Dynamic scheduling method and device for special operations with spatiotemporal changes based on edge computing

Abstract

This application provides a method and device for dynamic scheduling of special operations based on spatiotemporal changes in edge computing. By collecting spatiotemporal information, the system automatically matches nearby candidate camera groups, determines the task level of the special operation, and evaluates whether the remaining computing power at the current edge end can meet the computing tasks of the currently requested number of candidate camera groups. It dynamically allocates camera resources to ensure coverage of key areas; selects the corresponding hidden danger identification algorithm from the algorithm library, and updates the selected algorithm to the edge all-in-one machine in real time via a wireless network. It can automatically match the corresponding location camera according to the time and place of the special operation, and automatically load and update the corresponding hidden danger identification algorithm to the edge all-in-one machine for the possible hidden danger types. It takes effect immediately without restarting. The algorithm can be dynamically updated, and the cameras to be used can also be dynamically allocated. Users at the application layer can flexibly adjust the configuration at any time without having to change hardware parameters and program configuration.

Description

Technical Field

[0001] The present application relates to the field of edge computing job scheduling technology, and in particular to a method and device for dynamic scheduling of special operations with temporal and spatial changes based on edge computing. Background Art

[0002] During the construction and operation phases of large-scale projects, various special operations are common. These operations are a key focus for risk prevention, but their occurrences can occur at random times and locations. Furthermore, identifying hidden dangers in special operations differs from simple, conventional single-video behavior recognition. For example, identifying hidden dangers in special operations like electric fires and high-altitude operations often requires highly complex algorithms. Edge computing AI all-in-one machines have limited resources, typically connecting to 5-10 cameras. Complex algorithms can be applied concurrently to a limited number of cameras, often fixed, making them inflexible.

[0003] In engineering scenarios with hundreds or even thousands of cameras, the number of integrated machines required to connect all of them is large and the investment is high. In reality, the number of special operations carried out at the same time is relatively small, resulting in idle edge AI computing power.

[0004] Therefore, it is important for technical personnel in this field to design an edge computing method based on the dynamic scheduling video AI algorithm of special operations' temporal and spatial changes, automatically match the corresponding position camera according to the time and place of the special operations, and automatically load and update the corresponding hidden danger identification algorithm into the edge all-in-one machine according to the possible hidden danger types. Summary of the Invention

[0005] In view of this, it is necessary to provide a dynamic scheduling method for special operations with spatiotemporal changes based on edge computing, including: reducing invasiveness, ultrasound-guided precise positioning, reducing errors and complications, being easy to promote and apply, and being relatively simple to operate, suitable for promotion and application in more medical places.

[0006] In a first aspect, an embodiment of the present application provides a method for dynamic scheduling of special operations based on spatiotemporal changes in edge computing, the method comprising:

[0007] S1: Collect spatiotemporal information, obtain the special operation location through GPS or Beidou positioning system, and obtain the current time through the time synchronization system;

[0008] S2: Automatically match nearby candidate camera groups from the edge camera database based on the location and time of the special operation. The edge determines the special operation task level and evaluates whether the current remaining computing power of the edge can meet the computing task of the number of candidate camera groups currently requested based on the candidate camera group call request.

[0009] S3: When the special operation task level is high, if the current remaining computing power at the edge end meets the computing task of the number of candidate camera groups currently requested, camera resources are dynamically allocated to ensure coverage of key areas and provide computing power to complete the current computing task; if not, the task scheduling algorithm is used to schedule nearby available or unload computing resources with low task levels to provide computing power to complete the current computing task, and the resource list is updated;

[0010] S4: When the level of the special operation task is low, if the current remaining computing power at the edge end meets the computing task of the currently requested number of candidate camera groups, camera resources are dynamically allocated to ensure full coverage of the operation area and provide computing power to complete the current computing task; if not, the task scheduling algorithm is used to schedule the remaining computing power and call the computing task of the number of candidate camera groups that meet the remaining computing power, and dynamically allocate camera resources to ensure coverage of the key operation area;

[0011] S5: Detect and identify camera operations using the remaining computing power at the edge. Based on the potential risk type, select a corresponding risk identification algorithm from the algorithm library and update the selected algorithm to the edge device in real time via the wireless network.

[0012] S6: The updated algorithm takes effect immediately without restarting the edge device. The system automatically verifies the algorithm loading status to ensure normal operation. Users can adjust camera allocation and algorithm configuration at any time through the application layer interface. The system provides a visual interface for user monitoring and adjustment.

[0013] Optionally, in another implementation of the first aspect of the present invention, the step S1: collecting spatiotemporal information, obtaining a special operation location through GPS or BeiDou positioning system, and obtaining the current time through a time synchronization system includes:

[0014] Through the GPS or Beidou timing module, the device can obtain the current time and keep time synchronized with other devices;

[0015] Receive satellite signals through the built-in GPS module of the camera device;

[0016] The latitude and longitude information of the current location of the special operation site is calculated in real time by combining the base station and the satellite signal data through a real-time dynamic positioning algorithm, including:

[0017] Receive satellite signals at a base station with known precise coordinates and calculate the error between the observed value and the theoretical value;

[0018] The camera device receives the same satellite signal and the differential correction number from the base station; it uses the differential correction number to correct its own observation value and calculates the high-precision real-time position.

[0019] Optionally, in another implementation of the first aspect of the present invention, the step of determining the level of the special operation task and evaluating whether the remaining computing power of the current edge terminal can meet the number of candidate camera groups currently requested includes:

[0020] Set task priorities based on task urgency, complexity, scale, and impact;

[0021] Evaluate the remaining computing power at the edge from three aspects: hardware resources, task requirements, and real-time status, including:

[0022] Use system monitoring tools to obtain real-time CPU, GPU, and memory usage;

[0023] Estimate the required computing power based on the number of cameras and task type;

[0024] Compare the task requirements with the remaining computing power to determine whether they are met.

[0025] Optionally, in another implementation of the first aspect of the present invention, the task scheduling algorithm is:

[0026] Each task is assigned a time slice of fixed length, and tasks are executed in turn on a first-come, first-served basis;

[0027] Dynamically adjust the time slice length according to system load and task characteristics;

[0028] Determine the priority level of tasks and ensure that high-priority tasks are completed faster;

[0029] When a task's time slice is exhausted, the operating system suspends it and assigns the CPU to the next task.

[0030] Optionally, in another implementation of the first aspect of the present invention, dynamically adjusting the time slice length according to system load and task characteristics includes:

[0031] Build a dynamic time slice adjustment model based on system load, task priority, task execution time, and task response time, and dynamically adjust the time slice length based on system load and task characteristics;

[0032] The model formula is:

[0033] ,

[0034] in, is the length of the time slice after dynamic adjustment, is the basic time slice length, is the current system load, is the maximum load of the system, is the priority of the current task in the system, The highest priority in the system. represents the load adjustment factor, Indicates the priority adjustment factor.

[0035] Optionally, in another implementation of the first aspect of the present invention, S5: detecting and identifying the operation of the camera group using the current remaining computing power of the edge end, selecting a corresponding hidden danger identification algorithm from an algorithm library based on the possible hidden danger type, and updating the selected algorithm to the edge all-in-one machine in real time via a wireless network, including:

[0036] S5.1, Edge End Remaining Computing Power Assessment: Real-time monitoring of the CPU, GPU, and memory resource usage of the edge machine to calculate the remaining computing power; dynamically adjust the detection task allocation of the camera group based on the remaining computing power to ensure optimal utilization of computing power resources; set a computing power usage threshold. When the remaining computing power falls below the threshold, trigger algorithm optimization or task priority adjustment;

[0037] S5.2, Camera Cluster Operation Detection and Hazard Identification: The edge appliance performs real-time analysis of the camera cluster's video streams to detect abnormal behavior or potential hazards in the operation scenario. Based on the detection results, the hazards are classified into different types, including equipment failure, personnel violation, and environmental anomaly. Recognition algorithms corresponding to the hazard type are selected from a pre-set library of algorithms, including target detection, behavior recognition, and anomaly detection.

[0038] S5.3, Algorithm Library and Dynamic Updates: Maintain a versatile hidden danger identification algorithm library in the cloud or locally, covering identification models for various hidden danger scenarios. Select the most suitable algorithm based on the hidden danger type and the remaining computing power at the edge. Transmit the selected algorithm to the edge all-in-one device in real time via wireless network to ensure timely algorithm updates and deployment.

[0039] S5.4, continuous optimization: Dynamically adjust algorithms and task allocation based on detection results and computing power changes, and optimize edge computing power allocation strategies.

[0040] Optionally, in another implementation of the first aspect of the present invention, the optimizing edge computing power allocation strategy includes:

[0041] S5.4.1, Task Priority and Scheduling Optimization: Classify tasks into high-priority and low-priority categories based on their importance and real-time nature. Adopt an intelligent scheduling algorithm to dynamically allocate resources based on task priority and remaining computing power. Implement task migration and load balancing between edge nodes to avoid overloading a single node.

[0042] S5.4.2, Algorithm Lightweighting and Model Optimization: Use lightweight deep learning models to replace complex models to reduce computational overhead; compress models through pruning, quantization, and knowledge distillation techniques to improve inference speed; Dynamic Model Selection: Dynamically switch models of different complexities based on remaining computing power and task requirements;

[0043] S5.4.3, Edge-Cloud Collaboration: Offload some high-computing tasks to the cloud to reduce pressure on the edge; perform data preprocessing at the edge to reduce the amount of data transmitted; and achieve resource complementarity through an edge-cloud collaborative framework.

[0044] S5.4.4, Resource Reservation and Elastic Scaling: Reserve computing resources for core tasks to ensure that critical tasks are not affected; when computing power is insufficient, dynamically expand edge nodes or request cloud resource support; use container technology to achieve rapid deployment and resource isolation.

[0045] In a second aspect, an embodiment of the present application provides a device for dynamically scheduling special operations based on time and space changes based on edge computing, which is applied to the method for dynamically scheduling special operations based on time and space changes based on edge computing as described in the first aspect, and is characterized by including:

[0046] Time and space information acquisition module: collects time and space information, obtains special operation locations through GPS or Beidou positioning system, and obtains current time through time synchronization system;

[0047] Camera preliminary matching module: Automatically matches nearby candidate camera groups from the edge camera database based on the location and time of the special operation. The edge determines the special operation task level and evaluates whether the current remaining computing power of the edge can meet the calculation task of the number of candidate camera groups currently requested based on the candidate camera group call request.

[0048] Remaining computing power evaluation module: When the special operation task level is high, if the current remaining computing power at the edge end meets the computing task of the currently requested number of candidate camera groups, camera resources are dynamically allocated to ensure coverage of key areas and provide computing power to complete the current computing task; if not, the task scheduling algorithm is used to schedule nearby available or unload computing resources with low task levels to provide computing power to complete the current computing task and update the resource list;

[0049] Camera dynamic adjustment module: When the level of the special operation task is low, if the current remaining computing power at the edge end meets the calculation task of the currently requested number of candidate camera groups, camera resources are dynamically allocated to ensure full coverage of the operation area and provide computing power to complete the current calculation task; if it does not meet the requirements, the task scheduling algorithm is used to schedule the calculation tasks of the number of candidate camera groups that meet the remaining computing power, and dynamically allocate camera resources to ensure coverage of the key operation area;

[0050] Hidden danger identification module: This module uses the remaining computing power at the edge to detect and identify camera group operations. Based on the potential hidden danger type, it selects the corresponding hidden danger identification algorithm from the algorithm library and updates the selected algorithm to the edge machine in real time via the wireless network.

[0051] Application layer configuration module: Updated algorithms take effect immediately without restarting the edge device. The system automatically verifies algorithm loading to ensure normal operation. Users can adjust camera allocation and algorithm configuration at any time through the application layer interface. The system provides a visual interface for user monitoring and adjustment.

[0052] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0053] processor;

[0054] a memory for storing processor-executable instructions;

[0055] In which, the processor is configured to implement the dynamic scheduling method for special operations with spatiotemporal changes based on edge computing as described in the first aspect when executing the instructions.

[0056] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a program, and the program instructs a device to execute the dynamic scheduling method for special operations with spatiotemporal changes based on edge computing as described in the first aspect.

[0057] The technical solution provided by the present invention provides a method and device for dynamic scheduling of special operations with spatiotemporal changes based on edge computing. By collecting spatiotemporal information, the special operation location is obtained through GPS or Beidou positioning system, and the current time is obtained through time synchronization system; according to the special operation location and time, the nearby candidate camera groups are automatically matched from the edge camera database, and the edge end judges the special operation task level and evaluates whether the current edge end remaining computing power can meet the computing task of the currently requested number of candidate camera groups based on the candidate camera group call request; in the case of a high special operation task level, if the current edge end remaining computing power meets the computing task of the currently requested number of candidate camera groups, the camera resources are dynamically allocated to ensure coverage of key areas and provide computing power to complete the current computing task; if not, the surrounding available or unloaded computing resources with low task levels are scheduled through the task scheduling algorithm to provide computing power to complete the current computing task and update the resource. Source list; When the level of the special operation task is low, if the current remaining computing power at the edge end meets the calculation task of the currently requested number of candidate camera groups, the camera resources are dynamically allocated to ensure full coverage of the operation area and provide computing power to complete the current calculation task; If it does not meet the requirements, the task scheduling algorithm is used to schedule the remaining computing power and call the calculation tasks of some candidate camera groups that meet the remaining computing power, and dynamically allocate camera resources to ensure coverage of key operation areas; The operation of the camera group is detected and identified through the current remaining computing power at the edge end, and the corresponding hidden danger identification algorithm is selected from the algorithm library according to the possible type of hidden dangers, and the selected algorithm is updated to the edge all-in-one machine in real time through the wireless network; The updated algorithm does not require the edge all-in-one machine to be restarted and takes effect immediately. The system automatically verifies the algorithm loading status to ensure normal operation. Users can adjust the camera allocation and algorithm configuration at any time through the application layer interface. The system provides a visual interface for user monitoring and adjustment.

[0058] Beneficial effects:

[0059] (1) According to the time and place of the special operation, the corresponding location camera is automatically matched. According to the possible hidden danger types, the corresponding hidden danger identification algorithm is automatically loaded and updated into the edge all-in-one machine. No restart is required and it takes effect immediately.

[0060] (2) The algorithm can be updated dynamically, and the cameras to be used can also be dynamically allocated. Users can flexibly adjust the configuration at the application layer at any time without having to change the hardware parameters and program configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A flow chart of a method for dynamic scheduling of special operations with spatiotemporal changes based on edge computing provided in one embodiment of the present application.

[0062] Figure 2A schematic diagram of a module of a dynamic scheduling device for special operations with spatiotemporal changes based on edge computing provided in one embodiment of the present application.

[0063] Figure 3 A schematic diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0065] It should be noted that, in the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art in the art to which this application relates. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0066] It should be noted that, in the embodiments of the present application, words such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order. Features defined as "first" and "second" can explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way.

[0067] Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0068] Example 1

[0069] The present application provides a method for dynamic scheduling of special operations with temporal and spatial changes based on edge computing, comprising the following steps.

[0070] S1: Collect spatiotemporal information, obtain the special operation location through GPS or Beidou positioning system, and obtain the current time through the time synchronization system.

[0071] It is understandable that collecting spatiotemporal information is an important part of modern special operations, especially in scenarios that require precise positioning and real-time time synchronization.

[0072] Specifically, in this embodiment, the step S1: collecting spatiotemporal information, obtaining a special operation location through GPS or BeiDou positioning system, and obtaining the current time through a time synchronization system includes:

[0073] Through the GPS or Beidou timing module, the device can obtain the current time and keep time synchronized with other devices;

[0074] Receive satellite signals through the built-in GPS module of the camera device;

[0075] The latitude and longitude information of the current location of the special operation site is calculated in real time by combining the base station and the satellite signal data through a real-time dynamic positioning algorithm, including:

[0076] Receive satellite signals at a base station with known precise coordinates and calculate the error between the observed value and the theoretical value;

[0077] The camera device receives the same satellite signal and the differential correction number from the base station; it uses the differential correction number to correct its own observation value and calculates the high-precision real-time position.

[0078] It's understandable that GPS (Global Positioning System) and the BeiDou Satellite Navigation System are widely used positioning technologies worldwide, providing highly accurate geographic location information. These systems receive signals from multiple satellites, calculate the time difference between signal propagation, and combine this information with the satellite's position to determine the receiving device's spatial coordinates, including latitude, longitude, and altitude.

[0079] Special operations such as field exploration, emergency rescue, and military operations require real-time access to precise coordinates of the work site. In complex terrain or areas with weak signals, the Beidou system's short message function can facilitate data transmission. On the application side, devices with integrated GPS / Beidou modules (such as cameras and mobile devices) can be used. Combined with mapping software or GIS systems, coordinate information can be visualized, facilitating rapid location of the work site.

[0080] Time synchronization systems are crucial for ensuring the accuracy and consistency of time information during specialized operations. GPS and Beidou satellites not only provide positioning services but also transmit high-precision time signals via atomic clocks. After receiving satellite signals, equipment can synchronize to standard time (such as UTC), typically with an accuracy of nanoseconds. In operations requiring precise time recording (such as event logging and data collection), time synchronization systems ensure the accuracy of timestamps. In multi-device collaborative operations, time synchronization prevents operational errors caused by time discrepancies among devices.

[0081] In this embodiment, a terminal device or a Network Time Protocol (NTP) server that supports time synchronization is used. In an environment without satellite signals, time synchronization can be performed through a local area network or an external clock source.

[0082] Combining location and time information enables more efficient operation management. It records the spatial and temporal information of the work location, facilitating subsequent data analysis and task review. In multi-device collaborative operations, unified spatial and temporal information ensures consistent operation across all devices. Real-time monitoring of workers' spatial and temporal information ensures they remain in safe areas.

[0083] S2: According to the location and time of the special operation, the edge end automatically matches the nearby candidate camera groups from the edge end camera database. The edge end determines the special operation task level and evaluates whether the current remaining computing power of the edge end can meet the computing task of the number of candidate camera groups currently requested based on the candidate camera group call request.

[0084] Specifically, in this embodiment, the calculation task of determining the special operation task level and evaluating whether the current remaining computing power of the edge end can meet the number of candidate camera groups currently requested includes:

[0085] Set task priorities based on task urgency, complexity, scale, and impact;

[0086] Evaluate the remaining computing power at the edge from three aspects: hardware resources, task requirements, and real-time status, including:

[0087] Use system monitoring tools to obtain real-time CPU, GPU, and memory usage;

[0088] Estimate the required computing power based on the number of cameras and task type;

[0089] Compare the task requirements with the remaining computing power to determine whether they are met.

[0090] It is understood that after entering the latitude and longitude coordinates of the special operation site and the current time, the distance to all cameras in the edge camera database is calculated based on the latitude and longitude of the operation site. A distance threshold (such as 500 meters) is set to filter out candidate camera groups closest to the operation site. Based on the current time, cameras that are not operating or are turned off are excluded. Cameras that are running in real time or support remote activation are prioritized. Tasks are classified into different levels (such as low, medium, and high) based on the nature of the special operation. The call priority of the camera group is dynamically adjusted based on the task level.

[0091] Based on the number of candidate camera clusters, calculate the total computing power required for all cameras. Monitor edge resource usage, such as CPU, GPU, and memory, in real time. Compare the total computing power required with the remaining computing power at the edge to determine whether the task requirements are met. If computing power is insufficient, dynamically adjust the number of candidate camera clusters or downgrade the task level.

[0092] Use edge computing platforms (such as KubeEdge and EdgeX Foundry) to manage cameras and computing resources. When computing power is sufficient, you can optimize strategies, such as expanding the candidate camera group to obtain more comprehensive monitoring data. Elevating mid-level or low-level tasks to high-level tasks improves analysis accuracy.

[0093] S3: When the level of the special operation task is high, if the current remaining computing power at the edge end meets the computing task of the number of candidate camera groups currently requested, the camera resources are dynamically allocated to ensure coverage of key areas and provide computing power to complete the current computing task; if not, the task scheduling algorithm is used to schedule the surrounding available or unloaded computing resources with low operation task levels, provide computing power to complete the current computing task, and update the resource list.

[0094] Specifically, in this embodiment, when sufficient computing power is available at the edge, camera resources are dynamically allocated to cover key areas. Specifically, camera resources are prioritized to cover key areas (such as core operating areas and high-risk areas) based on the needs of specialized operations. Spatial analysis algorithms (such as Voronoi diagrams) are used to optimize camera layout to ensure there are no blind spots. Computing power can also be allocated, such as dynamically allocating excess computing power at the edge to candidate camera groups to support high-level tasks (such as real-time video analysis and multi-target tracking). Load balancing technology is used to ensure that each camera has sufficient computing resources.

[0095] After adjusting the camera resources, update the resource list, update the edge resource list, and record the allocated computing power and camera status to facilitate subsequent task scheduling.

[0096] When the remaining computing power at the edge is insufficient, the task scheduling algorithm calls upon available resources in the surrounding area. For example, the edge computing network retrieves available computing resources (such as other edge nodes and cloud servers). Some high-level tasks are offloaded to available resources, alleviating local computing pressure. Low-level tasks can also be freed up by pausing or reducing the computing power allocated to them (such as simple monitoring tasks) through the task scheduling algorithm. The freed-up computing power is then reallocated to high-level tasks to ensure their priority execution. Task offloading and collaboration are also possible, offloading some computing tasks to the cloud or other edge nodes, allowing collaborative computing to complete the high-level tasks. Distributed computing frameworks (such as Kubernetes and Apache Spark) are used to manage task allocation and execution. Finally, the resource list is updated, updating the edge resource list and recording the post-scheduling computing power allocation and task status for subsequent monitoring and adjustment.

[0097] S4: When the level of the special operation task is low, if the current remaining computing power at the edge end meets the computing task of the currently requested number of candidate camera groups, camera resources are dynamically allocated to ensure full coverage of the operation area and provide computing power to complete the current computing task; if it does not meet the requirements, the task scheduling algorithm is used to schedule the remaining computing power and call the computing task of part of the candidate camera groups that meet the remaining computing power, and dynamically allocate camera resources to ensure coverage of the key operation area.

[0098] Specifically, in this embodiment, the task scheduling algorithm is:

[0099] Each task is assigned a time slice of fixed length, and tasks are executed in turn on a first-come, first-served basis;

[0100] Dynamically adjust the time slice length according to system load and task characteristics;

[0101] Determine the priority level of tasks and ensure that high-priority tasks are completed faster;

[0102] When a task's time slice is exhausted, the operating system suspends it and assigns the CPU to the next task.

[0103] It is understood that the dynamic adjustment of the time slice length according to the system load and task characteristics includes:

[0104] Build a dynamic time slice adjustment model based on system load, task priority, task execution time, and task response time, and dynamically adjust the time slice length based on system load and task characteristics;

[0105] The model formula is:

[0106] ,

[0107] in, is the length of the time slice after dynamic adjustment, is the basic time slice length, is the current system load, is the maximum load of the system, is the priority of the current task in the system, The highest priority in the system. represents the load adjustment factor, Indicates the priority adjustment factor.

[0108] S5: Use the remaining computing power at the edge to detect and identify the camera group's operations. Based on the potential hidden danger types, select the corresponding hidden danger identification algorithm from the algorithm library and update the selected algorithm to the edge all-in-one machine in real time via the wireless network.

[0109] Specifically, in this embodiment, S5: detecting and identifying the camera group's operations using the current remaining computing power at the edge end, selecting a corresponding hidden danger identification algorithm from an algorithm library based on the type of potential hidden danger, and updating the selected algorithm to the edge all-in-one machine in real time via a wireless network, includes:

[0110] S5.1, Edge End Remaining Computing Power Assessment: Real-time monitoring of the CPU, GPU, and memory resource usage of the edge machine to calculate the remaining computing power; dynamically adjust the detection task allocation of the camera group based on the remaining computing power to ensure optimal utilization of computing power resources; set a computing power usage threshold. When the remaining computing power falls below the threshold, trigger algorithm optimization or task priority adjustment;

[0111] S5.2, Camera Cluster Operation Detection and Hazard Identification: The edge appliance performs real-time analysis of the camera cluster's video streams to detect abnormal behavior or potential hazards in the operation scenario. Based on the detection results, the hazards are classified into different types, including equipment failure, personnel violation, and environmental anomaly. Recognition algorithms corresponding to the hazard type are selected from a pre-set library of algorithms, including target detection, behavior recognition, and anomaly detection.

[0112] S5.3, Algorithm Library and Dynamic Updates: Maintain a versatile hidden danger identification algorithm library in the cloud or locally, covering identification models for various hidden danger scenarios. Select the most suitable algorithm based on the hidden danger type and the remaining computing power at the edge. Transmit the selected algorithm to the edge all-in-one device in real time via wireless network to ensure timely algorithm updates and deployment.

[0113] S5.4, continuous optimization: Dynamically adjust algorithms and task allocation based on detection results and computing power changes, and optimize edge computing power allocation strategies.

[0114] The strategy for optimizing edge computing power allocation includes:

[0115] S5.4.1, Task Priority and Scheduling Optimization: Classify tasks into high-priority and low-priority categories based on their importance and real-time nature. Adopt an intelligent scheduling algorithm to dynamically allocate resources based on task priority and remaining computing power. Implement task migration and load balancing between edge nodes to avoid overloading a single node.

[0116] S5.4.2, Algorithm Lightweighting and Model Optimization: Use lightweight deep learning models to replace complex models to reduce computational overhead; compress models through pruning, quantization, and knowledge distillation techniques to improve inference speed; Dynamic Model Selection: Dynamically switch models of different complexities based on remaining computing power and task requirements;

[0117] S5.4.3, Edge-Cloud Collaboration: Offload some high-computing tasks to the cloud to reduce pressure on the edge; perform data preprocessing at the edge to reduce the amount of data transmitted; and achieve resource complementarity through an edge-cloud collaborative framework.

[0118] S5.4.4, Resource Reservation and Elastic Scaling: Reserve computing resources for core tasks to ensure that critical tasks are not affected; when computing power is insufficient, dynamically expand edge nodes or request cloud resource support; use container technology to achieve rapid deployment and resource isolation.

[0119] S6: The updated algorithm takes effect immediately without restarting the edge device. The system automatically verifies the algorithm loading status to ensure normal operation. Users can adjust camera allocation and algorithm configuration at any time through the application layer interface. The system provides a visual interface for user monitoring and adjustment.

[0120] Specifically, in this embodiment, algorithm updates and immediate effectiveness can be dynamically loaded using hot update technology, including the use of dynamic link libraries (DLLs) or modular design to support dynamic loading and unloading of algorithms at runtime. There is no need to restart the edge all-in-one device, ensuring continuous system operation. During the update process, the system automatically releases the memory occupied by the old algorithm, loads the new algorithm, and allocates resources. Memory isolation technology is used to avoid memory leaks or conflicts during the update process. After the update is complete, the system automatically switches to the new algorithm to ensure immediate effectiveness. A status monitoring mechanism is used to verify the normal operation of the new algorithm.

[0121] As you can understand, the system has an automatic verification mechanism. After the update is complete, the system automatically performs a health check to verify the integrity and functionality of the algorithm. This includes checking metrics such as memory usage, computing performance, and output results. If verification fails, the system automatically rolls back to the old algorithm and logs the error. An exception notification function is provided to inform users of update failures and the reasons. During the algorithm's operation, the system continuously monitors its status to ensure long-term stable operation.

[0122] Example 2

[0123] like Figure 2 As shown, the present application provides a device for dynamic scheduling of special operations based on edge computing and spatiotemporal changes, which is applied to the method for dynamic scheduling of special operations based on edge computing and spatiotemporal changes as described in Example 1, including: a spatiotemporal information acquisition module 11, a camera preliminary matching module 12, a remaining computing power evaluation module 13, a camera dynamic adjustment module 14, a hidden danger identification module 15, and an application layer configuration module 16.

[0124] It can be understood that, in this embodiment, the spatiotemporal information acquisition module 11 is used to collect spatiotemporal information, obtain the special operation location through the GPS or Beidou positioning system, and obtain the current time through the time synchronization system.

[0125] It can be understood that in this embodiment, the camera preliminary matching module 12 is used to automatically match nearby candidate camera groups from the edge camera database based on the location and time of the special operation. The edge determines the special operation task level and evaluates whether the current remaining computing power of the edge can meet the computing task of the currently requested number of candidate camera groups based on the candidate camera group call request.

[0126] It can be understood that in this embodiment, the remaining computing power evaluation module 13 is used to dynamically allocate camera resources to ensure coverage of key areas and provide computing power to complete the current computing task when the level of the special operation task is high. If the current edge-end remaining computing power meets the computing task of the number of candidate camera groups currently requested, if it does not meet the requirements, the task scheduling algorithm is used to schedule the surrounding available or unload computing resources with low operation task levels to provide computing power to complete the current computing task and update the resource list.

[0127] It can be understood that in this embodiment, the camera dynamic adjustment module 14 is used to dynamically allocate camera resources to ensure full coverage of the operation area and provide computing power to complete the current computing task if the current edge-end remaining computing power meets the computing task of the currently requested number of candidate camera groups when the level of the special operation task is low; if it does not meet the requirements, the task scheduling algorithm is used to schedule the remaining computing power and call the computing task of part of the candidate camera group number that meets the remaining computing power, and dynamically allocate camera resources to ensure coverage of the key operation area.

[0128] It can be understood that in this embodiment, the hidden danger identification module 15 is used to detect and identify the operations of the camera group through the current remaining computing power of the edge end, select the corresponding hidden danger identification algorithm from the algorithm library according to the possible hidden danger type, and update the selected algorithm to the edge all-in-one machine in real time through the wireless network.

[0129] It can be understood that in this embodiment, the application layer configuration module 16 is used for the updated algorithm, and the updated algorithm takes effect immediately without restarting the edge all-in-one machine. The system automatically verifies the algorithm loading status to ensure normal operation. The user can adjust the camera allocation and algorithm configuration at any time through the application layer interface. The system provides a visual interface for user monitoring and adjustment.

[0130] Figure 3 This is an electronic device provided by an embodiment of the present application. Figure 3 As shown, the electronic device includes at least the following parts: a processor 101 and a memory 100 , a communication interface 103 , and a bus 102 .

[0131] In the embodiment of the present application, the memory 100 is used to store instructions executable by the processor 101. The processor 101 is configured to execute the instructions to implement the following Figure 2 The equipment module of the special operation spatiotemporal dynamic scheduling device based on edge computing is shown.

[0132] In an embodiment of the present application, a computer-readable storage medium includes instructions, and the instructions instruct a device to execute the method of the first aspect. For example, the instructions instruct the device to execute Figure 1 The process steps in the figure show a dynamic scheduling method for special operations with temporal and spatial changes based on edge computing.

[0133] The program running in the electronic device involved in one embodiment of the present application can be a program that controls a central processing unit (CPU) and the like to implement the functions of the above-mentioned embodiment involved in one aspect of the present invention (a program that causes a computer to function). The information processed by these devices is temporarily stored in random access memory (RAM) during processing, and then stored in various ROMs such as read-only memory (Flash ROM) and hard disk drives (HDDs), where it is read, modified, and written as needed by the CPU.

[0134] It should be noted that a portion of the electronic device of the above embodiment can also be implemented by a computer. In this case, a program for implementing the control function can be recorded on a computer-readable recording medium and implemented by reading the program recorded on the recording medium into a computer and executing it.

[0135] It should be noted that the "computer" mentioned here refers to a computer built into an electronic device, employing hardware including an operating system (OS) and peripheral devices. Furthermore, "computer-readable recording medium" refers to removable media such as floppy disks, magneto-optical disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into computers.

[0136] Furthermore, a "computer-readable recording medium" may include: a medium that dynamically stores a program for a short period of time, such as a communication line when the program is transmitted via a network such as the Internet or a communication line such as a telephone line; and a medium that stores a program for a fixed period of time, such as volatile memory within a computer serving as a server or client in this case. Furthermore, the program may be a program for implementing a portion of the aforementioned functions, or may be a program that can implement the aforementioned functions by combining with a program already stored in a computer.

[0137] Furthermore, the electronic device in the above-described embodiments can also be implemented as a collection of multiple devices (a device group). Each device comprising the device group can have some or all of the functions or functional blocks of the electronic device in the above-described embodiments. A device group only needs to have all of the functions or functional blocks of the electronic device.

[0138] Those skilled in the art should recognize that the above embodiments are merely intended to illustrate the present application and are not intended to limit the present application. As long as they are within the spirit of the present application, appropriate changes and modifications to the above embodiments are within the scope of protection claimed in the present application.

Claims

1. A method for dynamic scheduling of special operations based on edge computing, characterized by: The method comprises: S1: Collect spatiotemporal information, obtain the special operation location through GPS or Beidou positioning system, and obtain the current time through the time synchronization system; S2: Automatically match nearby candidate camera groups from the edge camera database based on the location and time of the special operation. The edge determines the special operation task level and evaluates whether the current remaining computing power of the edge can meet the computing task of the number of candidate camera groups currently requested based on the candidate camera group call request. S3: When the special operation task level is high, if the current remaining computing power at the edge end meets the computing task of the number of candidate camera groups currently requested, camera resources are dynamically allocated, and the camera layout is optimized through the spatial analysis algorithm Voronoi diagram to ensure coverage of key areas and provide computing power to complete the current computing task. If it is not met, the task scheduling algorithm is used to schedule nearby available or unload computing resources with low task levels to provide computing power to complete the current computing task, and the resource list is updated. S4: When the level of the special operation task is low, if the current remaining computing power at the edge end meets the computing task of the currently requested number of candidate camera groups, camera resources are dynamically allocated to ensure full coverage of the operation area and provide computing power to complete the current computing task; if not, the task scheduling algorithm is used to schedule the remaining computing power and call the computing task of the number of candidate camera groups that meet the remaining computing power, and dynamically allocate camera resources to ensure coverage of the key operation area; S5: Detect and identify camera operations using the remaining computing power at the edge. Based on the potential risk type, select a corresponding risk identification algorithm from the algorithm library and update the selected algorithm to the edge device in real time via the wireless network. S6: Updated algorithms take effect immediately without restarting the edge device. The system automatically verifies algorithm loading to ensure normal operation. Users can adjust camera allocation and algorithm configuration at any time through the application layer interface. The system provides a visual interface for easy monitoring and adjustment. The task scheduling algorithm is: Each task is assigned a time slice of fixed length, and tasks are executed in turn on a first-come, first-served basis; Dynamically adjust the time slice length according to system load and task characteristics; Determine the priority level of tasks and ensure that high-priority tasks are completed faster; When a task's time slice is used up, the operating system suspends it and assigns the CPU to the next task. Dynamically adjusting the time slice length based on system load and task characteristics includes: Build a dynamic time slice adjustment model based on system load, task priority, task execution time, and task response time, and dynamically adjust the time slice length based on system load and task characteristics; The model formula is: ， in, is the length of the time slice after dynamic adjustment, is the basic time slice length, is the current system load, is the maximum load of the system, is the priority of the current task in the system, The highest priority in the system. represents the load adjustment factor, Indicates the priority adjustment factor.

2. The method for dynamic scheduling of special operations based on edge computing according to claim 1 is characterized in that: S1: collecting spatiotemporal information, obtaining the special operation location through GPS or Beidou positioning system, and obtaining the current time through the time synchronization system, including: Through the GPS or Beidou timing module, the device can obtain the current time and keep time synchronized with other devices; Receive satellite signals through the built-in GPS module of the camera device; The latitude and longitude information of the current location of the special operation site is calculated in real time by combining the base station and the satellite signal data through a real-time dynamic positioning algorithm, including: Receive satellite signals at a base station with known precise coordinates and calculate the error between the observed value and the theoretical value; The camera device receives the same satellite signal and the differential correction number from the base station; it uses the differential correction number to correct its own observation value and calculates the high-precision real-time position.

3. The method for dynamic scheduling of special operations based on edge computing according to claim 2 is characterized in that: The calculation task of determining the level of the special operation task and evaluating whether the remaining computing power of the current edge end can meet the number of candidate camera groups currently requested includes: Set task priorities based on task urgency, complexity, scale, and impact; Evaluate the remaining computing power at the edge from three aspects: hardware resources, task requirements, and real-time status, including: Use system monitoring tools to obtain real-time CPU, GPU, and memory usage; Estimate the required computing power based on the number of cameras and task type; Compare the task requirements with the remaining computing power to determine whether they are met.

4. The method for dynamic scheduling of special operations based on edge computing according to claim 1 is characterized in that: S5: Detecting and identifying the camera group's operations using the current remaining computing power at the edge end, selecting a corresponding hidden danger identification algorithm from the algorithm library based on the possible hidden danger type, and updating the selected algorithm to the edge all-in-one machine in real time via the wireless network, including: S5.1, Edge End Remaining Computing Power Assessment: Real-time monitoring of the CPU, GPU, and memory resource usage of the edge machine to calculate the remaining computing power; dynamically adjust the detection task allocation of the camera group based on the remaining computing power to ensure optimal utilization of computing power resources; set a computing power usage threshold. When the remaining computing power falls below the threshold, trigger algorithm optimization or task priority adjustment; S5.2, Camera Cluster Operation Detection and Hazard Identification: The edge appliance performs real-time analysis of the camera cluster's video streams to detect abnormal behavior or potential hazards in the operation scenario. Based on the detection results, the hazards are classified into different types, including equipment failure, personnel violation, and environmental anomaly. Recognition algorithms corresponding to the hazard type are selected from a pre-set library of algorithms, including target detection, behavior recognition, and anomaly detection. S5.3, Algorithm Library and Dynamic Updates: Maintain a versatile hidden danger identification algorithm library in the cloud or locally, covering identification models for various hidden danger scenarios. Select the most suitable algorithm based on the hidden danger type and the remaining computing power at the edge. Transmit the selected algorithm to the edge all-in-one device in real time via wireless network to ensure timely algorithm updates and deployment. S5.4, continuous optimization: Dynamically adjust algorithms and task allocation based on detection results and computing power changes, and optimize edge computing power allocation strategies.

5. The method for dynamic scheduling of special operations based on edge computing according to claim 4 is characterized in that: The strategy for optimizing edge computing power allocation includes: S5.4.1, Task Priority and Scheduling Optimization: Classify tasks into high-priority and low-priority categories based on their importance and real-time nature. Adopt an intelligent scheduling algorithm to dynamically allocate resources based on task priority and remaining computing power. Implement task migration and load balancing between edge nodes to avoid overloading a single node. S5.4.2, Algorithm Lightweighting and Model Optimization: Use lightweight deep learning models to replace complex models to reduce computational overhead; compress models through pruning, quantization, and knowledge distillation techniques to improve inference speed; Dynamic Model Selection: Dynamically switch models of different complexities based on remaining computing power and task requirements; S5.4.3, Edge-Cloud Collaboration: Offload some high-computing tasks to the cloud to reduce pressure on the edge; perform data preprocessing at the edge to reduce the amount of data transmitted; and achieve resource complementarity through an edge-cloud collaborative framework. S5.4.4, Resource Reservation and Elastic Scaling: Reserve computing resources for core tasks to ensure that critical tasks are not affected; when computing power is insufficient, dynamically expand edge nodes or request cloud resource support; use container technology to achieve rapid deployment and resource isolation.

6. A device for dynamic scheduling of special operations with spatiotemporal changes based on edge computing, applied to the method for dynamic scheduling of special operations with spatiotemporal changes based on edge computing according to any one of claims 1 to 5, characterized in that: include: Time and space information acquisition module: collects time and space information, obtains special operation locations through GPS or Beidou positioning system, and obtains current time through time synchronization system; Camera preliminary matching module: Automatically matches nearby candidate camera groups from the edge camera database based on the location and time of the special operation. The edge determines the special operation task level and evaluates whether the current remaining computing power of the edge can meet the calculation task of the number of candidate camera groups currently requested based on the candidate camera group call request. Remaining computing power evaluation module: When the special operation task level is high, if the current remaining computing power at the edge end meets the computing task of the currently requested number of candidate camera groups, camera resources are dynamically allocated to ensure coverage of key areas and provide computing power to complete the current computing task; if not, the task scheduling algorithm is used to schedule nearby available or unload computing resources with low task levels to provide computing power to complete the current computing task and update the resource list; Camera dynamic adjustment module: When the level of the special operation task is low, if the current remaining computing power at the edge end meets the computing task of the currently requested number of candidate camera groups, camera resources are dynamically allocated to ensure full coverage of the operation area and provide computing power to complete the current computing task; If it is not met, the task scheduling algorithm will be used to schedule the computing tasks of the candidate camera groups that meet the remaining computing power, and dynamically allocate camera resources to ensure coverage of key operation areas; Hidden danger identification module: This module uses the remaining computing power at the edge to detect and identify camera group operations. Based on the potential hidden danger type, it selects the corresponding hidden danger identification algorithm from the algorithm library and updates the selected algorithm to the edge machine in real time via the wireless network. Application layer configuration module: Updated algorithms take effect immediately without restarting the edge device. The system automatically verifies algorithm loading to ensure normal operation. Users can adjust camera allocation and algorithm configuration at any time through the application layer interface. The system provides a visual interface for user monitoring and adjustment.

7. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the dynamic scheduling method for special operations with spatiotemporal changes based on edge computing as described in any one of claims 1 to 5 when executing the instructions.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, and the program instructs the device to execute the dynamic scheduling method for special operations with spatiotemporal changes based on edge computing as described in any one of claims 1 to 5.

Images