End-side collaborative intelligent task processing method and device in mobile scene, equipment and storage medium

Abstract

The invention discloses an end-edge cooperative intelligent task processing method, device and equipment in a mobile scene and a storage medium, and aims at the end-edge cooperative intelligent task processing in the mobile scene based on model segmentation in the switching process of a mobile intelligent terminal among coverage ranges of a plurality of edge nodes. Three task processing schemes of selecting original service node collaboration before switching, selecting affiliated node collaboration after switching and local processing are provided, and environment information such as computing power resources of the terminal equipment and the selected edge node, communication quality between the terminal equipment and the selected edge node, mobile position of the terminal equipment and the like are combined. Dynamic joint optimization decision making is carried out on an intelligent task processing scheme and model segmentation, so that the problems of dynamic decision making challenges caused by equipment environment and resource dynamic changes in a mobile scene and cold start caused by task migration between edge nodes are solved; and the processing time delay of the end-side collaborative intelligent task based on model segmentation in the node switching period of the end-side equipment is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of wireless communication technology, and specifically relates to a method, device, equipment and storage medium for end-edge collaborative intelligent task processing in a mobile scenario. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, large models represented by ChatGPT have received extensive attention and research. However, due to the further increase in the number of AI model parameters, the computing power required for AI model training and reasoning has exploded. At the same time, with the development of mobile smart terminals, the number of smart terminals has increased sharply, the smart business needs of mobile terminals have become richer, and the service quality requirements have further increased, which will bring massive smart task requests and data transmission on the mobile terminal side.

[0003] The traditional computing offloading paradigm based on cloud computing places computing and storage in a data center for centralized processing. On the one hand, the linearly growing computing devices in the cloud computing center cannot support the processing requests of massive computing-intensive intelligent applications. On the other hand, the massive edge data transmission will further increase the bandwidth load, making it difficult to ensure the real-time requirements of AI applications. Therefore, in order to address the problem of excessive centralized processing load, existing research considers sinking computing tasks from the cloud to the end and edge, and proposes an edge computing architecture. At the same time, it combines edge computing with AI and proposes the concept of edge intelligence. In order to further improve the computing performance of AI tasks and make full use of the available computing power and storage resources of the end-side devices, an end-edge collaborative intelligence paradigm based on model segmentation is proposed.

[0004] However, due to the dynamic changes in the communication environment and optional computing nodes of the device in the mobile scenario, and the coupling between model segmentation and task processing scheme decisions, how to make dynamic joint optimization decisions on model segmentation and task processing schemes for mobile terminal devices is an urgent challenge to be solved. At the same time, affected by the cache probability of different edge nodes, when the mobile terminal switches between different edge nodes, the migration of computing tasks between edge nodes may require the deployment of corresponding cache content, resulting in a cold start phenomenon, which in turn brings about the delay overhead of cache deployment.

[0005] It is crucial to propose a dynamic and efficient intelligent task processing solution for the end-edge collaborative architecture based on model segmentation in mobile scenarios. Summary of the invention

[0006] In view of this, an object of the present invention is to propose a method, apparatus, device and storage medium for end-edge collaborative intelligent task processing in a mobile scenario to solve or partially solve the problems mentioned in the background technology.

[0007] Based on the above objectives, in a first aspect, the present invention provides a method for device-edge collaborative intelligent task processing in a mobile scenario, comprising:

[0008] The central server receives a task processing request, which is initiated to the central server by a mobile intelligent terminal when generating an intelligent task, wherein the intelligent task includes an AI workflow task of model reasoning and model training;

[0009] The central server senses the available resources and environmental information of the devices in the current edge network to obtain the sensed data; the devices in the edge network include mobile intelligent terminals and edge nodes;

[0010] The central server uses the intelligent task processing decision algorithm according to the perception data to minimize the delay of the intelligent task end-edge collaborative processing based on model segmentation during node switching, makes a joint optimization decision on the processing scheme and model segmentation, and sends the joint optimization decision instruction to the mobile intelligent terminal and the edge node;

[0011] The mobile intelligent terminal and the edge node jointly execute the intelligent task according to the joint optimization decision of the processing scheme and the model segmentation, and return the execution result to the mobile intelligent terminal to complete the task processing request initiated by the mobile intelligent terminal.

[0012] As a preferred solution for the end-edge collaborative intelligent task processing method in a mobile scenario, if the intelligent task is determined by the intelligent task processing decision algorithm to be end-edge collaboratively processed by the original service edge node before switching, the current edge node and the adjacent nodes of the edge node are used as relays to establish a connection with the original service edge node, and model segmentation and collaborative processing are performed according to the model segmentation decision; the original service edge node is deployed with the AI ​​model required for the intelligent task before switching.

[0013] As a preferred solution for the end-edge collaborative intelligent task processing method in a mobile scenario, if the intelligent task is determined by the intelligent task processing decision algorithm to be end-edge collaboratively processed by the edge node to which it belongs after switching, it is determined whether the current edge node has a cache of the corresponding intelligent task model. If there is no cache of the corresponding intelligent task model, the model is requested from the data center; when the edge node has a cache of the corresponding intelligent task model, model segmentation and collaborative processing are performed according to the model segmentation decision.

[0014] As a preferred solution for the end-side collaborative intelligent task processing method in a mobile scenario, if the intelligent task is determined by the intelligent task processing decision algorithm to be processed locally, all intelligent task processing is completed on the end-side device.

[0015] As a preferred solution for the end-edge collaborative intelligent task processing method in a mobile scenario, the mobile intelligent terminal deploys the AI ​​model required for the intelligent task in advance;

[0016] The edge node randomly deploys the AI ​​model required for the intelligent task of the end-side device with a preset probability. If the edge node currently selected as the collaborative node has not deployed the AI ​​model in advance, the edge node currently selected as the collaborative node requests the data center equipped with the required model to download the model and complete the collaborative intelligent task processing;

[0017] The data center is a centralized network node of a macro base station and a cloud computing center to provide the AI ​​model cache required by the mobile smart terminal.

[0018] As a preferred solution for the end-edge collaborative intelligent task processing method in mobile scenarios, the available resources and environmental information of the devices in the current edge network include:

[0019] The available computing resources of the mobile intelligent terminal and the edge node, the location information of the mobile intelligent terminal, the communication environment between the mobile intelligent terminal and the edge node, and the cache status of the edge node;

[0020] The model segmentation regards the AI ​​model corresponding to the intelligent task initiated by the mobile intelligent terminal as a hierarchical structure, and each layer of the structure is regarded as a segmentation point; the segmentation point of the AI ​​model is obtained according to the model segmentation decision, and the AI ​​model is divided into two parts. The first half is processed on the terminal side device, and the intermediate feature data is transmitted to the selected collaborative node, and the selected node completes the model processing of the second half.

[0021] In a second aspect, the present invention provides a device-edge collaborative intelligent task processing apparatus in a mobile scenario, comprising:

[0022] A task processing request receiving module is used for the central server to receive a task processing request, wherein the task processing request is initiated to the central server when the mobile intelligent terminal generates an intelligent task, and the intelligent task includes an AI workflow task of model reasoning and model training;

[0023] A perception data acquisition module is used for the central server to perceive the available resources and environmental information of the devices in the current edge network to obtain perception data; the devices in the edge network include mobile intelligent terminals and edge nodes;

[0024] A joint optimization decision module is used for the central server to make joint optimization decisions on the processing scheme and model segmentation based on the perception data and the intelligent task processing decision algorithm, with the goal of minimizing the intelligent task end-edge collaborative processing delay based on model segmentation during node switching, and send the joint optimization decision instruction to the mobile intelligent terminal and the edge node;

[0025] The processing result returning module is used for the mobile intelligent terminal and the edge node to collaboratively execute the intelligent task according to the processing scheme and the joint optimization decision of the model segmentation, and return the execution result to the mobile intelligent terminal to complete the task processing request initiated by the mobile intelligent terminal.

[0026] As a preferred solution for the device-edge collaborative intelligent task processing device in a mobile scenario, in the joint optimization decision module:

[0027] If the intelligent task is determined by the intelligent task processing decision algorithm to be processed by the original service edge node before the switch, the current edge node and the adjacent nodes of the edge node are used as relays to establish a connection with the original service edge node, and model segmentation and collaborative processing are performed according to the model segmentation decision; the original service edge node is deployed with the AI ​​model required for the intelligent task before the switch;

[0028] If the intelligent task is determined by the intelligent task processing decision algorithm to be processed by the edge node after the switch, it is determined whether the current edge node has a cache of the corresponding intelligent task model. If there is no cache of the corresponding intelligent task model, the model is requested from the data center; when the edge node has a cache of the corresponding intelligent task model, model segmentation and collaborative processing are performed according to the model segmentation decision;

[0029] If the intelligent task is determined by the intelligent task processing decision algorithm to be processed locally, all intelligent task processing is completed on the terminal side device.

[0030] As a preferred solution for the device-edge collaborative intelligent task processing device in a mobile scenario, the mobile intelligent terminal deploys the AI ​​model required for the intelligent task in advance;

[0031] The edge node randomly deploys the AI ​​model required for the intelligent task of the end-side device with a preset probability. If the edge node currently selected as the collaborative node has not deployed the AI ​​model in advance, the edge node currently selected as the collaborative node requests the data center equipped with the required model to download the model and complete the collaborative intelligent task processing;

[0032] The data center is a centralized network node of a macro base station and a cloud computing center to provide the AI ​​model cache required by the mobile smart terminal.

[0033] As a preferred solution for the device-edge collaborative intelligent task processing device in the mobile scenario, the available resources and environmental information of the devices in the current edge network include:

[0034] The available computing resources of the mobile intelligent terminal and the edge node, the location information of the mobile intelligent terminal, the communication environment between the mobile intelligent terminal and the edge node, and the cache status of the edge node;

[0035] In the joint optimization decision module, the model segmentation regards the AI ​​model corresponding to the intelligent task initiated by the mobile intelligent terminal as a hierarchical structure, and each layer of the structure is regarded as a segmentation point; the segmentation point of the AI ​​model is obtained according to the model segmentation decision, and the AI ​​model is divided into two parts. The first half is processed on the terminal side device, and the intermediate feature data is transmitted to the selected collaborative node, and then the selected node completes the model processing of the second half.

[0036] According to a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an end-edge collaborative intelligent task processing method in a mobile scenario according to the first aspect or any possible implementation thereof is implemented.

[0037] In a fourth aspect, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable the computer to execute the end-edge collaborative intelligent task processing method in a mobile scenario of the first aspect or any possible implementation thereof.

[0038] From the above, it can be seen that the technical solution provided by the present invention is aimed at the end-edge collaborative intelligent task processing based on model segmentation in mobile scenarios when the mobile intelligent terminal switches between the coverage areas of multiple edge nodes. It proposes three task processing schemes: selecting the original service node for collaboration before switching, selecting the belonging node for collaboration after switching, and local processing. Combined with the computing power resources of the terminal device and the selected edge node, the communication quality between the two, the mobile location of the terminal device and other environmental information, a dynamic joint optimization decision is made on the intelligent task processing scheme and model segmentation to solve the dynamic decision-making challenges brought about by the dynamic changes of the device environment and resources in mobile scenarios, as well as the cold start problem caused by task migration between edge nodes, and reduce the processing delay of the end-edge collaborative intelligent tasks based on model segmentation during the node switching period of the end-side device. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1This is a schematic diagram of edge-end collaborative model reasoning based on model segmentation.

[0041] Figure 2 A schematic diagram of an AI end-edge collaborative reasoning solution based on model segmentation in the end-edge collaborative intelligent task processing method in a mobile scenario provided by an embodiment of the present invention;

[0042] Figure 3 A diagram showing training results of examples related to the method for processing end-edge collaborative intelligent tasks in a mobile scenario provided by an embodiment of the present invention;

[0043] Figure 4 An architecture diagram of a device-edge collaborative intelligent task processing apparatus in a mobile scenario provided by an embodiment of the present invention;

[0044] Figure 5 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0046] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The words "include" or "comprise" and the like used in the embodiments of the present invention mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, but do not exclude other elements or objects.

[0047] At present, in response to the problem of excessive centralized processing load, the existing technology considers sinking computing tasks from the cloud to the terminal side and edge side, and proposes the architecture of edge computing. At the same time, it combines edge computing with AI and proposes the concept of edge intelligence. In order to further improve the computing performance of AI tasks and make full use of the available computing power and storage resources of the terminal side devices, an end-edge collaborative intelligence paradigm based on model segmentation is proposed. For example, CN111445026B discloses a deep neural network multi-path reasoning acceleration for edge intelligent applications (prior art 1), which combines the structural characteristics of the AI ​​model, monitors and analyzes the network load and the computing power of the terminal and edge devices online in the edge computing environment, and cuts the multi-path model with the goal of minimizing the reasoning delay. The model blocks are deployed in the terminal layer and the edge layer respectively, and finally a multi-path reasoning acceleration framework is formed. In addition, considering that the mobile smart device itself has the characteristics of mobility, which causes its environment and available resources to change all the time, when the mobile smart device switches between different edge nodes, the task processing overhead will increase due to service migration and the lack of required cache on the edge node, which poses a challenge to the real-time dynamic offloading decision.

[0048] In the related technology, CN109862592B discloses a resource management and scheduling method in a mobile edge computing environment based on multi-base station collaboration, which considers dynamically migrating terminal computing tasks between the corresponding intelligent base station, the adjacent base stations of the corresponding intelligent base station, and the cloud, and optimizes transmission and computing delays, cache allocation, system benefits, etc. (prior technology 2).

[0049] However, prior art 1 only considers the end-edge collaborative AI reasoning solution based on model segmentation deployment, without considering the problems and challenges brought by the mobility of terminal devices to model segmentation decisions and resource scheduling. At the same time, prior art 2 only considers the migration deployment solution of computing tasks in mobile scenarios, ignores the computing power of terminal devices, and does not consider the improvement of AI intelligent service performance brought by the end-edge collaborative intelligent solution based on model segmentation. Comprehensively considering the existing technologies, there is a lack of end-edge collaborative intelligent task processing solutions for mobile scenarios based on model segmentation. Due to the dynamic changes in the communication environment of the device and the optional computing nodes and other resources in the mobile scenario, and the mutual coupling of model segmentation and task processing solution decisions, how to dynamically jointly optimize the model segmentation and task processing solutions is a challenge that needs to be solved urgently. At the same time, affected by the cache probability of different edge nodes, when the mobile terminal switches between different edge nodes, the migration of computing tasks between edge nodes may require the deployment of corresponding cache content, resulting in a cold start phenomenon, which in turn brings about the delay overhead of cache deployment. Therefore, it is crucial to propose a dynamic and efficient intelligent task processing solution for the end-edge collaborative architecture based on model segmentation in mobile scenarios, which is also the technical problem to be solved by this technical solution.

[0050] In view of this, the embodiments of the present invention propose a method, device, equipment and storage medium for end-edge collaborative intelligent task processing in mobile scenarios, which is based on model segmentation when a mobile intelligent terminal switches between the coverage areas of multiple edge nodes. The task processing scheme and model segmentation decision are jointly optimized to solve the dynamic decision-making challenges brought about by the dynamic changes of device environment and resources in mobile scenarios, as well as the cold start problem caused by task migration between edge nodes, and reduce the processing delay of end-edge collaborative intelligent tasks based on model segmentation when the end-side device is in node switching. The following is the specific content of the embodiments of the present invention.

[0051] In this embodiment, AI model reasoning is used as an example to illustrate the solution proposed by the present invention. Figure 1 As shown in the figure, it shows the schematic diagram of AI end-edge collaborative reasoning based on model segmentation. The AI ​​model is regarded as a hierarchical structure, and the total number of layers of the AI ​​model is defined as N. Two virtual layer structures l0 and l1 are added at the input and output ends respectively. N+1 , it is stipulated that l0 is executed on the end-side device, l N+1Executed on the base station side. Each layer of the AI ​​model can be used as a split point. If the selected split point is layer m, then l0~l m Execute on the client device. m+1 ~l N+1 Executed on the base station side. Define the amount of intermediate feature data after the i-th layer split point as I i , the computational load of the i-th layer is L i .

[0052] See also Figure 2 , an embodiment of the present invention provides a method for device-edge collaborative intelligent task processing in a mobile scenario, comprising the following steps:

[0053] Step 1: The central server receives a task processing request, which is initiated to the central server when a mobile smart terminal generates an intelligent task. The intelligent task includes an AI workflow task of model reasoning and model training.

[0054] Step 2: The central server senses the available resources and environmental information of the devices in the current edge network to obtain perception data; the devices in the edge network include mobile smart terminals and edge nodes; wherein the perception data includes the available computing resources of the mobile smart terminal and the edge node, the location information of the mobile smart terminal, the communication environment between the mobile smart terminal and the edge node, and the cache status of the edge node.

[0055] Step 3: The central server uses an intelligent task processing decision algorithm based on the perception data to minimize the latency of the intelligent task end-edge collaborative processing based on model segmentation during node switching, makes a joint optimization decision on the processing scheme and model segmentation, and sends the joint optimization decision instruction to the mobile intelligent terminal and the edge node.

[0056] Specifically, Figure 2 As shown, any layer of the AI ​​model can be selected for segmentation. For the end-to-end collaborative AI reasoning tasks based on model segmentation when the mobile intelligent terminal switches between the coverage areas of multiple edge nodes, there are three different processing schemes: 1) Execute locally on the mobile terminal; 2) Unload the intelligent task segmentation to the current edge node after switching for edge-to-end collaborative reasoning; 3) Unload the intelligent task segmentation to the original service edge node before switching for edge-to-end collaborative reasoning, select the current edge node and the adjacent nodes of the edge node as relays, and maintain connection with the original service node to collaboratively execute reasoning tasks.

[0057] The mobile intelligent terminal deploys the AI ​​model required for the intelligent task in advance;

[0058] The edge node randomly deploys the AI ​​model required for the intelligent task of the end-side device with a preset probability. If the edge node currently selected as the collaborative node has not deployed the AI ​​model in advance, the edge node currently selected as the collaborative node requests the data center equipped with the required model to download the model and complete the collaborative intelligent task processing;

[0059] The data center is a centralized network node of a macro base station and a cloud computing center to provide the AI ​​model cache required by the mobile smart terminal.

[0060] The available resources and environment information of the devices in the current edge network include:

[0061] The available computing resources of the mobile intelligent terminal and the edge node, the location information of the mobile intelligent terminal, the communication environment between the mobile intelligent terminal and the edge node, and the cache status of the edge node;

[0062] The model segmentation regards the AI ​​model corresponding to the intelligent task initiated by the mobile intelligent terminal as a hierarchical structure, and each layer of the structure is regarded as a segmentation point; the segmentation point of the AI ​​model is obtained according to the model segmentation decision, and the AI ​​model is divided into two parts. The first half is processed on the terminal side device, and the intermediate feature data is transmitted to the selected collaborative node, and the selected node completes the model processing of the second half.

[0063] In this embodiment, the model segmentation decision is defined as:

[0064] l∈[0,1,...,N]

[0065] If the number of optional edge intelligent base stations is M, the service execution decision is defined as:

[0066] x=[x 1,s ,x 1,r ,...,x M,s ,x M,s ]

[0067] where x i,s =1(i∈[1,M]) means that the i-th base station is selected as the service node and the task is split and offloaded to the base station for execution; x i,r =1(i∈[1,M]) means that the i-th base station is selected as the relay node, and a connection is established with the original serving base station through the relay node to perform the task; Indicates that the task is executed locally on the device. It means that at the same time, the mobile terminal selects at most one edge base station for task offloading.

[0068] Step 4: If the intelligent task is determined by the intelligent task processing decision algorithm to be executed locally on the mobile terminal, the AI ​​model will not be split and unloaded, and will be executed entirely by the mobile terminal.

[0069] Step 5: If the intelligent task is determined by the intelligent task processing decision algorithm to perform end-edge collaborative reasoning on the edge node after the switch, the central server will model the reasoning task initiated by the mobile terminal according to the local computing power, the computing power of the edge node, the channel state between the terminal and the node, and other environmental information, and distribute the model segmentation decision to the mobile terminal and the edge node for collaborative intelligent processing. If the edge node does not cache the corresponding model in advance, it is necessary to request the data center equipped with the required model to download the model and complete the end-edge collaborative reasoning.

[0070] Step 6: If the intelligent task is determined by the intelligent task processing decision algorithm to perform end-edge collaborative reasoning on the original service edge node before switching, the current edge node and the adjacent nodes of the current edge node are used as relays to establish a connection with the original service edge node. The central server models the intelligent reasoning tasks initiated by the mobile terminal according to environmental information such as local computing power, computing power of the original service edge node, and channel status between the terminal and the edge node, and distributes the model segmentation decisions to the mobile terminal and the original service edge node for end-edge collaborative reasoning. The intermediate feature data after model segmentation is transmitted to the original service edge node by the edge node to which it belongs and the adjacent nodes of the edge node as relays. The overhead of data migration between nodes is H, and the maximum number of relay nodes is set to e max .

[0071] Step 7: The mobile intelligent terminal and the edge node jointly execute the intelligent task according to the processing scheme and the joint optimization decision of the model segmentation, and return the execution result to the mobile intelligent terminal to complete the task processing request initiated by the mobile intelligent terminal.

[0072] Specifically, if you choose to execute the task locally, the intelligent task processing delay is:

[0073]

[0074] Among them, f local Provide local computing resources for users;

[0075] If the edge node to which it belongs is selected for device-edge collaborative reasoning after the switch, the intelligent task processing delay includes local computing delay, intermediate feature transmission delay, base station side computing delay and cache download delay:

[0076]

[0077] Among them, l jis the selected model split point, Calculate the latency locally. Calculate the delay on the edge node side, f i is the computing resource of the selected node, is the intermediate characteristic transmission delay, R i is the data transmission rate of the wireless channel between the mobile terminal and its edge node, is the cache download delay, Q is the required cache data volume, R c is the data transmission rate between the data center and the edge node. i Used to indicate the cache status of edge node i. If S i =1, it means that node i has cached the required model. If S i =0, it means that node i does not cache the required model and needs to download the cache from the data center.

[0078] Specifically, if the original service edge node is selected for device-edge collaborative reasoning before switching, the intelligent task processing delay includes local computing delay, intermediate feature transmission delay, node-side computing delay, and inter-node switching delay, which is:

[0079]

[0080] Where H is the switching delay between the current node and the adjacent node, which is related to the data transmission between nodes and the node reconfiguration overhead. sum is the cumulative switching delay between the neighboring node of the node and the original service node. If the neighboring node of the node is the original service node, then H sum =0. Γ is the penalty factor. If the number of selected relay nodes exceeds the threshold e max , then Γ is an infinite positive real number, otherwise Γ=0.

[0081] Among them, by combining different task execution plan decision variables with the corresponding task processing delay, the total task processing delay can be obtained as:

[0082]

[0083] Furthermore, when a mobile intelligent terminal switches between the coverage areas of multiple edge nodes, minimizing the latency of device-edge collaborative reasoning based on model segmentation can be transformed into the following problem:

[0084]

[0085] This optimization problem is a discrete optimization problem, and the task reasoning scheme decision and the model segmentation decision can be jointly optimized and scheduled in real time through the reinforcement learning algorithm. Specifically, a deep reinforcement learning algorithm framework based on the actor-critic structure is designed. The model input is the perception data, including the available computing power resources of the mobile smart terminal and the edge node, the location information of the mobile smart terminal, the communication environment between the mobile smart terminal and the edge node, and the cache status of the edge node; the model output is the service execution decision and the model segmentation decision. The opposite of the end-edge collaborative reasoning delay is used as the reward function to guide the reinforcement learning model to train until the model converges, and a joint optimization decision that minimizes the end-edge collaborative intelligent task processing delay is obtained. Solve the dynamic decision-making challenges brought about by the dynamic changes of device environment and resources in mobile scenarios, as well as the cold start problem caused by task migration between edge nodes, and reduce the processing delay of end-edge collaborative intelligent tasks based on model segmentation during node switching of the end-side device.

[0086] In order to verify the technical effect of the present invention, the following calculation examples are designed:

[0087] Consider a traffic scenario of 6300m*3500m, including a mobile vehicle user and multiple roadside base station units, where the maximum speed of the mobile vehicle user is 25m / s, and the roadside base station units are deployed at intervals of 250m. The mobile vehicle user and the roadside base station unit collaborate to perform image classification tasks based on Alexa Net. The computing power of the mobile vehicle is set to a CPU clock frequency of 20GHz, and the computing power of the roadside base station unit is randomly generated with a CPU clock frequency in the range of 80-100GHz. The mobile vehicle signal transmission power is 0.2W, the transmission bandwidth is 10MHz, the carrier frequency is 5.9GHz, and the path loss model refers to formula 16.7log 10 d+38.77+18.2log 10 f c , where is the distance between the mobile vehicle and the roadside base station unit, is the carrier frequency, and the channel noise power is -174dBm / Hz.

[0088] See also Figure 3 , for the problem of minimizing the latency of edge-to-edge collaborative reasoning based on model segmentation, this embodiment uses an actor-critic based deep reinforcement learning algorithm, and uses the inverse of the latency of edge-to-edge collaborative reasoning as the reward function for training to obtain the joint optimization decision of service execution and model segmentation. It can be seen from the training convergence curve in the figure below that the inference latency achieved by the algorithm used in this embodiment is close to the optimal performance of the exhaustive solution, and the convergence result is stable, indicating that the joint optimization of service execution and model segmentation decisions can be achieved and near-optimal performance can be achieved.

[0089] To summarize, the embodiment of the present invention receives a task processing request through a central server, and the task processing request is initiated to the central server when a mobile smart terminal generates an intelligent task, and the intelligent task includes AI workflow tasks of model reasoning and model training; the central server senses the available resources and environmental information of the devices in the current edge network to obtain perception data; the devices in the edge network include mobile smart terminals and edge nodes; the central server uses an intelligent task processing decision algorithm based on the perception data to minimize the end-edge collaborative processing delay of the intelligent task based on model segmentation during node switching, and makes a joint optimization decision on the processing scheme and model segmentation, and sends the joint optimization decision instruction to the mobile smart terminal and the edge node; the mobile smart terminal and the edge node collaboratively execute the intelligent task according to the joint optimization decision of the processing scheme and the model segmentation, and return the execution result to the mobile smart terminal to complete the task processing request initiated by the mobile smart terminal. Among them, if the intelligent task is judged by the intelligent task processing decision algorithm as the original service edge node performs end-side collaborative processing before switching, the current edge node and the adjacent nodes of the edge node are used as relays to establish a connection with the original service edge node, and model segmentation and collaborative processing are performed according to the model segmentation decision; the original service edge node is deployed with the AI ​​model required for the intelligent task before switching; if the intelligent task is judged by the intelligent task processing decision algorithm as the edge node to which it belongs performs end-side collaborative processing after switching, it is determined whether the current edge node has a cache of the corresponding intelligent task model, and if there is no cache of the corresponding intelligent task model, the model is requested from the data center; when the edge node has a cache of the corresponding intelligent task model, model segmentation and collaborative processing are performed according to the model segmentation decision; if the intelligent task is judged by the intelligent task processing decision algorithm as being processed locally, all intelligent task processing is completed on the end-side device. The present invention solves the dynamic decision-making challenges brought about by the dynamic changes of device environment and resources in mobile scenarios, as well as the cold start problem caused by task migration between edge nodes, and reduces the processing delay of end-side collaborative intelligent tasks based on model segmentation during node switching of the end-side device.

[0090] It should be noted that the method of the embodiment of the present invention can be performed by a single device, such as a computer or a server. The method of this embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present invention, and the multiple devices will interact with each other to complete the described method.

[0091] It should be noted that some embodiments of the present invention are described above. In some cases, the actions or steps recorded can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] See also Figure 4 Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present invention further provides a device-edge collaborative intelligent task processing apparatus in a mobile scenario, including:

[0093] The task processing request receiving module 100 is used for the central server to receive the task processing request, wherein the task processing request is initiated to the central server when the mobile intelligent terminal generates an intelligent task, and the intelligent task includes an AI workflow task of model reasoning and model training;

[0094] The perception data acquisition module 200 is used for the central server to perceive the available resources and environmental information of the devices in the current edge network to obtain the perception data; the devices in the edge network include mobile intelligent terminals and edge nodes;

[0095] The joint optimization decision module 300 is used for the central server to make joint optimization decisions on the processing scheme and model segmentation based on the perception data and the intelligent task processing decision algorithm, with the goal of minimizing the intelligent task end-edge collaborative processing delay based on model segmentation during node switching, and send the joint optimization decision instruction to the mobile intelligent terminal and the edge node;

[0096] The processing result returning module 400 is used for the mobile intelligent terminal and the edge node to collaboratively execute the intelligent task according to the processing scheme and the joint optimization decision of the model segmentation, and return the execution result to the mobile intelligent terminal to complete the task processing request initiated by the mobile intelligent terminal.

[0097] In this embodiment, in the joint optimization decision module 300:

[0098] If the intelligent task is determined by the intelligent task processing decision algorithm to be processed by the original service edge node before the switch, the current edge node and the adjacent nodes of the edge node are used as relays to establish a connection with the original service edge node, and model segmentation and collaborative processing are performed according to the model segmentation decision; the original service edge node is deployed with the AI ​​model required for the intelligent task before the switch;

[0099] If the intelligent task is determined by the intelligent task processing decision algorithm to be processed by the edge node after the switch, it is determined whether the current edge node has a cache of the corresponding intelligent task model. If there is no cache of the corresponding intelligent task model, the model is requested from the data center; when the edge node has a cache of the corresponding intelligent task model, model segmentation and collaborative processing are performed according to the model segmentation decision;

[0100] If the intelligent task is determined by the intelligent task processing decision algorithm to be processed locally, all intelligent task processing is completed on the terminal side device.

[0101] In this embodiment, the mobile intelligent terminal deploys the AI ​​model required for the intelligent task in advance;

[0102] The edge node randomly deploys the AI ​​model required for the intelligent task of the end-side device with a preset probability. If the edge node currently selected as the collaborative node has not deployed the AI ​​model in advance, the edge node currently selected as the collaborative node requests the data center equipped with the required model to download the model and complete the collaborative intelligent task processing;

[0103] The data center is a centralized network node of a macro base station and a cloud computing center to provide the AI ​​model cache required by the mobile smart terminal.

[0104] In this embodiment, the available resources and environment information of the devices in the current edge network include:

[0105] The available computing resources of the mobile intelligent terminal and the edge node, the location information of the mobile intelligent terminal, the communication environment between the mobile intelligent terminal and the edge node, and the cache status of the edge node;

[0106] In the joint optimization decision module, the model segmentation regards the AI ​​model corresponding to the intelligent task initiated by the mobile intelligent terminal as a hierarchical structure, and each layer of the structure is regarded as a segmentation point; the segmentation point of the AI ​​model is obtained according to the model segmentation decision, and the AI ​​model is divided into two parts. The first half is processed on the terminal side device, and the intermediate feature data is transmitted to the selected collaborative node, and then the selected node completes the model processing of the second half.

[0107] The device of the above embodiment is used to implement a corresponding end-edge collaborative intelligent task processing method in a mobile scenario in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0108] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an end-edge collaborative intelligent task processing method in a mobile scenario as described in any of the above embodiments is implemented.

[0109] Figure 5 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 510, a memory 520, an input / output interface 530, a communication interface 540, and a bus 550. The processor 510, the memory 520, the input / output interface 530, and the communication interface 540 are connected to each other through the bus 540 in the device.

[0110] The processor 510 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0111] The memory 520 may be implemented in the form of ROM (Read On ly Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 520 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 520 and are called and executed by the processor 510.

[0112] The input / output interface 530 is used to connect the input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0113] The communication interface 540 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WI FI, Bluetooth, etc.).

[0114] The bus 540 includes a path for transmitting information between the various components of the device (eg, the processor 510 , the memory 520 , the input / output interface 530 , and the communication interface 540 ).

[0115] It should be noted that, although the above device only shows the processor 510, the memory 520, the input / output interface 530, the communication interface 540 and the bus 540, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0116] The electronic device of the above-mentioned embodiment is used to implement a corresponding end-edge collaborative intelligent task processing method in a mobile scenario in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0117] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present invention also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute a terminal-edge collaborative intelligent task processing method in a mobile scenario as described in any of the above embodiments.

[0118] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0119] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute a terminal-edge collaborative intelligent task processing method in a mobile scenario as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0120] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0121] In addition, to simplify the description and discussion, and in order not to obscure the embodiments of the present invention, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the devices may be shown in the form of block diagrams to avoid obscuring the embodiments of the present invention, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present invention will be implemented (i.e., these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present invention, it will be apparent to those skilled in the art that embodiments of the present invention may be implemented without these specific details or with variations in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0122] Although the present invention has been described in conjunction with specific embodiments of the present invention, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0123] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the scope of the protection claimed. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for intelligent task processing in a mobile scenario by device-edge collaboration, wherein: include: The central server receives a task processing request, which is initiated to the central server by a mobile intelligent terminal when generating an intelligent task, wherein the intelligent task includes an AI workflow task of model reasoning and model training; The central server senses the available resources and environmental information of the devices in the current edge network and obtains the sensed data; The devices in the edge network include mobile intelligent terminals and edge nodes; The central server uses the intelligent task processing decision algorithm according to the perception data to minimize the delay of the intelligent task end-edge collaborative processing based on model segmentation during node switching, makes a joint optimization decision on the processing scheme and model segmentation, and sends the joint optimization decision instruction to the mobile intelligent terminal and the edge node; The mobile intelligent terminal and the edge node jointly execute the intelligent task according to the joint optimization decision of the processing scheme and the model segmentation, and return the execution result to the mobile intelligent terminal to complete the task processing request initiated by the mobile intelligent terminal.

2. According to claim 1, a method for processing intelligent tasks in a mobile scenario by device-edge collaboration, wherein: If the intelligent task is determined by the intelligent task processing decision algorithm to perform end-edge collaborative processing at the original service edge node before switching, the current edge node and the adjacent nodes of the edge node are used as relays to establish a connection with the original service edge node, and model segmentation and collaborative processing are performed according to the model segmentation decision; Before the switch, the original service edge node is deployed with the AI ​​model required for the intelligent task; If the intelligent task is determined by the intelligent task processing decision algorithm to be processed by the edge node after the switch, it is determined whether the current edge node has a cache of the corresponding intelligent task model. If there is no cache of the corresponding intelligent task model, the model is requested from the data center; when the edge node has a cache of the corresponding intelligent task model, model segmentation and collaborative processing are performed according to the model segmentation decision; If the intelligent task is determined by the intelligent task processing decision algorithm to be processed locally, all intelligent task processing is completed on the terminal side device.

3. According to the method for processing intelligent tasks in a mobile scenario in a device-edge collaborative manner, The mobile intelligent terminal deploys the AI ​​model required for the intelligent task in advance; The edge node randomly deploys the AI ​​model required for the intelligent task of the end-side device with a preset probability. If the edge node currently selected as the collaborative node has not deployed the AI ​​model in advance, the edge node currently selected as the collaborative node requests the data center equipped with the required model to download the model and complete the collaborative intelligent task processing; The data center is a centralized network node of a macro base station and a cloud computing center to provide the AI ​​model cache required by the mobile smart terminal.

4. According to the method for processing intelligent tasks in a mobile scenario in a device-edge collaborative manner, The available resources and environment information of devices in the current edge network include: The available computing resources of the mobile intelligent terminal and the edge node, the location information of the mobile intelligent terminal, the communication environment between the mobile intelligent terminal and the edge node, and the cache status of the edge node; The model segmentation regards the AI ​​model corresponding to the intelligent task initiated by the mobile intelligent terminal as a hierarchical structure, and each layer of the structure is regarded as a segmentation point; the segmentation point of the AI ​​model is obtained according to the model segmentation decision, and the AI ​​model is divided into two parts. The first half is processed on the terminal side device, and the intermediate feature data is transmitted to the selected collaborative node, and the selected node completes the model processing of the second half.

5. A device-edge collaborative intelligent task processing device in a mobile scenario, wherein: include: A task processing request receiving module is used for the central server to receive a task processing request, wherein the task processing request is initiated to the central server when the mobile intelligent terminal generates an intelligent task, and the intelligent task includes an AI workflow task of model reasoning and model training; A perception data acquisition module is used for the central server to perceive the available resources and environmental information of the devices in the current edge network to obtain perception data; the devices in the edge network include mobile intelligent terminals and edge nodes; A joint optimization decision module is used for the central server to make joint optimization decisions on the processing scheme and model segmentation based on the perception data and the intelligent task processing decision algorithm, with the goal of minimizing the intelligent task end-edge collaborative processing delay based on model segmentation during node switching, and send the joint optimization decision instruction to the mobile intelligent terminal and the edge node; The processing result returning module is used for the mobile intelligent terminal and the edge node to collaboratively execute the intelligent task according to the processing scheme and the joint optimization decision of the model segmentation, and return the execution result to the mobile intelligent terminal to complete the task processing request initiated by the mobile intelligent terminal.

6. The device-edge collaborative intelligent task processing apparatus in a mobile scenario according to claim 5, wherein: In the joint optimization decision module: If the intelligent task is determined by the intelligent task processing decision algorithm to perform end-edge collaborative processing at the original service edge node before switching, the current edge node and the adjacent nodes of the edge node are used as relays to establish a connection with the original service edge node, and model segmentation and collaborative processing are performed according to the model segmentation decision; Before the switch, the original service edge node is deployed with the AI ​​model required for the intelligent task; If the intelligent task is determined by the intelligent task processing decision algorithm to be processed by the edge node after the switch, it is determined whether the current edge node has a cache of the corresponding intelligent task model. If there is no cache of the corresponding intelligent task model, the model is requested from the data center; when the edge node has a cache of the corresponding intelligent task model, model segmentation and collaborative processing are performed according to the model segmentation decision; If the intelligent task is determined by the intelligent task processing decision algorithm to be processed locally, all intelligent task processing is completed on the terminal side device.

7. The device-edge collaborative intelligent task processing apparatus in a mobile scenario according to claim 5, wherein: The mobile intelligent terminal deploys the AI ​​model required for the intelligent task in advance; The edge node randomly deploys the AI ​​model required for the intelligent task of the end-side device with a preset probability. If the edge node currently selected as the collaborative node has not deployed the AI ​​model in advance, the edge node currently selected as the collaborative node requests the data center equipped with the required model to download the model and complete the collaborative intelligent task processing; The data center is a centralized network node of a macro base station and a cloud computing center to provide the AI ​​model cache required by the mobile smart terminal.

8. The device-edge collaborative intelligent task processing apparatus in a mobile scenario according to claim 5, wherein: The available resources and environment information of devices in the current edge network include: The available computing resources of the mobile intelligent terminal and the edge node, the location information of the mobile intelligent terminal, the communication environment between the mobile intelligent terminal and the edge node, and the cache status of the edge node; In the joint optimization decision module, the model segmentation regards the AI ​​model corresponding to the intelligent task initiated by the mobile intelligent terminal as a hierarchical structure, and each layer of the structure is regarded as a segmentation point; the segmentation point of the AI ​​model is obtained according to the model segmentation decision, and the AI ​​model is divided into two parts. The first half is processed on the terminal side device, and the intermediate feature data is transmitted to the selected collaborative node, and then the selected node completes the model processing of the second half.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the end-edge collaborative intelligent task processing method in a mobile scenario as described in any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the end-edge collaborative intelligent task processing method in a mobile scenario as described in any one of claims 1 to 4.

Images