Method, system and equipment for fusing edge computing and cloud computing, and medium

Abstract

The invention relates to the technical field of computer communication and computing, and discloses an edge computing and cloud computing integrated method, system, device and medium, comprising the following steps: S1, an edge node collects service data generated by a terminal device through cooperation of a plurality of links, executes a customized preprocessing process on the service data, and finally outputs standardized data; and S2, according to an intelligent task scheduling strategy set in advance, the calculation tasks corresponding to the standardized data are classified and judged, the processing levels of the calculation tasks are clarified, and the processing levels comprise the edge calculation level and the cloud calculation level. According to the invention, through the preset intelligent task scheduling strategy, the scheme can realize the scientific distribution of the calculation task at the edge end and the cloud end: for the real-time task which needs to be responded instantly, the characteristic of low delay of edge calculation is fully exerted to complete processing; and large-scale complex tasks are overcome by means of super-strong computing power of cloud computing.

Description

Technical Field

[0001] This invention relates to the field of computer communication and computing technology, and in particular to methods, systems, devices and media that integrate edge computing and cloud computing. Background Technology

[0002] With the rapid development of IoT, 5G communication, and artificial intelligence technologies, the number of terminal devices has exploded, generating massive amounts of business data. Cloud computing, as a traditional centralized computing model, has advantages such as strong computing power, large storage capacity, and good scalability, and can handle complex computing tasks with large-scale data. However, it also suffers from problems such as high data transmission latency, high network bandwidth consumption, and the risk of privacy data leakage. Edge computing, on the other hand, deploys computing resources at the network edge close to terminal devices, enabling local real-time data processing, reducing response latency, and alleviating network transmission pressure. However, edge nodes have limited computing power and storage resources, making it difficult to handle large-scale and complex computing tasks.

[0003] Currently, most practices integrating edge computing and cloud computing remain at the level of simple task splitting or data diversion, lacking flexible and intelligent task scheduling mechanisms. This not only leads to low resource utilization on the edge side and unbalanced load distribution on the cloud, but also makes it difficult to effectively guarantee the security and reliability of data transmission. Specifically, some solutions adopt fixed task allocation models, directly assigning specific types of tasks to the edge or cloud, failing to dynamically adapt and adjust according to real-time task requirements and the resource status of both sides. Other solutions do not consider encryption protection and traceability capabilities for data transmission, posing potential risks of data leakage or tampering. At the same time, existing integrated systems generally lack the ability to collaboratively optimize edge and cloud resources, making it difficult to maximize overall computing performance. Summary of the Invention

[0004] The technical problem this invention aims to solve is to provide methods, systems, devices, and media for integrating edge computing and cloud computing. Current practices in integrating edge computing and cloud computing largely remain at the level of simple task splitting or data diversion, lacking flexible and intelligent task scheduling mechanisms. This not only leads to low resource utilization on the edge side and unbalanced load distribution on the cloud, but also makes it difficult to effectively guarantee the security and reliability of data transmission. Specifically, some solutions adopt fixed task allocation models, directly assigning specific types of tasks to the edge or cloud, failing to dynamically adapt and adjust according to real-time task requirements and the resource status of both sides. Other solutions do not consider encryption protection and traceability capabilities for data transmission, posing potential risks of data leakage or tampering. At the same time, existing integrated systems generally lack the ability to collaboratively optimize edge and cloud resources, making it difficult to maximize overall computing performance.

[0005] To address the aforementioned problems, the present invention is implemented through the following technical solution.

[0006] A method for integrating edge computing and cloud computing, characterized by the following steps:

[0007] S1. Edge nodes cooperate through multiple links to collect business data generated by terminal devices, perform customized preprocessing processes on the business data, and finally output standardized data.

[0008] S2. According to the pre-set intelligent task scheduling strategy, classify and judge the computing tasks corresponding to the standardized data, and determine the processing level of the computing tasks. The processing level includes the edge computing level and the cloud computing level.

[0009] S3. If the computing task belongs to the edge computing layer, the edge node processes the computing task in the manner of local resource pooling management, and after obtaining the edge processing result, it synchronizes the edge processing result to the cloud computing platform through the incremental synchronization link.

[0010] S4. If the computing task belongs to the cloud computing level, the edge node uploads the standardized data to the cloud computing platform through a two-way authenticated secure transmission channel; then the cloud computing platform calls the distributed resource cluster to process the computing task, obtains the cloud processing result, and then transmits the cloud processing result back to the edge node through the result feedback link.

[0011] S5. The edge node performs integration and matching processing on the edge processing result or the cloud processing result, and then returns the customized final response result to the terminal device.

[0012] Preferably, the customized preprocessing process in step S1 includes intelligent data cleaning, heterogeneous format conversion, redundant data deduplication, and efficient lossless compression. Specifically, intelligent data cleaning is used to accurately remove outliers, missing values, and noisy data from the business data; heterogeneous format conversion converts heterogeneous data output from different terminal devices into a unified standard format; redundant data deduplication cleans up repeatedly collected redundant data; and efficient lossless compression uses appropriate algorithms to compress the standardized data. The pre-set intelligent task scheduling strategy in step S2 includes the following judgment rules:

[0013] Rule 1: If the response latency requirement of the computing task is ≤50ms and the data volume is ≤100MB, it is determined to be an edge computing layer;

[0014] Rule 2: If the response latency requirement of the computing task is >50ms, or the data volume of the business data is >100MB, or the computing task requires the use of large-scale distributed computing power, it is determined to be at the cloud computing level.

[0015] Rule 3: If the computing task includes real-time processing subtasks and non-real-time analysis subtasks, the real-time processing subtasks shall be assigned to the edge computing layer, and the non-real-time analysis subtasks shall be assigned to the cloud computing layer.

[0016] Preferably, in step S3, when the edge node processes the computing task in a local resource pooling management manner, a dynamic resource scheduling mechanism is adopted. Specifically, the CPU utilization, memory usage, and remaining storage space of the local resources are monitored in real time. If the local resource utilization is ≥80%, the low-priority edge computing task is paused first, and the high-priority edge computing task is processed first. When the local resource utilization is ≤60%, the low-priority edge computing task is resumed.

[0017] Preferably, in step S6, the cloud computing platform summarizes and analyzes the edge processing results and the cloud processing results to generate multi-dimensional resource optimization suggestions. The multi-dimensional resource optimization suggestions include resource expansion suggestions for the edge nodes, suggestions for adjusting the allocation ratio of computing tasks, and suggestions for optimizing data transmission bandwidth. Then, the multi-dimensional resource optimization suggestions are sent to the edge nodes.

[0018] Preferably, it includes an edge node module, a cloud computing platform module, and a data interaction module;

[0019] The edge node module is responsible for collecting business data from terminal devices, performing preprocessing on the business data to obtain standardized data, classifying the computing tasks corresponding to the standardized data according to the task scheduling strategy, clarifying the processing level of the computing tasks, executing the edge computing level tasks and synchronizing the edge processing results, and receiving the cloud processing results at the same time.

[0020] The cloud computing platform module is responsible for receiving the edge processing results synchronized by the edge node module, receiving the standardized data and executing cloud computing level tasks, and then feeding back the cloud processing results.

[0021] The data interaction module is responsible for establishing a secure transmission channel between the edge node module and the cloud computing platform module, enabling encrypted data transmission and interaction between the edge node module and the cloud computing platform module.

[0022] Preferably, the edge node module further includes a task priority dynamic sorting unit. The task priority dynamic sorting unit divides the computing tasks into four categories: urgent priority, high priority, medium priority, and low priority, based on the type of terminal device, the importance of the business data, and user needs. The processing priority of the computing tasks with urgent priority is higher than that of the computing tasks at other levels.

[0023] Preferably, the cloud computing platform module includes an intelligent computing power scheduling unit and a secure result storage unit; the intelligent computing power scheduling unit distributes the cloud computing level tasks evenly to the idle distributed nodes according to the load of the distributed nodes of the cloud computing platform; the secure result storage unit uses a distributed encrypted database to store the cloud processing results and the edge processing results, and supports fast querying based on timestamps, the identifiers of the computing tasks and the identifiers of the edge nodes.

[0024] Preferably, it includes an edge gateway, with a processor on one side of the front end of the edge gateway, and a memory on the side of the front end of the edge gateway corresponding to the processor. The processor is a multi-core CPU or a heterogeneous computing chip, and a first communication interface is provided on the outside of the edge gateway.

[0025] Preferably, a network cable is plugged into the first communication interface, and the end of the network cable away from the first communication interface is connected to an edge server. The edge server has a second communication interface at the point where it contacts the network cable.

[0026] Preferably, the computer-readable storage medium stores a computer program, which, when executed by a processor, enables the method of integrating edge computing and cloud computing as described in claim 1. The computer-readable storage medium includes media capable of storing computer programs, such as a USB flash drive with encrypted storage function, a secure portable hard drive, a read-only memory with a root of trust, an encrypted random access memory, an encrypted magnetic disk, or a Blu-ray encrypted optical disc.

[0027] This invention provides a method, system, device, and medium for integrating edge computing and cloud computing. Compared with existing technologies, it has the following advantages:

[0028] Through a pre-defined intelligent task scheduling strategy, this solution enables the scientific allocation of computing tasks between the edge and the cloud: for real-time tasks requiring immediate response, it fully leverages the low latency of edge computing to complete the processing; for large-scale complex tasks, it utilizes the superior computing power of cloud computing to overcome challenges, effectively improving the overall efficiency of task processing; through a pre-processing stage, the total amount of data transmission can be significantly reduced, minimizing the resource consumption of redundant data; at the data transmission level, a dedicated encrypted transmission method combined with a blockchain log recording mechanism comprehensively ensures the security and traceability of the data transmission process. With the help of dynamic resource allocation and edge-cloud collaborative optimization mechanisms, the resource utilization of both the edge and cloud is significantly improved, achieving dynamic adaptation and optimization of system performance; simultaneously, the corresponding system, equipment, and storage media of this invention are highly compatible with the core method, constructing a complete and feasible technical system that can be widely applied to diverse scenarios such as the Internet of Things, the Industrial Internet, and smart cities. Attached Figure Description

[0029] Figure 1 A flowchart illustrating the method of integrating edge computing and cloud computing.

[0030] Figure 2 This is a system architecture diagram for the integration of edge computing and cloud computing.

[0031] Figure 3 This is a schematic diagram of a device structure that integrates edge computing and cloud computing.

[0032] The attached figures are labeled as follows:

[0033] 1. Edge gateway; 2. Processor; 3. Memory; 4. First communication interface; 5. Network cable; 6. Second communication interface; 7. Edge server. Detailed Implementation

[0034] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0035] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention.

[0036] Reference Figures 1-3 A method for integrating edge computing and cloud computing, characterized by comprising the following steps:

[0037] S1. Edge nodes cooperate through multiple links to collect business data generated by terminal devices, perform customized preprocessing processes on the business data, and finally output standardized data.

[0038] S2. According to the pre-set intelligent task scheduling strategy, classify and judge the computing tasks corresponding to the standardized data, and clarify the processing level of the computing tasks. The processing level includes the edge computing level and the cloud computing level.

[0039] S3. If the computing task belongs to the edge computing layer, the edge node will process the computing task in the manner of local resource pooling management. After obtaining the edge processing result, the edge processing result will be synchronized to the cloud computing platform through the incremental synchronization link.

[0040] S4. If the computing task belongs to the cloud computing level, the edge node uploads the standardized data to the cloud computing platform through a secure transmission channel with two-way authentication. Then, the cloud computing platform calls the distributed resource cluster to process the computing task, obtains the cloud processing result, and then transmits the cloud processing result back to the edge node through the result feedback link.

[0041] S5: Edge nodes integrate and match edge processing results or cloud processing results, and then return the customized final response result to the terminal device.

[0042] Step S1 involves a customized preprocessing workflow, including intelligent data cleaning, heterogeneous format conversion, redundant data deduplication, and efficient lossless compression. Intelligent data cleaning precisely removes outliers, missing values, and noisy data from business data; heterogeneous format conversion transforms heterogeneous data output from different terminal devices into a unified standard format; redundant data deduplication cleans up repeatedly collected redundant data; and efficient lossless compression uses appropriate algorithms to compress standardized data. Step S2 includes a pre-defined intelligent task scheduling strategy with the following judgment rules:

[0043] Rule 1: If the response latency requirement of the computing task is ≤50ms and the data volume is ≤100MB, it is determined to be an edge computing layer;

[0044] Rule 2: If the response latency requirement of the computing task is >50ms, or the amount of business data is >100MB, or the computing task requires the use of large-scale distributed computing power, it is determined to be at the cloud computing level.

[0045] Rule 3: If a computing task includes real-time processing subtasks and non-real-time analysis subtasks, assign the real-time processing subtasks to the edge computing layer and the non-real-time analysis subtasks to the cloud computing layer.

[0046] In step S3, when edge nodes process computing tasks in a local resource pooling management manner, a dynamic resource scheduling mechanism is adopted. Specifically, the CPU utilization, memory usage, and remaining storage space of local resources are monitored in real time. If the local resource utilization is ≥80%, low-priority edge computing tasks are paused first, and high-priority edge computing tasks are processed first. When the local resource utilization is ≤60%, low-priority edge computing tasks are resumed.

[0047] In step S6, the cloud computing platform summarizes and analyzes the edge processing results and cloud processing results to generate multi-dimensional resource optimization suggestions. These suggestions include suggestions for expanding the resource capacity of edge nodes, adjusting the allocation ratio of computing tasks, and optimizing data transmission bandwidth. The multi-dimensional resource optimization suggestions are then distributed to the edge nodes.

[0048] It includes an edge node module, a cloud computing platform module, and a data interaction module;

[0049] The edge node module is responsible for collecting business data from terminal devices, performing preprocessing on the business data to obtain standardized data, classifying the computing tasks corresponding to the standardized data according to the task scheduling strategy, clarifying the processing level of the computing tasks, executing the edge computing level tasks and synchronizing the edge processing results, and receiving the cloud processing results at the same time.

[0050] The cloud computing platform module is responsible for receiving the edge processing results synchronized by the edge node module, receiving the standardized data and executing cloud computing level tasks, and then feeding back the cloud processing results.

[0051] The data interaction module is responsible for establishing a secure transmission channel between the edge node module and the cloud computing platform module, enabling encrypted data transmission and interaction between the edge node module and the cloud computing platform module.

[0052] The edge node module also includes a task priority dynamic sorting unit. The task priority dynamic sorting unit divides computing tasks into four categories: urgent priority, high priority, medium priority, and low priority, based on the type of terminal device, the importance of business data, and user needs. Among them, the processing priority of urgent priority computing tasks is higher than that of other levels of computing tasks.

[0053] The cloud computing platform module includes an intelligent computing power scheduling unit and a secure result storage unit. The intelligent computing power scheduling unit distributes cloud computing level tasks evenly to idle distributed nodes based on the load of the distributed nodes of the cloud computing platform. The secure result storage unit uses a distributed encrypted database to store cloud processing results and edge processing results, and supports fast querying based on timestamps, computing task identifiers, and edge node identifiers.

[0054] It includes an edge gateway 1, a processor 2 is provided on one side of the front end of the edge gateway 1, a memory 3 is provided on the side of the front end of the edge gateway 1 corresponding to the processor 2, the processor 2 is a multi-core CPU or a heterogeneous computing chip, and a first communication interface 4 is provided on the outside of the edge gateway 1.

[0055] A network cable 5 is plugged into the first communication interface 4. The end of the network cable 5 away from the first communication interface 4 is connected to an edge server 7. A second communication interface 6 is provided at the point where the edge server 7 contacts the network cable 5.

[0056] A computer-readable storage medium stores a computer program, which, when executed by a processor, enables the integration of edge computing and cloud computing as described in claim 1. The computer-readable storage medium includes media capable of storing computer programs, such as USB flash drives with encrypted storage functions, secure portable hard drives, read-only memory with a root of trust, encrypted random access memory, encrypted magnetic disks, or Blu-ray encrypted optical discs.

[0057] The present invention will be further described in detail below with reference to specific embodiments:

[0058] In the industrial production workshop of a certain factory, a total of 100 industrial control devices (that is, terminal devices) are installed. The edge nodes here are edge gateways, and the cloud computing platform is an industrial internet platform deployed in the cloud, which is specifically used to handle big data tasks in the workshop.

[0059] Step S1: The edge gateway collects operational data from each industrial control device via Ethernet cable, including key business data such as temperature, operating pressure, and rotation speed. This data is then processed and optimized (preprocessed): first, temperature data exceeding the device's normal operating range is removed; missing pressure data is supplemented using linear interpolation; then, the XML and JSON data output from different devices are uniformly converted to Protobuf format for easier subsequent processing; duplicate rotation speed data is deleted; and finally, the LZ77 algorithm is used to compress the data volume, resulting in standardized, well-organized data.

[0060] Step S2: Analyze the core information of each computing task. For example, tasks that require real-time response, such as adjusting the device speed, require a latency of no more than 20 milliseconds and a data volume of only 20MB. According to the previously set rule 1, this task is classified as an edge computing layer and processed directly at the edge gateway. On the other hand, big data tasks that analyze the long-term operating status of the device have a data volume of 800MB and require a computing power of 300GFLOPS. According to rule 2, this task is classified as a cloud computing layer and processed by the cloud platform.

[0061] Step S3: The edge gateway monitors its resource usage in real time and finds that the CPU is only used at 40%, the memory usage is 35%, and the storage space is also sufficient. It then directly uses dynamic resource allocation to process the speed adjustment task. After calculating the adjustment command (that is, the edge processing result), it immediately synchronizes it to the industrial internet platform in the cloud.

[0062] Step S4: The edge gateway uploads the compiled device operating status data to the cloud platform via an encrypted transmission channel. Simultaneously, blockchain technology is used to record the upload time, data summary, gateway number, and cloud confirmation of receipt, ensuring the data is tamper-proof and traceable. The cloud platform's computing power scheduling unit allocates this big data analysis task to three idle distributed nodes for processing. After calculating the device fault warning report (cloud processing result), it is then fed back to the edge gateway.

[0063] Step S5: The edge gateway sends the speed adjustment command directly to the corresponding industrial control equipment so that the equipment can adjust in time; at the same time, it pushes the fault warning report to the monitoring terminal in the workshop for the staff to view, thus completing the entire response process.

[0064] Step S6: The cloud platform compares and analyzes the processing results of the edge gateway and its own. It finds that the CPU utilization of the edge gateway in a certain area reaches 75% during peak hours, which is close to full load. It then generates a resource expansion suggestion to "increase the number of CPU cores of the edge gateway" and sends it to this edge gateway to complete the resource optimization.

[0065] Example 2: Deployment and Operation of the Converged System

[0066] We installed the edge node module directly in the edge gateway of the workshop. The unit responsible for data collection supports both Ethernet and 5G communication. The preprocessing unit integrates LZ77 compression and data cleaning algorithms to quickly complete data processing. The cloud computing platform module is deployed on Alibaba Cloud's industrial internet cluster. Its computing power scheduling unit uses a round-robin algorithm to distribute tasks, ensuring that each distributed node is neither too busy nor too idle. The data interaction module uses SSL / TLS 1.3 protocol to encrypt data transmission. The blockchain log records adopt a consortium blockchain architecture, which can only be viewed and verified by authorized nodes, further ensuring the security and immutability of data transmission. When the system is running normally, the edge node module and the cloud computing platform module transmit data in real time through the data interaction module. Compared with traditional processing solutions, the task processing speed is improved by 40%, and the data transmission latency is reduced to less than 30 milliseconds, which can well meet the real-time requirements of industrial production.

[0067] Example 3: Applications of electronic devices and storage media

[0068] The electronic devices used here are edge servers, which mainly act as edge nodes, responsible for collecting, organizing, and processing edge-level computing tasks. The cloud uses a cluster of 10 cloud servers configured with AMD EPYC7763 CPUs and 256GB of memory to specifically handle cloud-level tasks that require a lot of computing power. The storage medium for the relevant programs is a USB flash drive. We store the computer programs that implement the above integration method on the USB flash drive. When using it, we only need to plug the USB flash drive into the edge server or cloud server to install and run the program, easily realizing the integration of edge computing and cloud computing. It is very convenient to deploy and use.

[0069] Therefore, although the invention has been described herein with reference to specific embodiments thereof, freedom of modification, various changes and substitutions are also within the scope of the foregoing disclosure, and it should be understood that in some cases, certain features of the invention may be adopted without departing from the scope and spirit of the invention and without corresponding use of other features. Thus, many modifications can be made to adapt a particular environment or material to the essential scope and spirit of the invention. The invention is not intended to be limited to the specific terminology used in the following claims and / or the specific embodiments disclosed as the best mode for carrying out the invention, but the invention will include any and all embodiments and equivalents falling within the scope of the appended claims. Therefore, the scope of the invention will be defined only by the appended claims.

Claims

1. A method for integrating edge computing and cloud computing, characterized in that, Includes the following steps: S1. Edge nodes cooperate through multiple links to collect business data generated by terminal devices, perform customized preprocessing processes on the business data, and finally output standardized data. S2. According to the pre-set intelligent task scheduling strategy, classify and judge the computing tasks corresponding to the standardized data, and determine the processing level of the computing tasks. The processing level includes the edge computing level and the cloud computing level. S3. If the computing task belongs to the edge computing layer, the edge node processes the computing task in the manner of local resource pooling management, and after obtaining the edge processing result, it synchronizes the edge processing result to the cloud computing platform through the incremental synchronization link. S4. If the computing task belongs to the cloud computing level, the edge node uploads the standardized data to the cloud computing platform through a two-way certified secure transmission channel. The computing task is then processed by the distributed resource cluster called by the cloud computing platform, the cloud processing result is obtained, and the cloud processing result is then sent back to the edge node through the result feedback link. S5. The edge node performs integration and matching processing on the edge processing result or the cloud processing result, and then returns the customized final response result to the terminal device.

2. The method for integrating edge computing and cloud computing according to claim 1, characterized in that, The customized preprocessing process in step S1 includes intelligent data cleaning, heterogeneous format conversion, redundant data deduplication, and efficient lossless compression. Specifically, intelligent data cleaning accurately removes outliers, missing values, and noisy data from the business data; heterogeneous format conversion converts heterogeneous data output from different terminal devices into a unified standard format; redundant data deduplication cleans up repeatedly collected redundant data; and efficient lossless compression uses appropriate algorithms to compress the standardized data. The pre-set intelligent task scheduling strategy in step S2 includes the following judgment rules: Rule 1: If the response latency requirement of the computing task is ≤50ms and the data volume is ≤100MB, it is determined to be an edge computing layer; Rule 2: If the response latency requirement of the computing task is >50ms, or the data volume of the business data is >100MB, or the computing task requires the use of large-scale distributed computing power, it is determined to be at the cloud computing level. Rule 3: If the computing task includes real-time processing subtasks and non-real-time analysis subtasks, the real-time processing subtasks shall be assigned to the edge computing layer, and the non-real-time analysis subtasks shall be assigned to the cloud computing layer.

3. The method for integrating edge computing and cloud computing according to claim 1, characterized in that, In step S3, when the edge node processes the computing task in a local resource pooling management manner, a dynamic resource scheduling mechanism is adopted. Specifically, the CPU utilization, memory usage, and remaining storage space of the local resources are monitored in real time. If the local resource utilization is ≥80%, the low-priority edge computing task is paused first, and the high-priority edge computing task is processed first. When the local resource utilization is ≤60%, the low-priority edge computing task is resumed.

4. The method for integrating edge computing and cloud computing according to claim 1, characterized in that, In step S6, the cloud computing platform summarizes and analyzes the edge processing results and the cloud processing results to generate multi-dimensional resource optimization suggestions. The multi-dimensional resource optimization suggestions include resource expansion suggestions for the edge nodes, suggestions for adjusting the allocation ratio of computing tasks, and suggestions for optimizing data transmission bandwidth. Then, the multi-dimensional resource optimization suggestions are sent to the edge nodes.

5. A system integrating edge computing and cloud computing, characterized in that, It includes an edge node module, a cloud computing platform module, and a data interaction module; The edge node module is responsible for collecting business data from terminal devices, performing preprocessing on the business data to obtain standardized data, classifying the computing tasks corresponding to the standardized data according to the task scheduling strategy, clarifying the processing level of the computing tasks, executing the edge computing level tasks and synchronizing the edge processing results, and receiving the cloud processing results at the same time. The cloud computing platform module is responsible for receiving the edge processing results synchronized by the edge node module, receiving the standardized data and executing cloud computing level tasks, and then feeding back the cloud processing results. The data interaction module is responsible for establishing a secure transmission channel between the edge node module and the cloud computing platform module, enabling encrypted data transmission and interaction between the edge node module and the cloud computing platform module.

6. The system integrating edge computing and cloud computing according to claim 5, characterized in that, The edge node module also includes a task priority dynamic sorting unit. The task priority dynamic sorting unit divides the computing tasks into four categories: urgent priority, high priority, medium priority, and low priority, based on the type of terminal device, the importance of the business data, and user needs. The processing priority of the computing tasks with urgent priority is higher than that of the computing tasks at other levels.

7. The system integrating edge computing and cloud computing according to claim 6, characterized in that, The cloud computing platform module includes an intelligent computing power scheduling unit and a secure result storage unit; the intelligent computing power scheduling unit distributes the cloud computing level tasks evenly to the idle distributed nodes according to the load of the distributed nodes of the cloud computing platform. The secure result storage unit uses a distributed encrypted database to store the cloud processing results and the edge processing results, and supports quick querying based on timestamps, the identifier of the computing task, and the identifier of the edge node.

8. A device that integrates edge computing and cloud computing, characterized in that, The device includes an edge gateway (1), a processor (2) is provided on one side of the front end of the edge gateway (1), a memory (3) is provided on the side of the front end of the edge gateway (1) corresponding to the processor (2), the processor (2) is a multi-core CPU or a heterogeneous computing chip, and a first communication interface (4) is provided on the outside of the edge gateway (1).

9. The device integrating edge computing and cloud computing according to claim 8, characterized in that, A network cable (5) is inserted into the first communication interface (4). The end of the network cable (5) away from the first communication interface (4) is connected to an edge server (7). The edge server (7) has a second communication interface (6) at the point where it contacts the network cable (5).

10. A medium integrating edge computing and cloud computing, characterized in that, The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the method of integrating edge computing and cloud computing as described in claim 1 can be realized. The computer-readable storage medium includes media capable of storing computer programs, such as USB flash drives with encrypted storage functions, secure portable hard drives, read-only memory with root of trust, encrypted random access memory, encrypted magnetic disks, or Blu-ray encrypted optical discs.

Images