Task processing method based on cloud edge collaborative system and cloud management platform

Abstract

The invention provides a task processing method based on a cloud edge collaborative system and a cloud management platform, all levels of edge nodes in an edge node cluster contained in the cloud edge collaborative system can be matched with one another, and tasks issued by the cloud management platform can be automatically completed. The cloud edge collaboration system comprises an edge node cluster and a cloud management platform, the edge node cluster comprises first edge nodes and second edge nodes, and the first edge nodes and the second edge nodes are ranked according to levels from high to low. The first task may be issued to the first edge node. And then, the first edge node can disassemble the first task to obtain a second task, and sends the second task to the second edge node, so that the second edge node completes the second task.

Description

[0001] This application claims the priority of the Chinese patent application filed with the State Intellectual Property Office on September 13, 2023, with application number 202311186186.X and invention name “A distributed resilient system and task execution method with autonomous intelligence”, the entire contents of which are incorporated by reference in this application. Technical Field

[0002] The embodiments of the present application relate to the field of cloud technology, and in particular to a task processing method based on a cloud-edge collaborative system and a cloud management platform. Background Art

[0003] The cloud-edge collaborative system refers to the technical architecture formed by the cloud and the edge. In this system, the cloud places tasks such as network forwarding, storage, computing, and data analysis to the edge to realize cloud services. Therefore, when providing cloud services to users, the cloud-edge collaborative system can effectively reduce the pressure on the cloud and reduce various operating costs.

[0004] At present, the cloud-edge collaborative system includes a cloud management platform and multiple edge nodes, where the cloud management platform can manage these multiple edge nodes. When a user needs to complete a task, he can send the task to the cloud management platform. Then, the cloud management platform can distribute the task to each edge node to complete, thereby meeting the needs of the user.

[0005] In the above-mentioned cloud-edge collaborative system, since multiple edge nodes rely on the cloud management platform for unified control, in some special cases, once multiple edge nodes are disconnected from the cloud management platform, the edge nodes cannot perform tasks autonomously and thus cannot meet user needs. Summary of the invention

[0006] The embodiments of the present application provide a task processing method and a cloud management platform based on a cloud-edge collaborative system. Even if the network connection between the edge node cluster and the cloud management platform is disconnected and the cloud management platform cannot participate, the edge nodes at all levels in the edge node cluster can cooperate with each other to complete the tasks issued by the cloud management platform independently, thereby meeting the needs of users.

[0007] An embodiment of the present application provides a task processing method based on a cloud-edge collaborative system, and the cloud-edge collaborative system for implementing the method includes an edge node cluster and a cloud management platform for managing the edge node cluster. The edge node cluster includes at least two levels of edge nodes, wherein the edge node with the highest level can be called a first edge node, the edge node with the second highest level can be called a second edge node, the edge node with the third highest level can be called a third edge node, the edge node with the fourth highest level can be called a fourth edge node, and so on. For ease of explanation, the following is a schematic introduction to an edge node cluster including three levels of edge nodes, that is, the edge node cluster includes a first edge node, a second edge node, and a third edge node sorted from high to low levels. The method includes:

[0008] Since the cloud management platform has configured the task scheduling function for the first edge node, the second edge node and the third edge node, the cloud management platform can directly send the first task to the first edge node after receiving the first task input by the user. Then, the first edge node can disassemble the first task to obtain the second task, and send the second task to the second edge node. Then, the second edge node can disassemble the second task to obtain the third task, and send the third task to the third edge node, so that the third edge node completes the third task. It should be noted that the first task can be disassembled into multiple stages of the second task, and the second task can also be disassembled into multiple stages of the third task. Therefore, by repeating the above process continuously, the first edge node, the second edge node and the third edge node can collaboratively complete the first task specified by the user.

[0009] It should be noted that, in actual applications, the edge node cluster may also include only two levels of edge nodes (for example, the edge node cluster only includes the first edge node and the second edge node), the edge node cluster may also include four levels of edge nodes (for example, the edge node cluster only includes the first edge node, the second edge node, the third edge node and the fourth edge node), the edge node cluster may also include five levels of edge nodes, and so on.

[0010] It can be seen from the above method that: since the cloud management platform has configured the task scheduling function for edge nodes at all levels in the edge node cluster (i.e., the first edge node, the second edge node, and the third edge node), even if the network connection between the edge node cluster and the cloud management platform is disconnected, and the cloud management platform cannot participate, the edge nodes at all levels in the edge node cluster can cooperate with each other to disassemble and execute the tasks issued by the cloud management platform by themselves, thereby meeting user needs.

[0011] In one possible implementation, there are multiple second edge nodes, multiple third edge nodes, a first edge node is used to manage multiple second edge nodes, and one second edge node is used to manage multiple third edge nodes. In the aforementioned implementation, the edge node cluster can be presented in a tree structure. Generally, the edge node cluster in the tree structure can include three levels of edge nodes, one first edge node as a root node, multiple second edge nodes as intermediate nodes, and multiple third edge nodes as leaf nodes. The first edge node can be used to manage multiple second edge nodes, and each second edge node can be used to manage multiple third edge nodes.

[0012] In a possible implementation, the method further includes: the cloud management platform configures the first edge node to obtain the information of all second edge nodes and all third edge nodes in real time; the cloud management platform configures any second edge node to obtain the information of the first edge node, the information of the remaining second edge nodes and all third edge nodes in real time; the cloud management platform configures any third edge node to obtain the information of the first edge node, the information of all second edge nodes and the information of the remaining third edge nodes in real time. In the aforementioned implementation, the cloud management platform also configures the data synchronization function for the first edge node, the second edge node and the third edge node, so the first edge node can obtain the status information of all second edge nodes and all third edge nodes in real time when the first edge node, the second edge node and the third edge node collaborate to complete the first task. Similarly, for any second edge node among all second edge nodes, the second edge node can obtain the status information of the first edge node, the remaining second edge nodes and all third edge nodes in real time. Similarly, for any third edge node among all third edge nodes, the third edge node can obtain the information of the first edge node, all second edge nodes and the remaining third edge nodes in real time. It can be seen that since the cloud management platform has configured the data synchronization function for edge nodes at all levels in the edge node cluster, even if the network connection between the edge node cluster and the cloud management platform is disconnected and the cloud management platform cannot participate, the edge nodes at all levels in the edge node cluster can complete data synchronization by themselves, thereby ensuring the smooth completion of the task and meeting user needs.

[0013] In a possible implementation, the method further includes: the cloud management platform configures the first edge node to select the best third edge node from the multiple third edge nodes managed by the failed second edge node as a new second edge node based on the information of the multiple third edge nodes managed by the failed second edge node after determining that any one of the multiple second edge nodes has failed, and the new second edge node is used to manage the remaining third edge nodes managed by the failed second edge node. In the aforementioned implementation, since the cloud management platform has configured the internal structure adjustment function of the edge node cluster for the first edge node, after determining that any one of the multiple second edge nodes has failed, the first edge node can use the status information of the multiple third edge nodes managed by the second edge node to select the best third edge node from the multiple third edge nodes managed by the second edge node as a new second edge node, and let the new second edge node replace the second edge node to manage the remaining third edge nodes originally managed by the second edge node. It can be seen that since the cloud management platform has configured the internal structure adjustment function of the cluster for the highest-level edge node in the edge node cluster, even if the network connection between the edge node cluster and the cloud management platform is disconnected, and the cloud management platform cannot participate, if a certain intermediate-level edge node within the edge node cluster fails, the highest-level edge node can also adjust the internal structure of the edge node cluster by itself, thereby ensuring the normal operation of the edge node cluster, so as to successfully complete the task and meet the needs of users.

[0014] In a possible implementation, the method further includes: the cloud management platform configures multiple second edge nodes, after determining that the first edge node fails, based on the information of the multiple second edge nodes, selects the best second edge node from the multiple second edge nodes as the new first edge node, and the new first edge node is used to manage the remaining second edge nodes; the cloud management platform configures the new first edge node to select the best third edge node from the multiple third edge nodes managed by the best second edge node as the new second edge node, and the new second edge node is used to manage the remaining third edge nodes managed by the best second edge node. In the aforementioned implementation, since the cloud management platform has configured the internal structure adjustment function of the edge node cluster for the second edge node, after determining that the first edge node managing the multiple second edge nodes fails, the multiple second edge nodes can use the status information of the multiple second edge nodes to select the best second edge node from the multiple second edge nodes as the new first edge node, and let the new first edge node replace the failed first edge node to manage the remaining second edge nodes originally managed by the failed first edge node. Then, the new first edge node can use the information of multiple third edge nodes originally managed by the best second edge node to select the best third edge node as the new second edge node from the third edge nodes originally managed by the best second edge node, and let the new second edge node replace the best second edge node to manage the remaining third edge nodes originally managed by the best second edge node. It can be seen that since the cloud management platform has configured the internal structure adjustment function of the cluster for the intermediate-level edge nodes in the edge node cluster, even if the network connection between the edge node cluster and the cloud management platform is disconnected, and the cloud management platform cannot participate, if the highest-level edge node in the edge node cluster fails, the intermediate-level edge node can also adjust the internal structure of the edge node cluster by itself, thereby ensuring the normal operation of the edge node cluster, so as to successfully complete the task and meet the needs of users.

[0015] In a possible implementation, the method further includes: the cloud management platform configures the first edge node to determine a third edge node that has not failed from multiple third edge nodes managed by the second edge node that has failed, and to make another second edge node manage the third edge node that has not failed. In the aforementioned implementation, since the cloud management platform has configured the internal structure adjustment function of the edge node cluster for the first edge node, after determining that any one of the multiple second edge nodes has failed, the first edge node can determine the third edge node that has not failed from the multiple third edge nodes managed by the second edge node, and make another second edge node act as the agent of the second edge node to manage these third edge nodes that have not failed. It can be seen that since the cloud management platform has configured the internal structure adjustment function of the cluster for the highest-level edge node in the edge node cluster, even if the network connection between the edge node cluster and the cloud management platform is disconnected, if a certain intermediate-level edge node in the edge node cluster fails, the highest-level edge node can also adjust the internal structure of the edge node cluster by itself, thereby ensuring the normal operation of the edge node cluster, so as to successfully complete the task and meet the needs of users.

[0016] In a possible implementation, the method further includes: when the cloud management platform configures any third edge node to be in a network disconnected state, it attempts to establish a network connection with the first edge node or the second edge node used to manage the third edge node in the network disconnected state, and if the attempt fails, the preset action is performed after the third task is completed. In the aforementioned implementation, when any third edge node among the multiple third edge nodes detects that it is in a network disconnected state, the third edge node may attempt to establish a network connection with the first edge node or the second edge node used to manage the third edge node, and if the attempt fails, the preset action is performed after the third task is completed. It can be seen that since the cloud management platform has configured the network reconnection function for the low-level edge nodes in the edge node cluster, when a low-level edge node leaves the self-organizing network where the edge node cluster is located, the edge node can continuously try to join the self-organizing network on its own, and if it fails, the bottom-line action is performed, which can not only ensure the stability of the structure and function of the edge node cluster, but also ensure the recovery of orphan nodes.

[0017] In one possible implementation, the method further includes: when the cloud management platform configures any second edge node to be in a network disconnected state, it attempts to establish a network connection with the first edge node, and if the attempt fails, executes a preset action. In the aforementioned implementation, when any second edge node among the multiple second edge nodes detects that it is in a network disconnected state, the second edge node may attempt to establish a network connection with the first edge node, and if the attempt fails, directly executes the preset action. It can be seen that since the cloud management platform has configured the network reconnection function for the intermediate-level edge nodes in the edge node cluster, when an intermediate-level edge node leaves the self-organizing network where the edge node cluster is located, the edge node can continuously try to join the self-organizing network on its own, and if it fails, it executes a bottom-line action, which not only ensures the stability of the structure and function of the edge node cluster, but also ensures the recovery of orphan nodes.

[0018] In one possible implementation, the method further includes: the cloud management platform receives a creation request for an edge node cluster input by a user; based on the creation request, the cloud management platform sets the multiple edge nodes to be set as a first edge node, multiple second edge nodes managed by the first edge node, and multiple third edge nodes managed by each of the multiple second edge nodes. In the aforementioned implementation, when a user needs to create a dedicated edge node cluster, the cloud management platform may receive a creation request sent by the user. After receiving the creation request, the cloud management platform may set the levels of the multiple edge nodes to be set based on the creation request, that is, the multiple edge nodes to be set are set as a first edge node, multiple second edge nodes managed by the first edge node, and multiple third edge nodes managed by each of the multiple second edge nodes, so that an edge node cluster with a tree structure can be obtained, which can be used to provide cloud services to users.

[0019] The second aspect of an embodiment of the present application provides a cloud management platform, which is deployed in a cloud-edge collaborative system. The cloud-edge collaborative system includes an edge node cluster and a cloud management platform for managing the edge node cluster. The edge node cluster includes a first edge node and a second edge node sorted in descending order. The cloud management platform includes: a receiving module for receiving a first task input by a user; a configuration module for: configuring the first edge node to disassemble the first task to obtain a second task; configuring the first edge node to send the second task to the second edge node, so that the second edge node completes the second task.

[0020] In one possible implementation, the edge node cluster includes a first edge node, a second edge node, and a third edge node, which are sorted in descending order of level, and the configuration module is further used to: configure the second edge node to disassemble the second task to obtain a third task; configure the second edge node to send the third task to the third edge node, so that the third edge node completes the third task.

[0021] In a possible implementation, there are multiple second edge nodes, there are multiple third edge nodes, the first edge node is used to manage the multiple second edge nodes, and one second edge node is used to manage the multiple third edge nodes.

[0022] In one possible implementation, the configuration module is also used to: configure the first edge node to obtain information about all second edge nodes and all third edge nodes in real time; configure any second edge node to obtain information about the first edge node, information about the remaining second edge nodes, and information about all third edge nodes in real time; configure any third edge node to obtain information about the first edge node, information about all second edge nodes, and information about the remaining third edge nodes in real time.

[0023] In one possible implementation, the configuration module is also used to: configure the first edge node to select the best third edge node as a new second edge node from the multiple third edge nodes managed by the failed second edge node based on information of the multiple third edge nodes managed by the failed second edge node after determining that any second edge node has failed, and the new second edge node is used to manage the remaining third edge nodes managed by the failed second edge node.

[0024] In one possible implementation, the configuration module is further used to: configure multiple second edge nodes to select an optimal second edge node from multiple second edge nodes as a new first edge node based on information of the multiple second edge nodes after determining that the first edge node has failed, and the new first edge node is used to manage the remaining second edge nodes; configure the new first edge node to select an optimal third edge node from multiple third edge nodes managed by the optimal second edge node as a new second edge node, and the new second edge node is used to manage the remaining third edge nodes managed by the optimal second edge node.

[0025] In one possible implementation, the configuration module is further used to: configure the first edge node to determine a third edge node that has not failed from multiple third edge nodes managed by the failed second edge node after determining that any second edge node has failed, and to enable another second edge node to manage the third edge node that has not failed.

[0026] In one possible implementation, the configuration module is also used to: when configuring any third edge node to be in a network disconnected state, attempt to establish a network connection with the first edge node or the second edge node used to manage the third edge node in the network disconnected state; if the attempt fails, execute a preset action after completing the third task.

[0027] In a possible implementation, the configuration module is further used to configure any second edge node to attempt to establish a network connection with the first edge node when the second edge node is in a network disconnected state, and to execute a preset action if the attempt fails.

[0028] In one possible implementation, the receiving module is also used to receive a creation request for an edge node cluster input by a user; the cloud management platform also includes: a creation module, which is used to set the multiple edge nodes to be set as a first edge node, multiple second edge nodes managed by the first edge node, and multiple third edge nodes managed by each of the multiple second edge nodes based on the creation request.

[0029] A third aspect of an embodiment of the present application provides a computing device cluster, the computing device cluster includes at least one computing device, each computing device includes a processor and a memory: the memory is used to store instructions; the processor is used to enable the computing device cluster to execute the method described in the first aspect or any possible implementation method of the first aspect according to the instructions.

[0030] A fourth aspect of an embodiment of the present application provides a computer storage medium, which stores one or more instructions. When the instructions are executed by one or more computers, the one or more computers implement the method described in the first aspect or any possible implementation method of the first aspect.

[0031] A fifth aspect of the embodiments of the present application provides a computer program product, which stores instructions. When the instructions are executed by a computer, the computer implements the method described in the first aspect or any possible implementation method of the first aspect.

[0032] The embodiment of the present application provides a cloud-edge collaborative system including an edge node cluster and a cloud management platform for managing the edge node cluster, wherein the edge node cluster includes a first edge node, a second edge node, and a third edge node sorted from high to low in level. Since the cloud management platform has configured a task scheduling function for the first edge node, the second edge node, and the third edge node. Therefore, after receiving the first task input by the user, the cloud management platform can directly send the first task to the first edge node. Then, the first edge node can disassemble the first task to obtain the second task, and send the second task to the second edge node. Then, the second edge node can disassemble the second task to obtain the third task, and send the third task to the third edge node, so that the third edge node completes the third task. By repeating the aforementioned process continuously, the first edge node, the second edge node, and the third edge node can collaboratively complete the first task specified by the user. In the above process, since the cloud management platform has configured the task scheduling function for edge nodes at all levels in the edge node cluster (i.e., the first edge node, the second edge node, and the third edge node), even if the network connection between the edge node cluster and the cloud management platform is disconnected and the cloud management platform cannot participate, the edge nodes at all levels in the edge node cluster can cooperate with each other to independently disassemble and execute the tasks issued by the cloud management platform, thereby meeting user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic diagram of the structure of the cloud-edge collaboration system provided in the embodiment of the present application;

[0034] Figure 2 A schematic diagram of the structure of an edge node cluster provided in an embodiment of the present application;

[0035] Figure 3 A schematic diagram of the structure of an edge node provided in an embodiment of the present application;

[0036] Figure 4 A flow chart of an edge-cloud collaborative system provided in an embodiment of the present application;

[0037] Figure 5 Another schematic diagram of the structure of the edge node cluster provided in the embodiment of the present application;

[0038] Figure 6 A flowchart of task scheduling provided in an embodiment of the present application;

[0039] Figure 7 Another schematic diagram of the structure of the edge node cluster provided in the embodiment of the present application;

[0040] Figure 8 Another schematic diagram of the structure of the edge node cluster provided in the embodiment of the present application;

[0041] Fig. 9 Another schematic diagram of the structure of the edge node cluster provided in the embodiment of the present application;

[0042] Fig.10 A schematic diagram of the structure of the cloud management platform provided in the embodiment of the present application;

[0043] Fig.11 A schematic diagram of a computing device provided in an embodiment of the present application;

[0044] Fig.12 A schematic diagram of the structure of a computing device cluster provided in an embodiment of the present application;

[0045] Fig.13 A schematic diagram of computer devices in a computer cluster provided in an embodiment of the present application being connected via a network. DETAILED DESCRIPTION

[0046] The embodiments of the present application provide a task processing method and a cloud management platform based on a cloud-edge collaborative system. Even if the network connection between the edge node cluster and the cloud management platform is disconnected and the cloud management platform cannot participate, the edge nodes at all levels in the edge node cluster can cooperate with each other to complete the tasks issued by the cloud management platform independently, thereby meeting the needs of users.

[0047] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0048] The cloud-edge collaborative system refers to the technical architecture formed by the cloud and the edge. In this system, the cloud places tasks such as network forwarding, storage, computing, and data analysis to the edge to realize cloud services. Therefore, when providing cloud services to users, the cloud-edge collaborative system can effectively reduce the pressure on the cloud and reduce various operating costs.

[0049] At present, the cloud-edge collaborative system includes a cloud management platform and multiple edge nodes, among which the cloud management platform can manage these multiple edge nodes. When a user needs to complete a task, he can send the task to the cloud management platform. Then, the cloud management platform can distribute the task to each edge node to complete it, thereby meeting the needs of the user. For example, when a user needs to monitor a certain area, the cloud management platform can send the task to multiple drones, so that the drones fly to the area for monitoring, and return the corresponding detection results to the cloud management platform for users to view and use.

[0050] In the above-mentioned cloud-edge collaborative system, since multiple edge nodes rely on the cloud management platform for unified control, in some special cases, once multiple edge nodes are disconnected from the cloud management platform, the edge nodes cannot perform tasks autonomously and thus cannot meet user needs.

[0051] Furthermore, in the above-mentioned cloud-edge collaborative system, data synchronization between multiple edge nodes also needs to be implemented with the support of the cloud management platform. Once multiple edge nodes are disconnected from the cloud management platform, data synchronization cannot be achieved between the edge nodes, which will also affect the execution of tasks and thus fail to meet user needs.

[0052] Furthermore, in the above-mentioned cloud-edge collaborative system, the organizational structure formed by multiple edge nodes also needs to be controlled and adjusted by the cloud management platform. Once multiple edge nodes are disconnected from the cloud management platform, the organizational structure between the edge nodes will not be able to be appropriately adjusted in time when needed, which will also affect the execution of tasks and thus fail to meet user needs.

[0053] In order to solve the above problems, the embodiment of the present application provides a task processing method, which can be implemented through a cloud-edge collaborative system. Figure 1 A schematic diagram of the structure of the cloud-edge collaboration system provided in the embodiment of the present application is shown in FIG. Figure 1 As shown in the figure, the cloud-edge collaborative system includes the infrastructure that can provide cloud services and the cloud management platform that manages these infrastructures. The cloud management platform and infrastructure are introduced separately below:

[0054] The cloud management platform can coordinate the management of multiple edge nodes in the entire cloud service system (for example, arranging multiple edge nodes to be set into an edge node cluster presented in a tree structure, and configuring specific functions for each edge node in the edge node cluster, etc.), and can also be open to users outside the system and respond to their requests. For example, the cloud management platform can provide various interfaces such as login interface, creation interface and execution interface for access by the user's client (for example, the terminal device used by the user or the browser on the terminal device, etc.). Among them, the cloud management platform can authenticate the user's client through the login interface, and after successful authentication, the user's client can be allowed to log in to the cloud management platform. For another example, the cloud management platform can also allow the user's client to send a creation request for the edge node cluster to the cloud management platform through the creation interface, and then create an edge node cluster for the user based on the request. For another example, the cloud management platform can also allow the user's client to send a task to the cloud management platform through the execution interface, and then send the task to the edge node cluster, so that the edge node cluster can autonomously schedule and complete the task internally, thereby meeting the user's business needs.

[0055] The infrastructure includes an edge node cluster that is set up through a cloud management platform and can be used to execute user tasks. It is understandable that the edge node cluster is usually presented as a tree structure and includes at least two levels of edge nodes, and the higher-level edge nodes can be used to manage the lower-level edge nodes. For ease of explanation, the edge node with the highest level is referred to as the first edge node, the edge node with the second highest level is referred to as the second edge node, the edge node with the third highest level is referred to as the third edge node, the edge node with the fourth highest level is referred to as the fourth edge node, and so on. In order to further understand the edge node cluster provided in the embodiments of the present application, the following is combined with Figure 2 Further introduction to edge node clusters. Figure 2 A schematic diagram of the structure of the edge node cluster provided in the embodiment of the present application is as follows: Figure 2 As shown, assume that the edge node cluster is presented in a tree structure, and the tree structure includes three levels of edge nodes, wherein the number of first edge nodes as root nodes is one, the number of second edge nodes as intermediate nodes is multiple, the number of third edge nodes as leaf nodes is multiple, and the first edge node can be used to manage multiple second edge nodes, and each second edge node can be used to manage multiple third edge nodes. It should be noted that the first edge node and multiple second edge nodes can constitute an edge node group, and each second edge node and the multiple third edge nodes it manages can constitute an edge node group, so the edge node cluster can also be regarded as composed of multiple edge node groups.

[0056] It is worth noting that after the cloud management platform configures the multiple edge nodes to be configured into an edge node cluster, it can also install specific applications in the first edge node, the second edge node, the third edge node, etc. included in the edge node cluster, so as to configure specific functions for the first edge node, the second edge node, and the third edge node. Figure 3 As shown ( Figure 3 A structural diagram of an edge node provided in an embodiment of the present application) For any edge node in the edge node cluster (for example, the first edge node, the second edge node or the third edge node, etc.), from the hardware layer, the edge node may include various hardware such as a central processing unit (CPU), memory, network card and hard disk. Based on the hardware layer of the edge node, the cloud management platform can control the edge node to build a virtual instance (for example, a virtual machine (VM) or a container (docker), etc.) through virtualization technology. Furthermore, the cloud management platform can also install specific applications in the virtual instance of the edge node, and the specific application includes a distributed task scheduling module, a distributed cluster management module and a distributed data synchronization module. Then, since the cloud management platform has installed specific applications in the edge node, it is equivalent to configuring specific functions for the edge node, for example, the level setting function: the cloud management platform can set the level of the edge node in the edge node cluster (implemented through the distributed cluster management module), and the level adjustment function: the remaining edge nodes can adjust the level of the edge node in the edge node cluster (implemented through the distributed cluster management module). Another example is the level query function: the remaining edge nodes can query the level of the edge node in the edge node cluster (implemented through the distributed cluster management module), and another example is the task scheduling function: the edge node can perform task decomposition by itself, and after obtaining the subtasks, it can send the subtasks to the edge nodes managed by the edge node for execution (implemented through the distributed task scheduling module), and another example is the data synchronization function: the edge node can complete data synchronization with the remaining edge nodes by itself (implemented through the distributed data synchronization module), and so on.

[0057] Furthermore, for any edge node in the edge node cluster (for example, the first edge node, the second edge node or the third edge node, etc.), various sensors can be deployed on the edge node, and these sensors can be regarded as "terminals", so that the cloud management platform, the edge node and the sensor constitute a cloud-edge-end collaborative system. It can be understood that the sensor on the edge node is used to collect various task-related information so that the edge node can smoothly perform task scheduling or smoothly execute tasks.

[0058] Furthermore, the edge nodes of the embodiments of the present application can be presented in various ways, for example, the edge nodes can be drones, or smart vehicles, or inspection robots, etc. It can be seen that the cloud-edge collaboration system can be applied in various fields, such as smart inspection, high-altitude operations, autonomous driving, etc.

[0059] It can be seen that after the cloud management platform creates an edge node cluster, it can configure specific functions for the first edge node, the second edge node, the third edge node and other edge nodes contained in the edge node cluster. These functions include: (1) After the edge node cluster receives the task issued by the user, the edge nodes contained in the edge node cluster can cooperate with each other to complete the task scheduling together. (2) The edge nodes contained in the edge node cluster can also complete data synchronization by themselves. (3) The edge nodes contained in the edge node cluster can also adjust the internal structure of the edge node cluster (that is, adjust the level of one or some edge nodes) by themselves. (4) The edge nodes contained in the edge node cluster can also try to reconnect to the network after the network is disconnected, etc. It is precisely because of these functions that the edge node cluster can successfully complete the tasks issued by the user. In order to further understand the workflow of the edge-cloud collaborative system, the following is combined with Figure 4 To further introduce this workflow, Figure 4 A flow chart of an edge-cloud collaborative system provided in an embodiment of the present application is as follows: Figure 4 As shown, this method can be achieved by Figure 1 The cloud-edge collaborative system shown is implemented, and the method includes:

[0060] 401. The cloud management platform receives a first task input by a user.

[0061] In this embodiment, when the user needs to complete the first task with the help of the cloud, the cloud management platform can provide an execution interface (for example, a task input bar in the user interface, etc.) to the client used by the user, so the user can send the first task to the execution interface through the client, so that the cloud management platform receives the first task sent by the user's client through the execution interface.

[0062] After receiving the first task from the user, the cloud management platform can determine the edge node cluster that has been created for the user. For ease of explanation, the following is a schematic introduction that the edge node cluster includes three levels of edge nodes, such as Figure 2As shown, the edge node cluster presented in a tree structure may include a first edge node, a second edge node, and a third edge node, which are ordered from high to low levels, wherein the first edge node is the root node of the tree structure, so the number of first edge nodes is usually one, the second edge node is the middle node of the tree structure, so the number of second edge nodes is multiple, and the third edge node is the leaf node of the tree structure, so the number of third edge nodes is multiple, and the number of third edge nodes is greater than the number of second edge nodes. It can be seen that in the edge node cluster, the first edge node can be used to manage multiple second edge nodes, and each second edge node can be used to manage multiple third edge nodes.

[0063] Based on this, the cloud management platform may send the first task to the first edge node in the edge node cluster, so that the first edge node cooperates with the second edge node and the third edge node to complete the first task together.

[0064] For example, when a user needs to obtain data of a target area, the user can log in to the cloud management platform and enter the target task into the task input column provided by the cloud management platform, that is, the data of the target area needs to be obtained. After receiving the target task, the cloud management platform can call the drone cluster that provides services to the user. The drone cluster includes drone 1 as the root node, drones 2 to 4 as intermediate nodes, and drones 5 to 14 as leaf nodes. Therefore, the cloud management platform can send the target task to drone 1 as the root node, so that the drone cluster can cooperate with each other to complete the target task.

[0065] Specifically, before the user sends the first task to the cloud management platform, the cloud management platform can create an edge node cluster for the user in the following ways:

[0066] When a user needs to create a dedicated edge node cluster, the cloud management platform can provide a creation interface (for example, a cluster creation bar in the user interface, etc.) to the client used by the user, so the user can send a creation request for the user's dedicated edge node cluster to the creation interface through the client, so that the cloud management platform receives the creation request sent by the user's client through the creation interface. After receiving the creation request, the cloud management platform can set the levels of the multiple edge nodes to be set based on the creation request, that is, set the multiple edge nodes to be set as the first edge node, the multiple second edge nodes managed by the first edge node, and the multiple third edge nodes managed by the multiple second edge nodes, respectively, wherein the first edge node serves as the root node of the tree structure, all the second edge nodes serve as the intermediate nodes of the tree structure, and all the third edge nodes serve as the leaf nodes of the tree structure, so that an edge node cluster with a tree structure can be obtained, which can be used to provide cloud services for users.

[0067] In the user-exclusive edge node cluster, the cloud management platform can also configure specific functions for the first edge node, the second edge node, and the third edge node, including task scheduling, data synchronization, and level adjustment functions, etc., which will not be expanded here.

[0068] Still as in the above example, before the user issues the target task, the user can first create a dedicated drone cluster. The user can enter a creation request into the cluster creation column provided by the cloud management platform. The request is used to indicate that the user needs to create a drone cluster. Therefore, the cloud management platform can set a drone to be set as drone 1 (with the highest level) as the root node based on the creation request, set the three drones to be set as drones 2 to drone 4 (with middle levels) as intermediate nodes, and set the 10 drones to be set as drones 5 to drone 14 (with the lowest level) as leaf nodes. Therefore, a drone cluster with a tree structure can be obtained, which can be used to provide cloud services for users.

[0069] It should be understood that in this embodiment, the edge node cluster is only schematically introduced as including three levels of edge nodes, and does not limit the internal structure of the edge node cluster. The edge node cluster may also include only two levels of edge nodes, or the edge node cluster may also include four levels of edge nodes, or the edge node cluster may also include five levels of edge nodes, and so on, which can be set according to actual needs. For example, the edge node cluster may include a first edge node and a second edge node sorted from high to low levels, the first edge node being the root node of the tree structure, the second edge node being the leaf node of the tree structure, and so on. In this case, the first edge node as the root node needs to complete the task disassembly and distribution (for example, disassembling the first task into the second task and distributing it to the second edge node), and the second edge node as the leaf node needs to complete the task execution (for example, executing the second task). For another example, Figure 5 As shown ( Figure 5 Another structural diagram of the edge node cluster provided in the embodiment of the present application), the edge node cluster may include a first edge node, a second edge node, a third edge node and a fourth edge node arranged from high to low levels, the first edge node is the root node of the tree structure, the second edge node is the first-level intermediate node of the tree structure, the third edge node is the second-level intermediate node of the tree structure, the fourth edge node is the leaf node of the tree structure, and so on. In this case, the first edge node as the root node, the second edge node and the third edge node as the intermediate node need to complete the disassembly and distribution of the task, and the fourth edge node as the leaf node needs to complete the execution of the task.

[0070] 402. The cloud management platform configures the first edge node to decompose the first task to obtain a second task.

[0071] 403. The cloud management platform configures the first edge node to send the second task to the second edge node.

[0072] 404. The cloud management platform configures a second edge node to decompose the second task to obtain a third task.

[0073] 405. The cloud management platform configures the second edge node to send the third task to the third edge node, so that the third edge node completes the third task.

[0074] After receiving the first task, the first edge node can disassemble the first task by itself to obtain the second task, which is a subtask of the first task. Then, the first edge node can send the second task to multiple second edge nodes managed by it. After receiving the second task, multiple second edge nodes can disassemble the second task to obtain a third task, which is a subtask of the second task. Subsequently, multiple second edge nodes can send the third task to multiple third edge nodes managed by each of the multiple second edge nodes, so that the multiple third edge nodes managed by each of the multiple second edge nodes perform the third task.

[0075] It should be noted that the first task can be decomposed into multiple stages of second tasks, and the second task of each stage can be decomposed into multiple stages of third tasks. Then, the first edge node can first decompose the first task into multiple stages of second tasks, and then send the second task of the first stage to multiple second edge nodes. Multiple second edge nodes can decompose the second task of the first stage into multiple stages of third tasks, and send the third task of the first stage to multiple third edge nodes managed by multiple second edge nodes, so that these third edge nodes complete the third task of the first stage. Then, multiple second edge nodes can send the third task of the next stage to these third edge nodes, so that these third edge nodes complete the third task of the next stage, ..., until these third edge nodes complete the third task of the last stage. At this point, the second task of the first stage is successfully completed. Thereafter, the first edge node can also send the second task of the next stage to multiple second edge nodes, and multiple second edge nodes can decompose the second task of the next stage into multiple stages of third tasks, ..., and so on, until the second task of the last stage is successfully completed, which is equivalent to the edge node cluster successfully completing the first task and meeting the needs of users.

[0076] Still as in the above example, Figure 6 As shown ( Figure 6A flowchart of task scheduling provided in an embodiment of the present application is shown in FIG. 1 . After receiving the target task, UAV 1 can first analyze the target task, then perform a structured representation of the target task, and then comprehensively consider the preset task decomposition rules and the information of the UAVs as intermediate nodes (for example, the levels of these UAVs, the available resources of these UAVs, and the communication quality between these UAVs, etc.) to decompose the target task to obtain first-level subtasks of multiple stages, wherein the first-level subtask of the first stage is to plan a flight path to the target area, the first-level subtask of the second stage is to fly to the target area according to the path, and the first-level subtask of the third stage is to collect data for the target area.

[0077] Next, drone 1 can send the first-level subtask of the first stage to drones 2 to 4, and drones 2 to 4 can also disassemble the first-level subtask of the first stage in a similar manner to obtain multiple-stage second-level subtasks, where the first-stage second-level subtask is to determine the straight-line distance between the current position and the target area, and the second-level subtask of the second stage is to generate a straight path or a detour path based on the straight-line distance. Then, drones 2 to 4 can send the second-level subtask of the first stage to drones 5 to 14 under their respective management for execution, and then send the second-level subtask of the second stage to drones 5 to 14 under their respective management for execution, so that the first-level subtask of the first stage is completed.

[0078] Subsequently, UAV 1 can send the first-level subtask of the second stage to UAV 2 to UAV 4, and UAV 2 to UAV 4 can also disassemble the first-level subtask of the second stage in a similar manner, ..., and so on, until the first-level subtask of the third stage is successfully completed, which is equivalent to completing the target task.

[0079] Furthermore, during the process of the edge node cluster executing the first task, data synchronization can be completed within the edge node cluster in the following ways:

[0080] In the process of the first edge node, all the second edge nodes and all the third edge nodes working together to complete the first task, the first edge node can obtain the information of all the second edge nodes and the information of all the third edge nodes from all the second edge nodes and all the third edge nodes in real time. Similarly, for any one of the second edge nodes among all the second edge nodes, the second edge node can obtain the information of the first edge node, the information of the remaining second edge nodes and the information of all the third edge nodes from the first edge node, the remaining second edge nodes and all the third edge nodes in real time. Similarly, for any one of the third edge nodes among all the third edge nodes, the third edge node can obtain the information of the first edge node, the information of all the second edge nodes and the information of the remaining third edge nodes from the first edge node, all the second edge nodes and the remaining third edge nodes in real time. It can be seen that the edge node cluster constitutes an ad hoc network, and the first edge node, the second edge node and the third edge node inside it can complete data synchronization in real time.

[0081] It should be noted that the above-mentioned information of the edge node may refer to the status information of the edge node. For example, the information of the first edge node may refer to the status information of the first edge node, including the available resources of the first edge node and the communication quality of the first edge node, etc. For another example, for any second edge node among all second edge nodes, the information of the second edge node may refer to the status information of the second edge node, including the available resources of the second edge node and the communication quality of the second edge node, etc. For another example, for any third edge node among all third edge nodes, the information of the third edge node may refer to the status information of the third edge node, including the available resources of the third edge node and the communication quality of the third edge node, etc.

[0082] Furthermore, during the process of the edge node cluster executing the first task, if an edge node in the edge node cluster fails, the internal structure of the edge node cluster can be adjusted in the following ways:

[0083] (1) After determining that any one of the multiple second edge nodes fails, the first edge node may use information of the multiple third edge nodes managed by the second edge node as an evaluation result of the multiple third edge nodes managed by the second edge node, so as to determine and select the best third edge node from the multiple third edge nodes managed by the second edge node as a new second edge node based on the evaluation result, and let the new second edge node replace the second edge node to manage the remaining third edge nodes originally managed by the second edge node.

[0084] It should be noted that when the first edge node evaluates multiple third edge nodes managed by the second edge node, the evaluation is usually based on status information such as available resources and communication quality of these third edge nodes. Therefore, the first edge node can select the third edge node with the best status information (for example, the most available resources and / or the best communication quality, etc.) as the optimal third edge node.

[0085] Still as in the above example, Figure 7 As shown ( Figure 7 Another structural diagram of the edge node cluster provided in an embodiment of the present application), when UAV 1, which is the root node, determines that UAV 3, which is the intermediate node, fails, UAV 10 with the most available resources and the best communication quality can be selected from UAVs 8 to 11 managed by UAV 3 as a new intermediate node, so that UAV 10 replaces UAV 3 to manage UAVs 8, 9 and 11.

[0086] (2) After determining that a first edge node that manages multiple second edge nodes fails, the multiple second edge nodes can use the information of the multiple second edge nodes as evaluation results of the multiple second edge nodes, select the best second edge node from the multiple second edge nodes as a new first edge node based on the evaluation results, and use the new first edge node to replace the failed first edge node to manage the remaining second edge nodes originally managed by the failed first edge node.

[0087] Then, the new first edge node can use the information of multiple third edge nodes originally managed by the optimal second edge node (that is, the new first edge node) as the evaluation result of the multiple third edge nodes originally managed by the optimal second edge node, and select the optimal third edge node as the new second edge node from the third edge nodes originally managed by the optimal second edge node based on the evaluation result, and let the new second edge node replace the optimal second edge node to manage the remaining third edge nodes originally managed by the optimal second edge node.

[0088] It should be noted that when multiple second edge nodes evaluate multiple second edge nodes by themselves, the evaluation is usually based on status information such as available resources and communication quality of these second edge nodes. Therefore, multiple second edge nodes can negotiate to select the second edge node with the best status information (for example, the most available resources and / or the best communication quality, etc.) as the optimal second edge node.

[0089] It should be noted that when the new first edge node evaluates multiple third edge nodes originally managed by the optimal second edge node, the evaluation is usually based on status information such as available resources and communication quality of these third edge nodes. Therefore, the new first edge node can select the third edge node with the best status information (for example, the most available resources and / or the best communication quality, etc.) as the optimal third edge node.

[0090] Still as in the above example, Figure 8 As shown ( Figure 8 Another structural diagram of the edge node cluster provided in an embodiment of the present application), when UAV 2 to UAV 4, which are intermediate nodes, determine that UAV 1, which is the root node, has failed, they can select UAV 2 with the most available resources and the best communication quality from UAV 2 to UAV 4 as the new root node after negotiation, so that UAV 2 can replace UAV 1 to manage UAV 3 and UAV 4.

[0091] Then, drone 2 can select drone 6 with the most available resources and the best communication quality from drone 5 to drone 7 as a new intermediate node, and let drone 6 manage drone 5 and drone 7 instead of drone 2.

[0092] (3) After determining that any one of the multiple second edge nodes fails, the first edge node may determine a third edge node that has not failed from the multiple third edge nodes managed by the second edge node (for example, some of the multiple third edge nodes managed by the second edge node fail, while some of the third edge nodes do not fail. For another example, all of the multiple third edge nodes managed by the second edge node do not fail, etc.), and instruct another second edge node to act as the agent of the second edge node to manage these third edge nodes that have not failed.

[0093] Still as in the above example, Fig. 9 As shown ( Fig. 9 Another structural diagram of the edge node cluster provided in an embodiment of the present application) When drone 1, which is the root node, determines that drone 3, which is the intermediate node, fails, it can check whether there are any drones 8 to 11 managed by drone 3 that have not failed. Assume that drone 8 and drone 9 have not failed, and drone 10 and drone 11 have failed. Therefore, drone 1 can add drone 8 and drone 9 to the group of drone 2. In other words, drone 2 manages drones 5 to 9.

[0094] Furthermore, when the edge node cluster is executing the first task, if a network disconnection occurs inside the edge node cluster, the following methods can be used to resolve the problem:

[0095] (1) When any third edge node among multiple third edge nodes detects that it is in a network disconnected state, that is, it has left the self-organizing network formed by all edge nodes in the edge node cluster, the third edge node may attempt to establish a network connection with the first edge node or the second edge node used to manage the third edge node, so as to try to join the self-organizing network again. If the attempt fails, the preset action (for example, moving to a preset location, etc.) is performed after completing the third task.

[0096] Still taking the above example, suppose that after UAV 11 detects that the network connection between itself and UAV 4 is disconnected, it continuously tries to re-establish the network connection with UAV 4 or UAV 1 in order to enter the self-organizing network built by these UAVs. If the attempt fails, it means that it is called an orphan node. After completing the secondary subtask of a certain stage currently being executed, it flies to a designated location.

[0097] (2) When any second edge node among the multiple second edge nodes detects that it is in a network disconnected state, that is, it has left the self-organizing network formed by all edge nodes in the edge node cluster, the second edge node may attempt to establish a network connection with the first edge node to try to join the self-organizing network again. If the attempt fails, it executes a preset action (for example, moving to a preset location, etc.).

[0098] Still taking the above example, suppose that after UAV 4 detects that the network connection between itself and UAV 1 is disconnected, it continuously tries to re-establish the network connection with UAV 1 in order to enter the ad hoc network built by these UAVs. If the attempt fails, it means that it is called an orphan node and flies directly to a designated location.

[0099] The embodiment of the present application provides a cloud-edge collaborative system including an edge node cluster and a cloud management platform for managing the edge node cluster, wherein the edge node cluster includes a first edge node, a second edge node, and a third edge node sorted from high to low in level. Since the cloud management platform has configured a task scheduling function for the first edge node, the second edge node, and the third edge node. Therefore, after receiving the first task input by the user, the cloud management platform can directly send the first task to the first edge node. Then, the first edge node can disassemble the first task to obtain the second task, and send the second task to the second edge node. Then, the second edge node can disassemble the second task to obtain the third task, and send the third task to the third edge node, so that the third edge node completes the third task. By repeating the aforementioned process continuously, the first edge node, the second edge node, and the third edge node can collaboratively complete the first task specified by the user. In the above process, since the cloud management platform has configured the task scheduling function for edge nodes at all levels in the edge node cluster (i.e., the first edge node, the second edge node, and the third edge node), even if the network connection between the edge node cluster and the cloud management platform is disconnected and the cloud management platform cannot participate, the edge nodes at all levels in the edge node cluster can cooperate with each other to independently disassemble and execute the tasks issued by the cloud management platform, thereby meeting user needs.

[0100] Furthermore, since the cloud management platform has configured data synchronization functions for edge nodes at all levels in the edge node cluster, even if the network connection between the edge node cluster and the cloud management platform is disconnected and the cloud management platform cannot participate, edge nodes at all levels in the edge node cluster can complete data synchronization by themselves, thereby ensuring the smooth completion of the task and meeting user needs.

[0101] Furthermore, since the cloud management platform has configured the internal structure adjustment function of the cluster for edge nodes at all levels in the edge node cluster, even if the network connection between the edge node cluster and the cloud management platform is disconnected, and the cloud management platform cannot participate, if an edge node within the edge node cluster fails, the remaining edge nodes can also adjust the internal structure of the edge node cluster by themselves, thereby ensuring the normal operation of the edge node cluster, successfully completing tasks, and meeting user needs.

[0102] Furthermore, since the cloud management platform has configured the network reconnection function for edge nodes at all levels in the edge node cluster, when an edge node leaves the self-organizing network where the edge node cluster is located, the edge node can continuously try to join the self-organizing network on its own. If it fails, it will perform a bottom-line action. This not only ensures the stability of the structure and function of the edge node cluster, but also ensures the recovery of orphan nodes.

[0103] The above is a detailed description of the task processing method based on the cloud-edge collaborative system provided in the embodiment of the present application. The following will introduce the cloud management platform provided in the embodiment of the present application. Fig.10 A schematic diagram of the structure of the cloud management platform provided in the embodiment of the present application is shown in FIG. Fig.10 As shown in the figure, the cloud management platform is deployed in Figure 1 In the cloud-edge collaborative system shown, the cloud-edge collaborative system further includes an edge node cluster, the edge node cluster includes a first edge node, a second edge node, and a third edge node sorted from high to low in level, and the cloud management platform includes:

[0104] The receiving module 1001 is used to receive a first task input by a user; for example, the receiving module 1001 can be used to implement Figure 4 Step 401 in the illustrated embodiment.

[0105] The configuration module 1002 is used to: configure the first edge node to decompose the first task to obtain the second task; configure the first edge node to send the second task to the second edge node, so that the second edge node completes the second task. For example, the configuration module 1002 can be used to implement Figure 4 Step 402 to step 403 in the illustrated embodiment.

[0106] In a possible implementation, the edge node cluster includes a first edge node, a second edge node, and a third edge node, which are arranged in descending order of level, and the configuration module 1002 is further used to: configure the second edge node to decompose the second task to obtain the third task; configure the second edge node to send the third task to the third edge node, so that the third edge node completes the third task. For example, the configuration module 1002 can be used to implement Figure 4 Steps 404 to 405 in the illustrated embodiment.

[0107] In a possible implementation, there are multiple second edge nodes, there are multiple third edge nodes, the first edge node is used to manage the multiple second edge nodes, and one second edge node is used to manage the multiple third edge nodes.

[0108] In one possible implementation, the configuration module 1002 is also used to: configure the first edge node to obtain the information of all second edge nodes and all third edge nodes in real time; configure any second edge node to obtain the information of the first edge node, the information of the remaining second edge nodes and all third edge nodes in real time; configure any third edge node to obtain the information of the first edge node, the information of all second edge nodes and the information of the remaining third edge nodes in real time.

[0109] In one possible implementation, the configuration module 1002 is also used to: configure the first edge node to select the best third edge node as a new second edge node from the multiple third edge nodes managed by the failed second edge node based on information of the multiple third edge nodes managed by the failed second edge node after determining that any second edge node has failed, and the new second edge node is used to manage the remaining third edge nodes managed by the failed second edge node.

[0110] In one possible implementation, the configuration module 1002 is further used to: configure multiple second edge nodes to select an optimal second edge node from multiple second edge nodes as a new first edge node based on information of the multiple second edge nodes after determining that a first edge node fails, and the new first edge node is used to manage the remaining second edge nodes; configure the new first edge node to select an optimal third edge node from multiple third edge nodes managed by the optimal second edge node as a new second edge node, and the new second edge node is used to manage the remaining third edge nodes managed by the optimal second edge node.

[0111] In one possible implementation, the configuration module 1002 is further used to: configure the first edge node to determine a third edge node that has not failed from multiple third edge nodes managed by the failed second edge node after determining that any second edge node has failed, and to enable another second edge node to manage the third edge node that has not failed.

[0112] In one possible implementation, the configuration module 1002 is also used to: when any third edge node is configured to be in a network disconnected state, attempt to establish a network connection with the first edge node or the second edge node used to manage the third edge node in the network disconnected state; if the attempt fails, execute the preset action after completing the third task.

[0113] In a possible implementation, the configuration module 1002 is further configured to: configure any second edge node to attempt to establish a network connection with the first edge node when the second edge node is in a network disconnected state, and execute a preset action if the attempt fails.

[0114] In one possible implementation, the receiving module 1001 is also used to receive a creation request for an edge node cluster input by a user; the cloud management platform also includes: a creation module, which is used to set the multiple edge nodes to be set as a first edge node, multiple second edge nodes managed by the first edge node, and multiple third edge nodes managed by each of the multiple second edge nodes based on the creation request.

[0115] It should be noted that the information interaction, implementation process, etc. between the modules / units of the above-mentioned device are based on the same concept as the method embodiment of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown above in the embodiment of the present application, and will not be repeated here.

[0116] See also Fig.11 , Fig.11 A schematic diagram of a computing device provided in an embodiment of the present application. Fig.11 As shown, the computing device 1100 (which can be used to present the aforementioned cloud management platform) includes: a processor 1101, a memory 1102, a communication interface 1103 and a bus 1104. The processor 1101, the memory 1102 and the communication interface 1103 are coupled via a bus (not marked in the figure). The memory 1102 stores instructions. When the execution instructions in the memory 1102 are executed, the computing device 1100 executes the method executed by the cloud management platform in the above method embodiment.

[0117] The computing device 1100 may be one or more integrated circuits configured to implement the above method, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA), or a combination of at least two of these integrated circuit forms. For another example, when a unit in the device can be implemented in the form of a processing element scheduler, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0118] The processor 1101 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0119] The memory 1102 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0120] The memory 1102 stores executable program codes, and the processor 1101 executes the executable program codes to respectively implement the functions of the aforementioned receiving module and configuration module, thereby implementing the aforementioned task processing method based on the cloud-edge collaborative system. That is, the memory 1102 stores instructions for executing the aforementioned task processing method based on the cloud-edge collaborative system.

[0121] The communication interface 1103 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 1100 and other devices or a communication network.

[0122] In addition to the data bus, the bus 1104 may also include a power bus, a control bus, and a status signal bus, etc. The bus may be a peripheral component interconnect express (PCIe) bus, or an extended industry standard architecture (EISA) bus, a unified bus (Ubus or UB), a compute express link (CXL), a cache coherent interconnect for accelerators (CCIX), etc. The bus may be divided into an address bus, a data bus, a control bus, etc.

[0123] See also Fig.12 , Fig.12 A schematic diagram of the structure of a computing device cluster provided in an embodiment of the present application. Fig.12 As shown, the computing device cluster 1200 includes at least one computing device 1100 .

[0124] like Fig.12 As shown, the computing device cluster 1200 includes at least one computing device 1100. The memory 1102 in one or more computing devices 1100 in the computing device cluster 1200 may store the same instructions for executing the above-mentioned task processing method based on the cloud-edge collaborative system.

[0125] In some possible implementations, the memory 1102 of one or more computing devices 1100 in the computing device cluster 1200 may also respectively store partial instructions for executing the above-mentioned task processing method based on the cloud-edge collaborative system. In other words, the combination of one or more computing devices 1100 can jointly execute the above-mentioned task processing method based on the cloud-edge collaborative system.

[0126] It should be noted that the memory 1102 in different computing devices 1100 in the computing device cluster 1200 may store different instructions, which are respectively used to execute part of the functions of the above-mentioned cloud management platform. That is, the instructions stored in the memory 1102 in different computing devices 1100 may implement the functions of one or more modules such as the receiving module and the configuration module.

[0127] In some possible implementations, one or more computing devices 1100 in the computing device cluster 1200 may be connected via a network, which may be a wide area network or a local area network.

[0128] See also Fig.13 , Fig.13 A schematic diagram of computer devices in a computer cluster provided in an embodiment of the present application being connected via a network. Fig.13 As shown, two computing devices 1100A and 1100B are connected via a network. Specifically, they are connected to the network via a communication interface in each computing device.

[0129] In a possible implementation, the memory in the computing device 1100A stores instructions for executing functions of the receiving module and the like. Meanwhile, the memory in the computing device 1100B stores instructions for executing functions of the configuring module and the like.

[0130] It should be understood that Fig.13 The functions of the computing device 1100A shown in FIG. 1 may also be completed by multiple computing devices. Similarly, the functions of the computing device 1100B may also be completed by multiple computing devices.

[0131] The embodiment of the present application also relates to a computer storage medium, in which a program for signal processing is stored. When the program is run on a computer, the computer executes the following steps: Figure 4 The steps performed by the cloud management platform in the illustrated embodiment.

[0132] The present application also relates to a computer program product, which stores instructions, which, when executed by a computer, enable the computer to execute the following Figure 4 The steps performed by the cloud management platform in the illustrated embodiment.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A task processing method based on a cloud-edge collaborative system, characterized in that: The cloud-edge collaborative system includes an edge node cluster and a cloud management platform for managing the edge node cluster, the edge node cluster includes a first edge node and a second edge node sorted from high to low in level, and the method includes: The cloud management platform receives a first task input by a user; The cloud management platform configures the first edge node to decompose the first task to obtain a second task; The cloud management platform configures the first edge node to send the second task to the second edge node, so that the second edge node completes the second task.

2. The method according to claim 1, characterized in that The edge node cluster includes a first edge node, a second edge node, and a third edge node which are sorted in descending order of level, and the method further includes: The cloud management platform configures the second edge node to decompose the second task to obtain a third task; The cloud management platform configures the second edge node to send the third task to the third edge node, so that the third edge node completes the third task.

3. The method according to claim 2, characterized in that There are multiple second edge nodes, there are multiple third edge nodes, the first edge node is used to manage multiple second edge nodes, and one second edge node is used to manage multiple third edge nodes.

4. The method according to claim 3, characterized in that: The method further comprises: The cloud management platform configures the first edge node to obtain information of all second edge nodes and information of all third edge nodes in real time; The cloud management platform configures any second edge node to obtain information of the first edge node, information of other second edge nodes and information of all third edge nodes in real time; The cloud management platform configures any third edge node to obtain information about the first edge node, information about all second edge nodes, and information about the remaining third edge nodes in real time.

5. The method according to claim 3 or 4, characterized in that: The method further comprises: The cloud management platform configures the first edge node to select, after determining that any second edge node fails, an optimal third edge node from the multiple third edge nodes managed by the failed second edge node based on information of the multiple third edge nodes managed by the failed second edge node, as a new second edge node, wherein the new second edge node is used to manage the remaining third edge nodes managed by the failed second edge node.

6. The method according to any one of claims 3 to 5, characterized in that: The method further comprises: The cloud management platform configures the plurality of second edge nodes to select, after determining that the first edge node fails, an optimal second edge node from the plurality of second edge nodes based on information of the plurality of second edge nodes as a new first edge node, wherein the new first edge node is used to manage the remaining second edge nodes; The cloud management platform configures the new first edge node to select an optimal third edge node from multiple third edge nodes managed by the optimal second edge node as a new second edge node, and the new second edge node is used to manage the remaining third edge nodes managed by the optimal second edge node.

7. The method according to any one of claims 3 to 6, characterized in that: The method further comprises: The cloud management platform configures the first edge node to determine a third edge node that has not failed from multiple third edge nodes managed by the failed second edge node after determining that any second edge node has failed, and to enable another second edge node to manage the third edge node that has not failed.

8. The method according to any one of claims 3 to 7, characterized in that: The method further comprises: When any third edge node configured by the cloud management platform is in a network disconnected state, an attempt is made to establish a network connection with the first edge node or a second edge node used to manage the third edge node in a network disconnected state. If the attempt fails, a preset action is performed after completing the third task.

9. The method according to any one of claims 3 to 8, characterized in that: The method further comprises: When any second edge node configured by the cloud management platform is in a network disconnected state, an attempt is made to establish a network connection with the first edge node, and if the attempt fails, a preset action is executed.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: The cloud management platform receives a creation request for the edge node cluster input by the user; Based on the creation request, the cloud management platform respectively sets the multiple edge nodes to be set as the first edge node, the multiple second edge nodes managed by the first edge node, and the multiple third edge nodes managed by the multiple second edge nodes.

11. A cloud management platform, characterized in that: The cloud management platform is deployed in a cloud-edge collaborative system, the cloud-edge collaborative system includes an edge node cluster and a cloud management platform for managing the edge node cluster, the edge node cluster includes a first edge node and a second edge node sorted from high to low in level, and the cloud management platform includes: A receiving module, used for receiving a first task input by a user; Configuration modules for: configuring the first edge node to decompose the first task to obtain a second task; The first edge node is configured to send the second task to the second edge node, so that the second edge node completes the second task.

12. The cloud management platform according to claim 11, characterized in that: The edge node cluster includes a first edge node, a second edge node, and a third edge node which are sorted in descending order of level. The configuration module is further used for: configuring the second edge node to decompose the second task to obtain a third task; The second edge node is configured to send the third task to the third edge node, so that the third edge node completes the third task.

13. The cloud management platform according to claim 12, characterized in that: There are multiple second edge nodes, there are multiple third edge nodes, the first edge node is used to manage multiple second edge nodes, and one second edge node is used to manage multiple third edge nodes.

14. The cloud management platform according to claim 13, characterized in that: The configuration module is also used for: Configuring the first edge node to obtain information of all second edge nodes and information of all third edge nodes in real time; Configure any second edge node to obtain information of the first edge node, information of other second edge nodes, and information of all third edge nodes in real time; Any third edge node is configured to obtain information about the first edge node, information about all second edge nodes, and information about the remaining third edge nodes in real time.

15. The cloud management platform according to claim 13 or 14, characterized in that: The configuration module is also used for: After determining that any one of the second edge nodes fails, the first edge node is configured to select, based on information of multiple third edge nodes managed by the failed second edge node, an optimal third edge node from the multiple third edge nodes managed by the failed second edge node as a new second edge node, wherein the new second edge node is used to manage the remaining third edge nodes managed by the failed second edge node.

16. The cloud management platform according to any one of claims 13 to 15, characterized in that: The configuration module is also used for: After determining that the first edge node fails, configuring the multiple second edge nodes to select an optimal second edge node from the multiple second edge nodes as a new first edge node based on information of the multiple second edge nodes, wherein the new first edge node is used to manage the remaining second edge nodes; The new first edge node is configured to select an optimal third edge node from among multiple third edge nodes managed by the optimal second edge node as a new second edge node, and the new second edge node is used to manage the remaining third edge nodes managed by the optimal second edge node.

17. The cloud management platform according to any one of claims 13 to 16, characterized in that: The configuration module is also used for: After determining that any second edge node fails, the first edge node is configured to determine a third edge node that has not failed from multiple third edge nodes managed by the failed second edge node, and to enable another second edge node to manage the third edge node that has not failed.

18. The cloud management platform according to any one of claims 13 to 17, characterized in that: The configuration module is also used for: When any third edge node is configured to be in a network disconnected state, an attempt is made to establish a network connection with the first edge node or a second edge node for managing the third edge node in the network disconnected state. If the attempt fails, a preset action is performed after completing the third task.

19. The cloud management platform according to any one of claims 13 to 18, characterized in that: The configuration module is also used for: When any second edge node is configured to be in a network disconnected state, it attempts to establish a network connection with the first edge node, and if the attempt fails, executes a preset action.

20. The cloud management platform according to any one of claims 11 to 19, characterized in that: The receiving module is further configured to receive a creation request input by the user for the edge node cluster; The cloud management platform also includes: a creation module, which is used to set the multiple edge nodes to be set as the first edge node, the multiple second edge nodes managed by the first edge node, and the multiple third edge nodes managed by the multiple second edge nodes respectively based on the creation request.

21. A computing device cluster, characterized in that: The computing device cluster includes at least one computing device, each computing device including a processor and a memory: The memory is used to store instructions; The processor is configured to cause the computing device cluster to execute the method according to any one of claims 1 to 10 according to the instructions.

22. A computer storage medium, characterized in that The computer storage medium stores one or more instructions, which, when executed by one or more computers, enable the one or more computers to implement the method of any one of claims 1 to 10.

23. A computer program product, characterized in that The computer program product stores instructions, which, when executed by a computer, enable the computer to implement the method according to any one of claims 1 to 10.

Images