Cloud edge-end cooperative processing system based on network computing technology

Abstract

The invention relates to a cloud side-end cooperative processing system based on a network computing technology. A cloud computing platform is used for storage of large-scale data and training of a deep learning model; the edge computing node module is used for receiving the data stream from the end side equipment and processing the data stream in real time; the end side equipment is used for collecting environmental data and primarily processing the environmental data, and the end side equipment comprises one or more of an unmanned aerial vehicle, an unmanned vehicle and an unmanned ship; the cloud edge-end cooperation module is used for efficient communication and calculation cooperation among the cloud, the edge and the end-side equipment; and the task scheduling and resource allocation module is used for scheduling and allocating calculation tasks in real time according to current task requirements, resource states and network conditions. According to the invention, the overall operation efficiency and real-time performance of the cloud side-end cooperative processing system can be improved, and the defects of the existing system in the aspects of processing capability and task scheduling are overcome.

Description

Technical Field

[0001] The present invention relates to the field of unmanned system technology, and in particular to a cloud-edge-end collaborative processing system based on network computing technology. Background Art

[0002] Current unmanned systems have significant deficiencies in cloud-edge-end collaboration. Many systems still rely on independent cloud computing or edge computing and lack a unified scheduling mechanism, resulting in unbalanced resource usage. This independent operation mode often fails to achieve efficient resource allocation, making the system prone to resource waste or shortage when processing tasks, affecting overall performance and efficiency. In addition, the existing task allocation model is usually relatively fixed and cannot be flexibly adjusted according to real-time network conditions and device resources. This inflexible task allocation mechanism may lead to inefficient task execution in complex environments and inability to fully utilize available resources. When the system cannot adjust task allocation in real time to adapt to changing network conditions and resource conditions, the speed and quality of task processing will be affected, affecting the overall performance and reliability of the unmanned system.

[0003] Therefore, the key to improving the cloud-edge collaboration capabilities of unmanned systems lies in introducing intelligent scheduling mechanisms and flexible task allocation strategies to achieve optimal resource utilization and efficient task execution, thereby making up for the shortcomings of existing systems and promoting the application and development of unmanned systems in complex environments. Summary of the invention

[0004] In order to solve the technical problems existing in the above-mentioned prior art, the purpose of the present invention is to provide a cloud-edge-end collaborative processing system based on network computing technology, which can improve the overall operating efficiency and real-time performance of the cloud-edge-end collaborative processing system, make up for the shortcomings of the existing system in processing power and task scheduling, enhance the response speed of the system, improve the task execution capability in complex environments, and promote the intelligent and efficient development of unmanned systems.

[0005] To achieve the above-mentioned invention object, the present invention provides a cloud-edge-end collaborative processing system based on network computing technology, including a cloud computing platform, an edge computing node module, an end-side device, a cloud-edge-end collaborative module, and a task scheduling and resource allocation module;

[0006] The cloud computing platform is used for storing large-scale data and training deep learning models;

[0007] The edge computing node module is used to receive the data stream from the terminal device and perform real-time processing;

[0008] The terminal side device is used for collecting environmental data and preliminarily processing the environmental data, and the terminal side device includes one or more of a drone, an unmanned vehicle, and an unmanned ship;

[0009] The cloud-edge-device collaboration module is used for efficient communication and computing collaboration between cloud, edge and device devices;

[0010] The task scheduling and resource allocation module is used to schedule and allocate computing tasks in real time according to current task requirements, resource status and network conditions.

[0011] According to a technical solution of the present invention, the cloud computing platform includes:

[0012] A data storage module, used to store large-scale data from the edge computing node module and the terminal device;

[0013] A deep learning training module, used to train a machine learning model and perform reasoning in the edge computing node module and the end-side device;

[0014] Global task scheduling module, used to dynamically allocate computing tasks based on real-time data and task requirements;

[0015] The cloud computing platform processes complex analysis tasks through high-performance computing resources, and sends the results and models to the edge computing node module and the terminal device.

[0016] According to a technical solution of the present invention, the edge computing node module includes:

[0017] A real-time data processing module, used for receiving and processing environmental data from the terminal device;

[0018] A local decision module, used to make real-time decisions based on the instructions issued by the cloud computing platform and the local processing results;

[0019] The data forwarding module is used to feed back the processed data and decision results to the cloud computing platform or transmit them to other edge computing nodes.

[0020] According to a technical solution of the present invention, the terminal side device includes:

[0021] A sensor module, used to collect environmental information, wherein the environmental information includes at least images, sounds, and temperature;

[0022] Data processing module, used for preliminary processing and feature extraction of the collected raw data;

[0023] The communication module is used to send the preliminarily processed data to the edge computing node module.

[0024] According to a technical solution of the present invention, the cloud-edge-end collaboration module realizes efficient communication and computing collaboration by configuring a dynamic task allocation algorithm and a data flow control strategy.

[0025] A dynamic task allocation algorithm is used to dynamically adjust the allocation of tasks according to the real-time requirements of the tasks and the computing capabilities of the cloud computing platform, the edge computing node module, and the terminal device;

[0026] The data flow control strategy is used to optimize the data transmission path between the cloud computing platform, the edge computing node module, and the terminal device to reduce delay and bandwidth consumption.

[0027] According to a technical solution of the present invention, the cloud-edge-device collaboration module includes:

[0028] The CloudCore module is responsible for managing the computing resources of the cloud computing platform, scheduling tasks and monitoring the running status;

[0029] The EdgeCore module is responsible for managing the resources of the edge computing node module, executing local tasks and interacting with the cloud computing platform for data;

[0030] The cloud-edge collaboration module uses containerization technology to enable the cloud computing platform and the edge computing node module to achieve flexible resource management and task scheduling.

[0031] According to a technical solution of the present invention, the cloud-edge-device collaboration module further includes:

[0032] A service management module, used to manage and coordinate various services on the edge computing node module;

[0033] The data acquisition module is used to collect data from the terminal device and perform preliminary processing.

[0034] According to a technical solution of the present invention, the task scheduling and resource allocation module includes:

[0035] Task priority management module dynamically adjusts the priority of task execution according to the urgency of the task and resource consumption;

[0036] The real-time feedback module monitors the system status in real time and responds quickly to emergencies and changing requirements.

[0037] According to a technical solution of the present invention, the task scheduling and resource allocation module further includes:

[0038] A prediction module based on machine learning, used to predict task execution time and resource consumption;

[0039] The dynamic resource allocation module intelligently adjusts resource allocation based on prediction results and real-time feedback.

[0040] According to a technical solution of the present invention, the task scheduling and resource allocation module is configured with:

[0041] Multi-task scheduling strategy, reasonably arrange the execution of multiple tasks at the same time to reduce idle resources;

[0042] Adaptive adjustment mechanism dynamically adjusts the task execution strategy according to changes in network conditions and resource status.

[0043] By adopting the technical solution of the present invention, the overall performance of the unmanned system can be effectively improved. Compared with the prior art, the present invention has the following beneficial effects:

[0044] First, the system collaboration efficiency has been significantly improved. Based on the collaborative working mechanism of the cloud computing platform module, edge computing node module and terminal equipment, the system can dynamically allocate computing resources according to the actual needs of specific tasks. This intelligent resource allocation method reduces the delay of data during transmission, greatly improves the real-time response capability of the unmanned system, and ensures the timely execution of tasks. Especially in the face of complex and changing task scenarios, the cloud-edge-end collaboration module can effectively improve the flexibility and response speed of the system and adapt to various network environments and computing needs.

[0045] Secondly, the processing power of the end-side device is fully utilized. By preprocessing the data on the end-side device, the system can reduce the amount of data uploaded to the cloud computing platform module, thereby reducing the pressure on the network bandwidth. This not only reduces unnecessary data transmission, but also improves the processing efficiency of tasks, which is particularly critical in task environments with high bandwidth requirements. The end-side device can perform preliminary calculations and analysis, and transmit the processed key data to the edge computing node module or the cloud computing platform module, greatly speeding up the execution of tasks.

[0046] Finally, the system adopts a unified task scheduling and resource allocation mechanism. Through intelligent scheduling algorithms, the cloud computing platform module can coordinate the task execution process of the edge computing node module and the terminal device. The task scheduling center monitors and manages resource usage in real time, avoiding resource waste and ensuring that tasks can be reasonably allocated among the computing nodes. This mechanism not only optimizes resource utilization, but also improves the overall operating efficiency of the system, allowing the unmanned system to operate efficiently and stably in a multi-task environment.

[0047] In general, it can improve the overall operating efficiency and real-time performance of the cloud-edge collaborative processing system, make up for the shortcomings of the existing system in processing power and task scheduling, enhance the system's response speed, improve the task execution capability in complex environments, and promote the intelligent and efficient development of unmanned systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 A schematic diagram schematically shows the composition of a cloud-edge-device collaborative processing system based on network computing technology provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the cloud-edge-end collaborative processing system architecture based on network computing technology provided by an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0051] The description of the embodiments of this specification should be combined with the corresponding drawings, which should be considered as part of the complete specification. In the drawings, the shape or thickness of the embodiments may be enlarged and indicated for simplification or convenience. Furthermore, the parts of each structure in the drawings will be described separately. It is worth noting that the elements not shown in the drawings or not described in words are in a form known to ordinary technicians in the relevant technical field.

[0052] The description of the embodiments herein and any reference to directions and orientations are only for the convenience of description and are not to be construed as any limitation on the scope of protection of the present invention. The following description of the preferred embodiments may involve combinations of features, which may exist independently or in combination, and the present invention is not particularly limited to the preferred embodiments. The scope of the present invention is defined by the claims.

[0053] like Figure 1 and Figure 2 As shown, the present invention proposes a cloud-edge-end collaborative processing system based on network computing technology, including a cloud computing platform, an edge computing node module, a terminal device, a cloud-edge-end collaborative module, and a task scheduling and resource allocation module;

[0054] The cloud computing platform is used for storing large-scale data and training deep learning models;

[0055] The edge computing node module is used to receive the data stream from the terminal device and perform real-time processing;

[0056] The terminal side device is used for collecting environmental data and preliminarily processing the environmental data, and the terminal side device includes one or more of a drone, an unmanned vehicle, and an unmanned ship;

[0057] The cloud-edge-device collaboration module is used for efficient communication and computing collaboration between cloud, edge and device devices;

[0058] The task scheduling and resource allocation module is used to schedule and allocate computing tasks in real time according to current task requirements, resource status and network conditions.

[0059] By introducing intelligent scheduling mechanisms and flexible task allocation strategies, we can make up for the problems of unbalanced resource use and inefficient task execution. Through a unified scheduling system, the cloud-edge-end collaborative processing system can optimize resource utilization, thereby improving the task execution capabilities of unmanned systems (drones, unmanned vehicles, and unmanned ships) in complex environments. At the same time, the flexible task allocation mechanism enables the system to dynamically adjust according to real-time network conditions and device resources to ensure the speed and quality of task processing. This will significantly improve the overall performance and reliability of unmanned systems and promote their development in various complex application scenarios.

[0060] In some embodiments of the present invention, the cloud computing platform includes:

[0061] A data storage module, used to store large-scale data from the edge computing node module and the terminal device;

[0062] A deep learning training module, used to train a machine learning model and perform reasoning in the edge computing node module and the end-side device;

[0063] Global task scheduling module, used to dynamically allocate computing tasks based on real-time data and task requirements;

[0064] The cloud computing platform processes complex analysis tasks through high-performance computing resources, and sends the results and models to the edge computing node module and the terminal device.

[0065] In the cloud-edge-device architecture of unmanned systems, the cloud computing platform is used for large-scale data storage and deep learning model training. The cloud computing platform uses powerful computing resources to process massive amounts of data and train efficient deep learning models, which are then sent to edge and device devices for practical application. In addition to model training, the cloud computing platform also undertakes the global scheduling of tasks. It is responsible for analyzing data in the system, making global decisions, and coordinating computing tasks at all levels. This global scheduling function enables the cloud to effectively manage and optimize high-computation tasks to ensure that system resources are optimally configured.

[0066] This design of the cloud computing platform fully utilizes its powerful computing power and storage resources to handle complex data analysis and model training tasks. At the same time, by sending the trained model to the edge and end devices, the cloud ensures that the model can be applied in various practical application scenarios, thereby improving the overall performance and responsiveness of the system. This mode of centralizing high-computation tasks and global scheduling in the cloud not only ensures efficient data processing, but also improves the system's task execution capabilities in complex environments, providing a solid foundation for the intelligence and efficiency of unmanned systems.

[0067] In some embodiments of the present invention, the edge computing node module includes:

[0068] A real-time data processing module, used for receiving and processing environmental data from the terminal device;

[0069] A local decision module, used to make real-time decisions based on the instructions issued by the cloud computing platform and the local processing results;

[0070] The data forwarding module is used to feed back the processed data and decision results to the cloud computing platform or transmit them to other edge computing nodes.

[0071] Edge computing node modules play an important role in the cloud-edge architecture of unmanned systems. They are located at the edge of the network and are used to receive data streams from end-side devices and perform real-time processing. These edge computing node modules can perform preliminary data processing tasks near the data generation location, significantly reduce data transmission delays, and respond to the needs of end-side devices in a timely manner. By processing data locally, edge computing node modules not only improve the real-time performance of the system, but also reduce the computing pressure of the cloud computing platform module.

[0072] In terms of task execution, the edge computing node module makes local decisions based on the task instructions issued by the cloud computing platform module. This local decision-making capability enables the edge computing node module to quickly respond to dynamically changing environments and data inputs, and perform necessary computing tasks without frequently relying on the cloud computing platform module. This distributed processing method optimizes the use of computing resources and improves the overall efficiency of the system.

[0073] With the help of network computing technology, edge computing node modules can dynamically adjust their computing power to adapt to different task requirements and network conditions. This dynamic adjustment capability enables edge computing node modules to optimize the allocation of computing resources according to actual load and network conditions, and achieve efficient collaboration among multiple nodes. Through network computing technology, edge computing node modules can not only flexibly respond to changing task loads, but also collaborate with other edge computing node modules to jointly complete complex computing tasks.

[0074] The edge computing node module greatly improves the system's response speed and computing efficiency through real-time data processing and local decision-making functions in unmanned systems. The application of network computing technology further enhances the flexibility and coordination ability of the edge computing node module, making the entire system more efficient and intelligent in processing data and executing tasks. This design effectively reduces the computing burden of the cloud computing platform module, while improving the overall performance and reliability of the system in complex environments.

[0075] In some embodiments of the present invention, the terminal side device includes:

[0076] A sensor module, used to collect environmental information, wherein the environmental information includes at least images, sounds, and temperature;

[0077] Data processing module, used for preliminary processing and feature extraction of the collected raw data;

[0078] The communication module is used to send the preliminarily processed data to the edge computing node module.

[0079] In the cloud-edge-end architecture of unmanned systems, end-side devices, including drones, unmanned vehicles, and unmanned ships, play a vital role in the system. Although the computing power of these end-side devices is relatively limited, they are able to perform some basic task processing, especially in environmental perception, data collection, and preliminary signal processing. End-side devices are responsible for acquiring and processing environmental data in real time, such as collecting surrounding images, sounds, and other sensory information through sensors. During the data collection process, these end-side devices also perform preliminary signal processing to extract useful information and perform preliminary analysis.

[0080] By collaborating with the edge computing node module, the end-side device can complete the preprocessing of some tasks while collecting data. This collaborative mechanism enables the end-side device to not only perform basic tasks independently, but also transmit the preprocessed data to the edge computing node module. The edge computing node module further processes this data and performs more complex computing tasks, thereby reducing the burden of data transmission and improving the processing efficiency of the entire system. This pre-processing capability of the end-side device and the subsequent processing capability of the edge computing node module form an effective cooperative relationship, ensuring the efficient operation of the system.

[0081] Through the close collaboration between the end-side devices and the edge computing node modules, the entire system can achieve more efficient data processing and task execution. This processing mode with clear division of labor not only improves the real-time response capability of the system, but also optimizes the utilization of computing resources, allowing the unmanned system to operate more flexibly and efficiently in various application scenarios.

[0082] In some embodiments of the present invention, the cloud-edge-end collaboration module realizes efficient communication and computing collaboration by configuring a dynamic task allocation algorithm and a data flow control strategy.

[0083] A dynamic task allocation algorithm is used to dynamically adjust the allocation of tasks according to the real-time requirements of the tasks and the computing capabilities of the cloud computing platform, the edge computing node module, and the terminal device;

[0084] The data flow control strategy is used to optimize the data transmission path between the cloud computing platform, the edge computing node module, and the terminal device to reduce delay and bandwidth consumption.

[0085] In some embodiments of the present invention, the cloud-edge-end collaboration module includes:

[0086] The CloudCore module is used to manage the computing resources of the cloud computing platform, schedule tasks and monitor the running status;

[0087] EdgeCore module, used to manage the resources of the edge computing node module, execute local tasks and interact with the cloud computing platform for data;

[0088] The cloud-edge collaboration module uses containerization technology to enable the cloud computing platform and the edge computing node module to achieve flexible resource management and task scheduling.

[0089] In some embodiments of the present invention, the cloud-edge-end collaboration module further includes:

[0090] A service management module, used to manage and coordinate various services on the edge computing node module;

[0091] The data acquisition module is used to collect data from the terminal device and perform preliminary processing.

[0092] The cloud-edge-end collaboration module uses network computing technology (including network slicing, distributed computing, dynamic resource allocation, etc.) to achieve efficient communication and computing collaboration between the cloud computing platform module, edge computing node module and end-side devices. The system dynamically allocates tasks to the cloud computing platform module, edge computing node module or end-side device for execution based on the complexity and real-time requirements of the tasks, making full use of computing resources at different levels. Cloud-edge-end collaboration includes cloud-edge collaboration, edge-end collaboration and cloud-edge-end collaboration:

[0093] (1) Cloud-edge collaboration: The cloud computing platform module serves as the control plane, and the edge computing node module serves as the computing platform. The cloud computing platform module and the edge computing node module work together to achieve efficient data processing and transmission. The specific implementation methods include: Kubernetes control node and KubeEdge running node jointly implemented. Based on the Kubernetes control node, KubeEdge realizes the sinking of cloud computing orchestration containerized applications through CloudCore of the cloud computing platform module and EdgeCore of the edge computing node module.

[0094] (2) Edge-end collaboration: Manage services on the edge devices as edge loads. Collaborate with the edge devices through edge solutions such as EdgeXFoundry to achieve device control and data collection.

[0095] (3) Cloud-edge-device collaboration: Based on cloud-edge collaboration, the services of the end-side devices are further managed. The cloud computing platform module can influence the end-side devices by controlling the edge computing node module, thereby achieving comprehensive collaboration among the cloud, edge, and end.

[0096] The technical principle of the cloud-edge-end collaboration module is based on the collaborative work between cloud computing, edge computing, and end-side devices. Specifically, the cloud-edge-end collaboration module utilizes the powerful computing power and data storage capabilities of cloud computing, as well as the low latency and high reliability characteristics of edge computing, to migrate part of the computing tasks from end-side devices to edge computing node modules, thereby achieving more efficient, faster, and more reliable computing services.

[0097] In cloud-edge-end collaborative technology, the cloud computing platform module serves as the central control plane for global management and scheduling; the edge computing node module serves as the computing platform for local computing and storage; the end-side device serves as the perception and execution unit, responsible for receiving instructions and executing corresponding operations. Through the collaborative work of cloud computing and edge computing, rapid processing and transmission of data points can be achieved while ensuring data security and privacy.

[0098] The principles of the cloud-edge-device collaboration module mainly include the following aspects:

[0099] Data collection and processing: Various data, including sensor data, video data, etc., are collected through the terminal devices, and the data are transmitted to the edge computing node module for processing.

[0100] Edge computing: After receiving the data, the edge computing node module performs real-time processing and analysis and returns the results to the end-side device. Edge computing can greatly reduce the burden on the cloud computing platform module and reduce network transmission costs.

[0101] Cloud computing: The cloud computing platform module serves as the central control plane, responsible for global management and scheduling. The cloud computing platform module can manage and control the edge computing node modules to achieve optimal configuration of global resources.

[0102] End-side devices: As perception and execution units, end-side devices are responsible for receiving instructions and performing corresponding operations. End-side devices can be various smart terminals, such as smart home devices and smart wearable devices.

[0103] Network transmission: Connect the terminal devices, edge computing node modules and cloud computing platform modules through the network to realize the transmission and processing of data information.

[0104] In short, the cloud-edge-end collaborative module is a new type of distributed computing model. Through the collaborative work of cloud computing, edge computing, and end-side devices, more efficient, faster, and more reliable computing services can be achieved.

[0105] In some embodiments of the present invention, the task scheduling and resource allocation module includes:

[0106] Task priority management module dynamically adjusts the priority of task execution according to the urgency of the task and resource consumption;

[0107] The real-time feedback module monitors the system status in real time and responds quickly to emergencies and changing requirements.

[0108] In some embodiments of the present invention, the task scheduling and resource allocation module further includes:

[0109] A prediction module based on machine learning, used to predict task execution time and resource consumption;

[0110] The dynamic resource allocation module intelligently adjusts resource allocation based on prediction results and real-time feedback.

[0111] In some embodiments of the present invention, the task scheduling and resource allocation module is configured with:

[0112] Multi-task scheduling strategy, reasonably arrange the execution of multiple tasks at the same time to reduce idle resources;

[0113] Adaptive adjustment mechanism dynamically adjusts the task execution strategy according to changes in network conditions and resource status.

[0114] In unmanned systems, intelligent task scheduling and resource allocation modules play a vital role. With the widespread application of drones, unmanned vehicles and other equipment in various tasks, the diversification and complexity of task requirements make task scheduling extremely challenging. In order to cope with this complexity, the system needs to schedule and allocate computing tasks in real time according to the current task requirements, resource status and network conditions to ensure efficient execution of tasks.

[0115] Using machine learning algorithms is one of the important ways to improve scheduling efficiency. By analyzing historical data, machine learning algorithms can predict task execution time and resource consumption, which enables the system to allocate computing resources more accurately when facing different tasks. For example, when resources are limited, the system can prioritize computing power to tasks with shorter predicted execution times or less resource consumption to ensure the smooth operation of the overall task chain. In addition, based on real-time data feedback, the system can dynamically adjust task scheduling to adapt to changing network conditions and resource status, thereby further improving task execution efficiency.

[0116] The intelligent scheduling and resource allocation module can not only optimize resource utilization, but also reduce task delays and improve the overall response speed of the system. With the continuous optimization of the algorithm and the increase in data volume, the scheduling system can more accurately predict future resource requirements, reduce overload and resource waste. This efficient resource allocation model not only ensures the completion of tasks on time, but also greatly improves the overall performance of the unmanned system, providing strong support for automation systems in multi-task environments.

[0117] The serial numbers of the above-mentioned steps involved in the method of the present invention do not mean the order of execution of the method. The execution order of each step should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation mode of the present invention.

[0118] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cloud-edge-end collaborative processing system based on network computing technology, characterized in that: It includes cloud computing platform, edge computing node module, terminal equipment, cloud-edge-terminal collaboration module, task scheduling and resource allocation module; The cloud computing platform is used for storing large-scale data and training deep learning models; The edge computing node module is used to receive the data stream from the terminal device and perform real-time processing; The terminal side device is used for collecting environmental data and preliminarily processing the environmental data, and the terminal side device includes one or more of a drone, an unmanned vehicle, and an unmanned ship; The cloud-edge-device collaboration module is used for efficient communication and computing collaboration between cloud, edge and device devices; The task scheduling and resource allocation module is used to schedule and allocate computing tasks in real time according to current task requirements, resource status and network conditions.

2. The system according to claim 1, characterized in that The cloud computing platform includes: A data storage module, used to store large-scale data from the edge computing node module and the terminal device; A deep learning training module, used to train a machine learning model and perform reasoning in the edge computing node module and the end-side device; Global task scheduling module, used to dynamically allocate computing tasks based on real-time data and task requirements; The cloud computing platform processes complex analysis tasks through high-performance computing resources, and sends the results and models to the edge computing node module and the terminal device.

3. The system according to claim 1, characterized in that The edge computing node module includes: A real-time data processing module, used for receiving and processing environmental data from the terminal device; A local decision module, used to make real-time decisions based on the instructions issued by the cloud computing platform and the local processing results; The data forwarding module is used to feed back the processed data and decision results to the cloud computing platform or transmit them to other edge computing nodes.

4. The system according to claim 1, characterized in that The terminal side device includes: A sensor module, used to collect environmental information, wherein the environmental information includes at least images, sounds, and temperature; Data processing module, used for preliminary processing and feature extraction of the collected raw data; The communication module is used to send the preliminarily processed data to the edge computing node module.

5. The system according to claim 1, characterized in that The cloud-edge-end collaboration module realizes efficient communication and computing collaboration by configuring dynamic task allocation algorithms and data flow control strategies. A dynamic task allocation algorithm is used to dynamically adjust the allocation of tasks according to the real-time requirements of the tasks and the computing capabilities of the cloud computing platform, the edge computing node module, and the terminal device; The data flow control strategy is used to optimize the data transmission path between the cloud computing platform, the edge computing node module, and the terminal device to reduce delay and bandwidth consumption.

6. The system according to claim 1, characterized in that The cloud-edge-end collaboration module includes: The CloudCore module is responsible for managing the computing resources of the cloud computing platform, scheduling tasks and monitoring the running status; The EdgeCore module is responsible for managing the resources of the edge computing node module, executing local tasks and interacting with the cloud computing platform for data; The cloud-edge collaboration module uses containerization technology to enable the cloud computing platform and the edge computing node module to achieve flexible resource management and task scheduling.

7. The system according to claim 6, characterized in that The cloud-edge-end collaboration module also includes: A service management module, used to manage and coordinate various services on the edge computing node module; The data acquisition module is used to collect data from the terminal device and perform preliminary processing.

8. The system according to claim 1, characterized in that The task scheduling and resource allocation module includes: Task priority management module dynamically adjusts the priority of task execution according to the urgency of the task and resource consumption; The real-time feedback module monitors the system status in real time and responds quickly to emergencies and changing requirements.

9. The system according to claim 8, characterized in that The task scheduling and resource allocation module also includes: A prediction module based on machine learning, used to predict task execution time and resource consumption; The dynamic resource allocation module intelligently adjusts resource allocation based on prediction results and real-time feedback.

10. The system according to claim 9, characterized in that The task scheduling and resource allocation module is configured with: Multi-task scheduling strategy, reasonably arrange the execution of multiple tasks at the same time to reduce idle resources; Adaptive adjustment mechanism dynamically adjusts the task execution strategy according to changes in network conditions and resource status.

Images