System analysis method, device, computer equipment, readable storage medium and program product in the power field

Abstract

The present application relates to a system analysis method, device, computer equipment, readable storage medium and program product in the field of electric power. By satisfying the start-up analysis conditions, time series data is obtained from the source database of the system to be analyzed, and it is reconstructed into reconstructed data including the streaming calculation results of the judgment logic expression, and the state of the reconstructed data is detected based on the judgment logic expression. When the detection result is abnormal, a call request is sent to the system, and the analysis result corresponding to the system is obtained based on the multimedia data of the device corresponding to the reconstructed data returned by the system and the state detection result. Compared with the traditional method of manually analyzing the data of each system through each system, this solution reconstructs the data of each system through preset analysis rules, judges the state of the data based on the judgment logic expression, and obtains the multimedia data of the system through a call request. The system is analyzed based on the state detection and multimedia data, which improves the analysis efficiency.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a system analysis method, apparatus, computer equipment, computer-readable storage medium, and computer program product in the electric power field. Background Art

[0002] Electricity is a vital resource that supports daily life and production operations. The power sector encompasses multiple systems, each with distinct functions, and these systems collectively maintain its operation. To ensure the proper functioning of these systems, timely analysis of these systems and the timely resolution of any anomalies are essential. Current methods for analyzing power systems typically rely on personnel in each system collecting data and conducting manual analysis. However, this manual analysis by system personnel reduces the efficiency of system analysis.

[0003] Therefore, the current system analysis method for the power sector has the defect of low analysis efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a system analysis method, device, computer equipment, computer-readable storage medium and computer program product in the power field that can improve system efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides a system analysis method in the field of electric power, the method comprising:

[0006] When it is detected that a system to be analyzed in the power field meets the start-up analysis conditions, the time series data corresponding to the system is obtained from the source database of the system, and the time series data is reconstructed into reconstructed data of a streaming computing structure according to the preset analysis rules corresponding to the system; the reconstructed data includes a judgment logic expression;

[0007] Performing state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result;

[0008] If the state detection result is an abnormal state, sending a call request to the system to obtain multimedia data of the device corresponding to the abnormal reconstructed data returned by the system based on the call request;

[0009] An analysis result corresponding to the system is obtained according to the status detection result and the multimedia data.

[0010] In one embodiment, the preset analysis rules include a measurement point, a state value to be associated, and a logical expression for determining the association;

[0011] The reconstructing the time series data into reconstructed data of a streaming computing structure according to a preset analysis rule corresponding to the system includes:

[0012] Determining the data to be analyzed in the time series data according to the measurement points in the preset analysis rules;

[0013] Associating the to-be-associated state value with the state value corresponding to the to-be-analyzed data to obtain an associated state value;

[0014] Associating the data to be analyzed with the judgment logic expression to be associated to obtain the associated judgment logic expression;

[0015] Reconstructed data corresponding to the time series data is generated according to the data to be analyzed, the state value and the judgment logic expression.

[0016] In one embodiment, performing state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result includes:

[0017] Executing the judgment logic expression through a preset judgment component to determine the abnormal state value;

[0018] Obtaining the state value corresponding to the data to be analyzed in the reconstructed data;

[0019] According to the comparison result between the state value and the abnormal state value, a state detection result corresponding to the data to be analyzed is obtained.

[0020] In one embodiment, the reconstructed data also includes an interface call list corresponding to the system;

[0021] The sending of a call request to the system to obtain multimedia data of a device corresponding to abnormal reconstructed data returned by the system based on the call request includes:

[0022] Determining target interface call information corresponding to the multimedia acquisition device in the system according to the interface call list;

[0023] According to the target interface calling information, a calling request is sent to the multimedia acquisition device in the system, and multimedia data of the device corresponding to the abnormal reconstructed data returned by the system after calling the multimedia acquisition device based on the calling request is obtained.

[0024] In one embodiment, obtaining an analysis result corresponding to the system based on the status detection result and the multimedia data includes:

[0025] Inputting the multimedia data into a trained machine recognition model, and having the machine recognition model output a multimedia anomaly detection result corresponding to the system based on the multimedia data;

[0026] According to the status detection result and the multimedia anomaly detection result, an analysis result corresponding to the system is obtained.

[0027] In one embodiment, after obtaining the analysis result corresponding to the system based on the status detection result and the multimedia data, the method further includes:

[0028] If the analysis result indicates that the system is abnormal, generating an alarm message according to the analysis result;

[0029] The alarm information is pushed to the management terminal corresponding to the system.

[0030] In a second aspect, the present application provides a system analysis device in the field of electric power, the device comprising:

[0031] A detection module is configured to, upon detecting that a system to be analyzed in the power sector meets the conditions for starting analysis, obtain time series data corresponding to the system from a source database of the system, and reconstruct the time series data into reconstructed data of a streaming computing structure according to preset analysis rules corresponding to the system; the reconstructed data includes a judgment logic expression;

[0032] A reconstruction module, configured to perform a state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result;

[0033] a calling module configured to, if the state detection result is an abnormal state, send a calling request to the system and obtain multimedia data of a device corresponding to abnormal reconstructed data returned by the system based on the calling request;

[0034] The analysis module is used to obtain an analysis result corresponding to the system according to the status detection result and the multimedia data.

[0035] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor.

[0037] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0038] The above-mentioned system analysis method, apparatus, computer equipment, computer-readable storage medium, and computer program product in the power sector obtain time series data from the source database of the system to be analyzed, upon meeting the conditions for starting the analysis, reconstruct it into reconstructed data including the streaming calculation results of the judgment logic expression, perform status detection on the reconstructed data based on the judgment logic expression, and when the detection result is abnormal, send a call request to the system, and obtain the corresponding analysis result of the system based on the multimedia data of the device corresponding to the reconstructed data and the status detection result returned by the system. Compared with the traditional method of manually analyzing the data of each system, this solution reconstructs the data of each system through preset analysis rules, determines the status of the data based on the judgment logic expression, obtains the multimedia data of the system through call requests, and analyzes the system based on the status detection and multimedia data, thereby improving analysis efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 1 is a flow chart of a system analysis method in the electric power field according to an embodiment;

[0041] Figure 2 A flowchart of a system analysis method in the power field according to another embodiment;

[0042] Figure 3 is a flowchart of a system analysis method in the power field in another embodiment;

[0043] Figure 4 is a structural block diagram of a system analysis device in the electric power field in one embodiment;

[0044] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0046] In one embodiment, Figure 1As shown, a system analysis method for the power field is provided. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server, including the following steps S202 to S208. Among them:

[0047] In step S202, when it is detected that the system to be analyzed in the power field meets the conditions for starting analysis, the time series data corresponding to the system is obtained from the source database of the system, and the time series data is reconstructed into reconstructed data of a streaming computing structure according to the preset analysis rules corresponding to the system; the reconstructed data includes a judgment logic expression.

[0048] The power sector includes multiple systems, and the terminal can be a device independent of multiple systems in the power sector, used to call and analyze the data of each system in a coordinated manner. Specifically, the terminal can be an audio-visual master station in the power sector. Multi-system analysis and linkage in the power sector refer to the coordination and cooperation between different systems. The equipment status monitoring system or centralized control system collects equipment status data through sensors, and the monitoring system collects equipment appearance pictures and audio during operation through microphones and cameras. The audio-visual master station performs machine recognition on the pictures and audio to obtain analysis results. The data of the above systems can comprehensively describe the actual operation of the equipment. When the data of a certain system indicates that the equipment is abnormal, it can be linked with other systems to collect the data of the equipment at the current time for analysis to confirm whether the equipment is operating abnormally.

[0049] The terminal can continuously detect whether each system in the power sector meets the start-up analysis conditions. The start-up analysis conditions indicate the conditions under which data acquisition and abnormality analysis of the system are required. For example, the need to start analysis can be determined by detecting whether a preset cycle is met. When the terminal detects that the system to be analyzed in the power sector meets the start-up analysis conditions, it obtains the corresponding time series data of the system from the source database of the system to be analyzed. The above-mentioned system can be an electric power system in the power sector, which includes multiple electric power equipment. The time series data of the above-mentioned system can be status data corresponding to each electric power equipment in the system distributed in chronological order, etc.

[0050] The terminal may also pre-store preset analysis rules. These rules can be pre-configured based on rule templates and relevant information from each system. There can be only one rule template, and each preset analysis rule corresponds to a specific system. The preset analysis rules can be used to determine the data to be analyzed within the system's time series data and the logic used to determine the data. Based on the system's corresponding preset analysis rules, the terminal can reconstruct the time series data into reconstructed data in a streaming computing structure.

[0051] Because each system represents a different data source and corresponds to a different source database, the data structures of each system vary. Therefore, the data in each system needs to be restructured to meet the requirements of the terminal analysis. Stream computing is a real-time data processing technology that performs real-time calculations on unbounded data streams, performing calculations and outputting data immediately upon arrival. Stream computing differs significantly from traditional batch processing. In streaming computing, data flows continuously, unlike batch processing, where data is accumulated and then processed. This allows for higher efficiency and lower latency when processing real-time data streams.

[0052] The reconstructed data may include a judgment logic expression, wherein the judgment logic expression may be obtained by integrating the reconstructed data with a preset analysis rule, and the judgment logic expression may be used to judge whether the reconstructed data is abnormal.

[0053] Step S204: performing a state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result.

[0054] The judgment logic expression can be stored in the reconstructed data. The logic expression can also be stored in code format and used to determine abnormality detection in the system. The reconstructed data includes relevant status information corresponding to the system to be analyzed, such as the status of a device in the system. The terminal can perform status detection on the reconstructed data based on the judgment logic expression to obtain a status detection result.

[0055] Step S206: If the state detection result is an abnormal state, a call request is sent to the system to obtain multimedia data of the device corresponding to the abnormal reconstructed data returned by the system based on the call request.

[0056] The above-mentioned state detection results include normal state and abnormal state. The normal state and abnormal state can be determined according to the judgment strategy preset in the judgment logic expression. When the terminal detects that the above-mentioned state detection result is an abnormal state, it can be determined that the above-mentioned system has an abnormality, and the terminal can send a call request to the above-mentioned system, such as calling the multimedia acquisition device in the system. The system may include multiple devices in the power field, and the above-mentioned time series data may be data corresponding to multiple devices in the system. The terminal can determine that there are abnormal devices in the system through the reconstructed data of the abnormal state. After receiving the call request, the system can obtain the multimedia data of the device corresponding to the above-mentioned reconstructed data with the abnormality through the multimedia acquisition device based on the call request, and return these multimedia data to the terminal. The multimedia data includes audio, image and other data. Therefore, the terminal can process the abnormal state based on the multimedia data of the above-mentioned device.

[0057] Step S208: Obtain analysis results corresponding to the system based on the status detection results and the multimedia data.

[0058] After obtaining the multimedia data of the device corresponding to the aforementioned status detection results and abnormal reconstructed data, the terminal can analyze the status detection results and multimedia data to obtain the analysis results corresponding to the aforementioned system. The terminal can adopt different processing strategies for different analysis results. For example, if the analysis result indicates that the system is normal, the terminal can terminate the analysis. If the analysis result indicates that the system is abnormal, the terminal can issue a timely alarm.

[0059] In one embodiment, after obtaining the analysis result corresponding to the system based on the status detection result and the multimedia data, it also includes: if the analysis result is a system abnormality, generating alarm information based on the analysis result; and pushing the alarm information to the management terminal corresponding to the system.

[0060] In this embodiment, when the terminal determines that the system is abnormal based on the analysis results, the terminal can promptly alert the management terminal corresponding to the system, that is, output corresponding alarm information. For example, when the terminal determines that the analysis result indicates a system abnormality, the terminal can generate an alarm based on the analysis result. The analysis result is generated based on the status detection results of the system and the corresponding multimedia data. The terminal can then combine the detected status detection results and multimedia data to generate an alarm message and push it to the management terminal corresponding to the system. The management terminal can then perform appropriate maintenance on the system after receiving the corresponding alarm message.

[0061] Specifically, the terminal is equipped with an analysis result push module. The multimedia data includes audio, images, and other data collected by the monitoring equipment corresponding to the system. The terminal can combine the multimedia data, such as audio and images, collected by the monitoring equipment, with the status detection results and machine recognition results, and integrate them in the analysis result push module to push the alarm data and its accompanying audio, images, and machine recognition results.

[0062] In the above-mentioned system analysis method for the power sector, by satisfying the start-up analysis conditions, time series data is obtained from the source database of the system to be analyzed, reconstructed into reconstructed data including the streaming calculation results of the judgment logic expression, and the reconstructed data is subjected to status detection based on the judgment logic expression. If the detection result is abnormal, a call request is sent to the system, and the analysis result corresponding to the system is obtained based on the multimedia data of the device corresponding to the reconstructed data returned by the system and the status detection result. Compared with the traditional method of manually analyzing the data of each system, this solution reconstructs the data of each system through preset analysis rules, determines the status of the data based on the judgment logic expression, and obtains the multimedia data of the system through call requests. The system is analyzed based on the status detection and multimedia data, thereby improving analysis efficiency.

[0063] In one embodiment, according to the preset analysis rules corresponding to the system, the time series data is reconstructed into reconstructed data of a streaming computing structure, including: determining the data to be analyzed in the time series data according to the measurement points in the preset analysis rules; associating the state value to be associated with the state value corresponding to the data to be analyzed to obtain the associated state value; associating the data to be analyzed with the judgment logic expression to be associated to obtain the judgment logic expression after association; generating the reconstructed data corresponding to the time series data according to the data to be analyzed, the state value and the judgment logic expression.

[0064] In this embodiment, the above-mentioned preset analysis rule can be a rule template, which includes how to analyze the status value of the device to determine whether it is normal or abnormal, and the terminal needs to associate the device parameters that need to be analyzed with the corresponding positions in the preset analysis rule. The above-mentioned preset analysis rule includes measuring points, status values ​​to be associated, and logical expressions for judgment to be associated. When the terminal reconstructs the time series data based on the preset analysis rule, it can reconstruct based on the measuring points, status values ​​to be associated, and logical expressions for judgment to be associated in the preset analysis rule. Among them, the measuring point represents the device parameter that needs to be collected in the system, the status value to be associated represents the value that needs to be associated with the status parameter of the corresponding device in the system, and the logical expression for judgment to be associated represents the rule that needs to be filled with the corresponding status value and abnormal judgment logic in the system.

[0065] For example, the terminal can determine the data to be analyzed in the time series data based on the measurement points in the preset analysis rules. That is, the terminal determines the data to be analyzed that needs to be analyzed from the time series data based on the measurement points. The terminal can associate the state value to be associated with the state value corresponding to the data to be analyzed to obtain the associated state value. Among them, the associated state value can continuously detect the latest state of the state value corresponding to the data to be analyzed, and update it to the judgment logic expression in real time. The terminal can associate the above-mentioned data to be analyzed with the judgment logic expression to be associated. For example, the judgment logic expression can be a template, and the terminal will synchronously update the latest value of the data to be analyzed with the corresponding value in the associated judgment logic expression, so as to obtain the associated judgment logic expression. The terminal can generate reconstructed data corresponding to the time series data based on the above-mentioned data to be analyzed, state value and judgment logic expression.

[0066] Specifically, a time series data synchronization module is provided in the terminal, and all linkage rule information of the entire system is stored in the terminal, including the measurement points used for alarm judgment, the judgment logic of alarm judgment, and the parameters for calling the system. Through the data synchronization module, the terminal pulls the time series data from the source database corresponding to the system based on the above measurement points, obtains the above data to be analyzed, and processes other information in combination with the preset analysis rules corresponding to the system, such as associating the state value to be associated with the state value of the data to be analyzed, associating the data to be analyzed with the logic expression to be associated, etc., to form a structure suitable for streaming computing, which can be specifically expressed as: [time scale, measurement point identifier, state value, other measurement point attributes, policy identifier, alarm judgment logic expression, other policy attributes, interface call list]. The terminal can push the reconstructed data of the above streaming computing structure to the linkage module in the terminal for calculation and analysis, that is, to perform abnormal analysis and judgment.

[0067] Through this embodiment, the terminal can reconstruct the time series data of the above-mentioned system by combining the measurement points, status values, judgment logic expressions and other information in the preset analysis rules, so that the terminal can perform data analysis based on the reconstructed data suitable for streaming computing technology, thereby improving the efficiency of analyzing systems in the power field.

[0068] In one embodiment, a state detection is performed on the reconstructed data according to a judgment logic expression to obtain a state detection result, including: executing the judgment logic expression through a preset judgment component to determine the abnormal state value; obtaining the state value corresponding to the data to be analyzed in the reconstructed data; and obtaining the state detection result corresponding to the data to be analyzed based on the comparison result of the state value and the abnormal state value.

[0069] In this embodiment, the reconstructed data after reconstruction includes a judgment logic expression, and the judgment logic expression includes judgment logic for how to perform abnormal analysis on the status parameters of the device. The terminal can execute the judgment logic expression through a preset judgment component to determine the abnormal status value. That is, the terminal determines which of the above-mentioned systems has the abnormal status value by executing the judgment logic expression. The terminal can thus obtain the status value corresponding to the data to be analyzed in the reconstructed data, and obtain the status detection result corresponding to the data to be analyzed based on the comparison result of the status value corresponding to the above-mentioned data to be analyzed and the abnormal status value. For example, if the terminal detects that the above-mentioned status value is consistent with the abnormal status value, it means that the status detection result of the device to which the data to be analyzed belongs is abnormal; if the terminal detects that the above-mentioned status value is inconsistent with the abnormal status value, it means that the status detection result of the device to which the data to be analyzed belongs is normal.

[0070] Specifically, the terminal is equipped with a linkage module. After the analyzed data enters the linkage module, it first performs a logical judgment in the alarm judgment component to determine whether the status detection result is abnormal. If it is abnormal, the terminal will call multimedia data and issue an alarm. If it is not abnormal, the terminal can discard the data and end the judgment.

[0071] The preset analysis rules and judgment logic expressions can be an AviatorScript expression. AviatorScript is a high-performance, lightweight scripting language. This language focuses on expression execution rather than a complete programming language, but supports most common mathematical, comparison and logical operators, as well as variable and function calls. The above preset analysis rules can be specifically expressed as "20xx-xx-xx 21:10:21.493,1701868221493,M,1,R,{"alarm":"test(lambda(e)->str(e.state) == 'appeared' || toLong(e.state) == 1 end ,json.object(states.getMapState('mp_states' , 'R#M')))"},{"invokers":[{"apiId":"am1fQuLTA","httpMethod":"POST","path":" / base / v2 / priority / video"","args":[],"body":{"dataType":"json","content":"3Y1UMG06.ST.003"}}]}". This includes a judgment logic expression, which the terminal can integrate into the reconstructed data. M represents the measuring point, 1 represents the abnormal state value, and R represents the judgment logic expression. After receiving the processed data of the above-mentioned measuring point M, that is, when receiving the associated data to be analyzed, the terminal can write it to the state memory in the terminal. The terminal can execute the alarm judgment logic expression in the reconstructed data, that is, execute the above {"alarm":"test(lambda(e)->str(e.state) == 'appeared' || toLong(e.state) == 1 end , json.object(states.getMapState('mp_states', 'R#M')))"}. This expression can be specifically interpreted as: when the value of measurement point M is present or 1, the alarm signal is established, and the state detection result is determined to be abnormal. At this time, the terminal obtains the value of measurement point M from the state memory through the states.getMapState method, which is 1. Therefore, the alarm signal is established, and the state detection result is determined to be abnormal. The terminal can continue to execute the alarm steps corresponding to the state abnormality. If the value of M is any other value, the alarm signal is not established, and the state detection result is determined to be normal. The terminal can discard the data and end this calculation.

[0072] Through this embodiment, the terminal can combine the judgment logic expression to judge whether the system is abnormal, thereby improving the efficiency of abnormal analysis of the system in the power field.

[0073] In one embodiment, a call request is sent to the system to obtain multimedia data of a device corresponding to abnormal reconstructed data returned by the system based on the call request, including: determining target interface call information corresponding to the multimedia acquisition device in the system according to an interface call list; and sending a call request to the multimedia acquisition device in the system according to the target interface call information to obtain multimedia data of a device corresponding to the abnormal reconstructed data returned by the system after calling the multimedia acquisition device based on the call request.

[0074] In this embodiment, the above-mentioned reconstruction data also includes an interface call list corresponding to the above-mentioned system, wherein the above-mentioned system includes multiple devices, and a terminal outside the system can call these devices based on the interface call list. For example, when the terminal determines that the above-mentioned system is in an abnormal state, it is necessary to send a call request to the above-mentioned system. The terminal can determine the target interface call information corresponding to the multimedia acquisition device in the above-mentioned system based on the interface call list in the reconstruction data. The target interface call information may include one or more. Therefore, the terminal can send a call request to the multimedia acquisition device in the system based on the above-mentioned target interface call information. The above-mentioned system can call the multimedia acquisition device based on the call request and collect the multimedia data of the device corresponding to the above-mentioned abnormal reconstruction data, and then return it to the terminal. The terminal can obtain the multimedia data of the device corresponding to the abnormal reconstruction data returned by the system after calling the multimedia acquisition device based on the call request.

[0075] Specifically, the multimedia acquisition device may be a monitoring device, and the multimedia data may include audio, image, and other data. Upon determining that the status detection result of the system is abnormal, the terminal may read the contents of the interface call list segment in the reconstructed data, obtain the target interface call information corresponding to the monitoring device, and initiate a call request to the monitoring device. The interface call information can be specifically represented as {"invokers":[{"apiId":"am1fQuLTA","httpMethod":"POST","path":" / base / v2 / priority / video"","args":[],"body":{"dataType":"json","content":"3Y1UMG06.ST.003"}}]}. The fields contain the interface identifier, request method, request path, and request body. The terminal can initiate a request based on this information by calling a component. Alarm data flows to the push module in the terminal. Upon receiving the call request, the system invokes the monitoring device, captures images or records audio based on the input parameters, and pushes the audio and images to the terminal. The terminal then combines these audio and images to generate the corresponding alarm information. The terminal uses the analysis result push module to integrate the alarm data (status detection results) from the measurement points, the images and audio captured by the monitoring device, and the machine recognition results to generate alarm information and push it to the corresponding management terminal of the system.

[0076] Through this embodiment, the terminal can combine the interface call information and call the multimedia acquisition device in the above system when the status detection result of the device is abnormal, so as to obtain the multimedia data of the abnormal device. The terminal performs system analysis in the power field based on the multimedia data, thereby improving the analysis efficiency.

[0077] In one embodiment, an analysis result corresponding to the system is obtained based on the status detection result and the multimedia data, including: inputting the multimedia data into a trained machine recognition model, and the machine recognition model outputting the multimedia anomaly detection result corresponding to the system based on the multimedia data; and obtaining an analysis result corresponding to the system based on the status detection result and the multimedia anomaly detection result.

[0078] In this embodiment, the terminal can pre-train the machine recognition model to be trained. For example, the terminal can use multimedia data samples and corresponding multimedia anomaly detection result samples to train the machine recognition model to be trained. The terminal can input the multimedia data samples into the machine recognition model to be trained. The machine recognition model identifies the abnormal information in the multimedia data samples based on the multimedia data samples, and then outputs the corresponding multimedia anomaly prediction results. The terminal adjusts the model parameters of the machine recognition model based on the comparison of the multimedia anomaly prediction results and the above-mentioned multimedia anomaly detection results, and then trains and adjusts them multiple times to obtain a trained machine recognition model. Among them, the machine recognition model can be used to identify abnormal information in multimedia data, such as abnormal information in audio and abnormal information of devices in images.

[0079] The terminal can input the multimedia data into a trained machine recognition model, which then outputs a corresponding multimedia anomaly detection result based on the multimedia data. This multimedia anomaly detection result includes anomalies in the device's audio as detected by the machine recognition model, as well as information about anomalies in the device's images. Based on the status detection result and the multimedia anomaly detection result, the terminal can obtain the corresponding analysis result from the system.

[0080] Specifically, the multimedia data may be images and audio. After receiving the images and audio, the terminal may use a machine recognition model to perform machine recognition on them to identify abnormal information. The terminal may then send the recognition results, the corresponding audio and images, etc., to a push module in the terminal to push the alarm information.

[0081] Through this embodiment, the terminal can combine the machine recognition model to perform anomaly identification of multimedia data on abnormal devices in the above system. The terminal performs anomaly analysis of equipment in the power field based on multimedia data, thereby improving analysis efficiency.

[0082] In an exemplary embodiment, Figure 2 As shown, Figure 2 This is a flow chart of another embodiment of a system analysis method for the power sector. The various systems within the power sector are independent of each other, making it currently impossible to combine data from multiple systems to comprehensively determine abnormal equipment operating conditions and issue alarms. This embodiment provides a system analysis method for the power sector based on streaming computing technology, specifically including a time series data synchronization module in the terminal, a data-driven linkage module, and an analysis result push module. The linkage module includes an alarm determination component and an external device call component.

[0083] Specifically, the process of the system analysis method in the power field is as follows: Figure 3 As shown, Figure 3This is a flow chart of a system analysis method for the power sector in another embodiment. The time series data synchronization module stores all linkage rule information (preset analysis rules) for the entire system, including measurement points used for alarm determination, alarm decision logic (determination logic expressions), and parameters for calling monitoring devices (interface call lists). Based on the rule measurement points, the data synchronization module periodically pulls time series data from the system's source database, processes it into a structure suitable for streaming computing (reconstructed data) based on other information related to the rules, and then pushes it to the linkage module for computation and analysis.

[0084] After data enters the linkage module, the terminal first performs a logical judgment in the alarm determination component. If it is determined to be alarm data, the data will flow to the monitoring device call component, which will call a specific monitoring device (multimedia acquisition device) to collect images or audio for machine recognition. The terminal can return the collected audio and image and the corresponding machine recognition results together, and then flow to the next module. If the terminal determines that the data is not an alarm, it will be discarded.

[0085] The alarm data, audio and pictures collected by the monitoring equipment, and the corresponding recognition results will be integrated in the analysis result push module, and the alarm data and its accompanying audio, pictures, and recognition results will be pushed to the corresponding management terminal of the above system.

[0086] Among them, the above-mentioned data synchronization module can receive the re-run command initiated by the user and store it in the command list. The data synchronization task can check the command list during execution, and after finding the re-run command, it will pull the business data from the specified time and write it to the Kafka topic. In addition, for the corresponding calling component, the system can recognize the calling interface command. The command data has a specific format, including interface identifier, request method, request path and request body, and initiates a call request to the interface calling gateway. For the implementation of the analysis result push module: the terminal can integrate the alarm data, data collected by the monitoring equipment and the machine recognition results according to the data identifier and the instance identifier returned by the request interface.

[0087] Through the above-described embodiment, the terminal reconstructs data from various systems using preset analysis rules, determines the data's status based on logical expressions, and obtains multimedia data from the system through call requests. This system is then analyzed based on the status detection and multimedia data, improving analysis efficiency. Furthermore, the terminal integrates and processes measurement point data, alarm determination logic, and interface call information into a readable real-time data stream. Through streaming computing, this data-driven approach identifies alarms and mobilizes monitoring equipment to collect data, thereby enabling multi-system analysis and linkage in the power sector and improving analysis efficiency.

[0088] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0089] Based on the same inventive concept, embodiments of the present application also provide a system analysis device for the electric power sector for implementing the aforementioned system analysis method for the electric power sector. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more embodiments of the system analysis device for the electric power sector provided below can be found in the limitations of the system analysis method for the electric power sector described above and will not be repeated here.

[0090] In an exemplary embodiment, Figure 4 As shown, a system analysis device in the power field is provided, including: a detection module 500, a reconstruction module 502, a calling module 504 and an analysis module 506, wherein:

[0091] The detection module 500 is used to detect that the system to be analyzed in the power field meets the start-up analysis conditions, obtain the corresponding time series data of the system from the source database of the system, and reconstruct the time series data into reconstructed data of a streaming computing structure according to the preset analysis rules corresponding to the system; the reconstructed data includes a judgment logic expression.

[0092] The reconstruction module 502 is used to perform state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result.

[0093] The calling module 504 is configured to send a calling request to the system if the state detection result is an abnormal state, and obtain multimedia data of the device corresponding to the abnormal reconstructed data returned by the system based on the calling request.

[0094] The analysis module 506 is used to obtain analysis results corresponding to the system according to the status detection results and the multimedia data.

[0095] In one embodiment, the above-mentioned detection module 500 is used to determine the data to be analyzed in the time series data based on the measurement points in the preset analysis rules; associate the state value to be associated with the state value corresponding to the data to be analyzed to obtain the associated state value; associate the data to be analyzed with the judgment logic expression to be associated to obtain the judgment logic expression after association; generate reconstructed data corresponding to the time series data based on the data to be analyzed, the state value and the judgment logic expression.

[0096] In one embodiment, the reconstruction module 502 is used to execute a judgment logic expression through a preset judgment component to determine an abnormal state value; obtain a state value corresponding to the data to be analyzed in the reconstructed data; and obtain a state detection result corresponding to the data to be analyzed based on a comparison result between the state value and the abnormal state value.

[0097] In one embodiment, the above-mentioned calling module 504 is used to determine the target interface calling information corresponding to the multimedia acquisition device in the system according to the interface calling list; according to the target interface calling information, send a calling request to the multimedia acquisition device in the system, and obtain the multimedia data of the device corresponding to the abnormal reconstructed data returned by the system after calling the multimedia acquisition device based on the calling request.

[0098] In one embodiment, the above-mentioned analysis module 506 is used to input multimedia data into a trained machine recognition model, and the machine recognition model outputs the multimedia anomaly detection results corresponding to the system based on the multimedia data; and obtains the analysis results corresponding to the system according to the status detection results and the multimedia anomaly detection results.

[0099] In one embodiment, the above-mentioned device further includes: an alarm module, which is used to generate alarm information according to the analysis result if the analysis result shows that the system is abnormal; and push the alarm information to the management terminal corresponding to the system.

[0100] Each module in the aforementioned power system analysis device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0101] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a system analysis method in the power field. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0102] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0103] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the above-mentioned system analysis method in the power field when executing the computer program.

[0104] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the system analysis method in the power field is implemented.

[0105] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the computer program implements the above-mentioned system analysis method in the power field.

[0106] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0107] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a programmable logic unit (PLC), a data processing logic unit based on quantum computing, an artificial intelligence (AI) processor, and the like.

[0108] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0109] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A system analysis method in the field of electric power, characterized in that: The method comprises: When it is detected that a system to be analyzed in the power field meets the start-up analysis conditions, time series data corresponding to the system is obtained from the source database of the system, and the time series data is reconstructed into reconstructed data of a streaming computing structure according to the preset analysis rules corresponding to the system; the preset analysis rules include measurement points, state values ​​to be associated, and judgment logic expressions to be associated; the reconstructed data includes judgment logic expressions; the reconstructing of the time series data into reconstructed data of a streaming computing structure according to the preset analysis rules corresponding to the system includes: determining the data to be analyzed in the time series data according to the measurement points in the preset analysis rules; associating the state value to be associated with the state value corresponding to the data to be analyzed to obtain the associated state value; associating the data to be analyzed with the judgment logic expression to be associated to obtain the associated judgment logic expression; generating the reconstructed data corresponding to the time series data according to the data to be analyzed, the state value, and the judgment logic expression; Performing state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result; If the state detection result is an abnormal state, sending a call request to the system to obtain multimedia data of the device corresponding to the abnormal reconstructed data returned by the system based on the call request; An analysis result corresponding to the system is obtained according to the status detection result and the multimedia data.

2. The method according to claim 1, characterized in that The performing state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result includes: Executing the judgment logic expression through a preset judgment component to determine the abnormal state value; Obtaining the state value corresponding to the data to be analyzed in the reconstructed data; According to the comparison result between the state value and the abnormal state value, a state detection result corresponding to the data to be analyzed is obtained.

3. The method according to claim 1, characterized in that The reconstructed data also includes an interface call list corresponding to the system; The sending of a call request to the system to obtain multimedia data of a device corresponding to abnormal reconstructed data returned by the system based on the call request includes: Determining target interface call information corresponding to the multimedia acquisition device in the system according to the interface call list; According to the target interface calling information, a calling request is sent to the multimedia acquisition device in the system, and multimedia data of the device corresponding to the abnormal reconstructed data returned by the system after calling the multimedia acquisition device based on the calling request is obtained.

4. The method according to claim 1, wherein Obtaining an analysis result corresponding to the system according to the status detection result and the multimedia data includes: Inputting the multimedia data into a trained machine recognition model, and having the machine recognition model output a multimedia anomaly detection result corresponding to the system based on the multimedia data; According to the status detection result and the multimedia anomaly detection result, an analysis result corresponding to the system is obtained.

5. The method according to any one of claims 1 to 4, characterized in that After obtaining the analysis result corresponding to the system according to the status detection result and the multimedia data, the method further includes: If the analysis result indicates that the system is abnormal, generating an alarm message according to the analysis result; The alarm information is pushed to the management terminal corresponding to the system.

6. A system analysis device in the field of electric power, characterized in that: The device comprises: A reconstruction module is configured to, when detecting that a system to be analyzed in the power field meets the conditions for starting analysis, obtain time series data corresponding to the system from a source database of the system, and reconstruct the time series data into reconstructed data of a streaming computing structure according to preset analysis rules corresponding to the system; the preset analysis rules include measurement points, state values ​​to be associated, and judgment logic expressions to be associated; the reconstructed data include judgment logic expressions; and is specifically configured to: determine the data to be analyzed in the time series data according to the measurement points in the preset analysis rules; associate the state values ​​to be associated with the state values ​​corresponding to the data to be analyzed to obtain the associated state values; associate the data to be analyzed with the judgment logic expressions to be associated to obtain the associated judgment logic expressions; and generate reconstructed data corresponding to the time series data according to the data to be analyzed, the state values, and the judgment logic expressions; A detection module, configured to perform a state detection on the reconstructed data according to the judgment logic expression to obtain a state detection result; a calling module configured to, if the state detection result is an abnormal state, send a calling request to the system and obtain multimedia data of a device corresponding to abnormal reconstructed data returned by the system based on the calling request; The analysis module is used to obtain an analysis result corresponding to the system according to the status detection result and the multimedia data.

7. The device according to claim 6, characterized in that The detection module is specifically used to: Executing the judgment logic expression through a preset judgment component to determine the abnormal state value; Obtaining the state value corresponding to the data to be analyzed in the reconstructed data; According to the comparison result between the state value and the abnormal state value, a state detection result corresponding to the data to be analyzed is obtained.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images