in the present application embodiment, as shown in FIG4, specifically includes the following steps:

[0075] S401, obtaining historical link data of the link.

[0076] Among them, the historical link data may include but are not limited to the indicator data of each candidate risk indicator corresponding to the link; the candidate risk indicator may represent an indicator that may be related to a loss event that occurs in the power grid industry chain.

[0077] For example, data from each link of the power grid industry chain can be collected in real time through multiple channels such as power companies, power departments, statistical databases and industry research institutions, and data integration can be performed, and the integrated data from each link of the power grid industry chain can be stored in the data storage system in the server 104; furthermore, the historical link data of each link can be obtained based on the data collected from each link at historical time (past time).

[0078] S402, based on the historical link data and the target data of the link evaluation index corresponding to the link, calculate the correlation between each candidate risk index corresponding to the link and the link evaluation index to obtain the correlation value corresponding to each candidate risk index.

[0079] Among them, the link evaluation index can be used to evaluate the link performance index, such as the link evaluation index corresponding to the power generation link can be the total power generation; the correlation value can represent the degree of correlation between the candidate risk indicator and the link evaluation index.

[0080] Exemplarily, for each link, the correlation between each candidate risk indicator corresponding to the link and the link evaluation indicator can be calculated by using methods such as the Pearson correlation coefficient or the Spearman rank correlation coefficient to obtain the correlation value between each candidate risk indicator and the link evaluation indicator.

[0081] S403: Based on the correlation values ​​corresponding to the candidate risk indicators, select key risk indicators corresponding to the links from the candidate risk indicators.

[0082] Exemplarily, the candidate risk indicators may be ranked according to their corresponding correlation values. For example, the candidate risk indicators with larger correlation values ​​may be determined as key risk indicators. For example, the top 40% of the candidate risk indicators with larger correlation values ​​may be determined as key risk indicators.

[0083] In the embodiment of the present application, by introducing relevant values, a basis is provided for determining key risk indicators from candidate risk indicators, laying a foundation for accurately determining risk warnings.

[0084] Based on the above-mentioned embodiment, the embodiment of the present application explains the above-mentioned embodiment S202 in detail. Specifically, the process of determining the association relationship between each link in the embodiment of the present application specifically includes: for each link, the historical link data of the link is subjected to dimensionality reduction processing, and feature extraction is performed on the historical link data after dimensionality reduction processing to obtain the link feature corresponding to the link; based on the features of each link, the association analysis is performed on each link to obtain the association relationship between each link.

[0085] Among them, the link characteristics can represent the characteristic data of the main change trends in the link; the correlation relationship can characterize the influence relationship between the links, such as the total power generation index of the power generation link will affect the values ​​of the indicators in the subsequent links, such as affecting the total power consumption index in the power consumption link, etc.; optionally, the correlation relationship can be represented by an influence coefficient.

[0086] Exemplarily, for each link, the historical link data of the link can be processed and analyzed through methods such as principal component analysis, independent component analysis, linear regression, and K-means algorithm to achieve dimensionality reduction and feature extraction, and obtain the link characteristics corresponding to the link; further, the link characteristics corresponding to each link can be analyzed for correlation through methods such as correlation coefficient method, covariance analysis, cluster analysis, and time series analysis, and the correlation relationship between each link can be determined based on the results of the correlation analysis. Optionally, if the correlation coefficient method is used for correlation analysis, the correlation coefficient between each link can be obtained (-1<correlation coefficient<1), then the correlation relationship between each link can be determined based on the mapping relationship between the pre-set correlation coefficient and the correlation relationship.

[0087] Optionally, correlation analysis can be performed on each link through methods such as frequent item set mining, association rule mining, sequence pattern mining, association network analysis and multi-level association analysis.

[0088] In the embodiment of the present application, by introducing the correlation between each link, the influence relationship between each link in the power grid industry chain is taken into account, thus preparing the conditions for making accurate risk warnings.

[0089] Based on the above-mentioned embodiments, the embodiments of the present application explain the above-mentioned embodiment S203 in detail. Specifically, the process of risk warning in the embodiments of the present application specifically includes: determining the risk links in each link and the initial risk level corresponding to the risk links according to the risk information; determining the target risk level according to the initial risk level and the impact level of the risk link in the power grid industry chain; and conducting risk warning for the power grid industry chain based on the target risk level.

[0090] Among them, the risk link can indicate the link in the power grid industry chain where risk events may occur; the initial risk level can characterize the probability of an accident occurring in the risk link and the severity of the possible accident; the impact level can indicate the importance of the risk link in the power grid industry chain; the target risk level can indicate the severity of the risk accident that may occur in the power grid industry chain.

[0091] Exemplarily, information such as the risk link and the initial risk level corresponding to the risk link can be determined directly from the risk information; further, the initial risk level and the impact level of the risk link in the power grid industry chain can be averaged or summed, and the target risk level can be determined based on the processing result (for example, the processing result can be directly determined as the target risk level, or the correspondence between the processing result and the target risk level can be pre-set, and the target risk level can be determined based on the processing result and the correspondence); further, a risk warning can be issued based on the target risk level; wherein the risk warning can be presented in the form of a report, and the data of the risk indicator can be presented in the form of an icon to facilitate viewing by technical personnel.

[0092] In the embodiment of the present application, by introducing the impact level, the relationship between each link and the entire power grid industry chain is taken into account, that is, not only the individual links are considered, but also the degree of influence of each link in the entire power grid industry chain is considered, so that accurate risk warnings can be made.

[0093] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can 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, and 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 part of the steps or stages in other steps.

[0094] Based on the same inventive concept, the embodiment of the present application also provides a risk warning device for implementing the risk warning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more risk warning device embodiments provided below can refer to the limitations on the risk warning method above, and will not be repeated here.

[0095] In an exemplary embodiment, as shown in FIG5 , a risk warning device 1 is provided, comprising: an acquisition module 10, an information determination module 20 and a warning module 30, wherein:

[0096] The acquisition module is used to acquire the current link data of each link of the power grid industry chain; wherein the current link data of each link includes the indicator data of each key risk indicator corresponding to the link.

[0097] The information determination module is used to input the current link data of each link into the risk warning model to obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link.

[0098] The early warning module is used to issue risk warnings to the power grid industry chain based on risk information.

[0099] In one embodiment, the acquisition module 10 is specifically used for:

[0100] For each link of the power grid industry chain, the original data of each data source of the link is obtained; from each original data, the initial data of each key risk indicator corresponding to the link is extracted; the extracted initial data of each key risk indicator is integrated to obtain the indicator data of each key risk indicator corresponding to the link.

[0101] In one embodiment, the acquisition module 10 is further configured to:

[0102] The initial data of each key risk indicator is processed in a unified manner; wherein the unified processing includes at least one of unified processing of timestamps, unified processing of measurement units, and unified processing of coding methods; data cleaning is performed on each initial data after the unified processing; each initial data after data cleaning is integrated to obtain indicator data of each key risk indicator corresponding to the link.

[0103] In one embodiment, the risk warning device 1 specifically further includes:

[0104] The indicator determination module is used to obtain historical link data of a link; wherein the historical link data includes indicator data of each candidate risk indicator corresponding to the link; based on the historical link data and the target data of the link evaluation indicator corresponding to the link, the correlation between each candidate risk indicator corresponding to the link and the link evaluation indicator is calculated to obtain the correlation value corresponding to each candidate risk indicator; based on the correlation value corresponding to each candidate risk indicator, each key risk indicator corresponding to the link is selected from each candidate risk indicator.

[0105] In one embodiment, the risk warning device 1 specifically further includes:

[0106] The association determination module is used to perform dimensionality reduction processing on the historical link data of each link, and to extract features from the historical link data after dimensionality reduction processing to obtain the link features corresponding to the link; based on the features of each link, the association analysis is performed on each link to obtain the association relationship between the links.

[0107] In one embodiment, the early warning module 30 is specifically used for:

[0108] Based on the risk information, determine the risk links in each link and the initial risk level corresponding to the risk links; determine the target risk level based on the initial risk level and the impact level of the risk link in the power grid industry chain; based on the target risk level, conduct risk warning for the power grid industry chain.

[0109] Each module in the above risk warning device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0110] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG6. 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 database of the computer device is used to store indicator data. 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 risk early warning method is implemented.

[0111] Those skilled in the art will understand that the structure shown in FIG. 6 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.

[0112] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0113] Obtaining current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0114] Input the current link data of each link into the risk warning model, and obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0115] Based on risk information, risk warnings are issued for the power grid industry chain.

[0116] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0117] For each link of the power grid industry chain, the original data of each data source of the link is obtained; from each original data, the initial data of each key risk indicator corresponding to the link is extracted; the extracted initial data of each key risk indicator is integrated to obtain the indicator data of each key risk indicator corresponding to the link.

[0118] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0119] The initial data of each key risk indicator is processed in a unified manner; wherein the unified processing includes at least one of unified processing of timestamps, unified processing of measurement units, and unified processing of coding methods; data cleaning is performed on each initial data after the unified processing; each initial data after data cleaning is integrated to obtain indicator data of each key risk indicator corresponding to the link.

[0120] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0121] Obtain historical link data of the link; wherein the historical link data includes indicator data of each candidate risk indicator corresponding to the link; based on the historical link data and the target data of the link evaluation indicator corresponding to the link, calculate the correlation between each candidate risk indicator corresponding to the link and the link evaluation indicator to obtain the correlation value corresponding to each candidate risk indicator; based on the correlation value corresponding to each candidate risk indicator, select each key risk indicator corresponding to the link from each candidate risk indicator.

[0122] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0123] For each link, the historical link data of the link is processed by dimensionality reduction, and the features of the historical link data after dimensionality reduction are extracted to obtain the link features corresponding to the link; based on the features of each link, the correlation analysis is performed on each link to obtain the correlation relationship between the links.

[0124] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0125] Based on the risk information, determine the risk links in each link and the initial risk level corresponding to the risk links; determine the target risk level based on the initial risk level and the impact level of the risk link in the power grid industry chain; based on the target risk level, conduct risk warning for the power grid industry chain.

[0126] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0127] Obtaining current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0128] Input the current link data of each link into the risk warning model, and obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0129] Based on risk information, risk warnings are issued for the power grid industry chain.

[0130] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0131] For each link of the power grid industry chain, the original data of each data source of the link is obtained; from each original data, the initial data of each key risk indicator corresponding to the link is extracted; the extracted initial data of each key risk indicator is integrated to obtain the indicator data of each key risk indicator corresponding to the link.

[0132] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0133] The initial data of each key risk indicator is processed in a unified manner; wherein the unified processing includes at least one of unified processing of timestamps, unified processing of measurement units, and unified processing of coding methods; data cleaning is performed on each initial data after the unified processing; each initial data after data cleaning is integrated to obtain indicator data of each key risk indicator corresponding to the link.

[0134] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0135] Obtain historical link data of the link; wherein the historical link data includes indicator data of each candidate risk indicator corresponding to the link; based on the historical link data and the target data of the link evaluation indicator corresponding to the link, calculate the correlation between each candidate risk indicator corresponding to the link and the link evaluation indicator to obtain the correlation value corresponding to each candidate risk indicator; based on the correlation value corresponding to each candidate risk indicator, select each key risk indicator corresponding to the link from each candidate risk indicator.

[0136] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0137] For each link, the historical link data of the link is processed by dimensionality reduction, and the features of the historical link data after dimensionality reduction are extracted to obtain the link features corresponding to the link; based on the features of each link, the correlation analysis is performed on each link to obtain the correlation relationship between the links.

[0138] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0139] Based on the risk information, determine the risk links in each link and the initial risk level corresponding to the risk links; determine the target risk level based on the initial risk level and the impact level of the risk link in the power grid industry chain; based on the target risk level, conduct risk warning for the power grid industry chain.

[0140] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0141] Obtaining current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link;

[0142] Input the current link data of each link into the risk warning model, and obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between each link;

[0143] Based on risk information, risk warnings are issued for the power grid industry chain.

[0144] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0145] For each link of the power grid industry chain, the original data of each data source of the link is obtained; from each original data, the initial data of each key risk indicator corresponding to the link is extracted; the extracted initial data of each key risk indicator is integrated to obtain the indicator data of each key risk indicator corresponding to the link.

[0146] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0147] The initial data of each key risk indicator is processed in a unified manner; wherein the unified processing includes at least one of unified processing of timestamps, unified processing of measurement units, and unified processing of coding methods; data cleaning is performed on each initial data after the unified processing; each initial data after data cleaning is integrated to obtain indicator data of each key risk indicator corresponding to the link.

[0148] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0149] Obtain historical link data of the link; wherein the historical link data includes indicator data of each candidate risk indicator corresponding to the link; based on the historical link data and the target data of the link evaluation indicator corresponding to the link, calculate the correlation between each candidate risk indicator corresponding to the link and the link evaluation indicator to obtain the correlation value corresponding to each candidate risk indicator; based on the correlation value corresponding to each candidate risk indicator, select each key risk indicator corresponding to the link from each candidate risk indicator.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0151] For each link, the historical link data of the link is processed by dimensionality reduction, and the features of the historical link data after dimensionality reduction are extracted to obtain the link features corresponding to the link; based on the features of each link, the correlation analysis is performed on each link to obtain the correlation relationship between the links.

[0152] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0153] Based on the risk information, determine the risk links in each link and the initial risk level corresponding to the risk links; determine the target risk level based on the initial risk level and the impact level of the risk link in the power grid industry chain; based on the target risk level, conduct risk warning for the power grid industry chain.

[0154] It should be noted that the information (including but not limited to power grid industry chain 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 fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0155] Those skilled 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 the memory, database or other medium 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), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. 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). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0156] 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.

[0157] The above-described 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 present application. 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 present application shall be subject to the attached claims.

Claims

1. A risk early warning method, characterized in that: The method comprises: Acquire current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link; Inputting the current link data of each link into the risk warning model, and obtaining the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between the links; Based on the risk information, a risk warning is issued for the power grid industry chain.

2. The method according to claim 1, characterized in that The acquisition of current link data of each link of the power grid industry chain includes: For each link of the power grid industry chain, obtain the original data of each data source of the link; Extracting initial data of each of the key risk indicators corresponding to the link from each of the original data; The extracted initial data of each of the key risk indicators are fused to obtain indicator data of each of the key risk indicators corresponding to the link.

3. The method according to claim 2, characterized in that The step of fusing the extracted initial data of each of the key risk indicators to obtain the indicator data of each of the key risk indicators corresponding to the link includes: Performing unified processing on the initial data of each of the key risk indicators; wherein the unified processing includes at least one of unified processing of timestamps, unified processing of measurement units, and unified processing of coding methods; Perform data cleaning on the initial data after unified processing; The initial data after data cleaning are integrated to obtain the indicator data of each key risk indicator corresponding to the link.

4. The method according to claim 1, characterized in that: The key risk indicators corresponding to each link are determined in the following ways: Acquire historical link data of the link; wherein the historical link data includes indicator data of each candidate risk indicator corresponding to the link; Based on the historical link data and the target data of the link evaluation index corresponding to the link, a correlation calculation is performed on each candidate risk index corresponding to the link and the link evaluation index to obtain a correlation value corresponding to each candidate risk index; Based on the relevant values ​​corresponding to the candidate risk indicators, the key risk indicators corresponding to the link are selected from the candidate risk indicators.

5. The method according to claim 1, characterized in that: The relationship between each link is determined by the following method: For each link, the historical link data of the link is subjected to dimensionality reduction processing, and feature extraction is performed on the historical link data after dimensionality reduction processing to obtain link features corresponding to the link; Based on the characteristics of each link, the correlation analysis is carried out on each link to obtain the correlation relationship between each link.

6. The method according to claim 1, characterized in that According to the risk information, a risk warning is provided for the power grid industry chain: Determine the risk links in each link and the initial risk levels corresponding to the risk links according to the risk information; Determining a target risk level according to the initial risk level and the impact level of the risk link in the power grid industry chain; Based on the target risk level, a risk warning is issued for the power grid industry chain.

7. A risk warning device, characterized in that: The device comprises: An acquisition module is used to acquire current link data of each link of the power grid industry chain; wherein the current link data of each link includes indicator data of each key risk indicator corresponding to the link; An information determination module is used to input the current link data of each link into the risk warning model to obtain the risk information of the power grid industry chain output by the risk warning model based on the model parameters and the current link data of each link; wherein the model parameters include the correlation relationship between the links; The early warning module is used to issue risk early warning to the power grid industry chain according to the risk information.

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