Method and device for managing electric power supervision data and storage medium

Abstract

The embodiment of the invention provides a method and device for managing electric power supervision data and a storage medium. The method comprises the steps of obtaining a first supervision list in a target electric power system; according to the service type and the data structure of the first supervised and handled item, classifying the first supervised and handled item to obtain a second supervised and handled item; performing data mining, machine learning and knowledge base matching on the second supervision and handling item to obtain a third supervision and handling item; and managing and controlling the third supervision and handling list according to a strategy library. According to the method, the efficiency and quality of managing the electric power supervision data are improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technical supervision, and in particular to a method, a device and a storage medium for managing electric power supervision data. Background Art

[0002] In the power industry, intelligent management and control are mainly used to carry out various types of power supervision. As power technical supervision work becomes increasingly complex, the efficiency and accuracy of supervision matters are becoming more and more important.

[0003] In the existing technology, automatic intelligent control algorithms have been widely used in the field of power technical supervision. However, there are still some technical defects, such as untimely handling of supervision matters, lack of priority management and lack of intelligent support. Specifically, the existing technology often relies on manual processing and tracking of supervision matters, which is prone to problems such as untimely processing and omissions. Not only that, supervision matters often involve multiple fields and departments, and the processing order is unreasonable, which greatly affects the overall efficiency. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device and storage medium for managing power supervision data, which improves the efficiency and quality of managing power supervision data.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for managing power supervision data, the method comprising:

[0006] Obtain the top priority items in the target power system;

[0007] Classifying the first supervision items according to the business type and data structure of the first supervision items to obtain second supervision items;

[0008] Performing data mining, machine learning and knowledge base matching on the second supervision items to obtain third supervision items;

[0009] The third supervision matter is managed and controlled according to the strategy library.

[0010] Optionally, the obtaining of the first supervision item in the target power system includes:

[0011] Obtaining the first supervision item in the target power system according to the urgency, historical processing time and related equipment conditions of the supervision item;

[0012] The parameters of the first supervision item include supervision type, operation parameters, equipment status information, technical supervision indicators and operation and maintenance plan.

[0013] Optionally, classifying the first supervision items according to the business type and data structure of the first supervision items to obtain second supervision items includes:

[0014] Classifying the first supervision items according to the business types of the first supervision items to obtain second supervision items, wherein the business types include power generation business, power transmission business, power transformation business, power distribution business and power consumption business; and / or,

[0015] The first supervision items are classified according to the data organization form and / or timeliness of the first supervision items to obtain second supervision items.

[0016] Optionally, performing data mining, machine learning and knowledge base matching on the second supervision items to obtain the third supervision items includes:

[0017] Using an association rule mining algorithm to find out the association relationship between each data in the second supervision item;

[0018] The second supervision items are grouped by using a cluster analysis algorithm to obtain data clusters within the normal operating mode threshold range;

[0019] Obtain key features according to the association relationship and data cluster;

[0020] Acquire a template feature vector in a knowledge base, calculate the similarity between the key feature and the template feature vector, and determine the third supervision item according to the similarity.

[0021] Optionally, determining the third supervision item according to the similarity includes:

[0022] If the similarity meets the matching threshold range, the match is successful, and the key feature is set as the third supervision item;

[0023] If the similarity does not meet the matching threshold range, the key features are re-acquired or the knowledge base is updated.

[0024] Optionally, the knowledge base is a knowledge base of multiple types of supervision matters established according to power supervision standards and enterprise management requirements;

[0025] The knowledge base includes characteristic parameters, threshold ranges and trigger conditions of supervision items.

[0026] Optionally, the method further includes:

[0027] Pre-processing the first supervision item;

[0028] The preprocessing includes removing duplicate data, processing missing values ​​and correcting erroneous data.

[0029] On the other hand, the present invention also provides a device for managing power supervision data, the device comprising:

[0030] An acquisition module, used for acquiring a first supervision item in a target power system, wherein the first supervision item includes a supervision type, operating parameters, equipment status information, technical supervision indicators and an operation and maintenance plan;

[0031] A first processing module, configured to classify the first supervision items according to the business type and data structure of the first supervision items to obtain second supervision items;

[0032] A second processing module is used to perform data mining, machine learning and knowledge base matching on the second supervision items to obtain third supervision items;

[0033] The third processing module is used to manage and control the third supervision matter according to the policy library.

[0034] Optionally, performing data mining, machine learning and knowledge base matching on the second supervision items to obtain the third supervision items includes:

[0035] Using an association rule mining algorithm to find out the association relationship between each data in the second supervision item;

[0036] The second supervision items are grouped by using a cluster analysis algorithm to obtain data clusters within the normal operating mode threshold range;

[0037] Obtain key features according to the association relationship and data cluster;

[0038] Acquire a template feature vector in a knowledge base, calculate the similarity between the key feature and the template feature vector, and determine the third supervision item according to the similarity.

[0039] On the other hand, the present invention further proposes a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned method for managing power supervision data.

[0040] A method for managing power supervision data of the present invention includes: obtaining a first supervision item in a target power system; classifying the first supervision item according to the business type and data structure of the first supervision item to obtain a second supervision item; performing data mining, machine learning and matching knowledge base on the second supervision item to obtain a third supervision item; and managing the third supervision item according to a policy library. The present invention improves the efficiency and quality of managing power supervision data by automatically identifying, classifying, sorting and prioritizing supervision items, and provides more efficient and intelligent supervision management support for power technical supervision.

[0041] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0043] Figure 1 It is a flow chart of a method for managing power supervision data of the present invention;

[0044] Figure 2 It is a schematic diagram of a device for managing power supervision data of the present invention.

[0045] Description of Reference Numerals

[0046] 100-A device for managing power supervision data;

[0047] 200-Get module;

[0048] 300-first processing module;

[0049] 400-second processing module;

[0050] 500-the third processing module. DETAILED DESCRIPTION

[0051] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0052] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0053] Figure 1 is a flow chart of a method for managing power supervision data of the present invention, such as Figure 1 As shown, a method for managing power supervision data of the present invention includes:

[0054] Step S101 is to obtain the first supervision item in the target power system.

[0055] According to a specific implementation method, obtaining the first supervision item in the target power system includes: obtaining the first supervision item in the target power system based on the urgency of the supervision item, the historical processing time and the status of related equipment; the parameters of the first supervision item include supervision type, operating parameters, equipment status information, technical supervision indicators and operation and maintenance plan.

[0056] Specifically, data is collected from various monitoring devices, sensors, operation and maintenance management systems and related databases in the target power system. These data (i.e., the first supervision items) include but are not limited to the operating parameters of power equipment (such as voltage, current, power, temperature, etc.), equipment status information (such as switch status, alarm information, etc.), technical supervision index data (such as insulation performance indicators, relay protection action accuracy, etc.), operation and maintenance plans and record data, etc.

[0057] The method also includes: preprocessing the first supervision item; the preprocessing includes removing duplicate data, processing missing values ​​and correcting erroneous data. Specifically, the first supervision item is cleaned and preprocessed, such as removing noise data, erroneous data and incomplete data. Specifically, the rationality of the data can be checked through data verification rules, and the missing data can be supplemented with a suitable interpolation algorithm to ensure the accuracy and completeness of the data for subsequent analysis and processing.

[0058] Step S102 is to classify the first supervision items according to the business type and data structure of the first supervision items to obtain second supervision items.

[0059] According to a specific implementation method, the first supervision item is classified according to the business type and data structure of the first supervision item to obtain the second supervision item, including: classifying the first supervision item according to the business type of the first supervision item to obtain the second supervision item, the business type includes power generation business, transmission business, substation business, distribution business and electricity consumption business; and / or, classifying the first supervision item according to the data organization form and / or timeliness of the first supervision item to obtain the second supervision item.

[0060] Specifically, the pre-processed first supervision items are classified and integrated according to different business types and data structures, and stored in a specially designed data repository so that each algorithm module can efficiently access and call the required data.

[0061] The classification method can be a common machine learning algorithm such as support vector machine, random forest, neural network, etc., and can also be classified by algorithms such as naive Bayes, K nearest neighbor, decision tree, etc.

[0062] Step S103 is to perform data mining, machine learning and knowledge base matching on the second supervision items to obtain the third supervision items.

[0063] According to a specific implementation method, the data mining, machine learning and knowledge base matching of the second supervision item to obtain the third supervision item includes: using an association rule mining algorithm for the second supervision item to find the association relationship between the various data in the second supervision item; using a clustering analysis algorithm to group the second supervision item to obtain data clusters within the normal operating mode threshold range; obtaining key features based on the association relationship and the data clusters; obtaining a template feature vector from the knowledge base, calculating the similarity between the key features and the template feature vector, and determining the third supervision item based on the similarity.

[0064] Specifically, in addition to extracting features based on expert experience and historical data, the method of extracting the key features can also consider using unsupervised learning methods (such as clustering algorithms) to automatically discover potential features in the supervision items. In addition, deep learning models (such as convolutional neural networks) can also be used for feature extraction, especially when the data of the supervision items contains complex information such as images and texts.

[0065] Determining the third supervision item according to the similarity includes: if the similarity meets the matching threshold range, the match is successful and the key feature is set as the third supervision item; if the similarity does not meet the matching threshold range, the key feature is re-acquired or the knowledge base is updated.

[0066] The knowledge base is a knowledge base of multiple types of supervision items established according to power supervision standards and enterprise management requirements; the knowledge base includes characteristic parameters, threshold ranges and trigger conditions of supervision items.

[0067] Specifically, based on the power technical supervision standards and internal management requirements of the enterprise, a knowledge base of multiple types of key supervision items is established. The knowledge base contains information such as characteristic parameters, threshold ranges, trigger conditions, etc. of various key supervision items. For example, for the key supervision item of excessive transformer oil temperature, the knowledge base defines the normal oil temperature range and the supervision is triggered when it exceeds a certain threshold (such as 85°C) and lasts for a certain period of time (such as 10 minutes).

[0068] Use data mining and machine learning algorithms to analyze the integrated data in real time. For example, use cluster analysis algorithms to group the operating data of power equipment and identify data clusters that deviate greatly from the normal operating mode; use association rule mining algorithms to find the correlation between different operating parameters and discover potential abnormal patterns. By matching with the key supervision items knowledge base, determine whether there are key supervision items that meet the conditions.

[0069] When potential key supervision items are identified, further detailed analysis and verification are carried out. Combined with the historical operation data of the equipment, the operation experience of similar equipment and expert knowledge, a comprehensive judgment is made as to whether the item really needs to be supervised. For example, for a suspected relay protection misoperation event, in addition to checking the current protection action signal and related electrical quantity data, factors such as recent equipment maintenance records and changes in power grid operation modes are also analyzed to ensure the accuracy of the identification of key supervision items.

[0070] Step S104 is to control the third supervision matter according to the strategy library.

[0071] According to a specific implementation method, the corresponding intelligent management and control strategy is matched from a pre-set management and control strategy library according to the type and specific situation of the third supervision items identified. The management and control strategy library contains information such as the processing flow, responsibility allocation, and time node requirements for different third supervision items. For example, for key supervision items such as equipment failures, the management and control strategy may include immediately notifying maintenance personnel, formulating maintenance plans and setting a time limit for maintenance completion, and closely monitoring the operating status of related equipment during maintenance.

[0072] In addition, this application also uses optimization algorithms to optimize and adjust the control strategy. Considering the operating constraints of the power system (such as load balance, grid stability, etc.), resource availability (such as the number of maintenance personnel, spare parts inventory, etc.) and cost factors, the various parameters in the control strategy are optimized. For example, the deployment plan of maintenance personnel is optimized through genetic algorithms to minimize maintenance time and cost while ensuring the safe and stable operation of the power grid.

[0073] In addition to the priority determination model based on feature engineering and expert experience, you can also consider using multi-objective optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.) to find the optimal priority determination strategy. These algorithms can find a balance between multiple objectives, thereby obtaining a more reasonable priority ranking.

[0074] This application will also visualize and output the generated intelligent management and control strategies so that relevant personnel can clearly understand the processing procedures and requirements of the supervision items. The display content includes detailed information of the supervision items, steps of the management and control strategies, information of responsible persons, time schedule, etc., and will be pushed to relevant personnel in a timely manner through various means (such as system interface prompts, SMS notifications, email notifications, etc.).

[0075] In addition to automated allocation and dynamic monitoring, you can also consider introducing an intelligent recommendation system to intelligently recommend the best handling department or person based on factors such as the type, priority, and expertise of the handling department. In addition, you can also consider using reinforcement learning algorithms to optimize management and control strategies so that the algorithm can continuously adjust and improve based on feedback.

[0076] This application automatically starts the corresponding execution process according to the requirements of the intelligent management and control strategy. For example, it automatically dispatches maintenance personnel, issues maintenance task orders, and applies for required spare parts according to the maintenance plan. At the same time, it establishes interfaces with various types of automated operating equipment and control systems in the power system to achieve remote operation and control of some equipment, such as remotely adjusting the operating parameters of power equipment, switching backup equipment, etc., to improve processing efficiency.

[0077] Real-time monitoring of the execution process of key supervision items. By collecting relevant data during the execution process (such as maintenance progress data, equipment trial operation data, etc.), and comparing and analyzing them with the time nodes and quality requirements in the management and control strategy, deviations and abnormalities in the execution process can be discovered in a timely manner. For example, the maintenance progress curve is drawn using real-time monitoring data and compared with the preset progress plan. If the maintenance progress is found to be lagging behind, an early warning message is automatically issued and the cause is analyzed.

[0078] Dynamically adjust the execution process based on the monitoring results. When abnormal situations or changes in external conditions are found during the execution process, timely adjust the management and control strategies and execution plans. For example, if it is found during the maintenance process that the equipment failure is more serious than expected and requires more maintenance time and resources, re-optimize the maintenance plan, adjust the personnel deployment and spare parts application plan, and notify relevant personnel in a timely manner. At the same time, the adjusted information is fed back to the intelligent management and control strategy generation module to update and improve the strategy library and improve the algorithm's ability to cope with complex situations.

[0079] After the key supervision items are completed, the entire control process is comprehensively evaluated. Collect and analyze various data during the execution process, including processing time, cost expenditure, performance indicators after the equipment resumes normal operation, etc., and compare and evaluate with the expected goals. For example, calculate the deviation rate between the actual maintenance time and the preset maintenance time, calculate the difference between the maintenance cost and the budgeted cost, compare the operating parameters of the equipment after repair and the degree of compliance with the normal operation standards, etc., to evaluate the control effect in a quantitative way.

[0080] Generate a detailed evaluation report based on the evaluation results and summarize the lessons learned. The report includes basic information on the supervision items, an overview of the control process, analysis results of evaluation indicators, existing problems and improvement suggestions, etc. Feedback the evaluation report to the power technical supervision department and relevant management to provide a reference for subsequent management decisions, and also provide data support for the optimization and improvement of the algorithm.

[0081] Based on the evaluation feedback information, the knowledge base in the key supervision items identification module, the strategy base in the intelligent control strategy generation module, and the various parameters of the algorithm are regularly updated and optimized. For example, if it is found that the recognition accuracy of a certain type of key supervision items is low, the characteristic parameters and thresholds in the knowledge base are adjusted; if a certain control strategy is not effective in actual application, the processing flow and parameters in the strategy base are optimized and improved, so as to continuously improve the performance and adaptability of the automatic intelligent control algorithm and achieve continuous optimization and improvement of power technical supervision work.

[0082] This application uses machine learning algorithms to achieve automatic classification and priority determination of supervision items, reduce manual intervention, and improve processing efficiency. Dynamically adjust the management and control strategies according to the processing progress and risk situation of the supervision items to ensure the flexibility and effectiveness of the supervision work. And it is seamlessly integrated with the existing power technical supervision system, without the need for large-scale transformation of the existing system, reducing implementation costs. This application also provides an intuitive user interface and visual monitoring functions, which allows users to grasp the status and processing progress of supervision items in real time. This application can accurately classify and prioritize multiple types of key supervision items in power technical supervision, and effectively guide the processing of supervision items.

[0083] This application may consider combining a variety of machine learning algorithms (such as support vector machines, random forests, neural networks, etc.) and deep learning models (such as convolutional neural networks, recurrent neural networks, etc.) to form a hybrid model. This hybrid model can make full use of the advantages of various algorithms to improve the accuracy of classification and priority determination. If the data of the supervision items contains a large amount of text information (such as descriptions, notes, etc.), you can consider using natural language processing technology (such as text classification, sentiment analysis, entity recognition, etc.) to extract useful information and use it for classification and priority determination. In addition, you can also consider using a question-and-answer system or a dialogue robot to assist in the processing of supervision items. This method can directly extract features from the data of the supervision items, perform classification and priority determination, and generate intelligent management and control strategies. This solution usually has a higher degree of automation and better performance, but may require more data and computing resources.

[0084] Figure 2 Schematic diagram of a device for managing power supervision data of the present invention, such as Figure 2As shown, the present invention also proposes a device for managing power supervision data, and the device 100 for managing power supervision data includes: an acquisition module 200, used to acquire a first supervision item in a target power system, wherein the first supervision item includes a supervision type, operating parameters, equipment status information, technical supervision indicators, and an operation and maintenance plan; a first processing module 300, used to classify the first supervision item according to the business type and data structure of the first supervision item to obtain a second supervision item; a second processing module 400, used to perform data mining, machine learning, and matching knowledge base on the second supervision item to obtain a third supervision item; and a third processing module 500, used to manage and control the third supervision item according to a policy library.

[0085] According to a specific implementation method, the data mining, machine learning and knowledge base matching of the second supervision items to obtain the third supervision items include: using the association rule mining algorithm to find the association relationship between the various data in the second supervision items; using the cluster analysis algorithm to group the second supervision items to obtain data clusters within the normal operating mode threshold range; obtaining key features based on the association relationship and data clusters; obtaining the template feature vector in the knowledge base, calculating the similarity between the key feature and the template feature vector, and determining the third supervision item based on the similarity. The device improves the efficiency and quality of managing power supervision data by automatically identifying, classifying, sorting and prioritizing supervision items, and provides more efficient and intelligent supervision management support for power technical supervision.

[0086] A method for managing power supervision data of the present invention includes: obtaining a first supervision item in a target power system; classifying the first supervision item according to the business type and data structure of the first supervision item to obtain a second supervision item; performing data mining, machine learning and matching knowledge base on the second supervision item to obtain a third supervision item; and managing the third supervision item according to a policy library. The present invention improves the efficiency and quality of managing power supervision data by automatically identifying, classifying, sorting and prioritizing supervision items, and provides more efficient and intelligent supervision management support for power technical supervision.

[0087] On the other hand, an embodiment of the present invention provides a storage medium having a program stored thereon, and the program, when executed by a processor, implements the method for managing power supervision data.

[0088] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for managing power supervision data is executed when the program is running.

[0089] The embodiment of the present invention provides a device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: obtaining a first supervision item in a target power system; classifying the first supervision item according to the business type and data structure of the first supervision item to obtain a second supervision item; performing data mining, machine learning, and matching knowledge base on the second supervision item to obtain a third supervision item; and managing the third supervision item according to a policy library. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0090] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: obtaining a first supervision item in a target power system; classifying the first supervision item according to the business type and data structure of the first supervision item to obtain a second supervision item; performing data mining, machine learning and knowledge base matching on the second supervision item to obtain a third supervision item; and managing the third supervision item according to the policy library.

[0091] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0092] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0097] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0099] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for managing power supervision data, characterized in that: The method includes: Obtain the top priority items in the target power system; Classifying the first supervision items according to the business type and data structure of the first supervision items to obtain second supervision items; Performing data mining, machine learning and knowledge base matching on the second supervision items to obtain third supervision items; The third supervision matter is managed and controlled according to the strategy library.

2. The method according to claim 1, characterized in that The first task to be supervised in the target power system is obtained, including: Obtaining the first supervision item in the target power system according to the urgency, historical processing time and related equipment conditions of the supervision item; The parameters of the first supervision item include supervision type, operation parameters, equipment status information, technical supervision indicators and operation and maintenance plan.

3. The method according to claim 1, characterized in that The step of classifying the first supervision items according to the business type and data structure of the first supervision items to obtain the second supervision items includes: Classifying the first supervision items according to the business types of the first supervision items to obtain second supervision items, wherein the business types include power generation business, power transmission business, power transformation business, power distribution business and power consumption business; and / or, The first supervision items are classified according to the data organization form and / or timeliness of the first supervision items to obtain second supervision items.

4. The method according to claim 1, characterized in that The performing of data mining, machine learning and knowledge base matching on the second supervision items to obtain the third supervision items includes: Using an association rule mining algorithm to find out the association relationship between each data in the second supervision item; The second supervision items are grouped by using a cluster analysis algorithm to obtain data clusters within the normal operating mode threshold range; Obtain key features according to the association relationship and data cluster; Acquire a template feature vector in a knowledge base, calculate the similarity between the key feature and the template feature vector, and determine the third supervision item according to the similarity.

5. The method according to claim 4, characterized in that Determining the third supervision matter according to the similarity includes: If the similarity meets the matching threshold range, the match is successful, and the key feature is set as the third supervision item; If the similarity does not meet the matching threshold range, the key features are re-acquired or the knowledge base is updated.

6. The method according to claim 4, characterized in that The knowledge base is a knowledge base of multiple types of supervision matters established according to power supervision standards and enterprise management requirements; The knowledge base includes characteristic parameters, threshold ranges and trigger conditions of supervision items.

7. The method according to claim 1, characterized in that The method further includes: Pre-processing the first supervision item; The preprocessing includes removing duplicate data, processing missing values ​​and correcting erroneous data.

8. A device for managing power supervision data, characterized in that: The device includes: An acquisition module, used for acquiring a first supervision item in a target power system, wherein the first supervision item includes a supervision type, operating parameters, equipment status information, technical supervision indicators and an operation and maintenance plan; A first processing module, configured to classify the first supervision items according to the business type and data structure of the first supervision items to obtain second supervision items; A second processing module is used to perform data mining, machine learning and knowledge base matching on the second supervision items to obtain third supervision items; The third processing module is used to manage and control the third supervision matter according to the policy library.

9. The device according to claim 8, characterized in that The performing of data mining, machine learning and knowledge base matching on the second supervision items to obtain the third supervision items includes: Using an association rule mining algorithm to find out the association relationship between each data in the second supervision item; The second supervision items are grouped by using a cluster analysis algorithm to obtain data clusters within the normal operating mode threshold range; Obtain key features according to the association relationship and data cluster; Acquire a template feature vector in a knowledge base, calculate the similarity between the key feature and the template feature vector, and determine the third supervision item according to the similarity.

10. A machine-readable storage medium having instructions stored thereon, characterized in that: The instruction is used to enable the machine to execute the method for managing power supervision data as described in any one of claims 1-7.

Images