Configuration method and device

Abstract

The present application relates to a configuration method and a device. The method comprises: a first core network device receives a first request, wherein the first request is used for requesting execution of a first computing task; and the first core network device sends one or more pieces of first configuration information to one or more first nodes, wherein the one or more pieces of first configuration information are used by the one or more first nodes to collaboratively execute the first computing task, and different first configuration information among the one or more pieces of first configuration information correspond to different first nodes.

Description

Configuration method and device TECHNICAL FIELD

[0001] The present application relates to the field of communication, and more particularly, to a configuration method and device. BACKGROUND

[0002] With the development of communication technology, in a communication system, there can be a demand for network participation in computing power services, for example, various types of nodes on the network side can participate in computing to complete a computing task, which can include terminals, access network devices, network functions of core networks, application functions, and the like. However, in a communication system, how to accurately configure nodes performing a computing task to accurately and efficiently perform the computing task becomes a problem to be solved.

[0003] SUMMARY

[0004] Embodiments of the present application provide a configuration method and device.

[0005] Embodiments of the present application provide a configuration method, comprising:

[0006] The first core network device receives a first request, wherein the first request is used to request to perform a first computing task;

[0007] The first core network device sends one or more first configuration information to one or more first nodes, wherein the one or more first configuration information is used for the one or more first nodes to cooperatively perform the first computing task, and different first configuration information in the one or more first configuration information corresponds to different first nodes.

[0008] Embodiments of the present application provide a configuration method, comprising:

[0009] The target node receives first configuration information corresponding to the target node from the first core network device, wherein the first configuration information corresponding to the target node is used for the target node to cooperatively perform a first computing task with one or more other first nodes.

[0010] Embodiments of the present application provide a configuration method, comprising:

[0011] The first core network device sends second configuration information to the second core network device, wherein the second configuration information carries routing information of each second service in one or more second services, and the routing information of each second service includes a routing order of one or more fourth nodes cooperatively performing a computing task under each second service.

[0012] Embodiments of the present application provide a configuration method, comprising:

[0013] The second core network device receives second configuration information from the first core network device, wherein the second configuration information carries routing information of each of one or more second services, and the routing information of each of the one or more second services includes routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the one or more second services.

[0014] The embodiment of the present application provides a configuration method, comprising:

[0015] The first terminal receives third configuration information from the first core network device, wherein the third configuration information carries a first identifier of each of at least part of one or more second services and a second identifier associated with the first identifier.

[0016] The embodiment of the present application provides a first core network device, comprising:

[0017] The first communication unit is configured to receive a first request, wherein the first request is used to request to perform a first computing task, and send one or more first configuration information to one or more first nodes, wherein the one or more first configuration information is used for the one or more first nodes to cooperatively perform the first computing task, and different first configuration information in the one or more first configuration information corresponds to different first nodes.

[0018] The embodiment of the present application provides a target node, comprising:

[0019] The second communication unit is configured to receive first configuration information corresponding to the target node from the first core network device, wherein the first configuration information corresponding to the target node is used for the target node to cooperatively perform a first computing task with one or more other first nodes.

[0020] The embodiment of the present application provides a first core network device, comprising:

[0021] The first communication unit is configured to send second configuration information to a second core network device, wherein the second configuration information carries routing information of each of one or more second services, and the routing information of each of the one or more second services includes routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the one or more second services.

[0022] The embodiment of the present application provides a second core network device, comprising:

[0023] The third communication unit is configured to receive second configuration information from the first core network device, wherein the second configuration information carries routing information of each of one or more second services, and the routing information of each of the one or more second services includes routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the one or more second services.

[0024] The embodiment of the present application provides a first terminal, comprising:

[0025] The fourth communication unit is configured to receive third configuration information from the first core network device, wherein the third configuration information carries the first identifier of each of at least part of the one or more second services and the associated second identifier.

[0026] The embodiment of the present application provides a first core network device, comprising a transceiver, a processor and a memory. The memory is configured to store a computer program, the transceiver is configured to communicate with other devices, and the processor is configured to invoke and run the computer program stored in the memory, so that the first core network device executes the above method.

[0027] The embodiment of the present application provides a target node, comprising a transceiver, a processor and a memory. The memory is configured to store a computer program, the transceiver is configured to communicate with other devices, and the processor is configured to invoke and run the computer program stored in the memory, so that the target node executes the above method.

[0028] The embodiment of the present application provides a second core network device, comprising a transceiver, a processor and a memory. The memory is configured to store a computer program, the transceiver is configured to communicate with other devices, and the processor is configured to invoke and run the computer program stored in the memory, so that the second core network device executes the above method.

[0029] The embodiment of the present application provides a first terminal, comprising a transceiver, a processor and a memory. The memory is configured to store a computer program, the transceiver is configured to communicate with other devices, and the processor is configured to invoke and run the computer program stored in the memory, so that the first terminal executes the above method.

[0030] The embodiment of the present application provides a chip for implementing the above method.

[0031] Specifically, the chip comprises a processor configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the above method.

[0032] The embodiment of the present application provides a computer readable storage medium for storing a computer program, which causes a device to execute the above method when the computer program is run by the device.

[0033] The embodiment of the present application provides a computer program product comprising computer program instructions, which causes a computer to execute the above method.

[0034] By adopting the above scheme, the first core network device sends the corresponding first configuration information to each first node after receiving the first request of executing the first computing task, so that each first node can cooperatively execute the first computing task. In this way, in the scenario that the communication network participates in providing computing power service, the nodes executing the computing task can be accurately configured, so that the nodes providing computing power can accurately and efficiently cooperatively execute the computing task. BRIEF DESCRIPTION OF DRAWINGS

[0035] FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present application.

[0036] FIG. 2 is a schematic flowchart of a configuration method according to an embodiment of the present application.

[0037] FIG. 3 is a schematic flowchart of a configuration method according to another embodiment of the present application.

[0038] FIG. 4 is a schematic diagram of a system architecture to which the configuration method according to an embodiment of the present application is applied.

[0039] FIG. 5 is a schematic flowchart of a configuration method according to an embodiment of the present application.

[0040] FIG. 6 is a simple schematic flowchart of a configuration method according to an embodiment of the present application.

[0041] FIG. 7 is a schematic flowchart of a configuration method according to an embodiment of the present application.

[0042] FIG. 8 is another schematic flowchart of a configuration method according to an embodiment of the present application.

[0043] FIG. 9 is still another schematic flowchart of a configuration method according to an embodiment of the present application.

[0044] FIG. 10 is a schematic flowchart of a configuration method according to an embodiment of the present application.

[0045] FIG. 11 is a schematic flowchart of a core network user plane network element performing processing according to a configured routing table according to an embodiment of the present application.

[0046] FIG. 12 is a schematic block diagram of a first core network device according to an embodiment of the present application.

[0047] FIG. 13 is a schematic block diagram of a target node according to an embodiment of the present application.

[0048] FIG. 14 is a schematic block diagram of a second core network device according to an embodiment of the present application.

[0049] FIG. 15 is a schematic block diagram of a first terminal according to an embodiment of the present application.

[0050] Fig. 16 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0051] Fig. 17 is a schematic block diagram of a chip according to an embodiment of the present application.

[0052] Fig. 18 is a schematic block diagram of a communication system according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example, LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), NR (New Radio), evolution of NR, WLAN (Wireless Local Area Network), WiFi (Wireless Fidelity), or other communication systems, etc.

[0054] The embodiments of the present application describe various embodiments in combination with network devices and terminals. The terminals can be mobile or fixed, and can also be referred to as mobile stations, user units, etc. The terminals can be stations in WLAN, and can be smart terminals, wireless modems, notebook computers, tablet computers, etc. In the embodiments of the present application, the terminals can be VR (Virtual Reality) terminals / AR (Augmented Reality) terminals, industrial control terminals, unmanned driving terminals, remote medical terminals, smart grid terminals, transportation safety terminals, smart city terminals, or wireless terminals of smart homes, etc. As an example but not limitation, in the embodiments of the present application, the terminals can also be wearable devices.

[0055] In the embodiments of the present application, the network devices can be devices for communicating with the terminals. The network devices can be access points in WLAN, or evolved base stations in LTE, or relay stations, or network devices in vehicle-mounted devices, wearable devices, and NR networks, or network devices in future evolved PLMN networks, or network devices in non-ground networks, etc. As an example but not limitation, in the embodiments of the present application, the network devices can have mobile characteristics, for example, the network devices can be mobile devices.

[0056] In order to facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described as follows. The following related technologies can be combined with the technical solutions of the embodiments of the present application in any way, and all of them belong to the protection scope of the embodiments of the present application.

[0057] FIG. 1 illustrates a communication system 100. The communication system includes a network device 110 and a terminal 120. In a possible implementation, the communication system 100 can include a plurality of network devices 110, and each network device 110 can include one or more terminals 120 within a coverage range of the network device 110, which is not limited in the embodiments of the present application. In a possible implementation, the communication system 100 can further include a mobility management entity, an access and mobility management function, and other network entities, which are not limited in the embodiments of the present application. The network device can include an access network device and a first core network device. That is, the communication system can include a plurality of core networks for communicating with the access network device. The access network device can be a base station of an LTE, LTE-A, or NR system. For example, the communication system shown in FIG. 1 can include network devices and terminals with communication functions, and can further include other devices in the communication system, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0058] FIG. 2 is a schematic flowchart of a configuration method according to an embodiment of the present application. The method includes at least part of the following content.

[0059] S210, a first core network device receives a first request, where the first request is used to request to perform a first computing task.

[0060] S220, the first core network device sends one or more first configuration information to one or more first nodes, where the one or more first configuration information is used for the one or more first nodes to cooperatively perform the first computing task, and different first configuration information in the one or more first configuration information corresponds to different first nodes.

[0061] FIG. 3 is a schematic flowchart of a configuration method according to an embodiment of the present application. The method includes at least part of the following content.

[0062] S310, a target node receives first configuration information corresponding to the target node from a first core network device, where the first configuration information corresponding to the target node is used for the target node to cooperatively perform a first computing task with one or more other first nodes.

[0063] The first core network device can be a policy control network element. The first core network device has a policy control function, which can include receiving a message requesting to perform a computing task, and allocating resources used by each node cooperatively performing the task, where the resources can include at least one of computing capability (or computing power resource), communication resource, and the like.

[0064] The one or more first nodes include at least one of the following: one or more terminals, one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs). It should be noted that, in any case where a first node is an NF, the NF as the first node is different from the first core network device, the second core network device, the third core network device, and the fourth core network device that can be involved or referred to in the embodiments of the present application, and the following will not be repeatedly explained.

[0065] Preferably, the number of the one or more first nodes can be multiple. The target node can be any one of the one or more first nodes; in the multiple first nodes, the target node and one or more other first nodes can be included. The target node is one of the following: a target terminal, a target access network device, a target NF, and a target AF. The one or more other first nodes include at least one of the following: one or more other terminals, one or more other access network devices, one or more other NFs, and one or more other AFs.

[0066] In some possible implementation manners, the first request can be sent by a third party to the first core network device.

[0067] The third party can be one that generates and sends the first request to the first core network device in the case where there is a service processing requirement, and the embodiments do not limit the triggering or generation manner of the first request. The first request can also be referred to as a service processing request.

[0068] The third party can include at least one of the following: a third-party AF and a third-party UE (User Equipment), and the third-party AF is different from the one or more first nodes, and the third-party UE is different from the one or more first nodes.

[0069] The first request carries at least one of the following: a parameter of a service to which the first computing task belongs, a region parameter corresponding to the first computing task, a total time length requirement of an end-to-end task for executing the first computing task, a computing capability required for executing the first computing task, and an identifier (ID) of the first computing task.

[0070] The parameter of the service to which the first computing task belongs can include at least one of the following: an identifier of the service to which the first computing task belongs and a type of the service to which the first computing task belongs.

[0071] The identifier of the service to which the first computing task belongs can be used by the first core network device to uniquely identify the service to which the first computing task belongs. The identifier of the service to which the first computing task belongs can include at least one of the following: a first identifier of the service to which the first computing task belongs, a second identifier of the service to which the first computing task belongs.

[0072] The second identifier of the service to which the first computing task belongs can be an original ID (Identifier) of the service to which the first computing task belongs, which can also be referred to as a real ID, or a permanent ID, or a long-term ID.

[0073] The first identifier of the service to which the first computing task belongs can be an identifier other than the second identifier of the service to which the first computing task belongs.

[0074] In this embodiment, the specific type of the identifier of the service to which the first computing task belongs is not limited, as long as the first core network device can uniquely identify the service to which the first computing task belongs.

[0075] The type of the service to which the first computing task belongs can be any one of one or more optional service types, and the embodiment does not limit the one or more optional service types.

[0076] The area parameter corresponding to the first computing task can be used to indicate or determine a first area in which a node performing the first computing task is located. The area parameter corresponding to the first computing task can include at least one of the following: a network area parameter corresponding to the first computing task, a geographic area parameter corresponding to the first computing task. The network area parameter can be represented by at least one of a TAC (Tracking Area Code), a TAI (Tracking Area Identity), a cell identifier (such as a PCI (Physical Cell Identifier)), and the like; and the geographic area parameter can be represented by a geographic position coordinate (such as latitude and longitude) or a geographic area coordinate range.

[0077] The total time length requirement of the end-to-end task for performing the first computing task can be a total time length requirement that needs to be met by the sum of the computing time length and the transmission time length involved in the process from the start of the execution of the first computing task to the end of the execution of the first computing task.

[0078] The computing capability required for performing the first computing task can be a requirement of the computing capability that needs to be met or reached by the node performing the first computing task.

[0079] The computing capability is used to represent the number of calculations or operations or operations per unit time, which can be configured according to actual needs, such as the unit time can be a second. The unit (or measurement unit or measurement unit) used by the computing capability can be FLOPS (Floating-point Operations Per Second) or TOPS (Tera Operations Per Second).

[0080] It should be noted that in the embodiments of the present application, the computing capability can also be alternatively referred to as capability information, or processing capability, or operation capability, or operation capability, or running capability, etc. Here, all possible names of the computing capability are not limited or exhausted, as long as any possible name that can be used to represent the number of calculations or operations or operations per unit time is within the protection scope of the embodiments, and the following will not be repeated.

[0081] It should be noted that the above is only an exemplary description of the content carried by the first request, and the first request can also carry more other content in actual processing, such as the first request can carry the result to be obtained of the first computing task, the type of calculation required to be executed by the first computing task, etc. The result to be obtained of the first computing task can refer to the description information of the result expected to be obtained by the first computing task, etc. Here, all the contents that can be carried by the first request are not limited or exhausted.

[0082] In some possible implementations, after the first core network device receives the first request, the method further includes at least one of the following: the first core network device finds the computing capability that each of one or more second nodes located in the first area can provide, wherein the first area is determined based on the area parameter corresponding to the first computing task; the first core network device finds one or more third nodes that have a model supporting the first service, wherein the first service is determined based on the parameter of the service to which the first computing task belongs.

[0083] In an embodiment, the first core network device finds the computing capability that each of one or more second nodes located in the first area can provide, which can include: the first core network device finds the computing capability that each of one or more second nodes located in the first area can provide from a third core network device.

[0084] The third core network device can be used for computing power collection or computing power statistics or computing power management, and the third core network device can be referred to as a computing power management network element, or a computing power collection function, or a computing power management function.

[0085] At the third core network device side, the following processing can be performed: collecting the computing capability that one or more nodes can provide. The computing capability of each node in the one or more nodes can be measured by FLOPS or TOPS.

[0086] Here, each node in the one or more nodes can be a node that can provide computing capability and / or can perform computation managed or coverable by the third core network device. The one or more nodes can include one or more second nodes. The type of any node can be one of a terminal, an access network device, an NF, and an AF. It should be noted that any node (for example, in the case where the node is an NF) is different from the first core network device, the second core network device, the third core network device, and the fourth core network device that can be involved or mentioned in the present application, and the following will not be repeated.

[0087] In one case, the third core network device can collect the computing capability in the granularity of nodes. The third core network device collecting the computing capability that one or more nodes can provide can mean that the third core network device collects the computing capability that each node in all nodes capable of performing computation (or capable of providing computing capability) managed by the third core network device can provide.

[0088] In another case, the third core network device can collect the computing capability in the granularity of network slices. The third core network device collecting the computing capability that one or more nodes can provide can mean that the second core network device collects the computing capability that each node corresponding to each network slice in one or more network slices can provide. Each network slice in the one or more network slices can be identified by related content such as S-NSSAI (Single Network Slice Selection Assistance Information).

[0089] Further, the computing capability that each node can provide can further include the computing capability that the node can provide in one or more granularities. The one or more granularities can include at least one of the following: device, service (Service), application (Application), and the like.

[0090] For example, assuming that node A is any node of the third core network device collecting the computing capability, the computing capability of the node A can include at least one of the following: the computing capability that the node A can provide for one or more devices respectively, the computing capability that the node A can provide for one or more services respectively, and the computing capability that the node A can provide for one or more applications respectively. The device can be any type of device, such as a terminal.

[0091] The third core network device can also associate and save the collected computing capability that each node can provide with the area where the node is located and the identity of the node. The area where any node is located can be represented by at least one of the following: a network area where the node is located, a geographic area where the node is located. The network area can be a tracking area, a cell, and the like. The network area can be identified by a corresponding identity, such as a tracking area TAC, a tracking area TAI, a cell identity (such as PCI), and the like. The geographic area can be identified by geographic coordinates (such as latitude and longitude, and the like).

[0092] The first core network device can find, from the third core network device, the computing capability that each of the one or more second nodes located in the first area can provide, which can include: the first core network device sending, to the third core network device, the area parameter corresponding to the first computing task; and the first core network device receiving, from the third core network device, the computing capability that each of the one or more second nodes located in the first area can provide. The processing of the third core network device can include: the third core network device receiving, from the first core network device, the area parameter corresponding to the first computing task; the third core network device determining the first area based on the area parameter corresponding to the first computing task; the third core network device locally finding the one or more second nodes located in the first area and locally finding the computing capability that each of the one or more second nodes can provide; and the third core network device sending, to the first core network device, the computing capability that each of the one or more second nodes located in the first area can provide.

[0093] In an embodiment, the first core network device can find the computing capability that each of the one or more second nodes located in the first area can provide, which can include: the first core network device locally finding the computing capability that each of the one or more second nodes located in the first area can provide.

[0094] In this example, the first core network device can have the computing power statistics, or computing power management, or computing power collection function. The first core network device collects the computing capability that each node managed by the first core network device can provide in the same way as the third core network device collects the computing capability that each node can provide in the foregoing example, and thus no repeated description is provided.

[0095] The first core network device can locally find the computing capability that each of the one or more second nodes located in the first area can provide, which can include: the first core network device determining the first area based on the area parameter corresponding to the first computing task; and the first core network device locally finding the one or more second nodes located in the first area and locally finding the computing capability that each of the one or more second nodes can provide.

[0096] In an embodiment, the first core network device searching for one or more third nodes with a model capable of supporting the first service can comprise: the first core network device searching for one or more third nodes with a model capable of supporting the first service from a fourth core network device.

[0097] The fourth core network device can be used for model management, and the fourth core network device can be referred to as a model management function or a model management network element.

[0098] On the side of the fourth core network device, the following processing can be performed: receiving registration information from one or more nodes, wherein the registration information of each node of the one or more nodes includes parameters of a model supported by each node; and saving the parameters of the model supported by each node locally. The parameters of the model include at least one of the following: a manufacturer or a vendor of a node where the model is located, a scenario of use of the model, a service supported by the model, a type of the model, an identification of the model, a region or a location where the node where the model is located is located, and the like.

[0099] The type of the model can be divided according to the type of a neural network, for example, the type of any one model can include one of the following: CNN (Convolutional Neural Network), DNN (Deep Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), GAN (Generative Adversarial Network), and the like. This is only an example of dividing the type of the model according to the type of the neural network, and there can be more possibilities for dividing the type of the model according to the type of the neural network, which is not limited or enumerated in the embodiment.

[0100] It should be pointed out that the above division of the type of the model according to the type of the neural network is only an example of a division method, and the type of the model can also be divided in other ways in actual processing, for example, the type of the model can be divided into at least one of an image processing model and an audio processing model according to the type of a task. The present embodiment does not limit or enumerate all possible division methods of the type of the model and specific types that can be included in each division method.

[0101] The identification of the model can be defined by a 3GPP network or can be defined by a third party, and the identification of the model is used to specifically identify or uniquely identify one or a type of model.

[0102] In addition, the parameters of the above model are only exemplary, and in actual processing, the parameters of the model can further include more content, such as the parameters of the model can further include at least one of the following: dimension of the model, number of layers of the model, minimum unit of input and / or output data of the model, which can be configured according to actual conditions, such as a word, a punctuation mark, a number or a symbol, etc.

[0103] The fourth core network device saves the parameters of the model supported by each node locally, which can be that the fourth core network device associates and saves the parameters of the model supported by each node with the identifier of the node.

[0104] The fourth core network device can also support discovery of nodes with a specific model, specifically, the fourth core network device can support discovery of nodes with a specific model based on at least one of the following: area (or location), vendor, service, etc.

[0105] Optionally, the first core network device can find one or more third nodes with a model supporting the first service from the fourth core network device, which can include: the first core network device sends the parameters of the service to which the first computing task belongs to the fourth core network device; the first core network device receives the identifier of each of the one or more third nodes with a model supporting the first service from the fourth core network device. The processing of the fourth core network device can include: the fourth core network device receives the parameters of the service to which the first computing task belongs from the first core network device; determines the first service based on the parameters of the service to which the first computing task belongs; locally finds one or more third nodes with a model supporting the first service; and sends the identifier of each of the one or more third nodes with a model supporting the first service to the first core network device.

[0106] Optionally, the first core network device can find one or more third nodes with a model supporting the first service from the fourth core network device, which can be that the first core network device finds one or more third nodes located in the first area and with a model supporting the first service from the fourth core network device.

[0107] Specifically, the first core network device can find one or more third nodes located in the first area and having a model capable of supporting the first service from the fourth core network device by sending parameters of a service to which the first computing task belongs and area parameters corresponding to the first computing task to the fourth core network device, and receiving an identifier of each of the one or more third nodes located in the first area and having the model capable of supporting the first service from the fourth core network device. The processing of the fourth core network device can include receiving the parameters of the service to which the first computing task belongs and the area parameters corresponding to the first computing task from the first core network device, determining the first service based on the parameters of the service to which the first computing task belongs and determining the first area based on the area parameters corresponding to the first computing task, locally finding the one or more third nodes located in the first area and having the model capable of supporting the first service, and sending the identifier of each of the third nodes having the model capable of supporting the first service to the first core network device.

[0108] In some possible examples, the fourth core network device can be the same as the third core network device, for example, the third core network device can have both the computing power collection function and the model management function.

[0109] After the first core network device receives the first request, the method further includes at least one of the following: the first core network device finds, from the third core network device, computing power that each of one or more second nodes located in the first area is capable of providing; and the first core network device finds, from the third core network device, one or more third nodes having a model capable of supporting the first service from the one or more second nodes.

[0110] Since the one or more third nodes finally found by the third core network device are determined from the second nodes, the first core network device can directly obtain, from the third core network device, the computing power that each of the second nodes is capable of providing; or the first core network device can directly obtain, from the third core network device, the third nodes located in the first area and having the model capable of supporting the first service and the computing power that each of the third nodes is capable of providing.

[0111] In an embodiment, the first core network device finding the one or more third nodes having the model capable of supporting the first service can include the first core network device locally finding the one or more third nodes having the model capable of supporting the first service.

[0112] In this example, the first core network device can also have the model management function, and the first core network device receives registration information of each node and associates and saves parameters of a model supported by each node and an identifier of each node. The processing is the same as that in the foregoing example, and the difference is that the first core network device performs the processing in this example, and thus no further description is given.

[0113] The first core network device locally searches for one or more third nodes having a model supporting the first service, which can include: the first core network device determining the first service based on a parameter of a service to which the first computing task belongs, and locally searching for one or more third nodes having a model supporting the first service; or the first core network device determining the first service based on a parameter of a service to which the first computing task belongs, and determining a first region based on a region parameter corresponding to the first computing task, and locally searching for one or more third nodes located in the first region and having a model supporting the first service.

[0114] In some possible examples, the fourth core network device, the third core network device, and the first core network device can be the same, for example, the first core network device can simultaneously have a policy control function, a computing power collection function, and a model management function.

[0115] After the first core network device receives the first request, the method further includes at least one of the following: the first core network device locally searching for computing power that each of one or more second nodes located in the first region is capable of providing; and the first core network device locally searching for one or more third nodes having a model supporting the first service from the one or more second nodes.

[0116] In some embodiments, after the first core network device searches for computing power that each of one or more second nodes located in the first region is capable of providing, and / or after the first core network device searches for one or more third nodes having a model supporting the first service, the processing of the first core network device can further include: the first core network device determining the one or more first nodes satisfying a first condition based on the computing power that each of the one or more second nodes is capable of providing and / or the one or more third nodes, wherein the first condition includes at least one of the following: being located in the first region, having a model supporting the first service, and being capable of providing computing power satisfying a computing power required for performing the first computing task.

[0117] In an example, the first core network device can obtain computing power that each of one or more second nodes located in the first region is capable of providing; and the first core network device can further obtain one or more third nodes having a model supporting the first service, or one or more third nodes located in the first region and having a model supporting the first service.

[0118] The first condition includes all of the following: being located in the first region, having a model supporting the first service, and being capable of providing computing power satisfying a computing power required for performing the first computing task.

[0119] The first core network device determines the one or more first nodes satisfying the first condition based on the computing capability that each second node is capable of providing and / or the one or more third nodes can include that the first core network device determines whether there is one or more same nodes in the one or more third nodes and the one or more second nodes, wherein the one or more same nodes are nodes located in the first area and having a model supporting the first service; if there is one or more same nodes, the first core network device selects, based on the computing capability required for performing the first computing task, a node from the one or more same nodes that is capable of providing computing capability satisfying the computing capability required for performing the first computing task as a node satisfying the first condition, and determines the one or more first nodes from the nodes satisfying the first condition. The determination of the one or more first nodes from the nodes satisfying the first condition can be that all the nodes satisfying the first condition are selected as the one or more first nodes, or that part of the nodes satisfying the first condition are randomly selected as the one or more first nodes.

[0120] In an example, the first core network device only obtains the computing capability that each second node located in the first area is capable of providing.

[0121] The first condition can include that the nodes located in the first area and / or the computing capability that is capable of providing satisfies the computing capability required for performing the first computing task. The first core network device determines the one or more first nodes satisfying the first condition based on the computing capability that each second node is capable of providing and / or the one or more third nodes can include that the first core network device selects, based on the computing capability required for performing the first computing task, a node from the one or more second nodes located in the first area that is capable of providing computing capability satisfying the computing capability required for performing the first computing task as a node satisfying the first condition, and determines the one or more first nodes from the nodes satisfying the first condition.

[0122] In an example, the first core network device only obtains the one or more third nodes having a model supporting the first service, or only obtains the one or more third nodes located in the first area and having a model supporting the first service.

[0123] The first condition includes that the nodes located in the first area have a model supporting the first service. The first core network device determines the one or more first nodes satisfying the first condition based on the computing capability that each second node is capable of providing and / or the one or more third nodes can include that the first core network device selects the one or more third nodes as nodes satisfying the first condition, and determines the one or more first nodes from the nodes satisfying the first condition.

[0124] In some possible implementation manners, after determining the one or more first nodes, the first core network device can generate first configuration information corresponding to each of the one or more first nodes.

[0125] The one or more first configuration information are used for the one or more first nodes to cooperatively perform the first computing task. For example, assuming that the number of the one or more first nodes is a plurality, any one of the plurality of first nodes is a target node, and the plurality of first nodes further include one or more other first nodes in addition to the target node, the first configuration information corresponding to the target node is used for the target node to cooperatively perform the first computing task with the one or more other first nodes.

[0126] Each of the one or more first configuration information can include at least one of the following: a computing capability used by the each of the one or more first nodes to participate in performing the first computing task, and an execution strategy of the each of the one or more first nodes participating in performing the first computing task.

[0127] Still taking the example of the number of the one or more first nodes being a plurality, any one of the plurality of first nodes being a target node, and the plurality of first nodes further including one or more other first nodes in addition to the target node, the first configuration information corresponding to the target node includes at least one of the following: a computing capability used by the target node to participate in performing the first computing task, and an execution strategy of the target node participating in performing the first computing task.

[0128] In an embodiment, the execution strategy of the each of the one or more first nodes participating in performing the first computing task includes at least one of the following: an identifier of the first computing task, a previous-hop first node of the each of the one or more first nodes, a next-hop first node of the each of the one or more first nodes, and related information of a model used by the each of the one or more first nodes to participate in performing the first computing task.

[0129] Taking the target node as an example, the execution strategy of the target node participating in performing the first computing task includes at least one of the following: an identifier of the first computing task, a previous-hop other first node of the target node, a next-hop other first node of the target node, and related information of a model used by the target node to participate in performing the first computing task.

[0130] The previous-hop other first node can be indicated by using related information of the previous-hop other first node, and / or the next-hop other first node can be indicated by using related information of the next-hop other first node.

[0131] The related information of the other first node can include at least one of the following: an identification (ID) of the other first node, a tunnel identification of the other first node, a number of the other first node, an index number of the other first node, a network address of the other first node, and the like. The network address can include at least one of an Internet Protocol (IP) address, a Media Access Control (MAC) address, and the like.

[0132] If the target node is the first node to execute the first computing task, the target node can not have the previous-hop other first node. If the target node is the last node to execute the first computing task, the target node can not have the next-hop other first node.

[0133] In a possible scenario, the target node is the first node to execute the first computing task among the plurality of first nodes. In this case, the target node does not have the previous-hop other first node, i.e., the execution strategy in which the target node participates in the execution of the first computing task can not include the previous-hop other first node of the target node.

[0134] In a possible scenario, a terminal first processes the data packet of the first computing task and then sends the data packet to the first node (e.g., the target node) among the plurality of first nodes, but the terminal is not included in the plurality of first nodes. In this case, the target node can have the previous-hop terminal, but the previous-hop terminal is not included in the plurality of first nodes. The execution strategy in which the target node participates in the execution of the first computing task can not include the previous-hop other first node of the target node but can include the previous-hop terminal of the target node.

[0135] The model used by the target node to participate in the execution of the first computing task can be a model supported by the target node to support the first service.

[0136] The related information of the model includes at least one of the following: an identification of the model, a type of the model, related information of input data of the model, and related information of output data of the model.

[0137] The related information of the identification of the model and the type of the model is the same as in the foregoing embodiments, and will not be repeated here.

[0138] The related information of the input data of the model can be used to indicate at least one of the following: a source of the input data of the model, a requirement of the input data of the model, and the like.

[0139] The source of the input data of the model can be configured according to actual needs, for example, the source of the input data of the model can include at least one of the output data of the previous hop first node, the specified data local to the first node where the model is located, and the like.

[0140] The requirements of the input data of the model can be configured according to actual conditions, for example, can include the dimension requirement of the input data of the model, the type requirement of the input data of the model. The dimension requirement and the type requirement can be configured according to actual conditions, for example, the model processes picture class input data, which needs to meet the requirements of picture format, picture size, and the like.

[0141] The above related information of the input data of the model is exemplary and can be configured according to needs in actual processing, and the embodiment is not limited or exhaustive.

[0142] The related information of the output data of the model can also be configured according to actual conditions, for example, the related information of the output data of the model can include at least one of the dimension requirement of the output data of the model, the type requirement of the output data of the model, and the like. In actual setting, the related information of the output data of the model can be related to the requirements of the input data of the model of the next hop first node, or can be related to the result of the first computing task finally needed to be obtained, and the embodiment does not limit or exhaust the related information of the output data of the model.

[0143] It should be noted that the above is only an exemplary description of the content that the execution strategy of the target node participating in the execution of the first computing task can contain, and in actual processing, the execution strategy of the target node participating in the execution of the first computing task can also contain more content, for example, can include a task description, which can refer to the description information of the first computing task. The task description can include at least one of the description information of the result expected to be obtained by the first computing task, the type of the calculation required to be executed by the first computing task, the detailed description of the first computing task, and the like, and here the embodiment does not limit or exhaust all the content that the task description can contain.

[0144] In addition, the target node can also obtain the execution strategy of each of one or more other first nodes participating in the execution of the first computing task. The execution strategy of each of the one or more other first nodes participating in the execution of the first computing task can be included in the first configuration information corresponding to the target node, or can be included in the execution strategy of the target node participating in the execution of the first computing task, which is not limited here.

[0145] The above is mainly an example of a target node for participating in the execution of the first computing task. The first configuration information corresponding to each first node contains the relevant description of the execution strategy for participating in the execution of the first computing task, which is the same as the target node, so it is not repeated here.

[0146] For example, the first node includes RAN-1, NF-1, NF-2, and AF-1. The execution strategy of the first computing task participated by RAN-1, NF-1, NF-2, and AF-1 can be as shown in Table 1:

[0147] Table 1

[0148] Specifically, Table 1 above shows that the execution strategy corresponding to RAN-1 includes the ID and task description of the first computing task (i.e., the description information of the first computing task), the next-hop first node NF-1, and the relevant information of the model used by RAN-1 to participate in the execution of the first computing task. The next-hop first node NF-1 can be indicated or represented by at least one of the identifier, tunnel identifier, number, index number, IP address, and MAC address of NF-1. The execution strategy corresponding to NF-1 includes the ID and task description of the first computing task, the previous-hop first node RAN-1, the next-hop first node NF-2, and the relevant information of the model used by NF-1 to participate in the execution of the first computing task. The next-hop first node RAN-1 can be indicated or represented by at least one of the identifier, tunnel identifier, number, index number, IP address, and MAC address of RAN-1. The explanation of the execution strategy corresponding to NF2 and AF is similar to the above RAN and NF1, so it is not repeated here.

[0149] It should be noted that the above is only an example description, and in actual processing, each first node can obtain at least one of the following: the own last-hop first node, the own next-hop first node, and the model related information used by the own first node for performing the first computing task. Still taking Table 1 as an example, the execution strategy finally obtained by RAN-1 can include: the ID and task description of the first computing task, the next-hop first node of RAN-1 is NF-1, and the model related information used by RAN-1 for performing the first computing task. In addition, RAN-1 can also obtain at least one of the following: the last-hop first node of NF-1 is RAN-1, the next-hop first node of NF-1 is NF-2, the model related information used by NF-1 for performing the first computing task, the last-hop first node of NF-2 is NF-1, the next-hop first node of NF-2 is AF-1, the model related information used by NF-2 for performing the first computing task, the last-hop first node of AF-1 is NF-2, and the model related information used by AF-1 for performing the first computing task. Here, the content contained in the execution strategy finally obtained by each node will not be described one by one.

[0150] It should be understood that the above is only an example description, and in actual processing, not every first node can be configured with all the contents in the above execution strategy. For example, taking Table 1 as an example, RAN can only provide routing without performing computing processing, and the execution strategy corresponding to the RAN can only include the next-hop first node NF1.

[0151] In an embodiment, on the first core network device side, the computing capability used by each first node for performing the first computing task is determined based on at least one of the following: the computing capability required for performing the first computing task, and the computing capability that can be provided by each first node.

[0152] Taking the target node as an example, the computing capability used by the target node for performing the first computing task refers to the computing capability that needs to be invested or used by the target node in the process of participating in the execution of the first computing task.

[0153] Still taking the target node as an example, if the first request carries the computing capability required for performing the first computing task, the first core network device can determine the computing capability used by the target node for participating in performing the first computing task, which can be equal to the computing capability required for performing the first computing task. If the first request does not carry the computing capability required for performing the first computing task, the first core network device can determine the computing capability used by the target node for participating in performing the first computing task, which can be equal to the computing capability that the target node can provide. The first core network device determines the computing capability used by other first nodes for participating in performing the first computing task in the same manner as the target node, and thus is not described herein.

[0154] In an embodiment, the first request carries an end-to-end total task duration requirement for performing the first computing task. The first end-to-end total task duration for the one or more first nodes to collaboratively perform the first computing task meets the end-to-end total task duration requirement for performing the first computing task.

[0155] The first end-to-end total task duration is obtained based on the computing duration of each first node and / or the transmission duration for the one or more first nodes to collaboratively perform the first computing task.

[0156] Specifically, in the process of the one or more first nodes collaboratively performing the first computing task, an intermediate result needs to be obtained by performing processing of the first computing task from a starting node in the one or more first nodes, and then the intermediate result is transmitted to a next-hop first node, and so on. Each first node receives the intermediate result transmitted by a previous-hop first node, performs processing on the intermediate result to obtain a processed intermediate result of the first node, and sends the processed intermediate result to a next-hop first node, until a finishing node in the one or more first nodes completes the processing to obtain a final result of the first computing task. As can be seen, in the process of the one or more first nodes collaboratively performing the first computing task, two types of time consumption are involved. One is the computing duration of each first node in the process of the one or more first nodes collaboratively performing the first computing task, and the other is the transmission duration for the one or more first nodes to collaboratively perform the first computing task.

[0157] The computing duration of each first node can be the computing duration that each first node is likely to consume when participating in performing the first computing task, which is estimated by the first core network device. The computing duration of each first node is obtained based on the computing capability that each first node can provide and the computing amount of a model used by each first node for participating in performing the first computing task. The computing amount can be measured in FLOPs (floating point operations).

[0158] Specifically, the first core network device can calculate the computation duration of any one of the first nodes in the following manner: the first core network device determines a computation amount of a model used by the first node to participate in performing the first computing task, divides the computation amount of the model by the computation capability that can be provided by the first node, and obtains the computation duration of the first node.

[0159] The first core network device determines the computation amount of the model used by the first node to participate in performing the first computing task in the following manner: the first core network device determines the computation amount of the model based on at least one of a dimension of the model, a number of layers of the model, and a minimum unit of input and / or output data of the model used by the first node to participate in performing the first computing task.

[0160] For example, the first core network device determines that the computation amount of the model of the target node is 10000 FLOPs based on at least one of a dimension of the model, a number of layers of the model, and a minimum unit of input and / or output data of the model used by the target node to participate in performing the first computing task. The computation capability that can be provided by the target node is 5000 FLOPS. The first core network device can calculate 10000 / 5000 = 2 (seconds), that is, the computation duration of the target node is 2 seconds. The first core network device can calculate the computation duration of each first node in the same manner as the target node, which is not described herein.

[0161] The transmission duration of the one or more first nodes to cooperatively perform the first computing task is related to a topology relationship of the one or more first nodes, where the topology relationship of the one or more first nodes is used to indicate a previous hop first node of each first node and / or a next hop first node of each first node.

[0162] The transmission duration of the one or more first nodes to cooperatively perform the first computing task refers to a transmission duration of an intermediate result transmitted between a starting node and an ending node in a process in which the one or more first nodes cooperatively perform the first computing task.

[0163] Exemplarily, the manner in which the first core network device obtains the transmission duration of the one or more first nodes in cooperative execution of the first computing task can include: the first core network device obtaining, based on a topological relationship of the one or more first nodes, a next-hop first node of each first node; and calculating, based on a network parameter between each first node and its next-hop first node, a sub-transmission duration between each first node and its next-hop first node. The first core network device adds the sub-transmission duration corresponding to each first node in the one or more first nodes to obtain the transmission duration of the one or more first nodes in cooperative execution of the first computing task.

[0164] The network parameter is a relevant parameter for representing a network transmission environment, which can include a network bandwidth and the like, and is not limited or exhausted herein.

[0165] The first core network device obtains, based on a topological relationship of the one or more first nodes, a next-hop first node of each first node; and calculates, based on a network parameter between each first node and its next-hop first node, a sub-transmission duration between each first node and its next-hop first node. The first core network device can determine, based on the topological relationship of the one or more first nodes, a starting node from the one or more first nodes; take the starting node as a current node; determine whether the current node has a next-hop first node; if the current node has a next-hop first node, calculate, based on a network parameter between the current node and its next-hop first node, a sub-transmission duration between the current node and its next-hop first node; take the next-hop first node of the current node as a new current node, and return to the determination of whether the current node has a next-hop first node. In addition, in the case where the current node does not have a next-hop first node, the current node is determined as an ending node in the one or more first nodes, and the sub-transmission duration corresponding to the ending node can be equal to 0, that is, the ending node does not need to transmit a final result, and thus the sub-transmission duration corresponding to the ending node can be 0.

[0166] Exemplarily, the manner in which the first core network device obtains the transmission duration of the one or more first nodes in cooperative execution of the first computing task can include: the first core network device obtaining, based on a topological relationship of the one or more first nodes, a next-hop first node of each first node; and calculating, based on a network parameter between each first node and its next-hop first node, a sub-transmission duration between each first node and its next-hop first node. The first core network device adds the sub-transmission duration corresponding to each first node in the one or more first nodes to obtain the transmission duration of the one or more first nodes in cooperative execution of the first computing task.

[0167] The first core network device can calculate the first end-to-end task total time length in the following manner: the first core network device adds the calculation time length of each first node to obtain a total calculation time length; and adds the total calculation time length and the transmission time length of the one or more first nodes in cooperation with each other to perform the first calculation task to obtain the first end-to-end task total time length.

[0168] When the first core network device generates the first configuration information corresponding to each of the one or more first nodes, the one or more first nodes are required to work together to complete the first calculation task to meet the end-to-end task total time length requirement of performing the first calculation task. Specifically, the first core network device can calculate the first end-to-end task total time length of the one or more first nodes in cooperation with each other to perform the first calculation task according to at least one of the topological relationship of the one or more first nodes, the calculation capability that each first node can provide, and the model used in each first node to perform the first calculation task. When the first end-to-end task total time length meets the end-to-end task total time length requirement of performing the first calculation task, the calculation capability used by each first node to participate in performing the first calculation task and the execution strategy of each first node participating in performing the first calculation task can be determined according to at least one of the topological relationship of the one or more first nodes, the calculation capability that each first node can provide, and the model used in each first node to perform the first calculation task. The first configuration information corresponding to each first node is generated based on the calculation capability used by each first node to participate in performing the first calculation task and the execution strategy of each first node participating in performing the first calculation task.

[0169] In addition, the processing of the first core network device can further include: if the first end-to-end task total time length does not meet the end-to-end task total time length requirement of performing the first calculation task, the one or more first nodes are re-adjusted, the first end-to-end task total time length is recalculated based on at least one of the topological relationship of the re-adjusted one or more first nodes, the calculation capability that each first node can provide, and the model used in each first node to perform the first calculation task, and so on, until the first end-to-end task total time length meets the end-to-end task total time length requirement of performing the first calculation task. The calculation capability used by each first node to participate in performing the first calculation task and the execution strategy of each first node participating in performing the first calculation task can be determined according to at least one of the topological relationship of the one or more first nodes, the calculation capability that each first node can provide, and the model used in each first node to perform the first calculation task. The first configuration information corresponding to each first node is generated based on the calculation capability used by each first node to participate in performing the first calculation task and the execution strategy of each first node participating in performing the first calculation task.

[0170] The re-adjustment of the one or more first nodes can refer to that the first core network device can re-screen one or more first nodes satisfying a first condition. The first condition is the same as the foregoing embodiments, and will not be repeated.

[0171] The first core network device determines the computing capability used by each first node to participate in the execution of the first computing task and an execution strategy of each first node participating in the execution of the first computing task according to at least one of a topological relationship of the one or more first nodes, a computing capability that can be provided by each first node, and a model used by each first node to participate in the execution of the first computing task. The determination can include at least one of the following: the first core network device generates the execution strategy of each first node participating in the execution of the first computing task based on an identifier of the first computing task, the topological relationship of the one or more first nodes, and information about the model used by each first node to participate in the execution of the first computing task; and the first core network device determines the computing capability used by each first node to participate in the execution of the first computing task based on the computing capability that can be provided by each first node.

[0172] Here, the execution strategy of each first node participating in the execution of the first computing task is the same as the foregoing embodiments. The first core network device generates the execution strategy of each first node participating in the execution of the first computing task based on the identifier of the first computing task, the topological relationship of the one or more first nodes, and the information about the model used by each first node to participate in the execution of the first computing task. The generation can include: the first core network device determines at least one of a previous-hop first node of each first node and a next-hop first node of each first node based on the topological relationship of the one or more first nodes; and the first core network device generates the execution strategy of each first node participating in the execution of the first computing task based on at least one of the previous-hop first node of each first node, the next-hop first node of each first node, the information about the model used by each first node to participate in the execution of the first computing task, and the identifier of the first computing task.

[0173] The first core network device determines the computing capability used by each first node to participate in the execution of the first computing task based on the computing capability that can be provided by each first node. This can refer to that the first core network device takes the computing capability that can be provided by each first node as the computing capability used by each first node to participate in the execution of the first computing task.

[0174] In an embodiment, the first request does not carry an end-to-end total duration requirement for the execution of the first computing task, but carries a required computing capability for the execution of the first computing task.

[0175] In this embodiment, the first core network device can determine the computing capability used by each first node for participating in the execution of the first computing task based on the computing capability required for executing the first computing task. For example, the first core network device can take the computing capability required for executing the first computing task as the computing capability used by each first node for participating in the execution of the first computing task.

[0176] In this embodiment, the first core network device can generate the execution strategy of each first node for participating in the execution of the first computing task in the following manner: the first core network device generates the execution strategy of each first node for participating in the execution of the first computing task based on the identifier of the first computing task, the topological relationship of the one or more first nodes, and the related information of the model used by each first node for participating in the execution of the first computing task. The process of generating the execution strategy of each first node for participating in the execution of the first computing task is the same as that in the foregoing embodiments, and thus will not be described here.

[0177] It should also be noted that the above is the related description of the content and generation manner of the first configuration information corresponding to each first node, but the first configuration information corresponding to each first node can further include other content in addition to the above content. For example, the first configuration information corresponding to each first node can further include the QoS (Quality of Service) parameter of each segment of connection (between each first node and the previous-hop first node or between each first node and the next-hop first node), which can be used to guarantee the transmission delay. Here, no limitation or exhaustive enumeration is made.

[0178] In some possible implementation manners, after generating the one or more first configuration information, the first core network device can send the one or more first configuration information to the one or more first nodes. Here, the first core network device can determine that the one or more first nodes complete the establishment of a computing session after completing the sending of the corresponding first configuration information to each first node. The computing session can refer to a computing session in which the one or more first nodes execute the first computing task based on the one or more first configuration information.

[0179] Taking an arbitrary first node as an example, the target node can receive the first configuration information corresponding to the target node from the first core network device. The related description of the first configuration information corresponding to the target node is the same as that in the foregoing embodiments, and thus will not be described here.

[0180] After receiving the first configuration information corresponding to the target node from the first core network device, the target node further includes: the target node acquires first data packets; and the target node processes the first data packets based on the first configuration information to obtain second data packets.

[0181] In an example, the target node is a starting node in the one or more first nodes. In this example, the target node obtaining the first data packet can be that the target node locally obtains a to-be-processed raw data packet under the first computing task as the first data packet.

[0182] In an example, the target node is a starting node in the one or more first nodes, but the data packet of the first computing task is processed from a terminal not included in the one or more first nodes. This example refers to the terminal as an initial data processing terminal. In this example, the target node obtaining the first data packet can be that the target node receives the first data packet from the initial data processing terminal, where the first data packet carries an identification of the first computing task.

[0183] The first data packet can carry the identification of the first computing task at a specified position. The specified position can be a packet header position of the first data packet or can be another specified position. The protocol type of the first data packet can be any protocol (layer) for transmitting application data, which is not limited in the embodiment.

[0184] For example, the identification of the first computing task can be carried in an IP Header (Internet Protocol Header) of the first data packet, or the identification of the first computing task can be carried in a TCP header (Transmission Control Protocol Header) of the first data packet, or the identification of the first computing task can be carried in an IPv4 option field of the first data packet, or the identification of the first computing task can be carried in an IPv4 new protocol type header of the first data packet, or the identification of the first computing task can be carried in an IPv6 extension header of the first data packet, or the identification of the first computing task can be carried in a new TCP option in the TCP header of the first data packet.

[0185] In an example, the target node is an intermediate node in the one or more first nodes. In this example, the target node obtaining the first data packet can be that the target node determines a previous-hop other first node of the target node based on the first configuration information, and receives the first data packet from the previous-hop other first node, where the first data packet carries the identification of the first computing task.

[0186] The target node determines the next-hop other first node of the target node based on the first configuration information, which can be that the target node determines the next-hop other first node of the target node based on an execution strategy of the target node participating in executing the first computing task in the first configuration information.

[0187] The target node processes the first data packet based on the first configuration information to obtain a second data packet, which can include that the target node determines computing capability used this time based on computing capability used by the target node participating in executing the first computing task in the first configuration information; the target node determines a target model used this time based on related information of a model used by the target node participating in executing the first computing task included in the execution strategy of the target node participating in executing the first computing task in the first configuration information; and the target node processes the first data packet based on the computing capability used this time and the target model used this time to obtain the second data packet.

[0188] In an example, the target node is not an end node in the one or more first nodes, and in this example, after the second data packet is obtained, the target node determines a next-hop other first node of the target node based on the first configuration information and sends the second data packet to the next-hop other first node, where the second data packet carries an identifier of the first computing task.

[0189] The target node determines the next-hop other first node of the target node based on the first configuration information, which can be that the target node determines the next-hop other first node of the target node based on an execution strategy of the target node participating in executing the first computing task in the first configuration information.

[0190] The second data packet carries an identifier of the first computing task, and the related description of the identifier is the same as that of the first data packet, which is not repeated.

[0191] In an example, the target node is an end node in the one or more first nodes, and in this example, after the target node processes the first data packet based on the first configuration information to obtain the second data packet, the target node can no longer send the second data packet.

[0192] Since the processing of each first node is the same as that of the target node, it is not repeated.

[0193] In combination with FIG. 4, a system architecture to which the configuration method provided in this embodiment is applied is exemplarily described:

[0194] In FIG. 4, a computing power management network element is illustrated, which functions to collect the computing power (measured in FLOPS / TOPS) of each node, and the collection granularity can be node granularity or network slice granularity; the function can also include the computing power that each node can provide at one or more granularities, which can include devices, services, applications, and the like.

[0195] The each node can include a core network user plane network element (such as NF), a base station (access network device), an application server, an EC server (Edge Computing server) in an edge hosting environment, as shown in FIG. 4.

[0196] In FIG. 4, a model management network element is illustrated, which functions can include registration of model information of each node (i.e., the registration information in the foregoing embodiment), and discovery of network elements supporting a specific model.

[0197] In FIG. 4, a policy control network element is illustrated, which functions can include determining the allocation of computing power, the allocation of communication resources, and the like, according to the computing power of each node, at a service granularity or a user granularity, and the like. In the allocation process of computing power, the policy control network element can allocate the computing power (measured in FLOPS / TOPS) of each node according to the required computing power carried by a request (such as the first request in the foregoing embodiment); or the policy control network element can allocate the computing power of each node according to the end-to-end task total time length requirement for performing the first computing task carried by the request (such as the first request).

[0198] The function of the policy control network element can also include allocating the nodes and their computing power for performing a computing task for a specific service or user, which can be allocated based on the negotiation between the UE and the network, or can be allocated by a unified node (which can include the UE).

[0199] The function of the policy control network element can also include the allocation of the execution policy of each node. The execution policy is the same as the execution policy of each first node participating in the execution of the first computing task in the foregoing embodiment, and is not repeated here.

[0200] Next, an exemplary description of the configuration method provided by the embodiment is given in combination with FIG. 5 and FIG. 6, which includes:

[0201] At step 500, the policy control network element obtains a service processing request (i.e., a first request) of a third party, which can include at least one of a parameter of a service to which the first computing task belongs, a region parameter corresponding to the first computing task, a total time length requirement of an end-to-end task for executing the first computing task, a computing capability required for executing the first computing task, an identifier of the first computing task, and the like.

[0202] At step 501, the policy control network element obtains node computing capability from the computing power management network element to obtain a computing capability that each of one or more second nodes located in a first region can provide, wherein the first region is determined based on the region parameter corresponding to the first computing task. The architecture and information transmission between the policy control network element and the computing power management network element are shown in FIG. 6, in which step 501 is simply illustrated as node computing capability obtaining.

[0203] At step 502, the policy control network element performs model searching from the model management network element to obtain one or more third nodes located in the first region and having a model supporting the first service, wherein the first service is determined based on the parameter of the service to which the first computing task belongs. The architecture and information transmission between the policy control network element and the model management network element are shown in FIG. 6, in which step 502 is simply illustrated as model searching.

[0204] At step 503, the policy control network element determines a plurality of first nodes as nodes for executing the first computing task and determines a computing capability of each first node (i.e., a computing capability used by each first node for participating in executing the first computing task), and an execution strategy of each first node (i.e., an execution strategy of each first node for participating in executing the first computing task) based on the information obtained at steps 501 and 502. The execution strategy is the same as that described in the foregoing embodiments, and thus will not be described herein. In FIG. 6, step 503 is simply illustrated as computing capability and execution strategy distribution of the policy control network element.

[0205] Here, the first nodes (i.e., nodes for executing the first computing task) and the execution strategy determined at step 503 are used to establish a computing session, which can complete a corresponding task through division and cooperation of the plurality of first nodes while satisfying the total time length requirement of the end-to-end task for executing the first computing task (which can include communication time delay + computing time delay) in step 500, i.e., a sum of a processing time (i.e., a computing time length of each first node) and a transmission time (i.e., a transmission time length of one or more first nodes for cooperatively executing the first computing task).

[0206] The "task ID" in the above execution strategy can be carried in the IP or TCP header of the data packet transmitted subsequently, such as IPv4 option field, IPv4 new protocol type, IPv6 extension header, and a new TCP option in the TCP header.

[0207] Steps 504-507: The policy control network element sends the first computing task input computing capability and "execution strategy" for each of the plurality of first nodes. The plurality of first nodes can include a UE, a RAN, a CN (specifically, any NF in the CN), and an AF as shown in FIG. 5. The architecture composition relationship and information transmission between the policy control network element and the plurality of first nodes (i.e., the UE, the RAN, the CN, and the AF) are shown in FIG. 6, in which the steps 504-507 are simply illustrated by the dashed arrows to show that the policy control network element allocates the computing capability and execution strategy of the UE to the UE, the computing capability and execution strategy of the RAN to the RAN, the computing capability and execution strategy of the CN to the CN, and the computing capability and execution strategy of the AF to the AF.

[0208] Step 508: When the configuration is completed, the plurality of first nodes complete the establishment of a computing session. The computing session can refer to a computing session in which the plurality of first nodes execute the first computing task based on the respective execution strategies (and the computing capability input for the first computing task).

[0209] It should be further noted that the computing power management network element, the model management network element, and the policy control network element in FIGS. 4-6 correspond to three logical functions on the core network side. The computing power management network element, the model management network element, and the policy control network element can be disposed in the same physical device, or can be disposed in different physical devices, or any two of them can be disposed in the same physical device and the other in a different physical device, and so on. The physical device can be at least one of a hardware device, a physical device, a physical entity, and a physical entity device on the network side (such as the core network side). The specific arrangement of the above three logical functions in the physical device is not limited or exhausted here.

[0210] By using the above scheme, after receiving the first request to execute the first computing task, the first core network device sends corresponding first configuration information for each first node, so that each first node can cooperatively execute the first computing task. In this way, in the scenario where the communication network participates in providing computing power services, the nodes executing the computing task can be accurately configured, so that the nodes providing computing power can accurately and efficiently cooperatively execute the computing task.

[0211] FIG. 7 is a schematic flowchart of a configuration method according to an embodiment of the present application. The method comprises at least part of the following.

[0212] S710, the first core network device sends second configuration information to the second core network device, wherein the second configuration information carries routing information of each of one or more second services, and the routing information of each of the one or more second services comprises a routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the one or more second services.

[0213] FIG. 8 is a schematic flowchart of a configuration method according to an embodiment of the present application. The method comprises at least part of the following.

[0214] S810, the second core network device receives second configuration information from the first core network device, wherein the second configuration information carries routing information of each of one or more second services, and the routing information of each of the one or more second services comprises a routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the one or more second services.

[0215] FIG. 9 is a schematic flowchart of a configuration method according to an embodiment of the present application. The method comprises at least part of the following.

[0216] S910, the first terminal receives third configuration information from the first core network device, wherein the third configuration information carries a first identifier of each of at least part of one or more second services and a second identifier associated with the each of the at least part of the one or more second services.

[0217] The first core network device can be a policy control network element. The first core network device has a policy control function, and the related description of the policy control function is the same as the foregoing embodiments, which will not be repeated.

[0218] The second core network device can be a core network user plane network element, such as a UPF (User Plane Function).

[0219] The one or more fourth nodes can be nodes and / or AFs in a communication network (such as a 3GPP network). Specifically, the one or more fourth nodes can comprise at least one of the following: one or more access network devices, one or more NFs, and one or more AFs.

[0220] In an embodiment, before the first core network device sends the second configuration information to the second core network device, the first core network device can receive a second request from a third party. The third party can comprise at least one of a third party AF and a third party UE, the third party AF being different from the one or more fourth nodes, and the third party UE being different from the one or more fourth nodes.

[0221] The second request can carry at least one of the following: relevant information of each of one or more second services. The one or more second services can be services requested to be executed by a third party. The third party generates and sends the second request in a triggered or generated manner, and the third party determines each second service in a manner not limited by the embodiments.

[0222] The relevant information of the second service can include a second identifier of the second service. The second identifier of the second service can be an original ID of the second service, which can also be referred to as a real ID, or a permanent ID, or a long-term ID. Optionally, the relevant information of each second service can also include a type of the second service, and the like. The embodiments do not limit or exhaustively enumerate the content that the relevant information of the second service can include.

[0223] In an embodiment, the processing of the first core network device after receiving the second request can include: generating routing information of each of one or more second services.

[0224] Taking any one of the second services as the i-th second service (i is an integer greater than or equal to 1) as an example, the routing information of the i-th second service includes: a routing order of one or more fourth nodes that cooperatively execute a computing task under the i-th second service.

[0225] Taking any one of the one or more fourth nodes that cooperatively execute the computing task under the i-th second service as the j-th fourth node (j is an integer greater than or equal to 1) as an example, the routing order of the one or more fourth nodes that cooperatively execute the computing task under the i-th second service can be used to determine or indicate a previous hop node of the j-th fourth node that cooperatively executes the computing task under the i-th second service, and / or a next hop node of the j-th fourth node.

[0226] Since the relevant description of the routing information of each second service is the same as the relevant description of the routing information of the i-th second service, it is not repeated here.

[0227] In an embodiment, the second configuration information further carries the first identifier of each second service associated with the routing information of each second service.

[0228] The processing of the first core network device after receiving the second request can include: generating a first identifier corresponding to a second identifier of each of one or more second services.

[0229] The first identifier of the second service can be another type of identifier other than the second identifier of the second service. For example, the first identifier of the second service can include at least one of the following: a temporary identifier of the second service, or a Token of the second service, and the like.

[0230] The processing of the first core network device generating the first identifier corresponding to the second identifier of each of the one or more second services can include: associating (or corresponding to) the first identifier of each of the second services with the routing information of the second service.

[0231] In an embodiment, the manner in which the first core network device generates the second configuration information can include: adding the routing information of each of the one or more second services in the second configuration information; and adding the first identifier of each of the second services associated with the routing information of each of the second services in the second configuration information.

[0232] After the first core network device generates the second configuration information, the first core network device can send the second configuration information to the second core network device.

[0233] In combination with Table 2, the second configuration information generated by the first core network device is described as an example:

[0234] Table 2

[0235] Specifically, Table 2 above shows that the first identifiers corresponding to the three second services are Token-1, Token-2, and Token-3, respectively; and the first identifier of each of the second services is associated with corresponding routing information, for example, the first identifier of the second service is Token-1, and the associated routing information is “RAN→NF-1→AF-2→AF-5”, which indicates that the fourth node for performing the computing task of the second service with Token-1 as the first identifier includes RAN1, NF-1, AF-2, and AF-5, and the routing order is that RAN1 is the first execution node, NF-1 is the next hop node of RAN1, AF-2 is the next hop node of NF-1, AF-5 is the next hop node of AF-2 and is the last execution node. The relevant explanations of the routing information corresponding to Token-1 and Token-2 as the first identifier of the second service are similar to the explanation of the routing information corresponding to Token-1 as the first identifier of the second service, and thus are not repeated.

[0236] In an embodiment, the processing of the first core network device after receiving the second request can further include: determining one or more terminals based on the second identifier of each of the one or more second services, each of the one or more terminals can perform or initiate or correspond to at least part of the one or more second services.

[0237] The first core network device, after determining the one or more terminals, can comprise: the first core network device sending third configuration information corresponding to each terminal of the one or more terminals, wherein the third configuration information corresponding to each terminal carries the first identifier of each second service of at least part of the second service and its associated second identifier.

[0238] Taking the first terminal as an arbitrary one of the one or more terminals, the processing of the first core network device can comprise: the first core network device sending third configuration information to the first terminal, wherein the third configuration information carries the first identifier of each second service of at least part of the one or more second services and its associated second identifier.

[0239] Still taking the first terminal as an arbitrary one of the one or more terminals, after the first terminal receives the third configuration information from the first core network device, the method further comprises: the first terminal sending a third data packet to the second core network device, wherein the third data packet carries the first identifier of the target service, the first identifier of the target service is determined based on the second identifier of the target service, and the target service is one of the at least part of the second service.

[0240] The third data packet can carry the first identifier of the target service at a specified location. The specified location can be the packet header position of the third data packet or other specified location; the protocol type of the third data packet can be any transmission application data protocol (layer), which is not limited in the embodiment.

[0241] After the second core network device receives the second configuration information from the first core network device, the method further comprises: the second core network device receiving a third data packet from the first terminal, wherein the third data packet carries the first identifier of the target service, wherein the target service is one of the one or more second services; the second core network device determines the routing information of the target service based on the first identifier of the target service and the second configuration information; and the second core network device determines the routing order of one or more fourth nodes for cooperatively performing the computing task of the third data packet under the target service based on the routing information of the target service.

[0242] Wherein, the second core network device determines the routing information of the target service based on the first identifier of the target service and the second configuration information, which can comprise: the second core network device determines the routing information of the target service based on the first identifier of each second service associated with the routing information of each second service carried by the second configuration information.

[0243] After the second core network device determines the routing sequence of the one or more fourth nodes that cooperatively perform the computing task of the third data packet under the target service, the second core network device can further include: sending the third data packet to a first fourth node that cooperatively performs the computing task of the third data packet under the target service according to the routing sequence, and then receiving the processed intermediate data packet returned by the first fourth node; if there is a second fourth node based on the routing sequence, the second core network device sends the processed intermediate data packet returned by the first fourth node to the second fourth node, receives the processed intermediate data packet returned by the second fourth node, and so on until the data packet returned by the last fourth node is received.

[0244] The processing of sending the third data packet to the first fourth node that cooperatively performs the computing task of the third data packet under the target service can include: sending the third data packet to the first fourth node that cooperatively performs the computing task of the third data packet under the target service, and recording the IP address information of the third data packet. In addition, when the second core network device sends the third data packet to the first fourth node, the first identifier of the target service carried in the third data packet can be deleted or removed; or, the first identifier of the target service carried in the third data packet can also be retained.

[0245] Here, the intermediate data packet processed by any fourth node and the data packet before processing do not necessarily correspond one by one, but correspond to the same service (i.e., the target service in this embodiment).

[0246] It should be pointed out that the above mainly illustrates an exemplary process in which the first terminal receives the third configuration information and then sends the third data packet to make the second core network device control the execution of the computing task by each fourth node, and any terminal receiving the third configuration information can perform the same processing as the first terminal in actual processing, which is not described herein.

[0247] This embodiment assumes that the computing task is completed by the application layer, and does not need to be configured by the computing control plane. The network needs to perform fine routing, i.e., distributing the corresponding data packet to different nodes. For this purpose, the first core network device needs to perform fine routing configuration on the execution nodes.

[0248] The configuration method provided in this embodiment will be described in one exemplary manner in combination with FIG. 10, which specifically includes:

[0249] Step 1000: The policy control network element obtains a task request (i.e., the second request in the foregoing embodiment).

[0250] Step 1001, the policy control network element generates a first identifier (such as Token or Token identifier) and a routing table (i.e., the routing information in the foregoing embodiment) of the second service according to the obtained task request.

[0251] Step 1002, the policy control network element configures the first identifier of the second service (specifically, a mapping relationship or an association relationship between the first identifier of the second service (such as Token) and the ID of the second service) for the UE (i.e., the first terminal).

[0252] Step 1003, the policy control network element configures the first identifier (such as Token or Token identifier) and the routing table (i.e., the routing information in the foregoing embodiment) of the second service for the core network user plane network element, wherein the Token identifier is consistent with that configured for the UE.

[0253] The processing performed by the core network user plane network element (such as UPF) according to the configured routing table in this embodiment will be exemplarily described below with reference to FIG. 11, and specifically includes the following steps.

[0254] Step 1101, when a data packet corresponding to Application-1 (service-1, i.e., the target service) occurs, the UE marks the packet header of the data packet with the first identifier (such as Token-1) of the target service and sends the data packet to the network side UPF (the UE can send the data packet to the UPF through the RAN).

[0255] Step 1102, the network side UPF identifies the data packet carrying the first identifier (such as Token-1) of the target service, and finds that the routing order corresponding to the first identifier (such as Token-1) of the target service is NF-1->AF-2->AF5 according to the routing table.

[0256] Step 1103, the UPF sends the data packet to NF-1 (the data packet sent can remove the Token-1 information in the packet header), and records the IP address information of the data packet. In FIG. 11, in order to represent the processing of the data packet, the data packet is increased by one "*" after being processed once, which represents that the data packet is processed by the node.

[0257] Step 1104, the NF-1 returns the processed data packet (such as the data packet*in FIG. 11) to the UPF.

[0258] Step 1105, the UPF sends the data packet processed by the NF-1 (the data packet*in FIG. 11) to the AF-2, and receives the data packet processed by the AF-2 (the data packet**in FIG. 11).

[0259] At step 1006, the UPF sends the AF-2 processed data packet (packet** shown in FIG. 11) to the AF-2 and receives the processed data packet (packet*** shown in FIG. 11) from the AF-5.

[0260] By adopting the above scheme, the first core network device can configure the second core network device with the second configuration information, and the second core network device can obtain the routing order of the one or more fourth nodes that cooperatively perform the computing task under each second service through the second configuration information. In this way, the second core network device can accurately route the nodes performing the computing task according to the second configuration information when performing subsequent computing tasks, so as to accurately and efficiently cooperatively perform the computing task by the nodes providing computing power.

[0261] FIG. 12 is a schematic diagram of the component structure of the first core network device according to an embodiment of the present application, which includes:

[0262] The first communication unit 1201 is configured to receive a first request, wherein the first request is used to request to perform a first computing task; and send one or more first configuration information to one or more first nodes, wherein the one or more first configuration information is used for the one or more first nodes to cooperatively perform the first computing task, and different first configuration information in the one or more first configuration information corresponds to different first nodes.

[0263] The first request carries at least one of the following: a parameter of a service to which the first computing task belongs, a region parameter corresponding to the first computing task, a total time length requirement of an end-to-end task for performing the first computing task, a computing power required for performing the first computing task, and an identifier of the first computing task.

[0264] Each first configuration information in the one or more first configuration information includes at least one of the following: a computing power used by the each first node for participating in performing the first computing task, and an execution strategy of the each first node for participating in performing the first computing task.

[0265] The computing power used by the each first node for participating in performing the first computing task is determined based on at least one of the following: the computing power required for performing the first computing task, and the computing power that can be provided by the each first node.

[0266] The execution strategy of the each first node for participating in performing the first computing task includes at least one of the following: the identifier of the first computing task, a next-hop first node of the each first node, a next-hop first node of the each first node, and related information of a model used by the each first node for participating in performing the first computing task.

[0267] The related information of the model includes at least one of the following: an identifier of the model, a type of the model, related information of input data of the model, and related information of output data of the model.

[0268] The first end-to-end task total duration of the one or more first nodes cooperatively performing the first computing task meets an end-to-end task total duration requirement of performing the first computing task.

[0269] The first end-to-end task total duration is obtained based on a computing duration of each first node and / or a transmission duration of the one or more first nodes cooperatively performing the first computing task.

[0270] The computing duration of each first node is obtained based on a computing capability that can be provided by each first node and a computing amount of a model used by each first node for performing the first computing task.

[0271] The transmission duration of the one or more first nodes cooperatively performing the first computing task is related to a topological relationship of the one or more first nodes, where the topological relationship of the one or more first nodes is used to indicate a previous-hop first node of each first node and / or a next-hop first node of each first node.

[0272] As shown in FIG. 12, the first core network device further includes a first processing unit 1202 configured to perform at least one of the following: searching for a computing capability that can be provided by each second node of one or more second nodes located in a first region, where the first region is determined based on a region parameter corresponding to the first computing task; and searching for one or more third nodes having a model supporting a first service, where the first service is determined based on a parameter of a service to which the first computing task belongs.

[0273] The first processing unit is configured to determine, based on the computing capability that can be provided by each second node and / or the one or more third nodes, the one or more first nodes that meet a first condition, where the first condition includes at least one of the following: being located in the first region, having the model supporting the first service, and being capable of providing a computing capability required for performing the first computing task.

[0274] The one or more first nodes include at least one of the following: one or more terminals, one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

[0275] FIG. 13 is a schematic diagram of a composition structure of a target node according to an embodiment of the present application, including:

[0276] The second communication unit 1301 is configured to receive first configuration information corresponding to the target node from the first core network device, wherein the first configuration information corresponding to the target node is used for the target node to perform a first computing task in cooperation with one or more other first nodes.

[0277] The first configuration information corresponding to the target node comprises at least one of the following: a computing capability used by the target node for participating in performing the first computing task, and an execution strategy of the target node for participating in performing the first computing task.

[0278] The execution strategy of the target node for participating in performing the first computing task comprises at least one of the following: an identifier of the first computing task, a next-hop other first node of the target node, a next-hop other first node of the target node, and related information of a model used by the target node for participating in performing the first computing task.

[0279] The related information of the model comprises at least one of the following: an identifier of the model, a type of the model, related information of input data of the model, and related information of output data of the model.

[0280] As shown in FIG. 13, the target node further comprises a second processing unit 1302 configured to process the first data packet based on the first configuration information to obtain a second data packet.

[0281] The second communication unit is configured to obtain the first data packet.

[0282] The second processing unit is configured to determine, based on the first configuration information, a next-hop other first node of the target node.

[0283] The second communication unit is configured to receive the first data packet from the next-hop other first node, wherein the first data packet carries an identifier of the first computing task.

[0284] The second processing unit is configured to determine, based on the first configuration information, a next-hop other first node of the target node.

[0285] The second communication unit is configured to send the second data packet to the next-hop other first node, wherein the second data packet carries the identifier of the first computing task.

[0286] The target node is one of the following: a target terminal, a target access network device, a target network function (NF), and a target AF.

[0287] The first core network device of an embodiment of the present application comprises:

[0288] The first communication unit is configured to send second configuration information to the second core network device, wherein the second configuration information carries routing information of each of one or more second services, and the routing information of each of the second services comprises routing order of one or more fourth nodes that cooperatively perform a computing task under each of the second services.

[0289] The second configuration information further carries a first identifier of each of the second services associated with the routing information of each of the second services.

[0290] The first communication unit is configured to send third configuration information to the first terminal, wherein the third configuration information carries a first identifier of each of at least part of the one or more second services and a second identifier associated therewith.

[0291] The one or more fourth nodes comprise at least one of the following: one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

[0292] FIG. 14 is a schematic diagram of a constituent structure of a second core network device according to an embodiment of the present application, comprising:

[0293] The third communication unit is configured to receive second configuration information from the first core network device, wherein the second configuration information carries routing information of each of one or more second services, and the routing information of each of the second services comprises routing order of one or more fourth nodes that cooperatively perform a computing task under each of the second services.

[0294] The second configuration information further carries a first identifier of each of the second services associated with the routing information of each of the second services.

[0295] As shown in FIG. 14, the second core network device further comprises a third processing unit 1402 configured to determine routing information of the target service based on the first identifier of the target service and the second configuration information, and determine routing order of one or more fourth nodes that cooperatively perform a computing task of the third data packet under the target service based on the routing information of the target service.

[0296] The third communication unit is configured to receive a third data packet from the first terminal, wherein the third data packet carries a first identifier of a target service, and the target service is one of the one or more second services.

[0297] The one or more fourth nodes comprise at least one of the following: one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

[0298] FIG. 15 is a schematic diagram of a constituent structure of a terminal according to an embodiment of the present application, including:

[0299] The fourth communication unit 1501 is configured to receive third configuration information from the first core network device, wherein the third configuration information carries a first identifier of each of one or more second services of the at least part of the second services and a second identifier associated with the first identifier.

[0300] The fourth communication unit is configured to send a third data packet to the second core network device, wherein the third data packet carries a first identifier of a target service, and the first identifier of the target service is determined based on a second identifier of the target service, and the target service is one of the at least part of the second services.

[0301] The device of the embodiments of the present application can realize the corresponding functions of each device in the foregoing configuration method embodiments. The processes, functions, implementation manners and beneficial effects of each module (sub-module, unit or component, etc.) in the device can be referred to the corresponding description in the foregoing method embodiments, which will not be described here. It should be noted that the functions described with respect to each module (sub-module, unit or component, etc.) in the device of the embodiments of the present application can be realized by different modules (sub-modules, units or components, etc.), or can be realized by the same module (sub-module, unit or component, etc.).

[0302] FIG. 16 is a schematic structural diagram of a communication device 1600 according to an embodiment of the present application. The communication device 1600 includes a processor 1610, which can call and run a computer program from a memory to enable the communication device 1600 to implement the method in the embodiments of the present application. In a possible implementation manner, the communication device 1600 can further include a memory 1620. The processor 1610 can call and run a computer program from the memory 1620 to enable the communication device 1600 to implement the method in the embodiments of the present application. The memory 1620 can be a separate device independent of the processor 1610, or can be integrated in the processor 1610. In a possible implementation manner, the communication device 1600 can further include a transceiver 1630, and the processor 1610 can control the transceiver 1630 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 1630 can include a transmitter and a receiver. The transceiver 1630 can further include an antenna, and the number of antennas can be one or more.

[0303] In a possible implementation, the communication device 1600 can be the first core network device, or the target node, or the second core network device, or the first terminal of the embodiments of the present application, and the communication device 1600 can implement the corresponding procedures in the methods of the embodiments of the present application performed by the first core network device, or the target node, or the second core network device, or the first terminal. For brevity, details are not described herein.

[0304] FIG. 17 is a schematic structural diagram of a chip 1700 according to the embodiments of the present application. The chip 1700 includes a processor 1710, which can call and run a computer program from a memory to implement the methods in the embodiments of the present application. In a possible implementation, the chip 1700 can further include a memory 1720. The processor 1710 can call and run a computer program from the memory 1720 to implement the methods performed by the first core network device, or the target node, or the second core network device, or the first terminal in the embodiments of the present application. The memory 1720 can be a separate device independent of the processor 1710, or can be integrated in the processor 1710. In a possible implementation, the chip 1700 can further include an input interface 1730. The processor 1710 can control the input interface 1730 to communicate with other devices or chips, and specifically, can acquire information or data sent by other devices or chips. In a possible implementation, the chip 1700 can further include an output interface 1740. The processor 1710 can control the output interface 1740 to communicate with other devices or chips, and specifically, can output information or data to other devices or chips.

[0305] In a possible implementation, the chip can be applied to the first core network device, or the target node, or the second core network device, or the first terminal in the embodiments of the present application, and the chip can implement the corresponding procedures implemented by the first core network device, or the target node, or the second core network device, or the first terminal in various methods of the embodiments of the present application. For brevity, details are not repeated here. It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-on-chip, a system chip, a chip system or a system-on-chip, etc. The processor mentioned above can be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC) or other programmable logic devices, transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor mentioned above can be a microprocessor or any conventional processor, etc. The memory mentioned above can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM). It should be understood that the above memory is exemplary but not a limiting description, for example, the memory in the embodiments of the present application can also be a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synch link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.

[0306] FIG. 18 is a schematic block diagram of a communication system 1800 according to embodiments of the present application. The communication system 1800 includes a first core network device 1810, a target node 1820, a second core network device 1830, and a first terminal 1840. The first core network device 1810 can be configured to implement the corresponding function of the first core network device in the above-described methods. The target node 1820 can be configured to implement the corresponding function of the target node in the above-described methods. The second core network device 1830 can be configured to implement the corresponding function of the second core network device in the above-described methods. The first terminal 1840 can be configured to implement the corresponding function of the first terminal in the above-described methods. For brevity, details are not repeatedly described herein.

[0307] In the above-described embodiments, the whole or part of the embodiments can be realized by software, hardware, firmware, or any combination thereof. When realized by software, the whole or part of the embodiments can be realized in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed by a computer, the computer program instructions generate the processes or functions according to the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media sets. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, solid state disk (SSD)), etc.

[0308] It should be understood that the magnitude of the serial number of each process described above does not mean the order of execution, the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A configuration method, comprising: receiving, by a first core network device, a first request, wherein the first request is used to request to perform a first computing task; sending, by the first core network device, one or more first configuration information to one or more first nodes, wherein the one or more first configuration information is used for the one or more first nodes to cooperatively perform the first computing task, and different first configuration information in the one or more first configuration information corresponds to different first nodes.

2. The method of claim 1, wherein, The first request carries at least one of the following: a parameter of a service to which the first computing task belongs, a region parameter corresponding to the first computing task, a total end-to-end task time length requirement for performing the first computing task, a computing capability required for performing the first computing task, and an identifier of the first computing task.

3. The method of claim 2, wherein, Each first configuration information in the one or more first configuration information comprises at least one of the following: a computing capability used by the each first node for participating in performing the first computing task, and an execution strategy of the each first node for participating in performing the first computing task.

4. The method of claim 3, wherein, The computing capability used by the each first node for participating in performing the first computing task is determined based on at least one of the following: the computing capability required for performing the first computing task, and the computing capability that can be provided by the each first node.

5. The method of claim 3 or 4, wherein, The execution strategy of the each first node for participating in performing the first computing task comprises at least one of the following: the identifier of the first computing task, a previous-hop first node of the each first node, a next-hop first node of the each first node, and related information of a model used by the each first node for participating in performing the first computing task.

6. The method of claim 5, wherein, The related information of the model comprises at least one of the following: an identifier of the model, a type of the model, related information of input data of the model, and related information of output data of the model.

7. The method of claim 5 or 6, wherein, A first total end-to-end task time length of the one or more first nodes for cooperatively performing the first computing task meets a total end-to-end task time length requirement for performing the first computing task.

8. The method of claim 7, wherein, The first total end-to-end task time length is obtained based on a computing time length of the each first node and / or a transmission time length of the one or more first nodes for cooperatively performing the first computing task.

9. The method of claim 8, wherein, The computing time length of the each first node is obtained based on the computing capability that can be provided by the each first node and a computing amount of the model used by the each first node for participating in performing the first computing task.

10. The method of claim 8 or 9, wherein, The transmission time length of the one or more first nodes for cooperatively performing the first computing task is related to a topology relationship of the one or more first nodes, wherein the topology relationship of the one or more first nodes is used to indicate the previous-hop first node of the each first node and / or the next-hop first node of the each first node.

11. The method of any one of claims 2-10, wherein, The method further comprises at least one of the following: finding, by the first core network device, a computing capability that can be provided by each second node in one or more second nodes located in a first region, wherein the first region is determined based on a region parameter corresponding to the first computing task; The first core network device finds one or more third nodes having a model capable of supporting a first service, wherein the first service is determined based on a parameter of a service to which the first computing task belongs.

12. The method of claim 11, wherein, The method further includes: The first core network device determines the one or more first nodes satisfying a first condition based on the computing capability capable of being provided by each second node and / or the one or more third nodes, wherein the first condition includes at least one of the following: located in the first area, having a model capable of supporting the first service, and having a computing capability capable of being provided satisfying a computing capability required for performing the first computing task.

13. The method of any one of claims 1-12, wherein, The one or more first nodes include at least one of the following: one or more terminals, one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

14. A configuration method, comprising: A target node receives first configuration information corresponding to the target node from a first core network device, wherein the first configuration information corresponding to the target node is used for the target node to cooperatively perform a first computing task with one or more other first nodes.

15. The method of claim 14, wherein, The first configuration information corresponding to the target node includes at least one of the following: a computing capability used by the target node for participating in performing the first computing task, and an execution strategy of the target node for participating in performing the first computing task.

16. The method of claim 15, wherein, The execution strategy of the target node for participating in performing the first computing task includes at least one of the following: an identifier of the first computing task, a next-hop other first node of the target node, a next-hop other first node of the target node, and related information of a model used by the target node for participating in performing the first computing task.

17. The method of claim 16, wherein, The related information of the model includes at least one of the following: an identifier of the model, a type of the model, related information of input data of the model, and related information of output data of the model.

18. The method of claim 16 or 17, wherein, After the target node receives the first configuration information corresponding to the target node from the first core network device, the method further includes: The target node acquires a first data packet. The target node processes the first data packet based on the first configuration information to obtain a second data packet.

19. The method of claim 18, wherein, The target node acquires a first data packet, including: The target node determines a next-hop other first node of the target node based on the first configuration information, and receives the first data packet from the next-hop other first node, wherein the first data packet carries an identifier of the first computing task.

20. The method of claim 18 or 19, wherein, After the second data packet is obtained, the method further includes: The target node determines a next-hop other first node of the target node based on the first configuration information, and sends the second data packet to the next-hop other first node, wherein the second data packet carries the identifier of the first computing task.

21. The method of any one of claims 14-20, wherein, The target node is one of the following: a target terminal, a target access network device, a target network function (NF), and a target application function (AF).

22. A configuration method, comprising: The first core network device sends second configuration information to the second core network device, where the second configuration information carries routing information of each of one or more second services, and the routing information of each of the second services includes routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the second services.

23. The method of claim 22, wherein, The second configuration information further carries a first identifier of the each of the second services associated with the routing information of the each of the second services.

24. The method of claim 22 or 23, further comprising: The first core network device sends third configuration information to the first terminal, where the third configuration information carries a first identifier of each of at least part of the one or more second services and a second identifier associated with the each of the at least part of the one or more second services.

25. The method of any one of claims 22-24, wherein, The one or more fourth nodes include at least one of the following: one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

26. A configuration method, comprising: The second core network device receives second configuration information from the first core network device, where the second configuration information carries routing information of each of one or more second services, and the routing information of each of the second services includes routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the second services.

27. The method of claim 26, wherein, The second configuration information further carries a first identifier of the each of the second services associated with the routing information of the each of the second services.

28. The method of claim 27, wherein, After the second core network device receives the second configuration information from the first core network device, the method further comprises: The second core network device receives a third packet from the first terminal, where the third packet carries a first identifier of a target service, and the target service is one of the one or more second services. The second core network device determines routing information of the target service based on the first identifier of the target service and the second configuration information. The second core network device determines routing order of one or more fourth nodes that cooperatively perform a computing task of the third packet under the target service based on the routing information of the target service.

29. The method of any one of claims 26-28, wherein, The one or more fourth nodes include at least one of the following: one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

30. A configuration method, comprising: The first terminal receives third configuration information from the first core network device, where the third configuration information carries a first identifier of each of at least part of one or more second services and a second identifier associated with the each of the at least part of the one or more second services.

31. The method of claim 30, wherein, After the first terminal receives the third configuration information from the first core network device, the method further comprises: The first terminal sends a third packet to the second core network device, where the third packet carries a first identifier of a target service, and the first identifier of the target service is determined based on a second identifier of the target service, and the target service is one of the at least part of the second services.

32. A first core network device, comprising: The first communication unit is configured to receive a first request, wherein the first request is used to request to perform a first computing task; and send one or more first configuration information to one or more first nodes, wherein the one or more first configuration information is used for the one or more first nodes to cooperatively perform the first computing task, and different first configuration information in the one or more first configuration information corresponds to different first nodes.

33. The first core network device of claim 32, wherein, The first request carries at least one of the following: a parameter of a service to which the first computing task belongs, a region parameter corresponding to the first computing task, a total end-to-end task time length requirement for performing the first computing task, a computing capability required for performing the first computing task, and an identifier of the first computing task.

34. The first core network device of claim 33, wherein, Each first configuration information in the one or more first configuration information includes at least one of the following: a computing capability used by the each first node for participating in performing the first computing task, and an execution strategy of the each first node for participating in performing the first computing task.

35. The first core network device of claim 34, wherein, The computing capability used by the each first node for participating in performing the first computing task is determined based on at least one of the following: the computing capability required for performing the first computing task, and the computing capability that can be provided by the each first node.

36. The first core network device of claim 34 or 35, wherein, The execution strategy of the each first node for participating in performing the first computing task includes at least one of the following: the identifier of the first computing task, a previous-hop first node of the each first node, a next-hop first node of the each first node, and related information of a model used by the each first node for participating in performing the first computing task.

37. The first core network device of claim 36, wherein, The related information of the model includes at least one of the following: an identifier of the model, a type of the model, related information of input data of the model, and related information of output data of the model.

38. The first core network device of claim 36 or 37, wherein, A first total end-to-end task time length of the one or more first nodes for cooperatively performing the first computing task meets a total end-to-end task time length requirement for performing the first computing task.

39. The first core network device of claim 38, wherein, The first total end-to-end task time length is obtained based on a computing time length of the each first node and / or a transmission time length of the one or more first nodes for cooperatively performing the first computing task.

40. The first core network device of claim 39, wherein, The computing time length of the each first node is obtained based on the computing capability that can be provided by the each first node and a computing amount of the model used by the each first node for participating in performing the first computing task.

41. The first core network device of claim 39 or 40, wherein, The transmission time length of the one or more first nodes for cooperatively performing the first computing task is related to a topological relationship of the one or more first nodes, wherein the topological relationship of the one or more first nodes is used to indicate the previous-hop first node of the each first node and / or the next-hop first node of the each first node.

42. The first core network device of any of claims 33-41, further comprising: The first processing unit is configured to perform at least one of the following: find a computing capability that can be provided by each second node in one or more second nodes located in a first region, wherein the first region is determined based on a region parameter corresponding to the first computing task; and find one or more third nodes that have a model supporting a first service, wherein the first service is determined based on a parameter of a service to which the first computing task belongs.

43. The first core network device of claim 42, wherein, The first processing unit is configured to determine the one or more first nodes satisfying a first condition based on the computing capability that each second node is capable of providing and / or the one or more third nodes, where the first condition comprises at least one of the following: being located in the first region, having a model supporting the first service, and being capable of providing computing capability satisfying a computing capability required for performing the first computing task.

44. The first core network device of any of claims 32-43, wherein, The one or more first nodes comprise at least one of the following: one or more terminals, one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

45. A target node, comprising: a second communication unit configured to receive first configuration information corresponding to the target node from a first core network device, where the first configuration information corresponding to the target node is used for the target node to cooperatively perform a first computing task with one or more other first nodes.

46. The target node of claim 45, wherein, The first configuration information corresponding to the target node comprises at least one of the following: computing capability used by the target node for performing the first computing task, and an execution strategy of the target node for performing the first computing task.

47. The target node of claim 46, wherein, The execution strategy of the target node for performing the first computing task comprises at least one of the following: an identifier of the first computing task, a previous-hop other first node of the target node, a next-hop other first node of the target node, and related information of a model used by the target node for performing the first computing task.

48. The target node of claim 47, wherein, The related information of the model comprises at least one of the following: an identifier of the model, a type of the model, related information of input data of the model, and related information of output data of the model.

49. The target node of claim 47 or 48, wherein, The target node further comprises: a second processing unit configured to process a first data packet based on the first configuration information to obtain a second data packet; the second communication unit is configured to obtain the first data packet.

50. The target node of claim 49, wherein, The second processing unit is configured to determine, based on the first configuration information, a previous-hop other first node of the target node. The second communication unit is configured to receive, from the previous-hop other first node, the first data packet, where the first data packet carries an identifier of the first computing task. The second processing unit is configured to determine, based on the first configuration information, a next-hop other first node of the target node.

51. The target node of claim 49 or 50, wherein, The second communication unit is configured to send, to the next-hop other first node, the second data packet, where the second data packet carries the identifier of the first computing task. The target node is one of the following: a target terminal, a target access network device, a target network function (NF), and a target application function (AF).

52. The target node of any of claims 45-51, wherein, 53. A first core network device, comprising: a first communication unit configured to send second configuration information to a second core network device, where the second configuration information carries routing information of each second service in one or more second services, and the routing information of each second service comprises a routing order of one or more fourth nodes cooperatively performing a computing task under the each second service. ​ 54. The first core network device of claim 53, wherein, The second configuration information further carries a first identifier of each of the second services associated with the routing information of the each of the second services. 55.The first core network device of claim 53 or 54, wherein the first communication unit is configured to send third configuration information to the first terminal, and wherein The third configuration information carries a first identifier of each of at least part of the one or more second services and a second identifier associated therewith.

56. The first core network device of any of claims 53-55, wherein, The one or more fourth nodes comprise at least one of one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

57. A second core network device, comprising: a third communication unit, configured to receive second configuration information from a first core network device, wherein the second configuration information carries routing information of each of one or more second services, the routing information of each of the second services comprising a routing order of one or more fourth nodes that cooperatively perform a computing task under the each of the second services.

58. The second core network device of claim 57, wherein, The second configuration information further carries a first identifier of each of the second services associated with the routing information of the each of the second services.

59. The second core network device of claim 58, wherein, The second core network device further comprises: a third processing unit, configured to determine, based on the first identifier of a target service and the second configuration information, routing information of the target service, and determine, based on the routing information of the target service, a routing order of one or more fourth nodes that cooperatively perform a computing task under a third data packet of the target service; the third communication unit is configured to receive the third data packet from a first terminal, wherein the third data packet carries the first identifier of the target service, and the target service is one of the one or more second services.

60. The second core network device of any of claims 57-59, wherein, The one or more fourth nodes comprise at least one of one or more access network devices, one or more network functions (NFs), and one or more application functions (AFs).

61. A first terminal, comprising: a fourth communication unit, configured to receive third configuration information from a first core network device, wherein the third configuration information carries a first identifier of each of at least part of one or more second services and a second identifier associated therewith.

62. The first terminal of claim 61, wherein, The fourth communication unit is configured to send a third data packet to a second core network device, wherein the third data packet carries a first identifier of a target service, the first identifier of the target service is determined based on a second identifier of the target service, and the target service is one of the at least part of the second services.

63. A first core network device, comprising: a transceiver, a processor, and a memory, the memory being configured to store a computer program, the transceiver being configured to communicate with other devices, and the processor being configured to invoke and run the computer program stored in the memory, so that the first core network device performs the method according to any one of claims 1 to 13, or 22 to 25.

64. A target node, comprising: a transceiver, a processor, and a memory, the memory being configured to store a computer program, the transceiver being configured to communicate with other devices, and the processor being configured to invoke and run the computer program stored in the memory, so that the target node performs the method according to any one of claims 14 to 21.

65. A second core network device, comprising: a transceiver for communicating with other devices, a processor for invoking and running a computer program stored in a memory to cause the second core network device to perform the method of any one of claims 26-29.

66. A first terminal comprising: a transceiver for communicating with other devices, a processor for invoking and running a computer program stored in a memory to cause the first terminal to perform the method of any one of claims 30-31.

67. A chip comprising: a processor for invoking and running a computer program from a memory to cause a device in which the chip is installed to perform the method of any one of claims 1-13, or claims 14-21, or claims 22-25, or claims 26-29, or claims 30-31.

68. A computer-readable storage medium for storing a computer program which, when run by a device, causes the device to perform the method of any one of claims 1-13, or claims 14-21, or claims 22-25, or claims 26-29, or claims 30-31.

69. A computer program product comprising computer program instructions which cause a computer to perform the method of any one of claims 1-13, or claims 14-21, or claims 22-25, or claims 26-29, or claims 30-31.

70. A computer program which causes a computer to perform the method of any one of claims 1-13, or claims 14-21, or claims 22-25, or claims 26-29, or claims 30-31.

Images