Power grid safety production detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a power grid safety production detection method and device, electronic equipment and a storage medium. The method comprises the steps that safety production associated data of a target power grid are acquired, and the safety production associated data comprise power grid operation feature data and power grid safety question and answer data of a target object; performing risk detection on the safety production associated data by using a pre-established safety risk assessment model to obtain risk detection feature data; determining a target early warning scheme according to the risk detection feature data; the target early warning scheme is predicted by executing the risk prediction model, and the target safety detection report related to the target power grid safety production is generated according to the prediction result, so that the problems of insufficient data integration, inaccurate risk identification and inaccurate countermeasures in the prior art are solved; the safety production state of the power grid can be comprehensively detected, accurate early warning is provided, and the risk management efficiency and safety of the power grid are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of power grid safety technology, and in particular to a power grid safety production detection method, device, electronic equipment and storage medium. Background Art

[0002] During the operation of the power grid, the safe and stable operation of the power grid is of vital importance.

[0003] However, due to the complexity and dynamic nature of power grid systems, security risk assessment methods used in related technologies often struggle to comprehensively and accurately identify and predict potential safety hazards. Furthermore, models used to monitor power grid safety primarily rely on grid operational data, neglecting to examine the safety standards of safety personnel. This single data source makes it difficult to comprehensively assess both grid operational data and the safety awareness of safety personnel, resulting in inaccurate assessment results and an inability to provide comprehensive, targeted solutions for grid safety. Summary of the Invention

[0004] The present invention provides a power grid safety production detection method, device, electronic equipment and storage medium to solve the problems existing in related technologies such as insufficient data integration, inaccurate risk identification and inaccurate response measures.

[0005] According to one aspect of the present invention, a method for detecting power grid production safety is provided, comprising:

[0006] Acquire safety production related data of the target power grid, wherein the safety production related data includes power grid operation characteristic data and power grid safety question and answer data of the target object;

[0007] Perform risk detection on the production safety related data using a pre-established safety risk assessment model to obtain risk detection feature data;

[0008] Determining a target early warning plan based on the risk detection feature data;

[0009] The target early warning scheme is predicted by executing the risk prediction model, and a target safety detection report related to the safe production of the target power grid is generated according to the prediction results.

[0010] According to another aspect of the present invention, there is provided a power grid production safety detection device, comprising:

[0011] A safety production related data acquisition module is used to acquire safety production related data of the target power grid, wherein the safety production related data includes power grid operation characteristic data and power grid safety question and answer data of the target object;

[0012] A risk detection module is used to perform risk detection on the production safety related data using a pre-established safety risk assessment model to obtain risk detection feature data;

[0013] An early warning scheme determination module is used to determine a target early warning scheme based on the risk detection feature data;

[0014] The safety detection report generation module is used to predict the target early warning plan by executing the risk prediction model, and generate a target safety detection report related to the safe production of the target power grid based on the prediction results.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the power grid safety production detection method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the power grid production safety detection method described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention obtains the production safety related data of the target power grid. Since the production safety related data includes the power grid operation characteristic data and the power grid safety question and answer data of the target object, it can integrate the related information in the power grid production safety process and improve the detection accuracy; then, the production safety related data is subjected to risk detection using a pre-established safety risk assessment model to obtain risk detection characteristic data, which can accurately identify potential risks in the power grid operation; then, the target early warning scheme is determined based on the risk detection characteristic data, which can realize early discovery and rapid response to power grid safety hazards; finally, the target early warning scheme is predicted by executing the risk prediction model, and a target safety detection report related to the production safety of the target power grid is generated according to the prediction results, which can improve the predictability and accuracy of power grid safety management, solve the problems of insufficient data integration, inaccurate risk identification and inaccurate response measures in related technologies, can comprehensively detect the production safety status of the power grid, provide accurate early warnings, and significantly improve the efficiency and safety of power grid risk management.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flow chart of a power grid safety production detection method provided according to the first embodiment of the present invention;

[0024] Figure 2 This is a flow chart of a power grid safety production detection method provided according to the second embodiment of the present invention;

[0025] Figure 3 This is a schematic structural diagram of a power grid production safety detection device provided according to a third embodiment of the present invention;

[0026] Figure 4 It is a structural diagram of an electronic device for implementing the power grid safety production detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0032] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0033] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0034] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0035] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0036] Example 1

[0037] Figure 1 A flowchart of a power grid safety production detection method is provided for embodiment 1 of the present invention. This embodiment is applicable to comprehensive detection and evaluation of power grid safety production. The method can be executed by a power grid safety production detection device, which can be implemented in the form of hardware and / or software. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, PC or server, etc.

[0038] like Figure 1 As shown, the method may specifically include:

[0039] S110 . Acquire safety production related data of the target power grid, wherein the safety production related data includes power grid operation characteristic data and power grid safety question and answer data of the target object.

[0040] The target power grid can be understood as a specific area or type of power grid system, which is the subject of security assessment and testing. The safety production-related data can be understood as a collection of various types of information related to the safe operation of the power grid. This safety production-related data may include, but is not limited to, at least one of power grid operation characteristic data and target subject grid security question-and-answer data. The grid operation characteristic data can be understood as various parameters and indicators related to the power grid's operating status, including, but not limited to, voltage, current, frequency, and power. It can also include at least one of power equipment operating time, number of failures, and maintenance records. This grid operation characteristic data can be used to analyze the health, efficiency, and stability of the power grid and is an important basis for assessing power grid security and reliability. The power grid security question-and-answer data can be understood as a collection of questions and answers related to power grid security, used to understand the target subject's understanding and implementation of power grid safety regulations and identify potential human risk factors. This power grid security question-and-answer data may include, but is not limited to, at least one of employee training, safety inspections, and accident case analysis. The target subject can be understood as personnel related to power grid safety production, including, but not limited to, dispatchers, maintenance engineers, and technical support teams.

[0041] On the basis of the above scheme, optionally, the grid operation characteristic data of the target power grid is obtained, including: collecting the grid operation characteristic data by obtaining the electric meter or power sensor installed on the target power equipment in the target power grid; or, deploying a network proxy service at the target node in the power equipment, and collecting the grid operation characteristic data at a preset time interval through the network proxy service; or, pulling the grid operation characteristic data from the network equipment and the server through the network management protocol; or, obtaining the grid operation characteristic data by calling a preset data acquisition interface, etc.

[0042] On the basis of the above scheme, optionally, the power grid security question and answer data of the target object can be obtained, including: collecting the power grid security question and answer data of the target object through an online questionnaire system or an intelligent dialogue system; or, interacting with the target object and determining the power grid security question and answer data based on the interaction content, etc.

[0043] S120: Perform risk detection on the production safety related data using a pre-established safety risk assessment model to obtain risk detection feature data.

[0044] The safety risk assessment model can be understood as an assessment model used to quantify the degree of uncertainty and potential hazards in the power grid's safety production process. Specifically, through a comprehensive analysis of power grid operational characteristic data and safety Q&A data, risk points that may lead to safety accidents can be detected and quantitatively assessed. The risk detection characteristic data can be understood as data output by the safety risk assessment model, reflecting the main risks and characteristics currently facing the target power grid.

[0045] Based on the above scheme, optionally, the use of a pre-established safety risk assessment model to perform risk detection on the production safety-related data to obtain risk detection feature data includes: obtaining the operation feature data, and obtaining the target semantic features in the power grid safety question and answer data, and mapping the operation feature data into the state feature space to determine a preliminary risk point set, and using the power grid safety knowledge graph to perform contextual understanding of the target semantic features to determine the safety score of the target semantic features; using the safety risk assessment model to perform risk detection on each risk point and the safety score in the preliminary risk point set to obtain a preliminary risk detection result, and determining the risk concentration area and high-risk period of the target power grid based on the preliminary risk detection result and the time data and regional data of the risk points corresponding to the preliminary risk point set to obtain a risk distribution map; using the power grid safety knowledge graph to perform risk cause detection on the risk concentration area in the high-risk period in the risk distribution map to obtain a preliminary risk explanation list, and based on the corresponding associated risk data and historical risk cases in the power grid safety knowledge graph, performing confidence assessment and structured classification on each explanation in the preliminary risk explanation list to generate risk detection feature data.

[0046] The target semantic features can be understood as information extracted from grid security question-and-answer data, reflecting the target subject's understanding and implementation of grid security regulations. The state feature space can be understood as an abstract space, where each dimension represents a characteristic or attribute of grid operation. The state feature space includes at least one of information about the changing process of the grid state pattern and annotation information of the grid state pattern. By mapping operational feature data to the state feature space, the state feature space can visually represent the state evolution of the grid and identify potential risk points. The information about the changing process of the grid state pattern can be understood as the trends and patterns of grid state changes over time, which helps determine the dynamic behavior of the grid and predict possible future risk trends. Exemplarily, the information about the changing process of the grid state pattern includes, but is not limited to, at least two processes: normal operation, mild overload, severe overload, or voltage collapse. The annotation information can be understood as marking the grid state at a specific time point, time period, or for power equipment. Exemplarily, the annotation information can be a semantic annotation such as "increased risk of voltage instability." The preliminary point set can be understood as a set of locations or conditions that may pose a risk, derived from analysis of the state feature space. The grid security knowledge graph can be understood as a structured knowledge representation that uses nodes (entities) and edges (relationships) to indicate the connections between different power devices in the grid and how they work together to ensure grid stability and security. Contextual understanding can be understood as accurately capturing the true meaning of words, phrases, or sentences by analyzing the context of target semantic features when processing them. In this embodiment, contextual understanding can help more accurately parse the responses and questions of the target subject, thereby better assessing the target subject's understanding and implementation of safety production. The safety score can be understood as a score for the target semantic features extracted from the question and answer data based on the grid security knowledge graph, reflecting the risk level associated with the target semantic features. This score is used to quantify the impact of human factors on grid safety production and provide a reference for comprehensive risk assessment. The preliminary risk detection result can be understood as the result obtained by analyzing each risk point and safety score in the preliminary risk point set. It can indicate the current risk status of grid safety production and lay the foundation for further analysis. The risk concentration areas and high-risk periods can be understood as areas and time periods with a high probability of risk events occurring in the grid at specific times and locations. The risk distribution map can be understood as a graphical representation of the risk distribution at different locations and time periods within the power grid. Risk cause detection can be understood as identifying the specific causes of risk by analyzing high-risk periods and clustered areas. This can provide a basis for developing effective solutions and ensure that the problem can be fundamentally resolved. The preliminary risk explanation list can be understood as a list of various factors that may cause risk and their corresponding explanations.The associated risk data can be understood as data associated with power grid safety production during the power grid safety production assessment process. The associated risk data can be used to connect data from different sources (such as operating characteristic data or question-and-answer data, etc.) with known risk factors and historical risk cases to identify potential risk points and assess their impact. The historical risk cases can be understood as records of risk events that occurred in the past and involved power grid safety or other related fields. The historical risk cases may include but are not limited to at least one of the background of the incident, the development process, the final result and the post-event evaluation. The confidence assessment can be understood as a credibility evaluation of each explanation in the preliminary risk explanation list to determine its accuracy and reliability. The structured classification can be understood as organizing and classifying risk explanations according to certain rules and standards, so that the safety production associated data is more organized and clear, and convenient for reference and application.

[0047] An optional implementation method is to extract target semantic features from operation feature data using a sliding window technique and to perform natural language processing on power grid security question and answer data using word embedding techniques such as Word2Vec; then, the extracted operation feature data is mapped to the constructed state feature space using a nearest neighbor algorithm to identify a preliminary risk point set, and the extracted target semantic features are contextually understood using a power grid security knowledge graph using graph embedding techniques such as TransE to evaluate the safety score of the target object; then, a safety risk assessment model is used to perform risk detection (safety risk assessment and production anomaly detection) on each risk point and safety score in the preliminary risk point set, that is, the safety risk assessment model uses the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method to comprehensively consider equipment status, system stability, and human factors to obtain a preliminary risk assessment result; then, based on the spatiotemporal data of the risk points corresponding to the preliminary risk point set, a spatial statistical method such as kernel density estimation (KDE) is used to identify risk cluster areas, where the formula for the two-dimensional KDE is:

[0048]

[0049] Among them, K is the kernel function, h is the bandwidth parameter, (x i ,y i) is a sample point, and n represents the number of samples. KDE is used to identify grid risk clusters and high-risk periods in the preliminary risk assessment results, thereby generating a risk distribution map. A Bayesian network is then constructed on the grid security knowledge graph to detect risk causes in high-risk areas and generate a preliminary list of anomaly explanations. Based on the corresponding associated risk data and historical risk cases in the grid security knowledge graph, a random forest algorithm is used to assess the confidence of each explanation in the preliminary anomaly explanation list. By comprehensively considering the similarity of historical cases and the specificity of the current situation, hierarchical clustering or topic models such as LDA are used to perform structured classification on the evaluated explanations, ultimately generating an anomaly assessment result. For example, consider real-time voltage data from a substation. Wavelet transform is used to extract voltage trends, periodicity, and sudden changes. For target safety question-and-answer data, such as "Construction precautions near high-voltage lines," target semantic features such as "high voltage," "construction," and "safe distance" are identified. The extracted voltage feature vector is then mapped into the state feature space to find that it falls near an area indicating "voltage instability," thus identifying it as a potential risk point. At the same time, by analyzing the semantic features of the question-and-answer data, the employee's safety awareness score was assessed to be 85 points (out of 100); based on historical data, it was predicted that if the voltage continued to fluctuate, equipment overload might occur within 15 minutes. Through KDE analysis, it was found that the area where the substation was located was a risk cluster area, especially during peak power consumption hours; then, using the Bayesian network, it was inferred that the possible causes of voltage instability were: sudden increase in load (confidence 0.7), line failure (confidence 0.5), and equipment aging (confidence 0.3). The random forest model was used to evaluate these explanations. Taking into account historical cases and relevant risk data, it was finally concluded that a sudden increase in load was the most likely cause (confidence 0.8), and it was recommended to closely monitor load changes and prepare to start the backup power supply. Through this series of complex analysis processes, real-time data and security question and answer data are converted into specific risk assessment results and anomaly explanations. This method not only takes into account the real-time status of the equipment, but also combines the safety awareness level of the personnel, while utilizing the rich semantic information in the power grid security knowledge graph. This provides comprehensive and accurate decision-making support for power grid production safety supervision, helps to timely discover and prevent potential safety hazards, and thus improve the overall safety and reliability of the power grid.In addition, when extracting operational characteristic data, the sampling frequency of the data and possible delays need to be considered. When evaluating personnel safety awareness, the timeliness of the question-and-answer data and the work experience of employees need to be considered. When conducting risk detection, the weights of risk factors at different levels need to be balanced to ensure that the assessment results reflect both local risks and the safety status at the system level. Furthermore, it is necessary to deeply integrate the study of safety regulations into the work scenarios of production safety operators by adding more nodes and relationships related to specific work scenarios to the power grid safety knowledge graph. In addition, special attention needs to be paid to medium- and high-risk operations, such as giving such operations higher weights in the risk assessment model.

[0050] This technical solution uses the target semantic features in the grid operation characteristic data and the grid security question and answer data, and utilizes the pre-established security risk assessment model and grid security knowledge graph to achieve in-depth mining and precise positioning of potential risks in the power system. It can map the operation characteristics to the state feature space to determine the initial risk point set, and can also quantify the safety score of the grid security question and answer data through contextual understanding. Furthermore, the solution successfully draws a risk distribution map by analyzing the time data and regional data of the preliminary risk detection results, intuitively showing the risk concentration areas and high-incidence periods. Finally, it combines historical risk cases and related risk data to detect and explain the causes of risks, and generates detailed risk detection feature data through confidence assessment and structured classification, significantly improving the foresight, accuracy and response speed of grid safety production management, helping to take preventive measures in a timely manner to ensure the stable and safe operation of the power system.

[0051] S130: Determine a target early warning plan based on the risk detection feature data.

[0052] The target early warning scheme can be understood as preventive measures and emergency response plans designed for the security risks of the target power grid, aiming to take action in advance to avoid or mitigate the impact of possible security incidents.

[0053] On the basis of the above scheme, optionally, the target early warning scheme is determined according to the risk detection characteristic data, including: determining a preliminary risk score of a power grid production safety risk event according to the risk detection characteristic data, and determining the risk influencing factors of the target power grid based on the preliminary risk score and the power grid safety knowledge graph; determining a risk impact path according to the risk influencing factors, determining the risk impact objects in the risk impact path, and determining an impact hierarchy structure according to the risk impact objects and the risk impact factors; matching the detection and early warning response library corresponding to the impact hierarchy structure based on a preset multi-level early warning threshold system, and determining the target early warning scheme corresponding to the impact hierarchy structure according to the detection and early warning response library.

[0054] The preliminary risk score can be understood as the result of a quantitative assessment of power grid production safety risk events based on risk detection feature data. The preliminary risk score can be used to characterize, for example, the severity and urgency of the risk. The risk influencing factors can be understood as factors that may lead to risks in power grid operations, including but not limited to at least one of equipment failure, operational errors, and environmental changes. The risk impact path can be understood as the process chain from risk occurrence to risk impact diffusion, used to determine how the risk propagates within the power grid. The risk impact object can be understood as a specific component or area affected by the risk, including but not limited to at least one of specific equipment, substations, or transmission lines. The impact hierarchy can be understood as a hierarchical structure constructed based on risk influencing factors and risk impact objects, reflecting the risk impact relationships at different levels and enabling targeted, hierarchical management of risk impact objects. The multi-level warning threshold system can be understood as a preset risk level classification standard, with each level corresponding to different response requirements. This system can be used to ensure that appropriate warning and response measures are implemented for different levels of risk, avoiding overreaction or underreaction. The detection, warning, and response library can be understood as a database containing predefined warning and response plans, suitable for determining different types of risk management plans based on the impact hierarchy. The target warning scheme can be understood as the preventive measures and emergency response plan determined for grid safety production risk events in a specific power grid. It can be used to take action in advance to avoid or mitigate the impact of possible grid safety production risk events and ensure the safe and stable operation of the power grid.

[0055] An optional implementation method adopts a fuzzy comprehensive evaluation method, by establishing an evaluation index system, including the impact scope, duration and potential losses of the risk, and then using a fuzzy membership function to convert these indicators into fuzzy sets. The fuzzy synthesis operation of the evaluation matrix R and the weight vector A can be expressed as B = A·R, where "·" represents the fuzzy synthesis operator, thereby performing a quantitative analysis of the severity and urgency of the risk detection feature data to obtain a preliminary risk score for the power grid safety production risk event; then, based on the preliminary risk score and the power grid safety knowledge graph, a graph neural network (GNN) is used to determine the risk influencing factors of the target power grid and target object to capture the impact of the power grid safety production risk event on different components and personnel of the power grid, thereby obtaining an impact hierarchy structure of the risk influencing factors; then, based on a preset multi-level warning threshold system, a decision tree algorithm such as the C4.5 algorithm is used to use the information gain ratio to select the optimal partitioning feature to match the corresponding detection and warning response library, where the calculation formula of the C4.5 algorithm is:

[0056] Gain_ratio(A)=Gain(A) / SplitInfo(A);

[0057] Among them, Gain(A) is the information gain of feature A, and SplitInfo(A) is the split information of feature A. By constructing a decision tree, we can quickly match the appropriate warning response strategy (i.e., the detection warning response library) based on the different features that affect the hierarchical structure. Then, we use the collaborative filtering algorithm to perform warning role matching analysis on the detection warning response library. By assuming that R is the warning role-warning strategy scoring matrix, the goal is to decompose it into the product of the U and V matrices: R≈UV^T. The corresponding optimization objective function is expressed as:

[0058]

[0059] Among them, r ij is a known rating, u i and v j are the latent factor vectors of warning roles and warning strategies, respectively. λ is the regularization parameter. m is the total number of warning roles. n is the total number of warning strategies. i is the warning role, ranging from 1 to m. j is the warning strategy, ranging from 1 to n. In this way, the most suitable warning strategy is recommended for each warning role, and the final safety production detection warning strategy is generated. For example, suppose a transformer at a substation detects an abnormally high temperature. Fuzzy comprehensive evaluation might indicate this is a medium severity (0.6) and high urgency (0.8) risk event, resulting in an initial risk score of 0.7. Using GAT to analyze the power grid knowledge graph, it might be discovered that this anomaly affects not only the substation but also the downstream distribution network and electricity users, forming a three-tiered impact hierarchy. Based on this impact hierarchy, a decision tree algorithm might be used to match an early warning response library containing strategies such as "activate a backup transformer," "limit non-critical loads," and "notify the maintenance team." Finally, a collaborative filtering algorithm can be used to assign specific tasks to different roles: dispatchers are responsible for activating the backup transformer, operations and maintenance personnel are responsible for on-site inspections and repair preparations, and customer service personnel are responsible for notifying key customers who may be affected. This role matching ensures that each relevant person receives appropriate instructions, thereby improving the efficiency and accuracy of power grid safety supervision.

[0060] By adopting this technical solution, the preliminary risk score of power grid production safety risk events is determined by analyzing risk detection feature data, and the power grid safety knowledge map is used to identify key risk influencing factors and their paths, clarify the risk impact objects and hierarchical structure, and based on this, match the preset multi-level warning threshold system, and select the most appropriate target warning scheme from the detection and warning response library. This not only improves the accuracy and timeliness of the warning, but also enhances the pertinence and effectiveness of the response measures, ensuring that appropriate prevention and control measures can be taken before the risk occurs, effectively ensuring the safe and stable operation of the power grid, and reducing potential losses.

[0061] S140 , predicting the target early warning plan by executing the risk prediction model, and generating a target safety detection report related to the safe production of the target power grid according to the prediction result.

[0062] The risk prediction model can be understood as a model used to predict the likelihood of risks occurring and the extent of their impact after implementing the target early warning solution. The target safety inspection report can be understood as the results of all safety inspection activities conducted on the target power grid, including but not limited to at least one of the following: problems discovered, measures taken, and improvement suggestions. It can be provided to management and relevant departments as a reference to continuously optimize the safety management and operation of the target power grid.

[0063] The technical solution of the embodiment of the present invention obtains the production safety related data of the target power grid. Since the production safety related data includes the power grid operation characteristic data and the power grid safety question and answer data of the target object, it can integrate the related information in the power grid production safety process and improve the detection accuracy; then, the production safety related data is subjected to risk detection using a pre-established safety risk assessment model to obtain risk detection characteristic data, which can accurately identify potential risks in the power grid operation; then, the target early warning scheme is determined based on the risk detection characteristic data, which can realize early discovery and rapid response to power grid safety hazards; finally, the target early warning scheme is predicted by executing the risk prediction model, and a target safety detection report related to the production safety of the target power grid is generated according to the prediction results, which can improve the predictability and accuracy of power grid safety management, solve the problems of insufficient data integration, inaccurate risk identification and inaccurate response measures in related technologies, can comprehensively detect the production safety status of the power grid, provide accurate early warnings, and significantly improve the efficiency and safety of power grid risk management.

[0064] Example 2

[0065] Figure 2 A flowchart of a power grid production safety detection method provided in the second embodiment of the present invention, based on the differences between this embodiment and the above embodiments, further refines how to determine the safety risk assessment model. Optionally, determining the safety risk assessment model includes: obtaining multiple production safety reference data of the target power grid, and determining the state feature space of the target power grid based on the production safety reference data; wherein the state feature space includes the change process information of the power grid state mode and the annotation information of the power grid state mode; based on the state feature space, constructing a knowledge graph for the production safety reference data to obtain a power grid safety knowledge graph; using the power grid safety knowledge graph to perform a hierarchical risk assessment on a preset risk assessment model to obtain a safety risk assessment model. For specific implementation methods, please refer to the description of this embodiment. Among them, the technical features that are the same or similar to those in the above embodiments are not repeated here.

[0066] like Figure 2 As shown, the method may specifically include:

[0067] S210, obtaining a plurality of safety production reference data of a target power grid, and determining a state feature space of the target power grid based on the safety production reference data; wherein the state feature space includes change process information of a power grid state mode and annotation information of the power grid state mode;

[0068] Among them, the safety production reference data can be understood as various historical data related to the safe production operation of the power grid, including but not limited to at least one of historical operating parameters, historical maintenance records, historical fault reports and historical power grid safety question and answer data.

[0069] On the basis of the above scheme, after obtaining multiple safety production reference data of the target power grid, it also includes: preprocessing the safety production related data, and the preprocessing includes at least format unification processing, timestamp alignment and synchronization, missing value detection and interpolation, outlier detection and cleaning, data noise reduction and smoothing, and data standardization and normalization processing, etc.

[0070] On the basis of the above scheme, optionally, determining the state feature space of the target power grid according to the safe production reference data includes: performing time series decomposition on the safe production reference data to obtain time domain power grid characteristics, and using short-time Fourier transform to perform time-frequency transformation on the time domain power grid characteristics to obtain frequency domain power grid characteristics; performing nonlinear transformation on the time domain power grid characteristics and the frequency domain power grid characteristics to obtain data distribution characteristics; performing cross-domain feature correlation analysis on the safe production reference data based on the data distribution characteristics to obtain interactive power grid characteristics; performing feature fusion on the time domain power grid characteristics, the frequency domain power grid characteristics, the data distribution characteristics and the interactive power grid characteristics, and performing feature dimensionality reduction on the fused features to obtain low-dimensional power grid characteristics; clustering the low-dimensional power grid characteristics to obtain multiple clusters, determining the power grid state mode according to the cluster to which the low-dimensional power grid characteristics belong, semantically annotating the power grid state mode, and determining the state feature space of the target power grid according to the result of the semantic annotation.

[0071] The time series decomposition can be understood as the process of decomposing the time series data in the safety production reference data into multiple components, such as trends, seasonal components, and noise. The time domain grid characteristics can be understood as the characteristic parameters of the grid in the time dimension, obtained through time series decomposition, which can be used to capture the time-varying behavioral patterns of the target grid, such as voltage fluctuations or current changes. The short-time Fourier transform can be understood as the process of converting time domain signals into frequency domain signals while preserving local time information. The frequency domain grid characteristics can be understood as the characteristic parameters of the target grid in the frequency dimension, obtained through the short-time Fourier transform, which can capture information about the frequency components of the target grid and help identify anomalies or patterns at specific frequencies. The nonlinear transformation can be understood as performing a nonlinear mapping on data to reveal hidden data structures or features. For example, the nonlinear transformation can utilize methods such as kernel principal component analysis, which can capture complex nonlinear relationships between time domain and frequency domain grid characteristics. The data distribution characteristics can be understood as the data distribution properties obtained after the nonlinear transformation, which reflect information such as the skewness and / or kurtosis of the data distribution and help determine the operating status of the target grid. Cross-domain feature association analysis can be understood as a method for determining the relationships between different types of safety production reference data, discovering the interactions and dependencies between different types of safety production reference data. Interactive power grid features can be understood as features derived from cross-domain feature association analysis, used to determine the interactions between different data types. Feature fusion can be understood as integrating multiple types of features (such as time-domain power grid features, frequency-domain power grid features, operating status features, and interactive power grid features) into a unified feature representation to ensure that all relevant features can be utilized. Feature dimensionality reduction can be understood as a method for reducing the number of features while retaining as much important information as possible, simplifying data structures and reducing computational complexity. Low-dimensional power grid features can be understood as simplified feature representations after feature dimensionality reduction that still retain key information about safety production reference data. Clustering can be understood as grouping low-dimensional power grid features based on their similarities, with each group being called a cluster. This is used to classify low-dimensional power grid features and help identify different power grid status patterns. A cluster can be understood as each group formed after clustering low-dimensional power grid features, representing a group of power grid states with similar characteristics, facilitating classified management and targeted processing. The grid state model can be understood as different grid operation state categories defined by clustering results, reflecting the grid's performance at different time periods. The semantic annotation can be understood as assigning readable labels to the grid state model to describe its specific meaning, thereby enhancing the interpretability of the grid state model.

[0072] An optional implementation method, first, uses the empirical mode decomposition method to perform time series decomposition on the pre-processed production safety related data, so as to decompose the complex time series into a series of intrinsic mode functions (IMFs), thereby revealing the intrinsic time scale characteristics of the pre-processed production safety related data, and at the same time uses the short-time Fourier transform to perform time-frequency transformation on the results of the time series decomposition, so as to obtain frequency characteristics while retaining time information, which is helpful to identify periodic patterns and transient events in the power grid, and finally obtain time domain power grid characteristics and frequency domain power grid characteristics; then uses the kernel principal component analysis method to perform nonlinear transformation on the time domain power grid characteristics and frequency domain power grid characteristics, so as to capture the complex nonlinear relationship in the data and extract more representative features, and obtain Data distribution characteristics (wherein, data distribution characteristics reflect information such as the skewness and kurtosis of the data distribution, which helps to more comprehensively describe the operating status of the power grid); then, based on the data distribution characteristics, Tucker decomposition is used to perform cross-domain feature correlation analysis on the pre-processed production safety related data to reveal potential correlations between different types of data, such as the relationship between voltage fluctuations and load changes, or the connection between weather conditions and equipment failure rates, to obtain interactive power grid characteristics; then, feature cascading or feature fusion methods are used to combine time domain power grid characteristics, frequency domain power grid characteristics, data distribution characteristics, and interactive power grid characteristics, and the t-SNE algorithm is used for feature dimensionality reduction. The objective function of the t-SNE algorithm is:

[0073]

[0074] p ij and q ij are the similarities between points i and j in the high-dimensional space and the low-dimensional space, respectively. This reduces the dimensionality while preserving the local structure of the data, discovering potential patterns in the data, and obtaining low-dimensional grid features. The Gaussian mixture model (GMM) then performs cluster analysis on the low-dimensional grid features, classifying similar grid states. At the same time, typical grid state patterns, such as normal operation, high load, or fault state, are identified through clustering. The dynamic Bayesian network (DBN) is then used to capture the temporal evolution of the grid state (i.e., time series relationships). The identified state patterns are combined with professional knowledge to give them clear semantic interpretations. The joint probability distribution of the DBN is expressed as:

[0075]

[0076] X t represents the state variable set at time t, P(X1:T) represents the state variable from X1 to X T The joint probability of P(X1) represents the probability of the first variable X1, P(X t |X t-1 ) indicates that given the previous variable Xt-1 Under the condition that the variable X t For example, consider a set of substation voltage data. First, EMD is used to decompose the voltage signal into multiple IMFs. These IMFs may correspond to variations at different scales, such as daily load variations and periodic fluctuations. Then, WPT is applied to analyze the time-frequency characteristics of each IMF to identify specific frequency components associated with equipment failures. Next, bispectral analysis may reveal nonlinear coupling between certain frequency components, which may indicate abnormal patterns in the power grid. Furthermore, using GCN for cross-domain feature correlation analysis, substations are treated as nodes in the graph and power lines as edges to analyze the mutual influence between different substations. Using t-SNE dimensionality reduction, the data may form several distinct clusters in the low-dimensional space. These clusters correspond to different power grid operating states. GMM is used to model these clusters to obtain typical power grid state patterns, such as normal operation, mild overload, or severe overload. Finally, using DBN to model the temporal evolution of these state patterns, it may be discovered that certain state transition sequences indicate potential failure risks. For example, a state sequence such as "normal operation → mild overload → severe overload → voltage collapse" might be discovered and semantically labeled "increased risk of voltage instability." Through this complex analysis process, the original multi-source heterogeneous data is transformed into a semantically rich state feature space. This state feature space not only captures the static characteristics of the grid state but also captures the dynamic evolutionary relationships between states.

[0077] This technical solution extracts and analyzes multi-dimensional features of production safety reference data, including time series decomposition, time-frequency transformation, nonlinear transformation, and cross-domain feature association. It integrates time domain, frequency domain, data distribution, and interaction features, and determines the power grid state pattern through feature dimensionality reduction and cluster analysis. Combined with semantic annotation, it defines the state feature space of the target power grid. This can fully capture the dynamic characteristics and complex patterns of power grid operation, provide more accurate state assessment, and provide strong data support and technical guarantee for the safe and stable operation of the power grid, thereby improving the fault prediction and prevention capabilities.

[0078] S220: constructing a knowledge graph for the production safety reference data based on the state feature space to obtain a power grid safety knowledge graph;

[0079] On the basis of the above scheme, optionally, the knowledge graph of the production safety reference data is constructed based on the state feature space to obtain a power grid safety knowledge graph, including: determining the classification information of the state feature space, constructing an initial graph subject model according to the classification information, and performing entity recognition and relationship extraction on the production safety reference data according to the initial graph subject model to construct an initial power grid knowledge graph; aligning the initial graph subject model and the initial power grid knowledge graph to obtain power grid safety knowledge, and adjusting the power grid safety knowledge to obtain an initial dynamic knowledge graph; constructing a power grid safety knowledge graph according to the entities and relationships in the initial dynamic knowledge graph.

[0080] The classification information can be understood as the result of classifying data in the state feature space. The initial graph subject model can be understood as the basic framework for constructing a power grid security knowledge graph, defining the basic relationships between data such as power equipment and power grid state patterns in the graph. Entity recognition can be understood as identifying power grid-related entities from production safety reference data, including but not limited to at least one of power grid equipment, operators, and security events, to convert unstructured production safety reference data into structured information. Relationship extraction can be understood as extracting relationships between entities after entity recognition, including but not limited to at least one of the following: connected, responsible, and caused by. The initial power grid knowledge graph can be understood as a basic power grid security knowledge graph constructed based on the initial graph subject model and the identified entities and relationships. The initial power grid knowledge graph provides a preliminary representation of the knowledge structure in the field of power grid security, providing a foundation for further improvement and application. Alignment can be understood as the process of matching and integrating initial graph subject models from different sources or versions with the initial power grid knowledge graph to ensure semantic consistency of concepts and relationships within the graph, thereby improving the completeness and accuracy of the knowledge graph and avoiding duplicate or contradictory information. The grid security knowledge can be understood as a specific set of knowledge related to grid security obtained after alignment, including but not limited to at least one of entities, relationships, and their attributes. The initial dynamic knowledge graph can be understood as an adjusted grid security knowledge graph with dynamic update capabilities, capable of timely responding to new data and changes in circumstances, and providing more accurate decision support.

[0081] An optional implementation method is to systematically sort out the knowledge in the field of power grid security based on the state feature space, including but not limited to classification information of multiple dimensions such as power equipment, operating status, safety regulations and accident types, and use the formal ontology language OWL (Web Ontology Language) to define the concept hierarchy, where the key construct is expressed as: Class (A partial C1...Cn), where A represents a new class (concept), and C1 to Cn represent the parent classes of A. In this way, the hierarchical structure of concepts such as power grid equipment, safety status and operating procedures can be defined, thereby constructing an initial graph subject model; based on this initial graph subject model, for unstructured text data, deep learning models such as BERT are used for entity recognition, and for structured data, entities are extracted through predefined rules and mapping relationships. At the same time, remote supervised learning or graph neural networks are used to identify entities such as power grid equipment, operators and safety events from the original data, as well as various relationships between them, such as "connected", "responsible" or "caused", thereby constructing an initial power grid knowledge graph; ontology matching technology, such as semantic similarity calculation based on word vectors or graph structure matching algorithm, is used to identify and merge semantically similar concepts and relationships, thereby improving the initial graph. The subject model and the initial power grid knowledge graph are integrated and aligned with the power grid knowledge and security ontology to ensure the semantic consistency of the concepts and relationships in the initial power grid knowledge graph, and obtain semantically unified power grid security knowledge. Then, the power grid security knowledge is optimized (by adjusting and improving the nodes (entities) and edges (relationships) in the power grid security knowledge graph to improve the quality, efficiency and expressiveness of the graph) and the temporal expansion of the graph structure. Among them, the graph structure optimization includes but is not limited to adding new entities, deleting redundant or irrelevant entities, merging similar entities or making implicit relationships explicit, so as to improve the simplicity and expressiveness of the graph. At the same time, in order to capture the temporal evolution characteristics of power grid status and events, by introducing timestamp attributes or constructing temporal relationship edges, a temporal graph neural network (TGNN) is used to capture dynamic changes to represent the changes in entity status and the order of events. The update rule of TGNN is expressed as: is the hidden state of node v at time t, AGG is the aggregation function, and N(v) is the set of v's neighbors. This approach yields an initial dynamic knowledge graph of temporal relationships in the power grid (which not only encompasses the static knowledge structure but also reflects the dynamic characteristics of the power grid system). Furthermore, by predefining a series of security-related attributes and relationships, such as the safe operating parameter ranges of equipment and the safety prerequisites for operations, security logic rules must be constructed. These rules express complex security constraints and reasoning logic based on the entities and relationships in the graph. This allows for mapping power grid security domain knowledge and constructing and updating security logic rules based on the entities and relationships in the dynamic knowledge graph. For example, a rule such as "If the load of transformer A exceeds threshold X for a duration exceeding Y, trigger an overload warning" can be defined. These rules are automatically learned from historical data using rule mining algorithms or manually defined by domain experts. They should be able to be dynamically updated based on new data and knowledge, ultimately generating a power grid security knowledge graph with security reasoning capabilities. The power grid security knowledge graph not only contains rich power grid domain knowledge but also embeds security-related logical rules and reasoning capabilities. It supports complex knowledge querying, association analysis, and safety reasoning, providing powerful knowledge support for power grid safety production supervision. For example, when the system detects abnormal data from a substation, it quickly locates the relevant equipment through graphs, searches for similar historical cases, infers the possible cause and scope of impact, and provides appropriate treatment recommendations. It can also generate test questions and examination questions for production personnel to complete safety assessments.

[0082] This technical solution constructs a power grid security knowledge graph based on the state feature space, determines classification information, and builds an initial graph subject model. Entity recognition and relationship extraction are then performed to form an initial power grid knowledge graph. Next, through alignment processing and adjustment optimization, an initial dynamic knowledge graph with dynamic update capabilities is generated. Ultimately, a comprehensive and accurate power grid security knowledge graph is constructed based on the entities and relationships within it. This systematically integrates power grid operation data, improves data utilization efficiency, and enhances the understanding and prediction capabilities of power grid security situations, thereby effectively ensuring the safe and stable operation of the power grid.

[0083] S230: Perform a hierarchical risk assessment on a preset risk assessment model using the power grid security knowledge graph to obtain a security risk assessment model.

[0084] On the basis of the above scheme, optionally, the grid security knowledge graph is used to perform a hierarchical risk assessment on a preset risk assessment model to obtain a security risk assessment model, including: determining a potential risk factor set based on the potential risk factors in the grid security knowledge graph, hierarchically classifying the potential risk factor set to obtain a risk indicator system, and determining a security risk propagation network corresponding to the potential risk factor set based on the grid security knowledge graph; hierarchically decomposing the security risk propagation network based on the risk indicator system to obtain a hierarchical risk assessment scheme, and based on the hierarchical risk assessment scheme, extracting security rules from the security semantic information in the grid security knowledge graph to obtain risk assessment rules; fuzzifying the risk assessment rules to obtain a risk reasoning mechanism, and performing a multidimensional risk assessment on the potential risk factor set based on the risk reasoning mechanism and the hierarchical analysis method to obtain a multidimensional risk score, and determining a security risk assessment model based on the potential risk factor set and the multidimensional risk score.

[0085] The potential risk factors can be understood as factors that may affect power grid security, including but not limited to at least one of equipment failure, operational errors, and environmental changes. The hierarchical classification can be understood as the hierarchical organization of potential risk factors according to pre-set logical relationships. The risk indicator system can be understood as a systematic set of indicators used to quantify and evaluate different types of potential risk factors. The security risk propagation network can be understood as a network model of how risk propagates within a target power grid, including but not limited to at least one of the risk source, propagation path, and affected objects. The hierarchical decomposition can be understood as the hierarchical decomposition of a complex risk propagation network into multiple subnetworks, corresponding to hierarchical risk assessment schemes at different levels. The hierarchical risk assessment scheme can be understood as a risk assessment plan developed based on the results of the hierarchical decomposition, including but not limited to specific assessment methods and standards at different levels. The security semantic information can be understood as the semantic content contained in the power grid security knowledge graph, such as safety regulations and event descriptions. The security rule extraction can be understood as the extraction of specific rules from the security semantic information to guide how to assess and respond to specific types of risks. The risk assessment rules can be understood as a specific set of rules that are extracted and organized to guide risk assessment. The fuzzification can be understood as converting quantitative risk assessment rules into fuzzy logic form, allowing a certain degree of uncertainty and flexibility. The fuzzification adapts to the uncertainty in actual application scenarios, so that the assessment results are closer to the actual situation and avoid overly rigid judgments. The risk reasoning mechanism can be understood as an inference system constructed based on the fuzzified risk assessment rules, which is used to derive risk assessment conclusions. The hierarchical analysis method can be understood as a multi-criteria decision analysis method, which determines the weights of different factors by comparing their importance, and helps to quantify the relative importance between different potential risk factors. The multidimensional risk score can be understood as a comprehensive score for potential risk factors based on multiple dimensions (including but not limited to at least one of severity, probability of occurrence or scope of impact).

[0086] An optional implementation method first traverses the potential risk factors in the power grid security knowledge graph through depth-first search (DFS) to obtain a set of potential risk factors, and then uses a hierarchical clustering algorithm to gradually merge the most similar clusters in the set of potential risk factors starting from a single data point, and finally forms a hierarchical structure to achieve hierarchical classification of power grid security. The distance update formula of the agglomerative hierarchical clustering is: d(u,v)=min{d(s,t):s∈u,t∈v}, where u and v are two clusters and d(u,v) is the distance between them. By iteratively merging the nearest clusters, a multi-level risk indicator system is obtained, which may include risk indicators at the equipment layer, system layer, and management layer. , and based on the characteristics of the graph structure in the power grid security knowledge graph, the PageRank algorithm is used to perform graph structure association analysis on the set of potential risk factors to identify the nodes and edges that play a key role in risk propagation, thereby constructing a safety risk propagation network; then, based on the risk indicator system, spectral clustering is used to perform hierarchical decomposition of the safety risk propagation network, and the eigenvectors of the graph Laplace matrix are calculated by the spectral clustering algorithm: Lv=λv (where L is the graph Laplace matrix, v is the eigenvector, and λ is the corresponding eigenvalue). By analyzing these eigenvectors, the safety risk propagation network is decomposed into sub-networks at different levels, corresponding to hierarchical risk assessment schemes at different levels; then, based on this hierarchical risk assessment scheme, the safety risk propagation network is decomposed into sub-networks at different levels, corresponding to hierarchical risk assessment schemes at different levels. The graph attention network considers the local structure and global semantic information of the nodes, thereby extracting security rules from the security semantic information in the power grid security knowledge graph and obtaining context-aware risk assessment rules; then, by introducing fuzzy set theory, the deterministic rules in the risk assessment rules are transformed into fuzzy rules, thereby obtaining a risk reasoning mechanism; then, the hierarchical analysis method is used to perform multi-dimensional risk assessment on the set of potential risk factors, and by comprehensively considering multiple risk dimensions, such as severity, probability of occurrence and scope of impact, a multi-dimensional risk assessment result is obtained; then, an integrated learning method, such as random forest, is used to perform weighted fusion on the multi-dimensional risk assessment results to automatically learn the weights of different risk dimensions and combine multiple weak learners into an initial An initial risk assessment model is developed, and using preset risk assessment sample data, the initial risk assessment model is verified and optimized through cross-validation and parameter optimization techniques such as Bayesian optimization to find the optimal model parameters. Finally, a safety risk assessment model is obtained. The safety risk assessment model not only takes into account the complex structure and dynamic characteristics of the power grid system, but also integrates professional knowledge and historical experience in the security field, so that it can conduct multi-dimensional and multi-level assessments of potential safety risks, and has the ability of context perception and fuzzy reasoning. When the model is subsequently used in combination with real-time operation data and employee safety question and answer data, it can provide timely and accurate risk assessment results for power grid safety production supervision, effectively improving the safety and reliability of the power grid;This allows users to obtain real-time operational data on the power grid under supervision and safety Q&A data from supervised employees. Real-time operational data, including key parameters such as voltage, current, and power, is collected in real time through SCADA (Supervisory Control and Data Acquisition) systems or Internet of Things (IoT) devices. Safety Q&A data, collected through online questionnaires or intelligent dialogue systems, reflects employees' safety knowledge and awareness.

[0087] This technical solution uses the power grid security knowledge graph to conduct a hierarchical evaluation of the preset risk assessment model. First, the potential risk factor set is determined and classified, and a risk indicator system and a security risk propagation network are constructed. Then, based on the risk indicator system, the propagation network is hierarchically decomposed, a hierarchical risk assessment scheme is formulated, and security rules are extracted from it to form risk assessment rules. By fuzzifying these rules, a risk reasoning mechanism is established, and multi-dimensional risk assessment is achieved by combining the hierarchical analysis method. Finally, a security risk assessment model with multi-dimensional risk scores is obtained, which can accurately quantify and predict potential risks in the power grid, improve the scientific nature and foresight of risk management, and enhance the security and stability of the power grid.

[0088] S240: Acquire safety production related data of the target power grid, wherein the safety production related data includes power grid operation characteristic data and power grid safety question and answer data of the target object.

[0089] S250: Perform risk detection on the production safety related data using a pre-established safety risk assessment model to obtain risk detection feature data.

[0090] S260: Determine a target early warning plan based on the risk detection feature data.

[0091] S270: Predict the target early warning plan by executing the risk prediction model, and generate a target safety detection report related to the safe production of the target power grid according to the prediction results.

[0092] The technical solution of the embodiment of the present invention obtains the safe production reference data of the target power grid, constructs its state feature space to capture the power grid state pattern and its change process, and performs semantic annotation. Based on this state feature space, it further constructs a power grid security knowledge graph, integrates the entities and relationships in the power grid operation, and uses the power grid security knowledge graph to perform a hierarchical evaluation of the preset risk assessment model. Through the analysis of the risk indicator system and the propagation network, multi-dimensional risk scoring is achieved, and finally a safety risk assessment model is formed. This not only improves the accuracy and comprehensiveness of risk assessment, but also enhances the predictability and response speed of power grid security management, provides a solid guarantee for the stable operation of the power grid, and effectively reduces potential safety risks.

[0093] Example 3

[0094] Figure 3 This is a schematic diagram of the structure of a power grid safety production detection device provided by the third embodiment of the present invention. Figure 3 As shown, the device includes: a production safety related data acquisition module 310, a risk detection module 320, an early warning plan determination module 330 and a safety detection report generation module 340.

[0095] The production safety-related data acquisition module 310 is used to obtain the production safety-related data of the target power grid, wherein the production safety-related data includes power grid operation characteristic data and power grid safety question and answer data of the target object; the risk detection module 320 is used to perform risk detection on the production safety-related data using a pre-established safety risk assessment model to obtain risk detection characteristic data; the early warning scheme determination module 330 is used to determine the target early warning scheme based on the risk detection characteristic data; the safety detection report generation module 340 is used to predict the target early warning scheme by executing the risk prediction model, and generate a target safety detection report related to the production safety of the target power grid based on the prediction results.

[0096] The technical solution of the embodiment of the present invention obtains the production safety related data of the target power grid through the production safety related data acquisition module 310. Since the production safety related data includes the power grid operation characteristic data and the power grid safety question and answer data of the target object, the related information in the power grid production safety process can be integrated to improve the detection accuracy; then, the pre-established safety risk assessment model is used to perform risk detection on the production safety related data to obtain risk detection characteristic data, which can accurately identify potential risks in the power grid operation; then, the target early warning plan is determined according to the risk detection characteristic data, which can be used for early discovery and rapid response to power grid safety hazards; finally, the target early warning plan is predicted by executing the risk prediction model, and a target safety detection report related to the target power grid production safety is generated according to the prediction results, which can improve the predictability and accuracy of power grid safety management, solve the problems of insufficient data integration, inaccurate risk identification and inaccurate response measures in related technologies, and can comprehensively detect the power grid production safety status, provide accurate early warnings, and significantly improve the efficiency and safety of power grid risk management.

[0097] On the basis of the above scheme, the power grid production safety detection device optionally includes: a state feature space determination module, a power grid knowledge graph construction module and a risk assessment module. The state feature space determination module is used to obtain multiple production safety reference data of the target power grid and determine the state feature space of the target power grid based on the production safety reference data; the state feature space includes the change process information of the power grid state mode and the annotation information of the power grid state mode; the knowledge graph construction module is used to construct a knowledge graph for the production safety reference data based on the state feature space to obtain a power grid safety knowledge graph; the risk assessment module is used to use the power grid safety knowledge graph to perform a hierarchical risk assessment on a preset risk assessment model to obtain a safety risk assessment model.

[0098] Based on the above solution, optionally, the state feature space determination module includes: a time-frequency transformation submodule, a nonlinear transformation submodule, a cross-domain feature association analysis submodule, a feature dimensionality reduction submodule and a state feature space determination submodule. The time-frequency transformation submodule is configured to perform time series decomposition on the production safety reference data to obtain time-domain power grid characteristics, and perform time-frequency transformation on the time-domain power grid characteristics using short-time Fourier transform to obtain frequency-domain power grid characteristics. The nonlinear transformation submodule is configured to perform nonlinear transformation on the time-domain power grid characteristics and the frequency-domain power grid characteristics to obtain data distribution characteristics. The cross-domain feature association analysis submodule is configured to perform cross-domain feature association analysis on the production safety reference data based on the data distribution characteristics to obtain interactive power grid characteristics, wherein the cross-domain feature association analysis is configured to determine the relationship between different types of production safety reference data. The feature dimension reduction submodule is configured to perform feature fusion on the time-domain power grid characteristics, the frequency-domain power grid characteristics, the data distribution characteristics, and the interactive power grid characteristics, and perform feature dimension reduction on the fused features to obtain low-dimensional power grid characteristics. The state feature space determination submodule is configured to cluster the low-dimensional power grid characteristics to obtain multiple clusters, determine a power grid state mode based on the cluster to which the low-dimensional power grid characteristics belong, perform semantic annotation on the power grid state mode, and determine the state feature space of the target power grid based on the semantic annotation results.

[0099] On the basis of the above scheme, the power grid knowledge graph construction module optionally includes: an initial power grid knowledge graph construction submodule, an adjustment submodule and a power grid security knowledge graph construction submodule. Among them, the initial power grid knowledge graph construction submodule is used to determine the classification information of the state feature space, construct an initial graph main body model according to the classification information, and perform entity recognition and relationship extraction on the production safety reference data according to the initial graph main body model to construct an initial power grid knowledge graph; the adjustment submodule is used to align the initial graph main body model and the initial power grid knowledge graph to obtain power grid security knowledge, and adjust the power grid security knowledge to obtain an initial dynamic knowledge graph; the power grid security knowledge graph construction submodule is used to construct a power grid security knowledge graph based on the entities and relationships in the initial dynamic knowledge graph.

[0100] Based on the above scheme, the risk assessment module optionally includes: a security risk propagation network determination submodule, a security rule extraction submodule, and a security risk assessment model determination submodule. The security risk propagation network determination submodule is configured to determine a potential risk factor set based on the potential risk factors in the power grid security knowledge graph, perform hierarchical classification on the potential risk factor set to obtain a risk indicator system, and determine a security risk propagation network corresponding to the potential risk factor set based on the power grid security knowledge graph; the security rule extraction submodule is configured to perform hierarchical decomposition on the security risk propagation network based on the risk indicator system to obtain a hierarchical risk assessment scheme, and extract security rules from the security semantic information in the power grid security knowledge graph based on the hierarchical risk assessment scheme to obtain risk assessment rules; the security risk assessment model determination submodule is configured to fuzzify the risk assessment rules to obtain a risk inference mechanism, and perform multi-dimensional risk assessment on the potential risk factor set based on the risk inference mechanism and the hierarchical analysis method to obtain a multi-dimensional risk score, and determine a security risk assessment model based on the potential risk factor set and the multi-dimensional risk score.

[0101] On the basis of the above solution, optionally, the risk detection module includes: a safety score determination submodule, a risk distribution map determination submodule and a risk detection feature data generation submodule. Among them, the safety score determination submodule is used to obtain the operation feature data and the target semantic features in the power grid security question and answer data, and map the operation feature data into the state feature space to determine a preliminary risk point set, and use the power grid security knowledge graph to perform contextual understanding of the target semantic features to determine the safety score of the target semantic features; the risk distribution map determination submodule is used to use the security risk assessment model to perform risk detection on each risk point and the safety score in the preliminary risk point set to obtain preliminary risk detection results, and determine the risk concentration area and high-risk period of the target power grid based on the preliminary risk detection results and the time data and regional data of the risk points corresponding to the preliminary risk point set to obtain a risk distribution map; the risk detection feature data generation submodule is used to use the power grid security knowledge graph to perform risk cause detection on the risk concentration area in the high-risk period in the risk distribution map to obtain a preliminary risk explanation list, and based on the corresponding associated risk data and historical risk cases in the power grid security knowledge graph, perform confidence assessment and structured classification on each explanation in the preliminary risk explanation list to generate risk detection feature data.

[0102] On the basis of the above scheme, optionally, the early warning scheme determination module includes: a risk influencing factor determination submodule, an impact hierarchy determination submodule and a target early warning scheme determination submodule. Among them, the risk influencing factor determination submodule is used to determine the preliminary risk score of the power grid production safety risk event based on the risk detection characteristic data, and determine the risk influencing factors of the target power grid based on the preliminary risk score and the power grid safety knowledge map, wherein the preliminary risk score is used to characterize the severity and urgency of the risk; the impact hierarchy determination submodule is used to determine the risk impact path based on the risk influencing factors, determine the risk impact object in the risk impact path, and determine the impact hierarchy structure based on the risk impact object and the risk influencing factors; the target early warning scheme determination submodule is used to match the detection and early warning response library corresponding to the impact hierarchy structure based on a preset multi-level early warning threshold system, and determine the target early warning scheme corresponding to the impact hierarchy structure based on the detection and early warning response library.

[0103] The power grid production safety detection device provided in the embodiment of the present invention can execute the power grid production safety detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0104] Example 4

[0105] Figure 4A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0106] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0108] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for detecting power grid safety production.

[0109] In some embodiments, a method for detecting safe production of a power grid may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for detecting safe production of a power grid described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute a method for detecting safe production of a power grid by any other appropriate means (e.g., by means of firmware).

[0110] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0114] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0115] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0116] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0117] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting safe production of a power grid, characterized in that: include: Acquire safety production related data of the target power grid, wherein the safety production related data includes power grid operation characteristic data and power grid safety question and answer data of the target object; Using a pre-established safety risk assessment model to perform risk detection on the safety production related data to obtain risk detection feature data; Determine a target early warning plan based on the risk detection feature data; The target early warning scheme is predicted by executing the risk prediction model, and a target safety detection report related to the safe production of the target power grid is generated according to the prediction results.

2. The power grid safety production detection method according to claim 1, characterized in that: Determining the security risk assessment model includes: Acquire multiple safety production reference data of the target power grid, and determine the state feature space of the target power grid according to the safety production reference data; wherein the state feature space includes the change process information of the power grid state mode and the annotation information of the power grid state mode; Based on the state feature space, constructing a knowledge graph for the safety production reference data to obtain a power grid safety knowledge graph; The power grid security knowledge graph is used to perform a hierarchical risk assessment on a preset risk assessment model to obtain a security risk assessment model.

3. The power grid safety production detection method according to claim 2, characterized in that: The determining the state feature space of the target power grid according to the safety production reference data comprises: Performing time series decomposition on the safety production reference data to obtain time domain power grid characteristics, and performing time-frequency transformation on the time domain power grid characteristics using short-time Fourier transform to obtain frequency domain power grid characteristics; Performing nonlinear transformation on the time-domain power grid characteristics and the frequency-domain power grid characteristics to obtain data distribution characteristics; Based on the data distribution characteristics, cross-domain feature correlation analysis is performed on the safety production reference data to obtain interactive power grid characteristics, wherein the cross-domain feature correlation analysis is used to determine the relationship between different types of safety production reference data; Performing feature fusion on the time-domain power grid features, the frequency-domain power grid features, the data distribution features, and the interactive power grid features, and performing feature dimensionality reduction on the features of the feature fusion to obtain low-dimensional power grid features; The low-dimensional power grid features are clustered to obtain multiple clusters, a power grid state mode is determined according to the clusters to which the low-dimensional power grid features belong, the power grid state mode is semantically annotated, and the state feature space of the target power grid is determined according to the result of the semantic annotation.

4. The power grid safety production detection method according to claim 2, characterized in that: The step of constructing a knowledge graph for the production safety reference data based on the state feature space to obtain a power grid safety knowledge graph includes: Determine the classification information of the state feature space, construct an initial graph subject model according to the classification information, and perform entity recognition and relationship extraction on the safety production reference data according to the initial graph subject model to construct an initial power grid knowledge graph; Aligning the initial graph subject model with the initial power grid knowledge graph to obtain power grid security knowledge, and adjusting the power grid security knowledge to obtain an initial dynamic knowledge graph; A power grid security knowledge graph is constructed based on the entities and relationships in the initial dynamic knowledge graph.

5. The power grid production safety detection method according to claim 2, characterized in that: The method of using the power grid security knowledge graph to perform a hierarchical risk assessment on a preset risk assessment model to obtain a security risk assessment model includes: Determining a potential risk factor set according to the potential risk factors in the power grid security knowledge graph, classifying the potential risk factor set hierarchically to obtain a risk indicator system, and determining a security risk propagation network corresponding to the potential risk factor set according to the power grid security knowledge graph; Based on the risk indicator system, the security risk propagation network is hierarchically decomposed to obtain a hierarchical risk assessment scheme, and based on the hierarchical risk assessment scheme, security rules are extracted from the security semantic information in the power grid security knowledge graph to obtain risk assessment rules; The risk assessment rules are fuzzified to obtain a risk reasoning mechanism, and based on the risk reasoning mechanism and the hierarchical analysis method, a multi-dimensional risk assessment is performed on the potential risk factor set to obtain a multi-dimensional risk score, and a safety risk assessment model is determined based on the potential risk factor set and the multi-dimensional risk score.

6. The power grid production safety detection method according to claim 1, characterized in that: The method of performing risk detection on the safety production related data using a pre-established safety risk assessment model to obtain risk detection feature data includes: Acquire the operation feature data, and acquire the target semantic features in the power grid security question and answer data, and map the operation feature data to the state feature space, determine a preliminary risk point set, and use the power grid security knowledge graph to perform contextual understanding on the target semantic features to determine the safety score of the target semantic features; Perform risk detection on each risk point in the preliminary risk point set and the safety score using the safety risk assessment model to obtain a preliminary risk detection result, and determine the risk concentration area and high-risk period of the target power grid according to the preliminary risk detection result and the time data and regional data of the risk point corresponding to the preliminary risk point set to obtain a risk distribution map; The power grid security knowledge graph is used to detect risk causes in risk-intensive areas during high-risk periods in the risk distribution map to obtain a preliminary risk explanation list. Based on the corresponding associated risk data and historical risk cases in the power grid security knowledge graph, confidence assessment and structured classification are performed on each explanation in the preliminary risk explanation list to generate risk detection feature data.

7. The power grid safety production detection method according to claim 1, characterized in that: Determining a target early warning scheme according to the risk detection feature data includes: Determine a preliminary risk score of a power grid safety production risk event according to the risk detection feature data, and determine the risk influencing factors of the target power grid based on the preliminary risk score and the power grid safety knowledge graph, wherein the preliminary risk score is used to characterize the severity and urgency of the risk; Determine a risk impact path according to the risk impact factors, determine the risk impact object in the risk impact path, and determine an impact hierarchy structure according to the risk impact object and the risk impact factors; Based on a preset multi-level warning threshold system, a detection warning response library corresponding to the impact hierarchy structure is matched, and a target warning scheme corresponding to the impact hierarchy structure is determined according to the detection warning response library.

8. A power grid production safety detection device, characterized in that: include: A safety production related data acquisition module, used to acquire safety production related data of a target power grid, wherein the safety production related data includes power grid operation characteristic data and power grid safety question and answer data of a target object; A risk detection module is used to perform risk detection on the safety production related data using a pre-established safety risk assessment model to obtain risk detection feature data; An early warning scheme determination module is used to determine a target early warning scheme based on the risk detection feature data; The safety detection report generation module is used to predict the target early warning plan by executing the risk prediction model, and generate a target safety detection report related to the safe production of the target power grid according to the prediction results.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the power grid safety production detection method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the power grid safety production detection method according to any one of claims 1 to 7 when executed.

Images