Information processing method and device, electronic equipment, storage medium and computer program product

Abstract

This application discloses an information processing method, apparatus, electronic device, storage medium, and computer program product. The method includes: a first device using first information, second information, and third information of a first task to determine a joint allocation strategy for computing and communication resources related to the first task; wherein the first device is at least used for resource management in a network, the first task is collaboratively executed by one or more second devices, the first information characterizes a joint optimization objective for computing and communication resources related to the first task, the second information includes collaboration-related information of the first task, and the third information includes information related to the computing and communication resources available to the one or more second devices; and for each second device, sending the corresponding joint allocation strategy for computing and communication resources.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to an information processing method, apparatus, electronic device, storage medium, and computer program product. Background Technology

[0002] In related technologies, when performing computing tasks, networks can improve the efficiency of task execution by allocating network resources.

[0003] However, there is currently no effective solution for how to make full use of resources when allocating resources related to computing tasks. Summary of the Invention

[0004] To address the related technical problems, embodiments of this application provide an information processing method, apparatus, electronic device, storage medium, and computer program product.

[0005] The technical solution of this application embodiment is implemented as follows:

[0006] This application provides an information processing method applied to a first device, the first device being used at least for resource management in a network, including:

[0007] Using first information, second information, and third information of the first task, a strategy for allocating computing and communication resources related to the first task is determined; wherein the first task is executed collaboratively by one or more second devices, the first information characterizes the optimization objective of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information about computing and communication resources available to the one or more second devices.

[0008] For each second device, send the corresponding computing and communication resource allocation strategy.

[0009] The method in the above scheme further includes:

[0010] Obtain the first information.

[0011] In the above scheme, obtaining the first information includes:

[0012] The system receives a fifth message sent by a first function and uses the fifth message to determine the first message; wherein the first function is used at least for service management and orchestration, and the fifth message includes one or more of the following:

[0013] The first terminal contains information related to the optimization objectives of the first task, and the first terminal is used at least to initiate the first task.

[0014] The third device contains information related to the optimization objectives of the computing task, and the third device is at least used to provide services associated with the first task.

[0015] The first function generates optimization target-related information for the computational task.

[0016] The method in the above scheme further includes:

[0017] Obtain the second information, which includes one or more of the following:

[0018] Information related to the execution mode of collaboratively carrying out the first task;

[0019] The sixth information is used by the first device to determine the one or more second devices from a plurality of candidate devices;

[0020] Type-related information for the first model;

[0021] Information on one or more segmentation points of the first model;

[0022] Information on one or more exit points of the first model;

[0023] When the first task is executed using the first model, the communication resource information corresponding to each segmentation point of the first model;

[0024] When performing the first task using the first model, the computational resource information corresponding to each segment obtained based on each segmentation point of the first model is considered; wherein...

[0025] The first model can at least be used to perform the first task, and the candidate device can at least be used to collaboratively perform the task.

[0026] In the above scheme, obtaining the second information includes one of the following:

[0027] Receive the second information sent by the third device;

[0028] Receive the second information sent by the first terminal;

[0029] Receive the seventh information sent by the third device and the eighth information sent by the first terminal; use the seventh and eighth information to determine the second information; wherein,

[0030] The third device is used to provide services associated with the first task at least, the first terminal is used to initiate the first task at least, the seventh information is used to indicate one or more options associated with the second information, and the eighth information represents the selection result of the first terminal for the option indicated by the seventh information.

[0031] The method in the above scheme further includes:

[0032] The third information is obtained, and the third information includes one or more of the following:

[0033] Information related to available communication resources among multiple candidate devices;

[0034] Channel quality-related information among multiple candidate devices;

[0035] Information related to the available computing resources for each of the multiple candidate devices;

[0036] Energy consumption information for each of the multiple candidate devices;

[0037] Information related to the available resource validity period for each of the multiple candidate devices; among which,

[0038] The candidate devices are at least capable of collaboratively performing tasks, and the one or more second devices belong to the plurality of candidate devices.

[0039] In the above scheme, obtaining the third information includes:

[0040] Receive ninth information sent by one or more access network devices, and receive tenth information sent by the plurality of candidate devices; determine the third information using all the received ninth and tenth information; wherein,

[0041] The access network device is used to manage the communication resources of the plurality of candidate devices at least. The ninth information is associated with the communication resources of the plurality of candidate devices, and the tenth information is associated with the computing resources of the plurality of candidate devices.

[0042] This application embodiment also provides an information processing apparatus, disposed in a first device, the first device being used at least for resource management in a network, including:

[0043] A determining unit is configured to determine an allocation strategy for computing and communication resources related to the first task using first information, second information, and third information of the first task; wherein the first task is executed collaboratively by one or more second devices, the first information characterizes the optimization target of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information related to computing and communication resources available to the one or more second devices.

[0044] The sending unit is used to send the computing and communication resource allocation strategy corresponding to each second device.

[0045] This application also provides an electronic device, wherein the first device is at least used for resource management in a network, including:

[0046] A processor is configured to determine an allocation strategy for computing and communication resources related to a first task by utilizing first information, second information, and third information of a first task; wherein the first task is executed collaboratively by one or more second devices, the first information characterizes the optimization objective of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information related to computing and communication resources available to the one or more second devices.

[0047] The communication interface is used to send the computing and communication resource allocation strategy for each second device.

[0048] This application also provides an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor.

[0049] When the processor runs the computer program, it executes the steps of any of the above methods.

[0050] This application also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of any of the above methods.

[0051] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above methods.

[0052] The information processing method, apparatus, electronic device, storage medium, and computer program product provided in this application embodiment include a first device that uses first information, second information, and third information of a first task to determine a joint allocation strategy for computing and communication resources related to the first task; wherein, the first device is at least used for resource management in a network, the first task is executed collaboratively by one or more second devices, the first information represents the joint optimization objective of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information related to computing and communication resources available to the one or more second devices; and for each second device, a joint allocation strategy for computing and communication resources corresponding to the second device is sent. The solution provided in this application, when executing a computing task (i.e., the first task), simultaneously allocates (or jointly allocates) computing resources and communication resources for the computing task. When allocating, it considers: optimization objectives related to the simultaneous allocation of the two types of resources (such as minimizing end-to-end latency, reducing energy consumption, or improving resource utilization), the collaborative requirements of the computing task (such as AI model segmentation requirements), and the available resources of the devices that can collaboratively execute the computing task (i.e., the second device). In this way, it can achieve resource allocation that satisfies the optimization objectives as much as possible while making full use of resources. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating the information processing method according to an embodiment of this application;

[0054] Figure 2 This is a flowchart illustrating a resource optimization method for terminal collaboration, serving as an application example of this application.

[0055] Figure 3 This is a schematic diagram of the architecture of the Open Radio Access Network (O-RAN) used as an application example in this application.

[0056] Figure 4 A flowchart illustrating the process of setting optimization goals for the application example of this application;

[0057] Figure 5 This is a schematic diagram illustrating the process of obtaining task collaboration methods and generating and distributing resource allocation strategies under the O-RAN architecture, which is an application example of this application.

[0058] Figure 6 This is a schematic diagram of the information processing device structure according to an embodiment of this application;

[0059] Figure 7 This is a schematic diagram of the electronic device structure according to an embodiment of this application. Detailed Implementation

[0060] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0061] In existing wireless networks, the allocation of computing resources (which can also be understood as computing power resources or computing power resources) and the allocation of communication resources (which can also be understood as network resources or transmission resources, such as bandwidth resources) are usually carried out independently. That is to say, the computing scheduling mechanism related to the allocation of computing resources and the communication scheduling mechanism related to the allocation of communication resources are independent of each other.

[0062] In fourth-generation (4G) and fifth-generation (5G) mobile communication technology networks, one or more of the following schemes are typically used for resource allocation:

[0063] 1) The terminal (also known as the terminal device) offloads the computing task (or task) to a base station (also known as a standalone wireless base station or a single base station) near the terminal device, and the base station provides computing resources for executing the computing task; in this way, the terminal does not have to directly execute large computing tasks, reducing the computing burden of the terminal device; specifically, the terminal can determine whether to offload the computing task to the base station for execution based on the network connection status and / or channel quality.

[0064] 2) In scenarios employing Multi-access Edge Computing (MEC) technology, computing power is decentralized to the edge nodes of the wireless access network (also known as edge computing nodes). Terminals can offload computing tasks to these edge nodes, which then provide the computing resources for executing those tasks. Because the edge nodes are closer to the user terminal, data transmission latency is reduced, improving the terminal device's computing response speed and enabling low-latency computing task processing.

[0065] 3) The network allocates one or more of the following resources related to information transmission—bandwidth, time-domain resources (such as time slots), frequency-domain resources, and power resources—based on Quality of Service (QoS) requirements (one or more can also be understood as at least one)—to optimize the allocation of communication resources. For example, the scheduler in a 5G network can determine the priority of different services based on pre-defined policies in the base station and core network, and schedule communication resources based on the determined priorities.

[0066] Existing wireless network resource allocation strategies can solve the problem of allocating communication and computing resources to a certain extent; however, they still have certain limitations, including the following issues:

[0067] 1) Lack of inter-terminal collaboration mechanisms; specifically, terminals typically rely on base stations and / or edge computing nodes to assist in completing computing tasks, without fully considering the heterogeneity between terminals to achieve full utilization of other terminal resources. For example, terminals with weak computing power (which can also be understood as limited computing resources) but good network conditions (which can also be understood as good network connectivity or sufficient communication resources) cannot utilize terminals with strong computing power in the network to assist in completing computing tasks, resulting in a waste of computing resources; similarly, terminals with strong computing power but poor network conditions also find it difficult to utilize terminals with good network conditions as transmission relays or to assist in completing computing tasks (i.e., providing computing services). Here, terminals with strong computing power that can provide computing services can also be understood as computing user equipment (CUE).

[0068] 2) Independent scheduling of communication and computing resources; specifically, the allocation of computing and communication resources is usually optimized separately, failing to fully consider the dynamic relationship between computing and communication needs. This independent (or fragmented) resource scheduling method may lead to inefficient resource allocation. For example, when network bandwidth is insufficient, the base station may not consider the terminal's computing and communication needs simultaneously when allocating bandwidth, resulting in bandwidth being prioritized for low-priority data transmission tasks, affecting end-to-end task latency and system resource utilization.

[0069] 3) Network resource optimization solutions lack sufficient support for AI (Artificial Intelligence) model segmentation and heterogeneous computing architectures. Specifically, with the widespread application of AI, many terminals need to handle complex AI computing tasks, such as inference of deep learning models. Related technologies typically complete AI computing tasks locally on the terminal or completely offload AI computing tasks to edge computing nodes or the cloud, failing to flexibly support the segmentation and computation of AI models. For example, a large AI model can be divided into multiple parts, where some simpler parts can be executed locally on the terminal device, while more complex parts can be offloaded to edge computing nodes or the cloud. However, the resource allocation schemes in related technologies struggle to flexibly support model segmentation and collaborative computation, limiting the application efficiency of AI models.

[0070] Based on this, in various embodiments of this application, when executing a computing task, computing resources and communication resources for the computing task are allocated simultaneously (which can also be understood as joint allocation). When allocating, the following are considered: optimization objectives related to the simultaneous allocation of the two types of resources (such as minimizing end-to-end latency, reducing energy consumption, or improving resource utilization), the collaborative requirements of the computing task (such as AI model segmentation requirements), and the available resources of the devices that can collaboratively execute the computing task. In this way, resource allocation can be achieved to satisfy the optimization objectives as much as possible while making full use of resources.

[0071] This application provides an information processing method applied to a first device, which is at least used for resource management in a network, such as... Figure 1 As shown, the method includes:

[0072] Step 101: Using the first information, second information, and third information of the first task, determine the allocation strategy of computing resources and communication resources related to the first task; wherein, the first task is executed collaboratively by one or more second devices, the first information represents the optimization target of computing resources and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information on computing resources and communication resources available to the one or more second devices.

[0073] Step 102: For each second device, send the corresponding computing and communication resource allocation strategy.

[0074] In practical applications, the first device can be an electronic device already deployed in the network capable of resource management. For example, in an O-RAN architecture, the first device can be a Near-Real-Time RAN Intelligent Controller (NRT RIC). Alternatively, the first device can be a newly deployed electronic device capable of resource management within the network. This application does not limit the name of the first device, as long as its function is implemented; similarly, this application does not limit the network architecture for deploying the first device.

[0075] When a first terminal in the network needs to execute a first task (or initiate a first task), if the computing resources of the first terminal are limited and it is difficult to meet the execution requirements of the first task (such as latency requirements), the first device can schedule idle computing resources in the network, and one or more second devices can cooperate to execute the first task (or one or more second devices can assist the first terminal in executing the first task), thereby improving the execution efficiency of the task and meeting the execution requirements of the task. The first task can also be understood as a computing task or a computing power task; the name of the first task is not limited in this application embodiment. The terminal can be called a UE, user, etc., and this application embodiment does not limit this. The second device can also be understood as a cooperating device, specifically referring to a device that cooperates in executing the first task, such as an edge computing node, a computing power terminal, the first terminal, an access network device, etc. The name and specific implementation of the second device are not limited in this application embodiment.

[0076] In practical applications, the collaborative execution of the first task by one or more second devices means that, through resource allocation, the first task of the first terminal is completely or partially unloaded (unloading can also be understood as scheduling) and executed by one or more second devices. At this time, each second device needs to obtain information related to its own execution within the first task (hereinafter referred to as the task information of the second device) so that it can use the obtained information to collaboratively execute the first task. Here, when each second device obtains its own task information, the transmission of task information involves corresponding communication resources. If the communication resources for transmitting its own task information are limited for one or more second devices, it may result in these second devices being unable to execute the corresponding task in a timely manner, thus significantly affecting the execution efficiency of the first task.

[0077] Based on this, when allocating resources to one or more second devices collaboratively executing the first task, the first device can simultaneously allocate computing and communication resources. This ensures that when the one or more second devices collaboratively execute the first task, they can utilize sufficient computing resources for task processing and sufficient communication resources for transmitting task information and execution results. This guarantees the full and efficient use of network resources, achieving efficient execution of the first task. Here, simultaneously allocating computing and communication resources related to the first task can also be understood as: jointly allocating computing and communication resources related to the first task, or uniformly allocating computing and communication resources related to the first task, or allocating resources related to the first task that simultaneously meet both computing and communication resource requirements.

[0078] When the first device simultaneously allocates computing and communication resources related to the first task, it simultaneously considers the joint optimization objective of the two resources (which can also be understood as the optimization objective related to the simultaneous allocation of the two resources, or the joint optimization objective, i.e., the first information), the collaborative requirements of the computing task (i.e., the second information), and the available resources of each second device (i.e., the third information). This ensures that the allocated resources are feasible while meeting the task requirements, thereby obtaining a more reasonable resource allocation strategy.

[0079] Based on this, before executing step 101, the first device can first acquire the aforementioned multiple pieces of information that need to be considered (i.e., first information, second information, and third information), so that the first device can use all the acquired information to determine the resource allocation strategy. That is, in one embodiment, the method may further include one or more of the following:

[0080] Obtain the first information;

[0081] Obtain the second information;

[0082] Obtain the third information.

[0083] The first information can also be understood as resource optimization demand information or resource joint optimization target information, etc. The name of the first information is not limited in this application embodiment.

[0084] In practical applications, the first function of the network can acquire optimization target information generated (or set) by one or more devices (or multiple entities) of the network for the first task, and send the acquired optimization target information to the first device so that the first device can obtain the first information. The first function can also be understood as a service management and orchestration function (SMO). This application embodiment does not limit the name of the first function. The one or more devices can include one or more of the following: the first terminal, the third device, and the first function. The third device can also be understood as an application server, capable of providing services associated with computing tasks. This application embodiment does not limit the name of the third device, as long as its function is implemented.

[0085] Based on this, in one embodiment, obtaining the first information includes:

[0086] The system receives a fifth message sent by a first function and uses the fifth message to determine the first message; wherein the first function is at least used for service management and orchestration, and the fifth message contains optimization target-related information generated by one or more devices for the first task.

[0087] Specifically, when the one or more devices include the first terminal, the first terminal can generate optimization target-related information for the first task based on its own business logic and submit the generated optimization target-related information to the third device; then, the third device can send the received optimization target-related information to the first function, and the first function can then send the optimization target-related information to the first device. In this case, in one embodiment, the fifth information may include optimization target-related information from the first terminal and specific to the first task, whereby the first terminal is at least used to initiate the first task. In this case, the optimization target-related information may include one or more of the following:

[0088] Optimal service performance specifically means that the individual service performance indicators of the first terminal (such as end-to-end latency or service reliability) reach their optimal levels.

[0089] Optimal energy consumption (which can also be understood as meeting energy constraints) specifically means that the energy consumption of the one or more second devices performing the first task is the lowest, thereby achieving energy saving or meeting energy constraints.

[0090] When the one or more devices include the third device, the third device can generate optimization target-related information for a type of computing task corresponding to the first task based on internal logic, and send the generated optimization target-related information to the first function; then, the first function sends the optimization target-related information to the first device. In this case, in one embodiment, the fifth information may include optimization target-related information from the third device and for the computing task, wherein the third device is at least used to provide services associated with the first task. In this case, the optimization target-related information may include one or more of the following:

[0091] Optimal business performance specifically means that the overall business performance indicators (such as end-to-end latency or business reliability) of executing the first task are optimal.

[0092] Optimal energy consumption (which can also be understood as meeting energy constraints) specifically means that some or all of the one or more second devices consume the least energy when performing the first task, thereby achieving energy saving for the corresponding second device or meeting the energy constraints of the corresponding second device.

[0093] When the one or more devices include the first function, the first function can generate optimization target-related information for all computing tasks or a type of computing task corresponding to the first task based on its internal logic related to wireless network operation; then, the first function can send the optimization target-related information to the first device. In this case, in one embodiment, the fifth information may include the optimization target-related information for computing tasks generated by the first function. In this case, the optimization target-related information may include one or more of the following:

[0094] The lowest total system energy consumption specifically means that the overall energy consumption of the one or more second devices performing the first task is the lowest; here, the system refers to a system composed of all the second devices performing the first task.

[0095] The highest overall system resource utilization rate specifically means that the computing and / or communication resources of the one or more second devices performing the first task are utilized to the highest extent, thereby saving operating costs.

[0096] Load balancing across nodes within the system specifically means that the computational load of the one or more second devices performing the first task is balanced as much as possible.

[0097] As can be seen from the above description, the first device can receive optimization target-related information generated by one or more devices from the first function, including the first terminal, the third device, and the first function, according to actual needs. That is, the fifth information may include one or more of the following:

[0098] The first terminal contains information related to the optimization objectives of the first task, and the first terminal is used at least to initiate the first task.

[0099] The third device contains information related to the optimization objectives of the computing task, and the third device is at least used to provide services associated with the first task.

[0100] The first function generates optimization target-related information for the computational task.

[0101] When receiving optimization target-related information generated by multiple devices, the first device uses all the received optimization target-related information to determine the first information.

[0102] Regarding the second information, the second information is used to describe the specific way in which one or more second devices cooperate to perform the first task. The second information can also be called task cooperation method information. In this application embodiment, the name of the second information is not limited.

[0103] In practical applications, the collaborative execution of the primary task can be described by one or more of the following dimensions (one or more can also be understood as at least one):

[0104] The execution mode of collaboratively carrying out the first task (which can also be understood as a collaborative mode);

[0105] The preference for selecting one or more second devices from a pool of candidate devices capable of collaboratively performing the first task;

[0106] The type of the first model used to perform the first task;

[0107] The segmentation point of the first model;

[0108] The exit point of the first model;

[0109] The communication resources corresponding to each segment after the first model segmentation;

[0110] The computational resources corresponding to each segment after the first model is divided.

[0111] Specifically, the execution mode may include one of the following:

[0112] Unload all of the first task to the computing power platform;

[0113] Unload all of the first task to the computing power terminal;

[0114] The first task is executed collaboratively by the first terminal and the computing terminal (which can also be understood as collaborative computing);

[0115] The first task is executed collaboratively by the computing power platform and the computing power terminal;

[0116] The first task is executed collaboratively by the first terminal, the computing platform, and the computing terminal.

[0117] In practical applications, the second information may include relevant information for identifying and / or indicating the execution mode of the first task, such as an execution mode identifier. This relevant information may also be referred to as execution mode-related information for collaboratively executing the first task.

[0118] The selection preference for choosing one or more second devices from multiple candidate devices can be used to indicate one or more of the following: the priority of each candidate device being selected as a second device, the category of candidate devices that are preferred to be selected as second devices, and the candidate devices that are preferred to be selected as second devices.

[0119] In practical applications, the second information may include sixth information, which represents the aforementioned selection preference. Thus, the first device can utilize the sixth information to determine one or more second devices from multiple candidate devices. Specifically, the first device selects which second devices(s) to perform the first task based on the indication of the sixth information, or the first device determines which second devices(s) to perform the first task based on the priority indicated by the sixth information.

[0120] The first model specifically refers to the model that performs the first task, which may be a neural network model containing multiple layers (such as convolutional layers, output layers, etc.). This application embodiment does not limit the specific implementation and name of the first model. In practical applications, the second information may include type-related information of the first model to indicate its type. This type-related information may include the model name and / or version identifier, such as AlexNet_v0240101.

[0121] The first model may have one or more segmentation points, which indicate where the first model can be segmented and where each segment is computed. For example, the segmentation points of the Visual Geometry Group (VGG) 16 model are at layers 5 and 9. In practical applications, the second information may include information on one or more segmentation points of the first model to indicate one or more segmentation points of the first model.

[0122] The first model may have one or more exit points, which indicate where the first model can exit. For example, the exit point of the ResNet-18 model is at layer 9. In practical applications, the second information may include one or more exit point information of the first model to indicate one or more exit points of the first model.

[0123] After the first model is segmented at the segmentation point, multiple segments can be obtained. These segments can be deployed on different second devices, with each second device executing the computational task for its corresponding segment. This allows one or more second devices to collaboratively execute the first task. In this scenario, each second device needs to utilize its local computing resources to execute the computational task of the segment deployed on it. Furthermore, after completing the computational task of its segment, the second device needs to use communication resources to send the execution result of that segment to the second device corresponding to the next segment.

[0124] For example, suppose the first model is segmented at two points to obtain three segments, namely segment 1, segment 2, and segment 3. Segment 1 is deployed on second device 1, segment 2 is deployed on second device 2, and segment 3 is deployed on second device 3. In this case, when executing the first task, second device 1 first executes the computation task corresponding to segment 1 to obtain execution result 1; then, second device 1 sends execution result 1 to second device 2; second device 2 executes the computation task corresponding to segment 2 based on the received execution result 1 to obtain execution result 2; then, second device 2 sends execution result 2 to second device 3; second device 3 executes the computation task corresponding to segment 3 based on the received execution result 2 to obtain execution result 3, and uses execution result 3 as the execution result of the first task.

[0125] Based on this, the second information may include communication resource information corresponding to each segmentation point of the first model, to indicate how much data (i.e., the communication resources required) each second device needs to transmit to the next second device after completing the computation task of the corresponding segment. Simultaneously, the second information may include computation resource information corresponding to each segment, to indicate the computation resources required by each second device when executing the computation task of the corresponding segment.

[0126] As can be seen from the above description, the first device can determine the method of collaboratively executing the first task by obtaining second information, wherein the second information may include one or more related information for collaboratively executing the first task. That is, the second information may include one or more of the following:

[0127] Information related to the execution mode of collaboratively carrying out the first task;

[0128] Sixth information;

[0129] Type-related information for the first model;

[0130] Information on one or more segmentation points of the first model;

[0131] Information on one or more exit points of the first model;

[0132] When the first task is executed using the first model, the communication resource information corresponding to each segmentation point of the first model;

[0133] When performing the first task using the first model, the computational resource information corresponding to each segment obtained based on each segmentation point of the first model is obtained.

[0134] Specifically, when the first device receives the second information via a message, the message may contain one or more fields, and each field contains information related to the collaborative execution of the first task.

[0135] In practical applications, after the first device obtains the second information, it can determine (or calculate) the communication resource information corresponding to each segment of the first model and the computing resource information corresponding to each segment obtained from each segment of the first model based on the sixth information, one or more segmentation point information of the first model, and one or more exit point information of the first model.

[0136] In practical applications, the third device can set second information for all computing tasks according to actual needs and send the second information to the first device. In this case, in one embodiment, obtaining the second information includes:

[0137] Receive the second information sent by the third device.

[0138] Specifically, the third device can send the second information to the first function; then, the first function sends the second information to the first device.

[0139] Of course, the first terminal can send the second information to the first device, which can also be understood as a description of the task collaboration requirements of the first terminal for the first task. In this case, in one embodiment, obtaining the second information includes:

[0140] Receive the second information sent by the first terminal.

[0141] Specifically, the first terminal can send the second information to the access network device corresponding to the first terminal; then, the access network device can send the second information to the first device through the E2 interface.

[0142] Of course, the first function can send options corresponding to one or more relevant information for collaboratively executing the first task to the first terminal and the first device respectively; then, the first terminal can determine the selection result based on the received options and send the selection result to the first device; the first device can use the received options and the selection result to determine the second information. In this case, in one embodiment, obtaining the second information includes:

[0143] Receive the seventh information sent by the third device and the eighth information sent by the first terminal; use the seventh and eighth information to determine the second information; wherein,

[0144] The third device is used to provide services associated with the first task at least, the first terminal is used to initiate the first task at least, the seventh information is used to indicate one or more options associated with the second information, and the eighth information represents the selection result of the first terminal for the option indicated by the seventh information.

[0145] In practical applications, the seventh information can also be understood as a preset task collaboration option, and the eighth information can also be understood as the task collaboration mode selected by the first terminal. This application embodiment does not limit the names of the seventh and eighth information.

[0146] For example, the seventh information can be represented in tabular form, as shown in Table 1, and the seventh information includes multiple related information for collaboratively performing the first task. The eighth information can be represented in tabular form, as shown in Table 2.

[0147]

[0148]

[0149] Table 1

[0150]

[0151] Table 2

[0152] In practical applications, the first device can select from the above three methods to obtain the second information according to actual needs, and this application embodiment does not limit this.

[0153] Regarding the third information, it can also be understood as information related to the available computing and communication resources in the candidate device (or simply resource information). In this application embodiment, the name of the third information is not limited.

[0154] In practical applications, when allocating resources, the computing resources allocated by the first device to each second device for executing the first task cannot exceed the available computing resources of that second device, nor can they exceed the allowed energy consumption limit of that second device. Simultaneously, the communication resources allocated for data transmission to one or more second devices cannot exceed the available communication resources between the devices, and must meet channel quality requirements. Here, the one or more second devices belong to the plurality of candidate devices.

[0155] Based on this, in one embodiment, the third information may include one or more of the following:

[0156] Information related to available communication resources (such as bandwidth resources) among multiple candidate devices;

[0157] Channel quality-related information (such as channel quality requirements) among multiple candidate devices;

[0158] Information related to the available computing resources (such as the amount of computing resources) for each of the multiple candidate devices;

[0159] Energy consumption information (such as energy consumption limits) for each of the multiple candidate devices.

[0160] In practical applications, the communication and computing resources indicated by the third information may change over time. Therefore, the third information may also include information related to the available resource validity period for each of the multiple candidate devices. This ensures that the first device can utilize effective resource information to determine a resource allocation strategy, thereby improving the effectiveness of the resource allocation strategy in resource utilization.

[0161] In practical applications, the first device can obtain communication resource information of all candidate devices associated with one or more access network devices, and obtain computing resource information of candidate devices from multiple candidate devices. Specifically, in one embodiment, obtaining the third information includes:

[0162] Receive ninth information sent by one or more access network devices, and receive tenth information sent by the plurality of candidate devices; determine the third information using all the received ninth and tenth information; wherein,

[0163] The access network device is used to manage the communication resources of the plurality of candidate devices at least. The ninth information is associated with the communication resources of the plurality of candidate devices, and the tenth information is associated with the computing resources of the plurality of candidate devices.

[0164] For example, as shown in Table 3, the ninth information sent by the access network device includes multiple fields that can identify the communication resources of multiple candidate devices. Meanwhile, the tenth information sent by the candidate devices may include the tenth information sent by the terminal (including the first terminal and / or the computing power terminal) and the tenth information sent by the edge node (also understood as a computing power platform, such as O-Cloud). As shown in Table 4, the tenth information sent by the terminal includes terminal-related computing resource information; and as shown in Table 5, the tenth information sent by the edge node includes edge node-related computing resource information.

[0165]

[0166] Table 3

[0167]

[0168]

[0169] Table 4

[0170]

[0171] Table 5

[0172] In practical applications, after obtaining the first information, the second information, and the third information, in step 101, the first device generates an allocation strategy for computing resources and communication resources related to the first task based on the second information, the third information, and the resource allocation target corresponding to the first information. The allocation strategy can also be understood as a joint allocation strategy or a unified allocation strategy.

[0173] Specifically, the first device can utilize a local resource allocation optimization algorithm to generate optimal computing and communication resource allocation strategies, namely, a computing resource allocation strategy and a communication resource allocation strategy that meet the requirements for executing the first task and have the optimal resource utilization. The computing resource allocation strategy may include: a computing power allocation strategy corresponding to each second device, used to indicate how much computing resource to allocate to that second device for executing the first task; the communication resource allocation strategy may include one or more of the following:

[0174] The overall allocation of bandwidth and / or RB resources between multiple second devices (which can also be understood as between D2D pairs, such as between the first terminal and the computing terminal), and between the second devices and the access network devices; specifically including: the allocation of the proportion of resources for connections between multiple second devices and the proportion of resources for connections between the second devices and the access network devices;

[0175] Bandwidth and / or RB resource allocation between each second device and the access network device; specifically including: resource allocation between each second device and the access network device;

[0176] Bandwidth and / or RB resource allocation among multiple second devices; specifically including: resource allocation among multiple second devices.

[0177] After determining the allocation strategy for computing and communication resources related to the first task, in step 102, the first device can send the corresponding computing and communication resource allocation strategy to each second device. In this way, the second device can perform resource allocation operations based on the received allocation strategy and execute the first task.

[0178] The information processing method provided in this application embodiment involves a first device using first information, second information, and third information of a first task to determine a joint allocation strategy for computing and communication resources related to the first task. The first device is at least used for resource management within a network. The first task is executed collaboratively by one or more second devices. The first information represents the joint optimization objective of computing and communication resources related to the first task. The second information includes collaboration-related information of the first task. The third information includes information about the available computing and communication resources of the one or more second devices. For each second device, a joint allocation strategy for computing and communication resources corresponding to that second device is sent. The solution provided in this application embodiment, when executing a computing task (i.e., the first task), simultaneously allocates (or jointly allocates) computing and communication resources for the computing task. During allocation, it considers: optimization objectives related to simultaneously allocating both types of resources (e.g., minimizing end-to-end latency, reducing energy consumption, or improving resource utilization), the collaboration requirements of the computing task (e.g., AI model segmentation requirements), and the available resources of the devices capable of collaboratively executing the computing task (i.e., the second devices). This achieves resource allocation that satisfies the optimization objectives as much as possible while fully utilizing resources.

[0179] The following section provides a more detailed description of this application with reference to application examples.

[0180] This application example proposes a wireless network computing and communication resource optimization module (which can also be understood as a resource allocation module) for terminal collaboration. The resource optimization module can dynamically collect computing task requirements, idle computing power of each computing node, channel quality and other relevant information in the network, and jointly allocate computing and communication resources based on this information.

[0181] This application proposes a resource optimization method for terminal collaboration, such as... Figure 2 As shown, it includes the following steps:

[0182] Step 201: The resource optimization module sets the resource optimization target (i.e., the first information mentioned above);

[0183] Step 202: The resource optimization module obtains the collaborative task requirements (i.e., the second information mentioned above);

[0184] Step 203: The resource optimization module obtains computing resource and wireless communication resource information (i.e., the third information mentioned above);

[0185] Step 204: The resource optimization module generates a joint allocation strategy for computing and wireless communication resources based on computing and wireless communication resource information, collaborative task requirements, and resource optimization objectives.

[0186] Step 205: The resource optimization module issues the joint allocation strategy.

[0187] In practical applications, such as Figure 3 As shown, the resource optimization module can be deployed in the Near-RT RIC within the O-RAN architecture, meaning the resource optimization module is an entity within the Near-RT RIC platform. Based on the O-RAN architecture, in step 201, as... Figure 4 As shown, multiple entities in the network (such as terminals (i.e., the first terminal mentioned above), application servers (i.e., the third device mentioned above), and SMO (i.e., the first function mentioned above)) can participate in the setting of optimization targets at different levels (such as the terminal level (UE Level) and the network level (Network Level)). Finally, the optimization targets are set by the SMO or the resource optimization module in the resource optimization module.

[0188] Specifically, the implementation of optimizing target settings may include one or more of the following:

[0189] The optimization goals are set uniformly by the application server;

[0190] The optimization target is submitted by the terminal;

[0191] The optimization objective is generated by the SMO (which can also be understood as the optimization objective being generated by the network itself).

[0192] When the optimization target is set uniformly by the application server, the third-party application server outside O-RAN can generate resource optimization targets according to the internal logic of the application, and realize the setting of resource optimization targets through the interface opened by SMO. That is, the generated resource optimization targets are sent to SMO through the interface opened by SMO, and then SMO sends them to the resource optimization module.

[0193] When an optimization target is submitted by a terminal, the terminal submits its own resource optimization requirements (i.e., resource optimization targets) to a third-party application server outside the O-RAN according to its own business logic; the third-party application server generates resource optimization targets based on the received terminal resource optimization requirements; and then, the third-party application server sets the resource optimization targets through the interfaces exposed by the SMO.

[0194] When the SMO generates optimization targets, it generates resource optimization targets based on the internal preset logic of the wireless network operation and sends them to the resource optimization module in the Near-RT RIC.

[0195] Based on the O-RAN architecture, such as Figure 5 As shown, the specific implementation of step 202 may include performing one of steps 501 to 503:

[0196] Step 501: The terminal submits a description of its task collaboration requirements to the base station (i.e., the access network equipment mentioned above); the base station sends the task collaboration requirements to the resource optimization module through the E2 interface, which can also be understood as the resource optimization module collecting the terminal's task collaboration requirements through the E2 interface.

[0197] Step 502: The terminal submits a computing task collaboration request to the application server; Based on the received computing task collaboration request, the application server decides on the computing task collaboration method and sends the computing task collaboration method to the SMO (which can also be understood as the computing task collaboration method decision, or the computing task collaboration method decision result); The SMO sends the computing task collaboration method to the resource optimization module.

[0198] Step 503: The application server sends computing task collaboration mode options to the terminal and sends the computing task collaboration mode options to the resource optimization module through SMO; the terminal sends the task collaboration mode selection (selection can also be understood as preference) to the resource optimization module through the base station via the E2 interface; the resource optimization module determines the task collaboration mode based on the computing task collaboration mode options and the task collaboration mode selection.

[0199] In practical applications, the specific implementation of step 203 may include executing steps 504 to 506:

[0200] Step 504: The resource optimization module obtains wireless communication resource information and channel quality information from the base station through the E2 interface;

[0201] Step 505: The resource optimization module obtains the terminal's computing resource information from the base station via the E2 interface;

[0202] Step 506: The computing resources opened by the O-Cloud platform (i.e., the aforementioned edge node) are reported to the SMO through the O2 interface, and the SMO then sends the computing resource information to the resource optimization module; or, a new data path is added from the O-Cloud platform to the resource optimization module, and the computing resource status is reported in real time through the new data path.

[0203] In practical applications, the specific implementation of steps 204 to 205 may include executing steps 507 to 510:

[0204] Step 507: Based on all the data collected in the preceding steps and all the received computing task collaboration requirements, the resource optimization module generates the optimal resource allocation strategy according to the resource allocation goals set in the previous step, using the resource allocation optimization algorithm within the resource optimization module.

[0205] Step 508: The resource optimization module sends the communication resource optimization strategy to the base station through the E2 interface;

[0206] Step 509: The resource optimization module sends computing resource optimization strategies to the computing power terminal;

[0207] In practical applications, the resource optimization module can send computing resource optimization strategies to the computing terminal through the application server; alternatively, the resource optimization module can also send computing resource optimization strategies to the computing terminal through base station signaling.

[0208] Step 510: The resource optimization module sends the computing resource optimization strategy to the SMO, and then the SMO sends the computing resource optimization strategy to O-Cloud; or, the resource optimization module sends the computing resource optimization strategy to O-Cloud through the newly added data path.

[0209] The application example provided in this application introduces a wireless network computing and communication resource allocation module for terminal collaboration. This module can dynamically collect computing task requirements, idle computing power of each computing node, channel quality and other relevant information in the network, and jointly allocate computing and communication resources based on this information, thereby achieving preset system optimization goals, such as minimizing end-to-end latency, reducing terminal energy consumption and improving resource utilization.

[0210] To implement the method of the embodiments of this application, the embodiments of this application also provide an information processing device, disposed on an electronic device, wherein the first device is at least used for resource management in a network, such as... Figure 6 As shown, the device includes:

[0211] The determining unit 601 is used to determine a joint allocation strategy of computing resources and communication resources related to the first task by using first information, second information and third information of the first task; wherein the first task is executed collaboratively by one or more second devices, the first information represents the joint optimization objective of computing resources and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information on computing resources and communication resources available to the one or more second devices.

[0212] The sending unit 602 is used to send a joint allocation strategy of computing resources and communication resources corresponding to each second device.

[0213] In one embodiment, the device may further include:

[0214] The acquisition unit is used to acquire the first information.

[0215] In one embodiment, the acquisition unit is specifically used for:

[0216] The system receives a fifth message sent by a first function and uses the fifth message to determine the first message; wherein the first function is used at least for service management and orchestration, and the fifth message includes one or more of the following:

[0217] The first terminal contains information related to the optimization objectives of the first task, and the first terminal is used at least to initiate the first task.

[0218] The third device contains information related to the optimization objectives of the computing task, and the third device is at least used to provide services associated with the first task.

[0219] The first function generates optimization target-related information for the computational task.

[0220] In one embodiment, the acquisition unit is further configured to:

[0221] Obtain the second information, which includes one or more of the following:

[0222] Information related to the execution mode of collaboratively carrying out the first task;

[0223] The sixth information is used by the first device to determine the one or more second devices from a plurality of candidate devices;

[0224] Type-related information for the first model;

[0225] Information on one or more segmentation points of the first model;

[0226] Information on one or more exit points of the first model;

[0227] When the first task is executed using the first model, the communication resource information corresponding to each segmentation point of the first model;

[0228] When performing the first task using the first model, the computational resource information corresponding to each segment obtained based on each segmentation point of the first model is considered; wherein...

[0229] The first model can at least be used to perform the first task, and the candidate device can at least be used to collaboratively perform the task.

[0230] In one embodiment, the acquisition unit is specifically used to perform one of the following:

[0231] Receive the second information sent by the third device;

[0232] Receive the second information sent by the first terminal;

[0233] Receive the seventh information sent by the third device and the eighth information sent by the first terminal; use the seventh and eighth information to determine the second information; wherein,

[0234] The third device is used to provide services associated with the first task at least, the first terminal is used to initiate the first task at least, the seventh information is used to indicate one or more options associated with the second information, and the eighth information represents the selection result of the first terminal for the option indicated by the seventh information.

[0235] In one embodiment, the acquisition unit is further configured to:

[0236] The third information is obtained, and the third information includes one or more of the following:

[0237] Information related to available communication resources among multiple candidate devices;

[0238] Channel quality-related information among multiple candidate devices;

[0239] Information related to the available computing resources for each of the multiple candidate devices;

[0240] Energy consumption information for each of the multiple candidate devices;

[0241] Information related to the available resource validity period for each of the multiple candidate devices; among which,

[0242] The candidate devices are at least capable of collaboratively performing tasks, and the one or more second devices belong to the plurality of candidate devices.

[0243] In one embodiment, the acquisition unit is specifically used for:

[0244] Receive ninth information sent by one or more access network devices, and receive tenth information sent by the plurality of candidate devices; determine the third information using all the received ninth and tenth information; wherein,

[0245] The access network device is used to manage the communication resources of the plurality of candidate devices at least. The ninth information is associated with the communication resources of the plurality of candidate devices, and the tenth information is associated with the computing resources of the plurality of candidate devices.

[0246] In practical applications, the sending unit 602 can be implemented by the communication interface in the information processing device, the determining unit 601 can be implemented by the processor in the information processing device, and the acquiring unit can be implemented by the processor in the information processing device in combination with the communication interface.

[0247] It should be noted that the information processing apparatus provided in the above embodiments is only illustrated by the division of the above-described program units. In practical applications, the above processing can be assigned to different program units as needed, that is, the internal structure of the apparatus can be divided into different program units to complete all or part of the processing described above. In addition, the information processing apparatus and information processing method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0248] Based on the hardware implementation of the above program modules, and in order to implement the method of this application embodiment, this application embodiment also provides a first device, which is at least used for resource management in a network, such as... Figure 7 As shown, the electronic device 700 includes:

[0249] The communication interface 701 enables information exchange with other devices;

[0250] The processor 702 is connected to the communication interface 701 to enable information interaction with other devices and to execute the methods provided by one or more of the above-mentioned technical solutions when running a computer program;

[0251] The computer program is stored in memory 703.

[0252] Specifically, the processor 702 is used for:

[0253] Using first information, second information, and third information of the first task, a joint allocation strategy for computing and communication resources related to the first task is determined; wherein the first task is executed collaboratively by one or more second devices, the first information represents the joint optimization objective of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information related to computing and communication resources available to the one or more second devices.

[0254] The communication interface 701 is used for:

[0255] For each second device, send the joint allocation strategy for computing and communication resources corresponding to the second device.

[0256] In one embodiment, the processor 702 is further configured to:

[0257] The first information is obtained through the communication interface 701.

[0258] In one embodiment, the processor 702 is specifically used for:

[0259] The communication interface 701 receives the fifth information sent by the first function and uses the fifth information to determine the first information; wherein the first function is used at least for service management and orchestration, and the fifth information includes one or more of the following:

[0260] The first terminal contains information related to the optimization objectives of the first task, and the first terminal is used at least to initiate the first task.

[0261] The third device contains information related to the optimization objectives of the computing task, and the third device is at least used to provide services associated with the first task.

[0262] The first function generates optimization target-related information for the computational task.

[0263] In one embodiment, the processor 702 is further configured to:

[0264] The second information is obtained through the communication interface 701, and the second information includes one or more of the following:

[0265] Information related to the execution mode of collaboratively carrying out the first task;

[0266] The sixth information is used by the first device to determine the one or more second devices from a plurality of candidate devices;

[0267] Type-related information for the first model;

[0268] Information on one or more segmentation points of the first model;

[0269] Information on one or more exit points of the first model;

[0270] When the first task is executed using the first model, the communication resource information corresponding to each segmentation point of the first model;

[0271] When performing the first task using the first model, the computational resource information corresponding to each segment obtained based on each segmentation point of the first model is considered; wherein...

[0272] The first model can at least be used to perform the first task, and the candidate device can at least be used to collaboratively perform the task.

[0273] In one embodiment, the processor 702 is specifically configured to perform one of the following:

[0274] The second information sent by the third device is received through the communication interface 701;

[0275] The second information sent by the first terminal is received through the communication interface 701;

[0276] The system receives seventh information sent by a third device and eighth information sent by a first terminal through the communication interface 701; it then uses the seventh and eighth information to determine the second information; wherein,

[0277] The third device is used to provide services associated with the first task at least, the first terminal is used to initiate the first task at least, the seventh information is used to indicate one or more options associated with the second information, and the eighth information represents the selection result of the first terminal for the option indicated by the seventh information.

[0278] In one embodiment, the processor 702 is further configured to:

[0279] The third information is obtained through the communication interface 701, and the third information includes one or more of the following:

[0280] Information related to available communication resources among multiple candidate devices;

[0281] Channel quality-related information among multiple candidate devices;

[0282] Information related to the available computing resources for each of the multiple candidate devices;

[0283] Energy consumption information for each of the multiple candidate devices;

[0284] Information related to the available resource validity period for each of the multiple candidate devices; among which,

[0285] The candidate devices are at least capable of collaboratively performing tasks, and the one or more second devices belong to the plurality of candidate devices.

[0286] In one embodiment, the processor 702 is specifically used for:

[0287] The communication interface 701 receives ninth information sent by one or more access network devices and tenth information sent by the plurality of candidate devices; using all the received ninth and tenth information, the third information is determined; wherein,

[0288] The access network device is used to manage the communication resources of the plurality of candidate devices at least. The ninth information is associated with the communication resources of the plurality of candidate devices, and the tenth information is associated with the computing resources of the plurality of candidate devices.

[0289] It should be noted that the specific processing procedures of the processor 702 and the communication interface 701 can be understood by referring to the above method.

[0290] Of course, in practical applications, the various components in electronic device 700 are coupled together through bus system 704. It can be understood that bus system 704 is used to realize the connection and communication between these components. In addition to a data bus, bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in... Figure 7 The general designated all buses as Bus System 704.

[0291] The memory 703 in this embodiment is used to store various types of data to support the operation of the electronic device 700. Examples of such data include any computer program used to operate on the electronic device 700.

[0292] The methods disclosed in the embodiments of this application can be applied to the processor 702, or implemented by the processor 702. The processor 702 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 702 or by instructions in the form of software. The processor 702 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 702 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in a storage medium, which is located in the memory 703. The processor 702 reads the information in the memory 703 and combines its hardware to complete the steps of the aforementioned method.

[0293] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0294] It is understood that the memory (memory 703) in this embodiment of the application can be volatile memory or non-volatile memory, or both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); the magnetic surface memory can be disk storage or magnetic tape storage. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0295] In an exemplary embodiment, this application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, such as a memory 703 storing a computer program, which can be executed by the processor 702 of the electronic device 700 to complete the steps described in the aforementioned method. The computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM.

[0296] In an exemplary embodiment, this application also provides a computer program product, including a computer program that can be executed by the processor 702 of the electronic device 700 to complete the steps described in the aforementioned method.

[0297] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0298] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0299] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. An information processing method, characterized in that, Applied to a first device, the first device being used at least for resource management in a network, including: Using first information, second information, and third information of the first task, a strategy for allocating computing and communication resources related to the first task is determined; wherein the first task is executed collaboratively by one or more second devices, the first information characterizes the optimization objective of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information about computing and communication resources available to the one or more second devices. For each second device, send the corresponding computing and communication resource allocation strategy.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the first information.

3. The method according to claim 2, characterized in that, Obtaining the first information includes: The system receives a fifth message sent by a first function and uses the fifth message to determine the first message; wherein the first function is used at least for service management and orchestration, and the fifth message includes one or more of the following: The first terminal contains information related to the optimization objectives of the first task, and the first terminal is used at least to initiate the first task. The third device contains information related to the optimization objectives of the computing task, and the third device is at least used to provide services associated with the first task. The first function generates optimization target-related information for the computational task.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the second information, which includes one or more of the following: Information related to the execution mode of collaboratively carrying out the first task; The sixth information is used by the first device to determine the one or more second devices from a plurality of candidate devices; Type-related information for the first model; Information on one or more segmentation points of the first model; Information on one or more exit points of the first model; When the first task is executed using the first model, the communication resource information corresponding to each segmentation point of the first model; When performing the first task using the first model, the computational resource information corresponding to each segment obtained based on each segmentation point of the first model is considered; wherein... The first model can at least be used to perform the first task, and the candidate device can at least be used to collaboratively perform the task.

5. The method according to claim 4, characterized in that, Obtaining the second information includes one of the following: Receive the second information sent by the third device; Receive the second information sent by the first terminal; Receive the seventh information sent by the third device and the eighth information sent by the first terminal; use the seventh and eighth information to determine the second information; wherein, The third device is used to provide services associated with the first task at least, the first terminal is used to initiate the first task at least, the seventh information is used to indicate one or more options associated with the second information, and the eighth information represents the selection result of the first terminal for the option indicated by the seventh information.

6. The method according to claim 1, characterized in that, The method further includes: The third information is obtained, and the third information includes one or more of the following: Information related to available communication resources among multiple candidate devices; Channel quality-related information among multiple candidate devices; Information related to the available computing resources for each of the multiple candidate devices; Energy consumption information for each of the multiple candidate devices; Information related to the available resource validity period for each of the multiple candidate devices; among which, The candidate devices are at least capable of collaboratively performing tasks, and the one or more second devices belong to the plurality of candidate devices.

7. The method according to claim 6, characterized in that, The acquisition of the third information includes: Receive ninth information sent by one or more access network devices, and receive tenth information sent by the plurality of candidate devices; determine the third information using all the received ninth and tenth information; wherein, The access network device is used to manage the communication resources of the plurality of candidate devices at least. The ninth information is associated with the communication resources of the plurality of candidate devices, and the tenth information is associated with the computing resources of the plurality of candidate devices.

8. An information processing device, characterized in that, A first device is configured, the first device being used at least for resource management in the network, including: A determining unit is configured to determine an allocation strategy for computing and communication resources related to the first task using first information, second information, and third information of the first task; wherein the first task is executed collaboratively by one or more second devices, the first information characterizes the optimization target of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information related to computing and communication resources available to the one or more second devices. The sending unit is used to send the computing and communication resource allocation strategy corresponding to each second device.

9. An electronic device, characterized in that, The first device is used at least for resource management in the network, including: A processor is configured to determine an allocation strategy for computing and communication resources related to a first task by utilizing first information, second information, and third information of a first task; wherein the first task is executed collaboratively by one or more second devices, the first information characterizes the optimization objective of computing and communication resources related to the first task, the second information contains collaboration-related information of the first task, and the third information contains information related to computing and communication resources available to the one or more second devices. The communication interface is used to send the computing and communication resource allocation strategy for each second device.

10. An electronic device, characterized in that, include: The processor and the memory used to store computer programs that can run on the processor. When the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 7.

11. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images