Power transformation inspection video monitoring strategy management method and system
By dynamically adjusting the management method of substation inspection video surveillance strategy, the problems of uneven resource allocation and insufficient task priority management are solved, and the system resources are flexibly scheduled and the monitoring tasks are executed efficiently and stably.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-04
- Publication Date
- 2026-03-13
Smart Images
Figure CN121663785A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent inspection technology for power systems, and in particular to a method and system for managing video surveillance strategies for substation inspection. Background Technology
[0002] With the acceleration of intelligent inspection of power systems, the application of video analytics technology in substation inspection is constantly expanding. With its significant advantages, it has effectively replaced the traditional manual inspection mode, greatly improving detection efficiency and accuracy.
[0003] However, existing video analytics systems often face problems such as uneven distribution of computing resources and insufficient priority management of monitoring tasks, leading to resource shortages under high loads and resource waste under low loads. Furthermore, the lack of dynamic frame extraction mechanisms and flexible rule engine management makes it difficult to adjust computing resources in real time according to monitoring task requirements, affecting overall processing efficiency and system responsiveness, and limiting the further development of intelligent substation inspection. Summary of the Invention
[0004] The purpose of this invention is to solve at least one technical problem in the background art and to provide a substation inspection video surveillance strategy management method and system.
[0005] To achieve the above objectives, the present invention provides a substation inspection video surveillance strategy management method, comprising: The substation inspection visual analysis system receives and parses the control information and rule configuration information of the monitoring strategy. Extract monitoring identifiers from rule information and configuration information, and update the monitoring policy model library based on the monitoring identifiers and policy control instructions; Based on the updated monitoring strategy model library, a model change signal is triggered, and the minimum set of core parameters of the monitoring strategy is selected based on the model change signal. The corresponding rule engine execution unit is loaded based on the monitoring strategy with the smallest set of parameters selected, and the monitoring task of the corresponding monitoring strategy is executed. Based on the priority of monitoring tasks, the monitoring work of the rule engine execution unit is dynamically adjusted.
[0006] According to one aspect of the present invention, the control information of the monitoring strategy includes: strategy instance lifecycle management instructions, including control operations for querying the execution status of rule configuration, starting, stopping, pausing, resuming, restarting, and adjusting parameters; The rule configuration information includes rule information, which includes: inference analysis model ID, model tag ID, and target type to be identified; The rule configuration information includes configuration information, which includes: monitoring policy identifier, monitoring code, priority level, monitoring video stream identifier, video stream configuration information, alarm uploading configuration information, monitoring area, and monitoring time.
[0007] According to one aspect of the present invention, receiving and parsing the control information and rule configuration information of the monitoring strategy includes: The substation inspection visual analysis system acts as an HTTP server, deploys a policy management interface, starts a listening service, and receives request messages for control information and rule configuration information of the monitoring policy in real time. The request message is decoded according to the protocol, and triple verification is performed on the data type, value range, and dependency. After verification, three types of data entities were separated: policy control instructions, rules, and configuration parameters.
[0008] According to one aspect of the present invention, the step of extracting monitoring identifiers from rule information and configuration information, and updating the monitoring strategy model library based on the monitoring identifiers and according to policy control instructions, includes: The system parses configuration information using custom metadata structures and uses regular expressions to match and extract monitoring identifiers from preset fields. Verify the validity of the monitored identifiers and block illegal identifiers that do not conform to the format; A monitoring strategy model is constructed based on three types of data entity information: policy control instructions, rules, and configuration parameters. Based on policy control instructions, a unique binding index is established between the verified monitoring identifier and the corresponding monitoring policy model; The corresponding action is triggered based on the type of policy control instruction: when a model is added, the corresponding index associated monitoring policy model is added to the monitoring policy model library; when a model is updated, the associated monitoring policy model parameter information is modified synchronously; when a model is deleted, the binding relationship between the monitoring policy model and the monitoring identifier is released, and the corresponding monitoring policy model resources in the monitoring policy model library are cleaned up.
[0009] According to one aspect of the present invention, the step of triggering a model change signal based on the updated monitoring strategy model library, and filtering the minimum set of core parameters of the monitoring strategy based on the model change signal, includes: When a model in the monitoring strategy model library changes, a model change signal is triggered. Analyze the rule configuration and control information in the model change signals and extract the key information fields; Filter the core parameters that affect the execution of the monitoring strategy from the key information fields, remove redundant or low-impact parameters, and retain the necessary parameter set; The filtered parameters are standardized in format, and then the minimum set of parameters required for the execution of each monitoring strategy is sent.
[0010] According to one aspect of the present invention, the step of loading the corresponding rule engine execution unit according to the monitoring strategy that selects the minimum set of parameters and executing the monitoring task of the corresponding monitoring strategy includes: Load the corresponding rule engine execution unit according to the monitoring strategy, and initialize the monitoring task parameters and environment; Parse video stream data and match it with target detection, behavior analysis, or alarm conditions according to preset rules; Output monitoring and analysis results, and trigger corresponding event alarm processing procedures according to alarm policies.
[0011] According to one aspect of the present invention, the dynamic adjustment of the monitoring work of the rule engine execution unit based on the priority of the monitoring task includes: Regularly check the running status of each rule engine execution unit, including the current number of tasks, CPU / GPU usage, and memory usage; According to the priority of the monitoring strategy, set the running priority of the corresponding rule engine execution unit to ensure the priority execution of important monitoring tasks; Adjust the frame dropping frequency of the video stream based on the current system load. When certain rule engine execution units are idle or under low load for a long time, release the resources they occupy; Based on the monitoring task execution status and the overall system resource usage, the number of rule engine execution units can be dynamically increased or decreased according to priority.
[0012] To achieve the above objectives, the present invention also provides a substation inspection video surveillance strategy management system, comprising: The information receiving and parsing module of the substation inspection visual analysis system receives and parses the control information and rule configuration information of the monitoring strategy. The monitoring strategy model library update module extracts monitoring identifiers from rule information and configuration information, and updates the monitoring strategy model library based on the monitoring identifiers and policy control instructions. The monitoring strategy key parameter filtering module triggers a model change signal based on the updated monitoring strategy model library, and then filters the minimum set of core parameters of the monitoring strategy based on the model change signal. The monitoring task execution module loads the corresponding rule engine execution unit based on the monitoring strategy with the smallest set of parameters selected, and executes the monitoring task corresponding to the monitoring strategy. The rule engine execution unit dynamic adjustment module dynamically adjusts the monitoring work of the rule engine execution unit based on the priority of the monitoring tasks.
[0013] To achieve the above objectives, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the substation inspection video monitoring strategy management method as described above.
[0014] To achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the substation inspection video monitoring strategy management method as described above.
[0015] According to the present invention, by decoupling model management from engine execution, the modularity, scalability, and stability of the system are significantly improved. Updates to the monitoring strategy model library and the execution of the rule engine do not interfere with each other, achieving flexibility in resource scheduling and multi-task parallel processing capabilities.
[0016] This invention optimizes system resource utilization and monitoring task execution efficiency through precise monitoring strategy management, an efficient monitoring strategy model library update mechanism, and dynamic rule engine management. It enables flexible parsing and adjustment of monitoring strategies, including key functions such as task priority, video stream processing, and alarm mechanisms, and achieves seamless integration between model and engine execution through a model triggering mechanism. Simultaneously, it dynamically adjusts the working state of the rule engine execution unit based on hardware resource usage, ensuring efficient and stable operation of inspection tasks. Attached Figure Description
[0017] Figure 1 This illustration represents one embodiment of the invention. Detailed Implementation
[0018] The invention will now be discussed with reference to exemplary embodiments. It should be understood that the described embodiments are merely intended to enable those skilled in the art to better understand and thus implement the invention, and are not intended to imply any limitation on the scope of the invention.
[0019] As used herein, the term "comprising" and its variations are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "at least partially based on". The terms "one embodiment" and "an embodiment" are to be interpreted as "at least one embodiment".
[0020] Figure 1 This is a schematic diagram of a substation inspection video surveillance strategy management method according to an embodiment of the present invention. Figure 1 As shown, in this embodiment, the substation inspection video surveillance strategy management method includes: The substation inspection visual analysis system receives and parses the control information and rule configuration information of the monitoring strategy. Extract monitoring identifiers from rule information and configuration information, and update the monitoring policy model library based on the monitoring identifiers and policy control instructions; Based on the updated monitoring strategy model library, a model change signal is triggered, and the minimum set of core parameters of the monitoring strategy is selected based on the model change signal. The corresponding rule engine execution unit is loaded based on the monitoring strategy with the smallest set of parameters selected, and the monitoring task of the corresponding monitoring strategy is executed. Based on the priority of monitoring tasks, the monitoring work of the rule engine execution unit is dynamically adjusted.
[0021] Furthermore, according to one embodiment of the present invention, a monitoring strategy refers to a set of rules, configurations, and operational logics formulated to achieve specific monitoring task objectives.
[0022] The control information for monitoring policies includes: policy instance lifecycle management instructions, including control operations for querying the execution status of rule configurations, starting, stopping, pausing, resuming, restarting, and adjusting parameters; The rule configuration information includes rule information, which includes: inference analysis model ID, model tag ID, and target type to be identified; The rule configuration information includes configuration information, which includes: monitoring policy identifier, monitoring code, priority level, monitoring video stream identifier, video stream configuration information, alarm uploading configuration information, monitoring area, and monitoring time.
[0023] Furthermore, according to one embodiment of the present invention, receiving and parsing control information and rule configuration information of the monitoring strategy includes: The substation inspection visual analysis system acts as an HTTP server, deploys a policy management interface, starts a listening service, and receives request messages for control information and rule configuration information of the monitoring policy in real time. The request message is decoded according to the protocol, and triple verification is performed on the data type, value range, and dependency. After verification, three types of data entities were separated: policy control instructions, rules, and configuration parameters.
[0024] Specifically, in this embodiment, the substation inspection visual analysis system acts as an HTTP server, deploys a policy management interface, starts a listening service, and receives request messages for control information and rule configuration information of the monitoring policy in real time, including: Deploy monitoring policy listening service: Build an HTTP server based on the HTTP protocol, read local service configuration parameters, and bind to a specified IP and port; Start the network listening service: Initialize the network listener service, establish a session and put the received messages into the message queue for processing, and start a multi-threaded listening service to receive external request messages in real time.
[0025] In this embodiment, the request message is decoded according to the protocol, and triple verification of data type, value range, and dependency is performed, including: Message reception and protocol decoding: Based on pre-defined format specifications or custom parsing rules, the received binary data (request message) is converted into a recognizable structured data object; Perform basic verification of the request: Basic verification includes: message structure verification, signature pre-verification, and token verification; Specifically, message structure verification mainly checks the JSON format of Content-Type and Body, as well as the completeness of required fields. Signature pre-verification mainly verifies the existence of signature fields and whether the parameter sorting rules are met. Token verification mainly verifies the existence of the token. Configure parameter validation rule base: implement a triple validation mechanism in sequence for data type, value range, and related dependencies; Specifically, data type validation ensures that each configuration parameter conforms to the expected data format. Strict type checking prevents program errors caused by data type mismatches. Value range validation ensures that configuration parameter values are within a reasonable range. This validation not only prevents the input of illegal values but also improves system stability. Dependency validation ensures that the relationships between multiple configuration parameters are reasonable and consistent. Different monitoring identification type configurations are coupled with monitoring areas and monitoring times, and alarm configurations. Therefore, establishing a dependency validation function between parameters can automatically detect and fix potential problems when setting parameters.
[0026] In this embodiment, after verification, three types of data entities are separated: policy control instructions, rules, and configuration parameters, including: First, the configuration parameters are extracted and their compliance is verified. Second, the rule elements are loaded to build the recognition logic. Third, the control commands (such as start and stop commands) and other parameters are parsed.
[0027] Furthermore, according to one embodiment of the present invention, the monitoring identifier is extracted from the rule information and configuration information, and the monitoring strategy model library is updated based on the monitoring identifier and according to the strategy control instructions, including: The system parses configuration information using custom metadata structures and uses regular expressions to match and extract monitoring identifiers from preset fields. Verify the validity of unique monitoring identifiers and block illegal identifiers that do not conform to the format; verify that the identifier length does not exceed 32 characters and only letters, numbers and underscores are allowed, and block abnormal identifiers containing special characters; A monitoring strategy model is constructed based on three types of data entity information: policy control instructions, rules, and configuration parameters. Based on policy control instructions, a unique binding index is established between the verified monitoring identifier and the corresponding monitoring policy model; Based on the policy control instruction type (create / update / delete), trigger the corresponding action: when a model is added, add the corresponding index associated monitoring policy model to the monitoring policy model library; when a model is updated, synchronously modify the associated monitoring policy model parameter information; when a model is deleted, unbind the monitoring policy model from the monitoring identifier and clean up the corresponding monitoring policy model resources in the monitoring policy model library.
[0028] Furthermore, according to one embodiment of the present invention, a model change signal is triggered based on the updated monitoring strategy model library, and a minimum set of core parameters of the monitoring strategy is selected based on the model change signal, including: When a model in the monitoring strategy model library changes, a model change signal is triggered. Analyze the rule configuration and control information in the model change signals and extract the key information fields; Filter the core parameters that affect the execution of the monitoring strategy from the key information fields, remove redundant or low-impact parameters, and retain the necessary parameter set; The necessary parameter set after screening is standardized in format, and then the minimum set of parameters required for the execution of each monitoring strategy is sent to reduce the data transmission and computational burden.
[0029] Furthermore, according to one embodiment of the present invention, the corresponding rule engine execution unit is loaded according to the monitoring strategy that selects the minimum set of parameters, and the monitoring task corresponding to the monitoring strategy is executed, including: Load the corresponding rule engine execution unit according to the monitoring strategy, and initialize the monitoring task parameters and environment; Parse video stream data and match it with target detection, behavior analysis, or alarm conditions according to preset rules; Output monitoring and analysis results, and trigger corresponding event alarm processing procedures according to alarm policies.
[0030] In this embodiment, video stream data is parsed and matched with target detection, behavior analysis, or alarm conditions according to preset rules, including: In the rule engine execution unit, the streaming media processing engine first performs real-time protocol decoding and frame extraction on the received monitoring video stream. Then, the AI inference engine loads the corresponding algorithm model based on pre-parsed rule configuration information (such as inference analysis model ID and target type), performing target detection or behavior analysis on the processed image data. Finally, the alarm decision engine performs a multi-dimensional comparison between the analysis results output by the AI inference and the logical conditions set in the configuration information, such as monitoring area, monitoring time, and alarm threshold, to determine whether the alarm triggering conditions are met and generates the corresponding structured alarm event. This stage focuses on alarm determination. It outputs monitoring analysis results and triggers the corresponding event alarm handling process according to the alarm strategy. Analysis: After generating an alarm event, the alarm decision engine triggers the specific handling process. This stage focuses on the triggering and execution of the alarm.
[0031] In this embodiment, the rule engine execution unit includes: Streaming media processing engine: supports real-time streaming media push and pull transmission and encoding / decoding; AI inference engine: Loads new models to perform object detection and behavior analysis; Alarm decision engine: Generates alarm events and triggers handling processes based on rule-configured thresholds.
[0032] Furthermore, according to one embodiment of the present invention, dynamically adjusting the monitoring work of the rule engine execution unit based on the priority of the monitoring task includes: Regularly check the running status of each independent rule engine execution unit that does not interfere with each other, including the current number of tasks, CPU / GPU usage, and memory usage; According to the priority of the monitoring strategy, set the running priority of the corresponding rule engine execution unit to ensure the priority execution of important monitoring tasks and reduce the running frequency of secondary tasks; Adjust the frame extraction frequency of the video stream based on the current system load, reducing computational load under high load and improving analysis accuracy under low load. When certain rule engine execution units are idle or under low load for a long time, release the resources they occupy; Based on the monitoring task execution status and the overall system resource usage, the number of rule engine execution units can be dynamically increased or decreased according to priority.
[0033] According to the above-described solution of the present invention, by decoupling model management from engine execution, the present invention significantly improves the modularity, scalability, and stability of the system. Updates to the monitoring strategy model library and the execution of the rule engine do not interfere with each other, achieving flexibility in resource scheduling and multi-task parallel processing capabilities.
[0034] This invention optimizes system resource utilization and monitoring task execution efficiency through precise monitoring strategy management, an efficient monitoring strategy model library update mechanism, and dynamic rule engine management. It enables flexible parsing and adjustment of monitoring strategies, including key functions such as task priority, video stream processing, and alarm mechanisms, and achieves seamless integration between model and engine execution through a model triggering mechanism. Simultaneously, it dynamically adjusts the working state of the rule engine execution unit based on hardware resource usage, ensuring efficient and stable operation of inspection tasks.
[0035] Furthermore, to achieve the above objectives, the present invention also provides a substation inspection video surveillance strategy management system, comprising: The information receiving and parsing module of the substation inspection visual analysis system receives and parses the control information and rule configuration information of the monitoring strategy. The monitoring strategy model library update module extracts monitoring identifiers from rule information and configuration information, and updates the monitoring strategy model library based on the monitoring identifiers and policy control instructions. The monitoring strategy key parameter filtering module triggers a model change signal based on the updated monitoring strategy model library, and then filters the minimum set of core parameters of the monitoring strategy based on the model change signal. The monitoring task execution module loads the corresponding rule engine execution unit based on the monitoring strategy with the smallest set of parameters selected, and executes the monitoring task corresponding to the monitoring strategy. The rule engine execution unit dynamic adjustment module dynamically adjusts the monitoring work of the rule engine execution unit based on the priority of the monitoring tasks.
[0036] Furthermore, according to one embodiment of the present invention, a monitoring strategy refers to a set of rules, configurations, and operational logics formulated to achieve specific monitoring task objectives.
[0037] The control information for monitoring policies includes: policy instance lifecycle management instructions, including control operations for querying the execution status of rule configurations, starting, stopping, pausing, resuming, restarting, and adjusting parameters; The rule configuration information includes rule information, which includes: inference analysis model ID, model tag ID, and target type to be identified; The rule configuration information includes configuration information, which includes: monitoring policy identifier, monitoring code, priority level, monitoring video stream identifier, video stream configuration information, alarm uploading configuration information, monitoring area, and monitoring time.
[0038] Furthermore, according to one embodiment of the present invention, receiving and parsing control information and rule configuration information of the monitoring strategy includes: The substation inspection visual analysis system acts as an HTTP server, deploys a policy management interface, starts a listening service, and receives request messages for control information and rule configuration information of the monitoring policy in real time. The request message is decoded according to the protocol, and triple verification is performed on the data type, value range, and dependency. After verification, three types of data entities were separated: policy control instructions, rules, and configuration parameters.
[0039] Specifically, in this embodiment, the substation inspection visual analysis system acts as an HTTP server, deploys a policy management interface, starts a listening service, and receives request messages for control information and rule configuration information of the monitoring policy in real time, including: Deploy monitoring policy listening service: Build an HTTP server based on the HTTP protocol, read local service configuration parameters, and bind to a specified IP and port; Start the network listening service: Initialize the network listener service, establish a session and put the received messages into the message queue for processing, and start a multi-threaded listening service to receive external request messages in real time.
[0040] In this embodiment, the request message is decoded according to the protocol, and triple verification of data type, value range, and dependency is performed, including: Message reception and protocol decoding: Based on pre-defined format specifications or custom parsing rules, the received binary data (request message) is converted into a recognizable structured data object; Perform basic verification of the request: Basic verification includes: message structure verification, signature pre-verification, and token verification; Specifically, message structure verification mainly checks the JSON format of Content-Type and Body, as well as the completeness of required fields. Signature pre-verification mainly verifies the existence of signature fields and whether the parameter sorting rules are met. Token verification mainly verifies the existence of the token. Configure parameter validation rule base: implement a triple validation mechanism in sequence for data type, value range, and related dependencies; Specifically, data type validation ensures that each configuration parameter conforms to the expected data format. Strict type checking prevents program errors caused by data type mismatches. Value range validation ensures that configuration parameter values are within a reasonable range. This validation not only prevents the input of illegal values but also improves system stability. Dependency validation ensures that the relationships between multiple configuration parameters are reasonable and consistent. Different monitoring identification type configurations are coupled with monitoring areas and monitoring times, and alarm configurations. Therefore, establishing a dependency validation function between parameters can automatically detect and fix potential problems when setting parameters.
[0041] In this embodiment, after verification, three types of data entities are separated: policy control instructions, rules, and configuration parameters, including: First, the configuration parameters are extracted and their compliance is verified. Second, the rule elements are loaded to build the recognition logic. Third, the control commands (such as start and stop commands) and other parameters are parsed.
[0042] Furthermore, according to one embodiment of the present invention, the monitoring identifier is extracted from the rule information and configuration information, and the monitoring strategy model library is updated based on the monitoring identifier and according to the strategy control instructions, including: The system parses configuration information using custom metadata structures and uses regular expressions to match and extract monitoring identifiers from preset fields. Verify the validity of unique monitoring identifiers and block illegal identifiers that do not conform to the format; verify that the identifier length does not exceed 32 characters and only letters, numbers and underscores are allowed, and block abnormal identifiers containing special characters; A monitoring strategy model is constructed based on three types of data entity information: policy control instructions, rules, and configuration parameters. Based on policy control instructions, a unique binding index is established between the verified monitoring identifier and the corresponding monitoring policy model; Based on the policy control instruction type (create / update / delete), trigger the corresponding action: when a model is added, add the corresponding index associated monitoring policy model to the monitoring policy model library; when a model is updated, synchronously modify the associated monitoring policy model parameter information; when a model is deleted, unbind the monitoring policy model from the monitoring identifier and clean up the corresponding monitoring policy model resources in the monitoring policy model library.
[0043] Furthermore, according to one embodiment of the present invention, a model change signal is triggered based on the updated monitoring strategy model library, and a minimum set of core parameters of the monitoring strategy is selected based on the model change signal, including: When a model in the monitoring strategy model library changes, a model change signal is triggered. Analyze the rule configuration and control information in the model change signals and extract the key information fields; Filter the core parameters that affect the execution of the monitoring strategy from the key information fields, remove redundant or low-impact parameters, and retain the necessary parameter set; The necessary parameter set after screening is standardized in format, and then the minimum set of parameters required for the execution of each monitoring strategy is sent to reduce the data transmission and computational burden.
[0044] Furthermore, according to one embodiment of the present invention, the corresponding rule engine execution unit is loaded according to the monitoring strategy that selects the minimum set of parameters, and the monitoring task corresponding to the monitoring strategy is executed, including: Load the corresponding rule engine execution unit according to the monitoring strategy, and initialize the monitoring task parameters and environment; Parse video stream data and match it with target detection, behavior analysis, or alarm conditions according to preset rules; Output monitoring and analysis results, and trigger corresponding event alarm processing procedures according to alarm policies.
[0045] In this embodiment, the rule engine execution unit includes: Streaming media processing engine: supports real-time streaming media push and pull transmission and encoding / decoding; AI inference engine: Loads new models to perform object detection and behavior analysis; Alarm decision engine: Generates alarm events and triggers handling processes based on rule-configured thresholds.
[0046] Furthermore, according to one embodiment of the present invention, dynamically adjusting the monitoring work of the rule engine execution unit based on the priority of the monitoring task includes: Regularly check the running status of each independent rule engine execution unit that does not interfere with each other, including the current number of tasks, CPU / GPU usage, and memory usage; According to the priority of the monitoring strategy, set the running priority of the corresponding rule engine execution unit to ensure the priority execution of important monitoring tasks and reduce the running frequency of secondary tasks; Adjust the frame extraction frequency of the video stream based on the current system load, reducing computational load under high load and improving analysis accuracy under low load. When certain rule engine execution units are idle or under low load for a long time, release the resources they occupy; Based on the monitoring task execution status and the overall system resource usage, the number of rule engine execution units can be dynamically increased or decreased according to priority.
[0047] According to the above-described solution of the present invention, by decoupling model management from engine execution, the present invention significantly improves the modularity, scalability, and stability of the system. Updates to the monitoring strategy model library and the execution of the rule engine do not interfere with each other, achieving flexibility in resource scheduling and multi-task parallel processing capabilities.
[0048] This invention optimizes system resource utilization and monitoring task execution efficiency through precise monitoring strategy management, an efficient monitoring strategy model library update mechanism, and dynamic rule engine management. It enables flexible parsing and adjustment of monitoring strategies, including key functions such as task priority, video stream processing, and alarm mechanisms, and achieves seamless integration between model and engine execution through a model triggering mechanism. Simultaneously, it dynamically adjusts the working state of the rule engine execution unit based on hardware resource usage, ensuring efficient and stable operation of inspection tasks.
[0049] Furthermore, to achieve the above objectives, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the substation inspection video monitoring strategy management method as described above.
[0050] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the substation inspection video monitoring strategy management method as described above.
[0051] Those skilled in the art will recognize that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0052] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and equipment can be referred to the corresponding process in the foregoing method implementation, and will not be repeated here.
[0053] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.
[0054] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the objectives of the embodiments of the present invention, depending on actual needs.
[0055] In addition, the functional modules in the embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.
[0056] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the sending / receiving methods of various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.
[0057] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in this application.
[0058] It should be understood that the sequence number of each step in the invention and its embodiments does not absolutely imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Claims
1. A method for managing video surveillance strategies during substation inspections, characterized in that, include: The substation inspection visual analysis system receives and parses the control information and rule configuration information of the monitoring strategy. Extract monitoring identifiers from rule information and configuration information, and update the monitoring policy model library based on the monitoring identifiers and policy control instructions; Based on the updated monitoring strategy model library, a model change signal is triggered, and the minimum set of core parameters of the monitoring strategy is selected based on the model change signal. The corresponding rule engine execution unit is loaded based on the monitoring strategy with the smallest set of parameters selected, and the monitoring task of the corresponding monitoring strategy is executed. Based on the priority of monitoring tasks, the monitoring work of the rule engine execution unit is dynamically adjusted.
2. The substation inspection video surveillance strategy management method according to claim 1, characterized in that, The control information of the monitoring strategy includes: policy instance lifecycle management instructions, including control operations for querying the execution status of rule configurations, starting, stopping, pausing, resuming, restarting, and adjusting parameters; The rule configuration information includes rule information, which includes: inference analysis model ID, model tag ID, and target type to be identified; The rule configuration information includes configuration information, which includes: monitoring policy identifier, monitoring code, priority level, monitoring video stream identifier, video stream configuration information, alarm uploading configuration information, monitoring area, and monitoring time.
3. The substation inspection video surveillance strategy management method according to claim 1, characterized in that, The process of receiving and parsing the control information and rule configuration information of the monitoring strategy includes: The substation inspection visual analysis system acts as an HTTP server, deploys a policy management interface, starts a listening service, and receives request messages for control information and rule configuration information of the monitoring policy in real time. The request message is decoded according to the protocol, and triple verification is performed on the data type, value range, and dependency. After verification, three types of data entities were separated: policy control instructions, rules, and configuration parameters.
4. The substation inspection video surveillance strategy management method according to claim 3, characterized in that, The extraction of monitoring identifiers from rule information and configuration information, based on these monitoring identifiers, updates the monitoring policy model library according to policy control instructions, including: The system parses configuration information using custom metadata structures and uses regular expressions to match and extract monitoring identifiers from preset fields. Verify the validity of the monitored identifiers and block illegal identifiers that do not conform to the format; A monitoring strategy model is constructed based on three types of data entity information: policy control instructions, rules, and configuration parameters. Based on policy control instructions, a unique binding index is established between the verified monitoring identifier and the corresponding monitoring policy model; The corresponding action is triggered based on the type of policy control instruction: when a model is added, the corresponding index associated monitoring policy model is added to the monitoring policy model library; when a model is updated, the associated monitoring policy model parameter information is modified synchronously; when a model is deleted, the binding relationship between the monitoring policy model and the monitoring identifier is released, and the corresponding monitoring policy model resources in the monitoring policy model library are cleaned up.
5. The substation inspection video surveillance strategy management method according to claim 1, characterized in that, The step involves triggering a model change signal based on the updated monitoring strategy model library, and then filtering the minimum set of core parameters for the monitoring strategy based on the model change signal, including: When a model in the monitoring strategy model library changes, a model change signal is triggered. Analyze the rule configuration and control information in the model change signals and extract the key information fields; Filter the core parameters that affect the execution of the monitoring strategy from the key information fields, remove redundant or low-impact parameters, and retain the necessary parameter set; The filtered parameters are standardized in format, and then the minimum set of parameters required for the execution of each monitoring strategy is sent.
6. The substation inspection video surveillance strategy management method according to claim 1, characterized in that, The step of loading the corresponding rule engine execution unit based on the monitoring strategy that selects the minimum set of parameters, and executing the monitoring task corresponding to the monitoring strategy, includes: Load the corresponding rule engine execution unit according to the monitoring strategy, and initialize the monitoring task parameters and environment; Parse video stream data and match it with target detection, behavior analysis, or alarm conditions according to preset rules; Output monitoring and analysis results, and trigger corresponding event alarm processing procedures according to alarm policies.
7. The substation inspection video surveillance strategy management method according to any one of claims 1-6, characterized in that, The dynamic adjustment of the monitoring work of the rule engine execution unit based on the priority of monitoring tasks includes: Regularly check the running status of each rule engine execution unit, including the current number of tasks, CPU / GPU usage, and memory usage; According to the priority of the monitoring strategy, set the running priority of the corresponding rule engine execution unit to ensure the priority execution of important monitoring tasks; Adjust the frame dropping frequency of the video stream based on the current system load. When certain rule engine execution units are idle or under low load for a long time, release the resources they occupy; Based on the monitoring task execution status and the overall system resource usage, the number of rule engine execution units can be dynamically increased or decreased according to priority.
8. A substation inspection video surveillance strategy management system, characterized in that, include: The information receiving and parsing module of the substation inspection visual analysis system receives and parses the control information and rule configuration information of the monitoring strategy. The monitoring strategy model library update module extracts monitoring identifiers from rule information and configuration information, and updates the monitoring strategy model library based on the monitoring identifiers and policy control instructions. The monitoring strategy key parameter filtering module triggers a model change signal based on the updated monitoring strategy model library, and then filters the minimum set of core parameters of the monitoring strategy based on the model change signal. The monitoring task execution module loads the corresponding rule engine execution unit based on the monitoring strategy with the smallest set of parameters selected, and executes the monitoring task corresponding to the monitoring strategy. The rule engine execution unit dynamic adjustment module dynamically adjusts the monitoring work of the rule engine execution unit based on the priority of the monitoring tasks.
9. An electronic device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the substation inspection video surveillance strategy management method as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the substation inspection video surveillance strategy management method as described in any one of claims 1-7.