Computing power negotiation method and device, target computing power node, network function and medium

Abstract

The invention relates to a computing power negotiation method and device, a target computing power node, a network function and a medium. The method comprises the following steps: a target computing power node receives a computing power resource request sent by a first NF; if the target computing power node does not meet the computing power requirement corresponding to the computing power resource request, the target computing power node obtains computing power information of an adjacent computing power node; and the target computing power node sends a computing power resource response to the first NF according to the computing power information of the adjacent computing power node. According to the invention, the computing power service can be provided to the outside more reliably.

Description

Technical Field

[0001] This application relates to the field of mobile communication technology, and in particular to a computing power negotiation method, apparatus, target computing power node, network function, and medium. Background Technology

[0002] Currently, research on 6G (6th Generation Mobile Networks) is actively underway, and there are many speculations about the 6G network architecture. For example, in addition to communication capabilities, 6G networks may add new capabilities such as sensing, intelligence, computing, and security, and the concept of computing-network convergence has been proposed.

[0003] There is currently no research or methodology on how mobile communication networks can reliably provide computing power services to the outside world in the face of massive computing demands. Summary of the Invention

[0004] This application provides a computing power negotiation method, apparatus, target computing power node, network function, and medium, which can provide computing power services to the outside world more reliably.

[0005] In a first aspect, embodiments of this application provide a computing power negotiation method. The computing power negotiation method is used for a target computing power node, and the method includes:

[0006] Receive the computing resource request sent by the first NF;

[0007] If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, then obtain the computing power information of the neighboring computing power nodes;

[0008] Based on the computing power information of the neighboring computing power nodes, a computing power resource response is sent to the first NF.

[0009] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0010] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0011] In one embodiment, the computing power information includes a computing power node identifier and computing power attribute information, wherein the computing power attribute information includes at least one of the following:

[0012] Computing node types;

[0013] The service location range of computing power nodes;

[0014] Computing node service time;

[0015] Supported business types;

[0016] Business identifiers that support the business;

[0017] Supported application types;

[0018] Supported application identifiers;

[0019] Support capability information;

[0020] Calculate force and force information;

[0021] Description of computing power usage.

[0022] In one embodiment, the computing resource request includes computing service type requirements and / or computing resource requirements.

[0023] In one embodiment, obtaining the computing power information of neighboring computing power nodes includes:

[0024] The system receives a first computing power notification sent by the neighboring computing power node, the first computing power notification carrying the computing power information of the neighboring computing power node.

[0025] In one embodiment, obtaining the computing power information of neighboring computing power nodes includes:

[0026] Send a first computing power information request to the neighboring computing power nodes;

[0027] Receive the computing power information of the neighboring computing power nodes sent in response to the first computing power information request.

[0028] In one embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement.

[0029] If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

[0030] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the method further includes:

[0031] If a response rejection message is received from the neighboring computing power node, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0032] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the method further includes:

[0033] If no computing power information is received from the neighboring computing power node within a preset time period, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0034] In one embodiment, obtaining the computing power information of neighboring computing power nodes includes:

[0035] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0036] In one embodiment, obtaining the computing power information of neighboring computing power nodes includes:

[0037] The target computing node reads the computing power information of the neighboring computing power node from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power node.

[0038] In one embodiment, obtaining the computing power information of neighboring computing power nodes includes:

[0039] Receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

[0040] In one embodiment, the method further includes:

[0041] A first computing power discovery request is sent to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0042] In one embodiment, the method further includes:

[0043] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0044] The task decomposition information corresponding to the multiple computing subtasks is sent to the neighboring computing nodes.

[0045] In one embodiment, the method further includes:

[0046] The system receives task decomposition information corresponding to multiple computing subtasks sent by the master computing power node. These multiple computing subtasks are obtained by the master computing power node decomposing the computing power task corresponding to the computing power resource request; or...

[0047] The system receives task decomposition information corresponding to multiple computing power subtasks sent by the first NF, wherein the multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

[0048] In one embodiment, the task breakdown information includes at least one of the following:

[0049] The computing power task identifier of the computing power task;

[0050] The computing power requirements of the computing power task;

[0051] The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

[0052] In one embodiment, the method further includes:

[0053] The system receives a subtask acceptance response from the neighboring computing power node in response to the task decomposition information. The subtask acceptance response carries the computing power information of the neighboring computing power node.

[0054] In one embodiment, the method further includes:

[0055] Send computing task decomposition negotiation confirmation information to the neighboring computing power nodes.

[0056] In one embodiment, the method further includes:

[0057] Receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

[0058] Secondly, embodiments of this application provide a computing power negotiation method. The computing power negotiation method is used in a first NF, and the method includes:

[0059] Send a computing resource request to the target computing node;

[0060] The target computing power node receives a computing power resource response sent in response to the computing power resource request. The computing power resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing power resource request.

[0061] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0062] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0063] In one embodiment, the method further includes:

[0064] Obtain the computing power information of the neighboring computing power nodes and send the computing power information of the neighboring computing power nodes to the target computing power node.

[0065] In one embodiment, before obtaining the computing power information of the neighboring computing power nodes, the method further includes:

[0066] The system receives a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0067] In one embodiment, obtaining the computing power information of the neighboring computing power nodes includes:

[0068] The system receives a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

[0069] In one embodiment, obtaining the computing power information of the neighboring computing power nodes includes:

[0070] Send a second computing power information request to the neighboring computing power nodes;

[0071] Receive the computing power information of the neighboring computing power node sent in response to the second computing power information request.

[0072] In one embodiment, obtaining the computing power information of the neighboring computing power nodes includes:

[0073] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0074] In one embodiment, obtaining the computing power information of the neighboring computing power nodes includes:

[0075] The computing power information of the neighboring computing power nodes is read from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF historically monitoring the neighboring computing power node.

[0076] In one embodiment, the method further includes:

[0077] Generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

[0078] In one embodiment, the method further includes:

[0079] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0080] The task decomposition information corresponding to the multiple computing power subtasks is sent to the neighboring computing power nodes and the target computing power node.

[0081] In one embodiment, the method further includes:

[0082] The computing resource response is sent to the second NF, and the computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

[0083] Thirdly, embodiments of this application provide a computing power negotiation method. The computing power negotiation method is used in a third NF, and the method includes:

[0084] The target computing node receives a computing resource response from the second NF. The computing resource response is sent to the first NF by the target computing node based on the computing power information of the neighboring computing nodes, and then forwarded to the second NF by the first NF. The computing power information of the neighboring computing nodes is obtained by the target computing node when it does not meet the computing power requirements corresponding to the computing resource request.

[0085] Based on the computing power resource response, a service session is established to reach the target computing power node via the neighboring computing power nodes.

[0086] Fourthly, embodiments of this application provide a computing power negotiation device. The computing power negotiation device is used for a target computing power node, and the device includes:

[0087] The receiving module is used to receive the computing resource request sent by the first NF;

[0088] The acquisition module is used to acquire computing power information of neighboring computing power nodes if the target computing power node does not meet the computing power requirements corresponding to the computing power resource request.

[0089] The response module is used to send a computing resource response to the first NF based on the computing power information of the neighboring computing power nodes.

[0090] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0091] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0092] In one embodiment, the computing power information includes a computing power node identifier and computing power attribute information, wherein the computing power attribute information includes at least one of the following:

[0093] Computing node types;

[0094] The service location range of computing power nodes;

[0095] Computing node service time;

[0096] Supported business types;

[0097] Business identifiers that support the business;

[0098] Supported application types;

[0099] Supported application identifiers;

[0100] Support capability information;

[0101] Calculate force and force information;

[0102] Description of computing power usage.

[0103] In one embodiment, the computing resource request includes computing service type requirements and / or computing resource requirements.

[0104] In one embodiment, the acquisition module is specifically used to receive a first computing power announcement sent by the neighboring computing power node, the first computing power announcement carrying the computing power information of the neighboring computing power node.

[0105] In one embodiment, the acquisition module is specifically used to send a first computing power information request to the neighboring computing power node; and to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the first computing power information request.

[0106] In one embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement.

[0107] If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

[0108] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the acquisition module is further configured to determine that the neighboring computing power node does not support shared computing power and acquire the computing power information of other neighboring computing power nodes if it receives a response rejection message sent by the neighboring computing power node.

[0109] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the acquisition module is further configured to determine that the neighboring computing power node does not support shared computing power if it does not receive the computing power information sent by the neighboring computing power node within a preset time period, and to acquire the computing power information of other neighboring computing power nodes.

[0110] In one embodiment, the acquisition module is specifically used to monitor the computing power information of the neighboring computing power nodes in real time or periodically.

[0111] In one embodiment, the acquisition module is specifically used to read the computing power information of the neighboring computing power nodes from a first storage location. The first storage location stores a mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power nodes.

[0112] In one embodiment, the acquisition module is specifically used to receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

[0113] In one embodiment, the acquisition module is further configured to send a first computing power discovery request to the master computing power node or the first NF, wherein the first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0114] In one embodiment, the device further includes:

[0115] The task decomposition module is used to decompose the computing power task corresponding to the computing power resource request into multiple computing power sub-tasks.

[0116] The sending module is used to send the task decomposition information corresponding to the multiple computing power subtasks to the neighboring computing power nodes.

[0117] In one embodiment, the receiving module is further configured to receive task decomposition information corresponding to multiple computing power sub-tasks sent by the master control computing power node, wherein the multiple computing power sub-tasks are obtained by the master control computing power node decomposing the computing power task corresponding to the computing power resource request; or...

[0118] The receiving module is further configured to receive task decomposition information corresponding to multiple computing power subtasks sent by the first NF, wherein the multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

[0119] In one embodiment, the task breakdown information includes at least one of the following:

[0120] The computing power task identifier of the computing power task;

[0121] The computing power requirements of the computing power task;

[0122] The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

[0123] In one embodiment, the receiving module is further configured to receive a subtask acceptance response returned by the neighboring computing power node in response to the task decomposition information, the subtask acceptance response carrying the computing power information of the neighboring computing power node.

[0124] In one embodiment, the sending module is further configured to send computing power task decomposition negotiation confirmation information to the neighboring computing power nodes.

[0125] In one embodiment, the receiving module is further configured to receive a subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

[0126] Fifthly, embodiments of this application provide a computing power negotiation device. The computing power negotiation device is used in a first NF, and the device includes:

[0127] The sending module is used to send computing resource requests to the target computing power node;

[0128] The receiving module is configured to receive a computing resource response sent by the target computing power node in response to the computing resource request. The computing resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing resource request.

[0129] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0130] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0131] In one embodiment, the device further includes:

[0132] The acquisition module is used to acquire the computing power information of the neighboring computing power nodes;

[0133] The sending module is also used to send the computing power information of the neighboring computing power nodes to the target computing power node.

[0134] In one embodiment, before obtaining the computing power information of the neighboring computing power nodes, the receiving module is further configured to receive a second computing power discovery request sent by the target computing power node, the second computing power discovery request being used to request the computing power information of the neighboring computing power nodes.

[0135] In one embodiment, the acquisition module is specifically used to receive a second computing power announcement sent by the neighboring computing power node, the second computing power announcement carrying the computing power information of the neighboring computing power node.

[0136] In one embodiment, the acquisition module is specifically used to send a second computing power information request to the neighboring computing power node; and to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the second computing power information request.

[0137] In one embodiment, the acquisition module is specifically used to monitor the computing power information of the neighboring computing power nodes in real time or periodically.

[0138] In one embodiment, the acquisition module is specifically used to read the computing power information of the neighboring computing power nodes from a second storage location. The second storage location stores a mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF historically monitoring the neighboring computing power node.

[0139] In one embodiment, the device further includes:

[0140] A generation module is used to generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

[0141] In one embodiment, the device further includes:

[0142] The task decomposition module is used to decompose the computing power task corresponding to the computing power resource request into multiple computing power sub-tasks.

[0143] The sending module is also used to send the task decomposition information corresponding to the multiple computing power subtasks to the neighboring computing power nodes and the target computing power node.

[0144] In one embodiment, the sending module is further configured to send the computing resource response to the second NF, the computing resource response being used by the second NF to send the computing resource response to the third NF, the computing resource response being used by the third NF to establish a service session that reaches the target computing node via the neighboring computing nodes.

[0145] Sixthly, embodiments of this application provide a computing power negotiation device. The computing power negotiation device is used in a third NF, and the device includes:

[0146] The receiving module is used to receive the computing power resource response sent by the second NF. The computing power resource response is sent by the target computing power node to the first NF according to the computing power information of the neighboring computing power nodes, and then forwarded by the first NF to the second NF. The computing power information of the neighboring computing power nodes is obtained by the target computing power node when the computing power requirement corresponding to the computing power resource request is not met.

[0147] The session establishment module is used to establish a service session that reaches the target computing power node through the neighboring computing power nodes based on the computing power resource response.

[0148] Seventhly, embodiments of this application provide a target computing power node. The target computing power node includes a memory, a transceiver, and a processor.

[0149] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0150] Control the transceiver to receive the computing resource request sent by the first NF;

[0151] If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, then obtain the computing power information of the neighboring computing power nodes;

[0152] Based on the computing power information of the neighboring computing power nodes, the transceiver is controlled to send a computing power resource response to the first NF.

[0153] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0154] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0155] In one embodiment, the computing power information includes a computing power node identifier and computing power attribute information, wherein the computing power attribute information includes at least one of the following:

[0156] Computing node types;

[0157] The service location range of computing power nodes;

[0158] Computing node service time;

[0159] Supported business types;

[0160] Business identifiers that support the business;

[0161] Supported application types;

[0162] Supported application identifiers;

[0163] Support capability information;

[0164] Calculate force and force information;

[0165] Description of computing power usage.

[0166] In one embodiment, the computing resource request includes computing service type requirements and / or computing resource requirements.

[0167] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0168] The transceiver is controlled to receive a first computing power notification sent by the neighboring computing power node, the first computing power notification carrying the computing power information of the neighboring computing power node.

[0169] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0170] Control the transceiver to send a first computing power information request to the nearby computing power node;

[0171] The transceiver is controlled to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the first computing power information request.

[0172] In one embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement.

[0173] If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

[0174] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the processor is configured to read the computer program in the memory and further perform the following operations:

[0175] If a response rejection message is received from the neighboring computing power node, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0176] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the processor is configured to read the computer program in the memory and further perform the following operations:

[0177] If no computing power information is received from the neighboring computing power node within a preset time period, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0178] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0179] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0180] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0181] The target computing node reads the computing power information of the neighboring computing power node from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power node.

[0182] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0183] The transceiver is controlled to receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

[0184] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0185] The transceiver is controlled to send a first computing power discovery request to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0186] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0187] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0188] The transceiver is controlled to send the task decomposition information corresponding to the multiple computing subtasks to the neighboring computing nodes.

[0189] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0190] The transceiver is controlled to receive task decomposition information corresponding to multiple computing subtasks sent by the master computing power node. These multiple computing subtasks are obtained by the master computing power node decomposing the computing power task corresponding to the computing power resource request; or...

[0191] The transceiver is controlled to receive task decomposition information corresponding to multiple computing power subtasks sent by the first NF. The multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

[0192] In one embodiment, the task breakdown information includes at least one of the following:

[0193] The computing power task identifier of the computing power task;

[0194] The computing power requirements of the computing power task;

[0195] The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

[0196] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0197] The transceiver is controlled to receive the subtask acceptance response returned by the neighboring computing power node in response to the task decomposition information. The subtask acceptance response carries the computing power information of the neighboring computing power node.

[0198] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0199] The transceiver is controlled to send computing task decomposition negotiation confirmation information to the neighboring computing power nodes.

[0200] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0201] The transceiver is controlled to receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

[0202] Eighthly, embodiments of this application provide a network function. The network function includes a memory, a transceiver, and a processor.

[0203] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0204] Control the transceiver to send a computing resource request to the target computing node;

[0205] The transceiver is controlled to receive the computing resource response sent by the target computing power node in response to the computing resource request. The computing resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing resource request.

[0206] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0207] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0208] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0209] The system acquires the computing power information of the neighboring computing power nodes and controls the transceiver to send the computing power information of the neighboring computing power nodes to the target computing power node.

[0210] In one embodiment, before acquiring the computing power information of the neighboring computing power nodes, the processor is configured to read the computer program in the memory and further perform the following operations:

[0211] The transceiver is controlled to receive a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0212] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0213] The transceiver is controlled to receive a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

[0214] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0215] Control the transceiver to send a second computing power information request to the nearby computing power node;

[0216] The transceiver is controlled to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the second computing power information request.

[0217] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0218] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0219] In one embodiment, the processor is configured to read a computer program from the memory and specifically perform the following operations:

[0220] The computing power information of the neighboring computing power nodes is read from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the network function historically monitoring the neighboring computing power node.

[0221] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0222] Generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

[0223] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0224] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0225] The transceiver is controlled to send the task decomposition information corresponding to the multiple computing subtasks to the neighboring computing nodes and the target computing node.

[0226] In one embodiment, the processor is configured to read a computer program from the memory and also perform the following operations:

[0227] The transceiver is controlled to send the computing resource response to the second NF. The computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

[0228] Ninthly, embodiments of this application provide a network function. The network function includes a memory, a transceiver, and a processor.

[0229] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0230] The transceiver is controlled to receive the computing power resource response sent by the second NF. The computing power resource response is sent by the target computing power node to the first NF according to the computing power information of the neighboring computing power nodes, and then forwarded by the first NF to the second NF. The computing power information of the neighboring computing power nodes is obtained by the target computing power node when the computing power requirement corresponding to the computing power resource request is not met.

[0231] Based on the computing power resource response, a service session is established to reach the target computing power node via the neighboring computing power nodes.

[0232] In a tenth aspect, embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the methods described in the first, second, or third aspects above.

[0233] Eleventhly, embodiments of this application also provide a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps described in the first, second, or third aspects above.

[0234] In a twelfth aspect, embodiments of this application provide a chip. The chip includes programmable logic circuitry and / or program instructions, which, when executed, implement the steps described in the first, second, or third aspect above.

[0235] The aforementioned computing power negotiation method, apparatus, target computing power node, network function, and medium allow the target computing power node to receive a computing power resource request sent by a first NF. If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, it obtains the computing power information of neighboring computing power nodes. Based on the computing power information of neighboring computing power nodes, the target computing power node sends a computing power resource response to the first NF. In this way, even when the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, it can coordinate with the computing resources of neighboring computing power nodes to respond to the computing power resource request, thereby improving the reliability of the response to the computing power resource request and enabling more reliable provision of computing power services. Attached Figure Description

[0236] Figure 1 This application provides a schematic diagram of a mobile communication network architecture as an embodiment of the present application.

[0237] Figure 2 A flowchart illustrating a computing power negotiation method provided in an embodiment of this application;

[0238] Figure 3 This is a schematic diagram illustrating a process for a target computing node to obtain computing power information of neighboring computing power nodes, provided in an embodiment of this application.

[0239] Figure 4 A schematic diagram illustrating another process for a target computing node to obtain computing power information of neighboring computing power nodes, provided in an embodiment of this application;

[0240] Figure 5 A schematic diagram illustrating another process for a target computing node to obtain computing power information of neighboring computing power nodes, provided in an embodiment of this application;

[0241] Figure 6 A schematic diagram illustrating another process for a target computing node to obtain computing power information of neighboring computing power nodes, provided in an embodiment of this application;

[0242] Figure 7 A flowchart illustrating the task decomposition of a target computing power node provided in an embodiment of this application;

[0243] Figure 8 A flowchart illustrating a computing power task negotiation process provided for an embodiment of this application;

[0244] Figure 9 A flowchart illustrating another computing power negotiation method provided in an embodiment of this application;

[0245] Figure 10 A flowchart illustrating another computing power negotiation method provided in an embodiment of this application;

[0246] Figure 11 A flowchart illustrating another computing power negotiation method provided in an embodiment of this application;

[0247] Figure 12 A structural block diagram of a computing power negotiation device provided in an embodiment of this application;

[0248] Figure 13 A structural block diagram of another computing power negotiation device provided in the embodiments of this application;

[0249] Figure 14 A structural block diagram of another computing power negotiation device provided in the embodiments of this application;

[0250] Figure 15 This is a schematic diagram of the structure of the target computing node provided in the embodiments of this application;

[0251] Figure 16 A schematic diagram of the network function provided in the embodiments of this application;

[0252] Figure 17 This is a schematic diagram of the chip structure provided in an embodiment of this application. Detailed Implementation

[0253] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0254] Currently, research on 6G is actively underway, and there are many speculations about the 6G network architecture. For example, in addition to communication capabilities, 6G networks may add new capabilities such as sensing, intelligence, computing, and security. The concept of computing-network convergence has also been proposed, and in the future, 6G will support the opening of integrated computing-network capabilities to form a mobile computing network.

[0255] Mobile computing networks are open computing network infrastructures based on mobile network capabilities and infrastructure, and jointly composed of mobile network architecture and computing resources. Their purpose is to achieve synergy between mobile networks and computing power to achieve the optimal experience of accessing computing power within mobile networks. They represent the concrete manifestation of computing networks in mobile access scenarios. Mobile computing networks are applications of computing networks in mobile network scenarios, and include the following characteristics:

[0256] Firstly, in terms of business operations, mobile computing networks, based on mobile networks, meet business experience and user demands, achieving optimal interconnection between users, computing power, and applications. They provide optimal access paths and experiences for user-to-user and user-to-application interactions, and possess characteristics such as ubiquitous mobile access, end-to-end network collaboration, controllable experience, and high stability for telecommunications. Current mobile networks support user mobility and, based on mobility management and session management capabilities, provide efficient scheduling and QoS (Quality of Service) guarantees for services in mobile mode. Therefore, mobile computing networks, by further incorporating computing power factors, can provide high-quality computing-network collaborative mobile connectivity capabilities.

[0257] Secondly, in terms of architecture, the mobile computing network is based on the mobile network infrastructure. Building upon the core capabilities of the mobile network, it introduces two key architectural innovations: network-integrated computing power and unified scheduling of network and computing power. This encompasses computing resources such as edge computing power and end-to-end computing power. Centered on services, it leverages computing power scheduling to enhance the user experience of mobile network services and then gradually expands to wider areas. Therefore, the mobile computing network can achieve network-assisted computing and network-driven computing, optimizing the end-to-end computing network experience and improving the utilization rate of mobile computing network resources.

[0258] Among them, "computing power" is a new attribute added from mobile network to mobile computing power network. Since the mobile network itself can close the loop of all mobile services, the combination of mobile network and computing power will bring powerful advantages in terms of orchestration efficiency and capability access.

[0259] In the context of computing and network convergence, facing massive computing and network demands, mobile communication networks need to analyze and interpret the application requirements of external applications and open up and share available computing and network resources with external applications.

[0260] There is currently no research or methodology on how mobile communication networks can more reliably provide computing power services to meet the diverse application needs of various industries, especially when the computing resources of a node itself are insufficient to meet the computing power demand. This requires coordinating the computing resources of neighboring nodes to open up capabilities to applications in order to provide computing power services to the outside world more reliably.

[0261] In view of this, the embodiments of this application provide a computing power negotiation method, apparatus, target computing power node, network function and medium, which can provide computing power services to the outside world more reliably and empower industry applications.

[0262] The network architecture involved in the embodiments of this application will be described exemplarily below.

[0263] In one possible implementation, the network architecture is a service-oriented network architecture. See also... Figure 1 In this embodiment, a new network function, CCF (Compute Control Function), is added to the original 5G core network control plane. This function is responsible for the registration of computing nodes and the periodic maintenance of computing resources. The functions of CCF will be described in the following embodiments.

[0264] Figure 1 In the network architecture shown, both the Application Function (AF) and each User Equipment (UE) support proximity communication services. For example, each UE... Figure 1 The UE1, UE2, UE3, etc. shown, UE1, UE2, UE3 and UE4 also support network relay function.

[0265] It should be noted that, Figure 1 The other network functions shown are those in the original 5G core network control plane. For related concepts and functions, please refer to the relevant existing technologies, which will not be repeated here.

[0266] In other possible implementations, the network architecture can also be a non-service network architecture. The specific form of the network architecture is not limited here. The following embodiments all use a service-oriented network architecture as an example for illustration.

[0267] The technical solutions of this application and how they solve the aforementioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0268] In one embodiment, such as Figure 2 As shown, a computing power negotiation method is provided. Taking the application of this method to a target computing power node as an example, in this embodiment, the target computing power node can be a UE, network function, server, virtualization cloud platform, etc. The method includes the following steps:

[0269] Step 201: The target computing node receives the computing resource request sent by the first NF.

[0270] The third NF (Network Function) is such as AF or SMF (Session Management Function). Taking AF as an example, AF needs to establish / update a session (business session or application session) to the target computing power node. AF sends the computing power request to the second NF in the session establishment / update request. The second NF is such as NEF (Network Exposure Function).

[0271] Optionally, AF can estimate the computing resources required by AF.

[0272] Then, NEF authenticates AF and the computing power request sent by AF. After successful authentication, NEF forwards the session establishment / update request carrying the computing power request to CCF.

[0273] Optionally, CCF estimates the computing resources required for AF.

[0274] As mentioned above, the CCF is responsible for registering computing power nodes and periodically maintaining computing power resources. Therefore, regardless of whether the AF or the CCF performs the computing power estimation, after the CCF determines the type of computing power service and / or computing power resource metric requested by the AF during the estimation process, the CCF also needs to determine whether a target computing power node can be selected to provide the computing power service required by the AF. For example, the CCF verifies whether the target computing power node is registered with the CCF and whether the target computing power node is allowed to provide computing power services externally. If the verification is successful, the CCF sends a computing power resource request to the selected target computing power node.

[0275] In one implementation, a computing resource request includes a computing service type requirement and / or a computing resource requirement. A computing service type requirement may include, for example, a data processing computing service, a video rendering computing service, etc. A computing resource requirement may include, for example, the size of the computing resources, the duration of their use, etc. Of course, a computing resource request may also include computing service type requirements and other requirement information besides computing resource requirements; therefore, the specific content included in a computing resource request is not limited here.

[0276] In this way, the target computing node receives the computing resource request sent by the first NF.

[0277] Step 202: If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, the target computing power node obtains the computing power information of the neighboring computing power nodes.

[0278] When a target computing power node receives a computing power resource request, it can determine whether it meets the computing power requirements corresponding to the request, such as whether it meets the computing power service type requirements and / or computing power resource requirements.

[0279] In one possible implementation, if the target computing node fully meets the computing power requirements corresponding to the computing power resource request, then the target computing node provides computing power services for the session.

[0280] In another possible implementation, if the target computing node does not meet the computing power requirements corresponding to the computing power resource request, for example, if the target computing node does not meet the computing service type requirements and / or computing power resource requirements corresponding to the computing power resource request, the target computing node obtains the computing power information of neighboring computing nodes, thereby discovering the computing resources that neighboring computing nodes can provide. Several possible implementation methods for the target computing node to obtain the computing power information of neighboring computing nodes will be described in the following embodiments.

[0281] In one implementation, the computing power information of neighboring computing power nodes includes the computing power node identifier of the neighboring computing power node and the computing power attribute information of the neighboring computing power node. The computing power attribute information includes at least one of the following: the computing power node type of the neighboring computing power node; the service location range of the neighboring computing power node; the service time of the neighboring computing power node; and the service type of the services supported by the neighboring computing power node.

[0282] The service identifier of the services supported by the nearby computing power nodes; the application type of the applications supported by the nearby computing power nodes; the application identifier of the applications supported by the nearby computing power nodes; the capability information of the capabilities supported by the nearby computing power nodes; the computing power information of the nearby computing power nodes; and the computing power usage description information of the nearby computing power nodes.

[0283] Among them, the computing node type includes heterogeneous hardware types such as CPU (Central Processing Unit) / GPU (Graphics Processing Unit), UE type, network function type, physical machine / server device type, virtualization cloud platform type, etc.; the capability information of the neighboring computing nodes is used to characterize the capabilities / operations supported by the neighboring computing nodes, such as the computing capabilities, communication capabilities, storage capabilities, caching capabilities, etc. of the neighboring computing nodes; the computing power information of the neighboring computing nodes includes, for example, the accuracy of the computing resources that the neighboring computing nodes can provide, processing speed, processing time / latency, computing resource metric (Flops), etc.

[0284] After the target computing node obtains the computing power information of the neighboring computing nodes, it can discover the computing resources that the neighboring computing nodes can provide. Then, the target computing node coordinates with the computing resources of the neighboring computing nodes to provide computing power services for the session.

[0285] In this embodiment of the application, the target computing power node mentioned in step 202 not meeting the computing power requirements corresponding to the computing power resource request includes at least the following two situations:

[0286] 1) The target computing node does not meet all the computing power requirements corresponding to the computing power resource request.

[0287] In this case, optionally, if the computing power resource request only includes computing power service type requirements, the target computing power node cannot provide the computing power service types requested in the computing power resource request. For example, the computing power resource request includes computing power service type requirements of video rendering type and data processing type, but the target computing power node cannot provide computing power services of video rendering type and data processing type. In this case, the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request.

[0288] Optionally, if the computing power resource request only includes computing power resource requirements, the target computing power node cannot provide the computing power resources requested in the computing power resource request. For example, the computing power resource requirement included in the computing power resource request is computing power resources with latency meeting a certain condition. However, the latency of the target computing power node does not meet the condition, that is, the target computing power node cannot provide computing power resources with latency meeting the above condition. In this case, the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request.

[0289] Optionally, if the computing power resource request includes computing power service type requirements and computing power resource requirements, then the target computing power node not meeting all the computing power requirements corresponding to the computing power resource request means that the target computing power node cannot provide the computing power service type and computing power resources requested by the computing power resource request.

[0290] If the target computing node does not meet all the computing power requirements corresponding to the computing power resource request, the computing resources of the neighboring computing nodes will provide computing power services for the session.

[0291] 2) The target computing node does not meet part of the computing power requirement corresponding to the computing power resource request.

[0292] In this case, the target computing node can meet part of the computing power requirement corresponding to the computing power resource request. However, if the target computing node cannot meet the other part of the computing power requirement corresponding to the computing power resource request, then the other part of the computing power requirement will be met by the neighboring computing nodes of the target computing node.

[0293] For example, if a computing power resource request includes a computing power service type requirement, which is video rendering and data processing, the target computing power node can provide video rendering computing power services but cannot provide data processing computing power services. However, the neighboring computing power nodes of the target computing power node can provide data processing computing power services. Therefore, the target computing power node and the neighboring computing power nodes will work together to provide computing power services for this session.

[0294] Step 203: The target computing node sends a computing resource response to the first NF based on the computing power information of neighboring computing nodes.

[0295] For example, after the target computing node obtains the computing power information of neighboring computing nodes, it can determine whether the neighboring computing nodes meet the computing power requirements corresponding to the computing power resource request based on the computing power information. If the neighboring computing nodes meet the computing power requirements corresponding to the computing power resource request, the target computing node sends a computing power resource response to the first NF based on the computing power information of the neighboring computing nodes. The following embodiments all use the example of neighboring computing nodes meeting the computing power requirements corresponding to the computing power resource request for illustration. The number of neighboring computing nodes that meet the computing power requirements corresponding to the computing power resource request can be one or more.

[0296] As mentioned above, the target computing node not meeting the computing power requirements corresponding to the computing power resource request includes at least two scenarios: the target computing node does not meet all the computing power requirements corresponding to the computing power resource request, or the target computing node does not meet some of the computing power requirements corresponding to the computing power resource request. Therefore, the neighboring computing nodes meeting the computing power requirements corresponding to the computing power request also includes two scenarios:

[0297] 1) If the target computing node does not meet all the computing power requirements corresponding to the computing power resource request, then the computing power service for this session will be provided entirely by the computing resources of the neighboring computing nodes. That is, the neighboring computing nodes need to meet all the computing power requirements corresponding to the computing power resource request. Therefore, the computing power resource response includes the computing power information of the neighboring computing nodes.

[0298] 2) If the target computing node cannot meet part of the computing power requirement corresponding to the computing power resource request, the target computing node can meet part of the computing power requirement corresponding to the computing power resource request. However, the target computing node cannot meet another part of the computing power requirement corresponding to the computing power resource request. The neighboring computing node needs to meet the other part of the computing power requirement corresponding to the computing power resource request. In this case, the target computing node and the neighboring computing node cooperate to provide computing power services for the session. Therefore, the computing power resource response includes the computing power information of the neighboring computing node and the computing power information of the target computing node.

[0299] The computing power information of the target computing power node includes content similar to that of the computing power information of the neighboring computing power nodes. For example, the computing power information of the target computing power node includes the computing power node identifier and the computing power attribute information of the target computing power node. The computing power attribute information includes at least one of the following: the computing power node type of the target computing power node; the service location range of the target computing power node; the service time of the target computing power node; the service type of the service supported by the target computing power node; the service identifier of the service supported by the target computing power node; the application type of the application supported by the target computing power node; the application identifier of the application supported by the target computing power node; the capability information of the capabilities supported by the target computing power node; the computing power information of the target computing power node; and the computing power occupancy description information of the target computing power node.

[0300] After the target computing node sends a computing resource response to the first NF (e.g., CCF), the first NF sends the computing resource response to the second NF (e.g., NEF). The contents of the computing resource response can be found in the description above, and will not be repeated here.

[0301] The second NF sends the computing resource response to the third NF (e.g., AF). After receiving the computing resource response from the second NF, the third NF establishes a service session that reaches the target computing node through the neighboring computing nodes based on the computing resource response.

[0302] In this embodiment, both the target computing node and the neighboring computing nodes can be UEs. The UEs can employ multi-level relays; for example, please refer to [link to relevant documentation]. Figure 1 Assuming the target UE is UE5, UE5 can access the network through neighboring UE2 and neighboring UE1.

[0303] In the above embodiment, the target computing node receives the computing resource request sent by the first NF. If the target computing node does not meet the computing power requirements corresponding to the computing power request, the target computing node obtains the computing power information of the neighboring computing nodes. Based on the computing power information of the neighboring computing nodes, the target computing node sends a computing resource response to the first NF. In this way, when the target computing node does not meet the computing power requirements corresponding to the computing power request, the target computing node can coordinate with the computing resources of the neighboring computing nodes to respond to the computing resource request, thereby improving the reliability of the response to the computing resource request and enabling more reliable provision of computing power services to the outside world.

[0304] exist Figure 2 Based on the embodiments shown, the following describes the process of a target computing node obtaining computing power information of neighboring computing power nodes through four different implementation methods.

[0305] 1) The first method for a target computing node to obtain computing power information from neighboring computing nodes:

[0306] See Figure 3 In this embodiment, Figure 1 In the network architecture shown, a UE can proactively initiate a computing power announcement to a neighboring UE (both the UE and the neighboring UE support the neighbor communication service and share computing power). The computing power announcement carries its own computing power information.

[0307] Therefore, in this embodiment, the target computing power node can receive a first computing power announcement sent by a neighboring computing power node. The first computing power announcement carries the computing power information of the neighboring computing power node, thereby enabling the target computing power node to obtain the computing power information of the neighboring computing power node. In this method, the neighboring computing power node actively sends the first computing power announcement, and the target computing power node can conveniently obtain the computing power information of the neighboring computing power node. The acquisition method is simple and easy to implement.

[0308] 2) A second method for the target computing node to obtain computing power information of neighboring computing nodes:

[0309] See Figure 4 In this embodiment, Figure 1 In the network architecture shown, the UE can send a computing power information request to a neighboring UE (both the UE and the neighboring UE support the neighboring communication service and share computing power). The neighboring UE responds to the computing power information request and feeds back its own computing power information.

[0310] Therefore, in this embodiment, the target computing node can send a first computing power information request to neighboring computing power nodes. The target computing power node receives a computing power discovery response from the neighboring computing power nodes in response to the first computing power information request. This computing power discovery response carries the computing power information of the neighboring computing power nodes, thereby realizing the process of the target computing power node obtaining the computing power information of the neighboring computing power nodes. In this method, the neighboring computing power nodes only send their computing power information to the target computing power node after receiving the first computing power information request, avoiding the additional resource consumption caused by the neighboring computing power nodes frequently announcing their computing power information, and thus saving the communication resources of the neighboring computing power nodes.

[0311] In this embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct neighboring computing power nodes to return computing power information corresponding to the computing power discovery requirement. The computing power discovery requirement may include, for example, computing power service type (e.g., computing service, storage service, etc.), computing power resource requirements (e.g., computing performance requirements, data processing requirements, application or workload requirements, time requirements, etc.), etc. In this way, the neighboring computing power nodes return computing power information corresponding to the computing power discovery requirement according to the instruction of the computing power discovery requirement.

[0312] If the first computing power information request does not carry a computing power discovery requirement, the first computing power information request is used to instruct neighboring computing power nodes to return all computing power information. After the neighboring computing power nodes return all computing power information according to the instructions of the first computing power information request, the target computing power node filters out the computing power information required for the computing power resource request.

[0313] In this embodiment, neighboring computing nodes can also flexibly choose whether to respond to the first computing power information request based on the actual workload (e.g., the number of tasks to be processed). After the target computing node sends the first computing power information request to the neighboring computing nodes, if the target computing node receives a response rejection message from the neighboring computing nodes, the target computing node determines that the neighboring computing nodes do not support shared computing power and obtains the computing power information of other neighboring computing nodes. Alternatively, after the target computing node sends the first computing power information request to the neighboring computing nodes, it can also start a timer. If it does not receive computing power information from the neighboring computing nodes after a preset time (i.e., the timer expires), the target computing node determines that the neighboring computing nodes do not support shared computing power and obtains the computing power information of other neighboring computing nodes.

[0314] 3) A third way for the target computing node to obtain computing power information from neighboring computing nodes:

[0315] See Figure 5 In this embodiment, Figure 1 In the network architecture shown, the UE can monitor the computing power of neighboring UEs (both the UE and the neighboring UE support neighbor communication services and share computing power) and store the computing power information of neighboring UEs.

[0316] Therefore, in this embodiment, the target computing power node can monitor the computing power information of neighboring computing power nodes in real time or periodically, so as to realize the process of the target computing power node obtaining the computing power information of neighboring computing power nodes.

[0317] As one implementation method, the target computing power node can also monitor the computing power information of neighboring computing power nodes in advance. Once the computing power information of neighboring computing power nodes is updated, the target computing power node can obtain the latest computing power information of neighboring computing power nodes. The target computing power node stores the latest computing power information of neighboring computing power nodes and maintains the mapping relationship between the computing power node identifier and the computing power information of neighboring computing power nodes. It can be understood that once the target computing power node monitors the latest computing power information of neighboring computing power nodes, the target computing power node updates the mapping relationship.

[0318] In this approach, the target computing node can also read the computing power information of neighboring computing nodes from the first storage location. The first storage location stores the aforementioned mapping relationship between the computing node identifier of the neighboring computing node and the computing power information of the neighboring computing node. The computing power information of the neighboring computing node is obtained by the target computing node through historical monitoring of the neighboring computing nodes, thereby realizing the process of the target computing node obtaining the computing power information of the neighboring computing nodes.

[0319] The target computing power node obtains the computing power information of neighboring computing power nodes by listening to it. This ensures that the target node obtains the latest computing power information of neighboring computing power nodes, which helps to guarantee the accuracy of the computing power information of neighboring computing power nodes.

[0320] 4) The fourth way for a target computing node to obtain computing power information from neighboring computing nodes:

[0321] The first, second, and third methods mentioned above for the target computing power node to obtain computing power information of neighboring computing power nodes can also be achieved through CCF or... Figure 1 The network architecture shown is executed by a specific UE (e.g., the master UE) in a subnet composed of multiple UEs. The target UE obtains computing power information of nearby computing power nodes from the CCF or the master UE.

[0322] Please see Figure 6 Optionally, the target UE sends a neighboring computing power discovery request to the CCF or the master UE. Similar to the first computing power information request in the second method described above for the target computing power node to obtain computing power information of neighboring computing power nodes, the neighboring computing power discovery request may carry a computing power discovery requirement, which is used to instruct the CCF or the master UE to return the computing power information corresponding to the computing power discovery requirement. Alternatively, the neighboring computing power discovery request may not carry a computing power discovery requirement, in which case the CCF or the master UE will return all computing power information of the neighboring computing power nodes. Optionally, the computing power discovery process may not be triggered by the target UE, but may be initiated directly by the CCF or the master UE.

[0323] The CCF or the master UE can discover other neighboring UEs that can provide computing power by using any one of the first, second, or third methods to obtain computing power information of neighboring computing power nodes from the target computing power node, and generate a proximity relationship for the neighboring computing power nodes. The proximity relationship includes the mapping relationship between the neighboring computing power nodes and the target computing power node. The proximity relationship refers to the link layer identifier mapping between the target UE and the neighboring UE. The link layer identifier, or Layer 2 ID, is used to identify the sender or receiver device as a neighboring communication frame.

[0324] The CCF or the master UE sends a neighboring computing power discovery response to the target UE or synchronizes neighboring computing power information with the target UE, so that the target UE can obtain the computing power information of neighboring UEs.

[0325] Therefore, in this embodiment, the target computing node (e.g., the target UE mentioned above) can receive computing power information of neighboring computing nodes sent by the master computing node (e.g., the master UE mentioned above) or the first NF (e.g., the CCF mentioned above) to realize the process of obtaining computing power information of neighboring computing nodes.

[0326] Optionally, before the target computing power node receives the computing power information of neighboring computing power nodes sent by the master computing power node or the first NF, the target computing power node may also send a first computing power discovery request to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of neighboring computing power nodes.

[0327] In this way, in scenarios with multiple UEs in a network, the master UE or CCF can discover computing power and synchronize computing power information, which is beneficial for the unified management of computing power resources of each UE.

[0328] In this application embodiment, the target computing power node can obtain the computing power information of neighboring computing power nodes through any of the above implementation methods. The implementation methods are flexible and diverse, and can be flexibly selected in the actual implementation process, which improves the implementation flexibility of this application embodiment.

[0329] In the above Figure 2 Based on the illustrated embodiment, if the target computing node can meet a portion of the computing power requirement corresponding to the computing power resource request, and neighboring computing nodes meet the other portion of the computing power requirement corresponding to the computing power resource request, i.e., the target computing node and neighboring computing nodes need to collaborate to provide computing power services for the session between the third NF and the target computing node, see [reference needed]. Figure 7 The computing power negotiation method in this application embodiment also includes Figure 7 Steps 701 and 702 are shown below:

[0330] Step 701: The target computing node decomposes the computing task corresponding to the computing resource request into multiple computing subtasks.

[0331] Step 702: The target computing node sends the task decomposition information corresponding to multiple computing subtasks to the neighboring computing nodes.

[0332] As mentioned above, the number of neighboring computing power nodes that can meet the partial computing power requirements corresponding to the computing power resource request can be one or more. The target computing power node uses one or more neighboring computing power nodes as cooperative nodes and negotiates tasks with the cooperative nodes.

[0333] The target computing power node can decompose the computing power task corresponding to the computing power resource request into multiple computing power sub-services, which then collaborate to complete the computing power task. After decomposition, the target computing power node sends the task decomposition information corresponding to the multiple computing power sub-tasks to neighboring computing power nodes to complete the computing power task negotiation.

[0334] Optionally, if the target computing node and neighboring computing nodes need to collaborate to provide computing power services for the session between the third NF and the target computing node, and the target computing node only sends a computing power resource response to the first NF without decomposing the computing power task corresponding to the computing power resource request, then the first NF (e.g., CCF) or the master computing node decomposes the computing power task corresponding to the computing power resource request into multiple computing power sub-services, and sends the task decomposition information corresponding to the multiple computing power sub-services to the neighboring computing nodes and the target computing node.

[0335] In this way, the target computing node can receive task decomposition information corresponding to multiple computing subtasks sent by the master computing node. The multiple computing subtasks are obtained by the master computing node decomposing the computing task corresponding to the computing resource request. Alternatively, the target computing node can receive task decomposition information corresponding to multiple computing subtasks sent by the first NF. The multiple computing subtasks are obtained by the first NF decomposing the computing task corresponding to the computing resource request.

[0336] In this embodiment of the application, the task decomposition information includes at least one of the following: the computing task identifier of the computing task; the computing power requirement of the computing task (which may be represented by computing power information corresponding to the computing power resource request); and a list of computing subtask information, wherein the list of computing subtask information includes computing node identifiers (target computing node or computing node identifier of neighboring computing nodes), computing subtask identifiers of each computing subtask, computing power requirement information of each computing subtask, and network requirement information of each computing subtask.

[0337] Optionally, after receiving the task decomposition information, the neighboring computing power node can also return a subtask acceptance response to the target computing power node. This subtask acceptance response carries the computing power information of the neighboring computing power node. Alternatively, the neighboring computing power node can return a subtask rejection response to the target computing power node. Or, according to network management requirements, the neighboring computing power node may be required to support the computing power subtasks decomposed by the CCF / master computing power node / target computing power node. In this case, the neighboring computing power node may not need to respond.

[0338] In this way, the target computing node receives a subtask acceptance response from the neighboring computing node in response to the task decomposition information, or the target computing node receives a subtask rejection response from the neighboring computing node in response to the task decomposition information. If the target computing node receives a subtask acceptance response from the neighboring computing node in response to the task decomposition information, the target computing node can also send computing task decomposition negotiation confirmation information to the neighboring computing node to complete the negotiation process.

[0339] Please see Figure 8 Taking the target computing power node as the target UE, the first NF as the CCF, and the master computing power node as the master UE as an example, the negotiation process of computing power tasks is illustrated.

[0340] The target UE / CCF / master UE decomposes the computing power task corresponding to the computing power resource request into multiple computing power sub-services. These sub-services then collaborate to complete the computing power task. After decomposition, the target UE / CCF / master UE sends the task decomposition information corresponding to the multiple computing power sub-tasks to the nearest computing power nodes. If the task decomposition is performed by the CCF / master UE, the task decomposition information is synchronized to the target UE to complete the computing power task negotiation.

[0341] In the above embodiments, for the computing power requirements of the third NF, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request or does not meet part of the computing power requirements corresponding to the computing power resource request, the computing resources of neighboring computing power nodes are coordinated, and the computing power of the business / application is negotiated based on the communication capabilities of the neighboring computing power nodes to empower industry applications.

[0342] In one embodiment, see Figure 9 A computing power negotiation method is provided for the first NF, which can be, for example, the aforementioned CCF. The method includes the following steps:

[0343] Step 901: The first NF sends a computing resource request to the target computing node.

[0344] Step 902: The first NF receives the computing resource response sent by the target computing node in response to the computing resource request.

[0345] The computing power resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing power resource request.

[0346] In one embodiment, if the target computing node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0347] If the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0348] In one embodiment, the computing power negotiation method further includes the following steps:

[0349] Step A1: The first NF obtains the computing power information of the neighboring computing power nodes and sends the computing power information of the neighboring computing power nodes to the target computing power node.

[0350] In one embodiment, prior to step A1, the computing power negotiation method further includes the following steps:

[0351] Step A2: The first NF receives a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request computing power information of neighboring computing power nodes.

[0352] In one embodiment, the first NF can implement the process of obtaining the computing power information of neighboring computing power nodes in step A1 in any of the following ways:

[0353] Optionally, the first NF receives a second computing power announcement sent by a neighboring computing power node, the second computing power announcement carrying computing power information of the neighboring computing power node.

[0354] Optionally, the first NF sends a second computing power information request to a neighboring computing power node; the first NF receives the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the second computing power information request.

[0355] Optionally, the first NF monitors the computing power information of neighboring computing power nodes in real time or periodically.

[0356] Optionally, the first NF reads the computing power information of neighboring computing power nodes from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF through historical monitoring of neighboring computing power nodes.

[0357] First NF can also generate proximity relationships for neighboring computing power nodes, which include the mapping relationship between neighboring computing power nodes and the target computing power node.

[0358] In one embodiment, the computing power negotiation method further includes the following steps:

[0359] Step A3: The first NF decomposes the computing power task corresponding to the computing power resource request into multiple computing power sub-tasks.

[0360] In step A4, the first NF sends the task decomposition information corresponding to multiple computing power subtasks to the neighboring computing power nodes and the target computing power node.

[0361] In one embodiment, the computing power negotiation method further includes the following steps:

[0362] Step A5: The first NF sends a computing resource response to the second NF. The computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

[0363] For details on the implementation method and beneficial effects of the computing power negotiation method for the first NF, please refer to the relevant descriptions in the above embodiments of the computing power negotiation method for the target computing power node, which will not be repeated here.

[0364] In one embodiment, see Figure 10 A computing power negotiation method is provided for the third NF, which can be, for example, the aforementioned AF or SMF. The method includes the following steps:

[0365] Step 1001: The third NF receives the computing power resource response sent by the second NF. The computing power resource response is sent by the target computing power node to the first NF based on the computing power information of the neighboring computing power nodes, and then forwarded by the first NF to the second NF. The computing power information of the neighboring computing power nodes is obtained by the target computing power node when the computing power requirement corresponding to the computing power resource request is not met.

[0366] Step 1002: The third NF establishes a service session that reaches the target computing node through neighboring computing nodes based on the computing resource response.

[0367] For the implementation method and beneficial effects of the computing power negotiation method for the third NF, please refer to the relevant description in the above embodiment of the computing power negotiation method for the target computing power node, which will not be repeated here.

[0368] The following example illustrates the implementation process of the computing power negotiation method in this application, taking the target computing power node as the target UE, the neighboring computing power nodes as neighboring UEs, the first NF as CCF, the second NF as NEF, and the third NF as AF. See also... Figure 11 The method includes the following steps:

[0369] Step 1: The AF needs to establish / update a session with the target UE. The AF sends the computing power request to the NEF in the session establishment / update request.

[0370] Optionally, AF can estimate the computing resources required by AF; alternatively, CCF can estimate the computing resources required by AF. Figure 11In the process, steps 1-4 include two implementation schemes, Scheme A and Scheme B. The difference between the two schemes is that Scheme A uses AF to estimate the computing power resources required by AF, while Scheme B uses CCF to estimate the computing power resources required by AF.

[0371] Step 2: NEF authenticates AF.

[0372] Step 3: After successful authentication, NEF will forward the session establishment / update request carrying the computing power request to CCF.

[0373] Step 4: CCF determines the computing resources required by AF based on the computing power request.

[0374] Step 5: The CCF determines whether the target UE can be selected to provide the computing power service required by the AF based on the computing power resources required by the AF.

[0375] Step 6: If the CCF determines that it can select the target UE to provide the computing power service required by AF, the CCF sends a computing power resource request to the target UE, and the target UE receives the computing power resource request sent by the CCF. The computing power resource request includes computing power service type requirements and / or computing power resource requirements.

[0376] Step 7: If the target UE does not meet the computing power requirements corresponding to the computing power resource request, the target UE obtains the computing power information of neighboring UEs, that is, the target UE performs neighboring computing power discovery.

[0377] Step 8, optionally, involves the target UE performing computing power task decomposition and negotiation.

[0378] Step 9: The target UE sends a computing power resource response to the CCF based on the computing power information of neighboring UEs.

[0379] If the target UE does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of neighboring UEs. If the target UE does not meet only part of the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of neighboring UEs and the computing power information of the target UE.

[0380] Computing power information includes computing power node identifiers and computing power attribute information. The computing power attribute information includes at least one of the following: computing power node type; computing power node service location range; computing power node service time.

[0381] Supported business types; Supported business identifiers; Supported application types; Supported application identifiers; Supported capability information; Computing power information; Computing power usage description information.

[0382] Step 10, optionally, CCF performs computing power task decomposition and negotiation.

[0383] Step 11: CCF sends a computing resource response to NEF.

[0384] Step 12: NEF sends a session request response to AF based on the computing resource response. AF then establishes a service session with the target UE by passing through a neighboring UE, based on the computing resource response in the session request response.

[0385] In the above embodiments, the CCF and AF interact and negotiate to jointly complete the computing power discovery, computing power, and computing power scheduling process. If the target UE does not meet the computing power requirements corresponding to the computing power resource request, the target UE can coordinate with the computing resources of neighboring UEs to respond to the computing power resource request, thereby improving the reliability of the response to the computing power resource request and thus being able to provide computing power services to the outside world more reliably.

[0386] It should be understood that although the steps in the flowchart above are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart above may include multiple steps or multiple stages, which are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0387] In one embodiment, such as Figure 12 As shown, a computing power negotiation device is provided for a target computing power node. The device includes:

[0388] The receiving module 1201 is used to receive the computing resource request sent by the first NF;

[0389] The acquisition module 1202 is used to acquire the computing power information of neighboring computing power nodes if the target computing power node does not meet the computing power requirements corresponding to the computing power resource request.

[0390] The response module 1203 is used to send a computing resource response to the first NF based on the computing power information of the neighboring computing power nodes.

[0391] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0392] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0393] In one embodiment, the computing power information includes a computing power node identifier and computing power attribute information, wherein the computing power attribute information includes at least one of the following:

[0394] Computing node types;

[0395] The service location range of computing power nodes;

[0396] Computing node service time;

[0397] Supported business types;

[0398] Business identifiers that support the business;

[0399] Supported application types;

[0400] Supported application identifiers;

[0401] Support capability information;

[0402] Calculate force and force information;

[0403] Description of computing power usage.

[0404] In one embodiment, the computing resource request includes computing service type requirements and / or computing resource requirements.

[0405] In one embodiment, the acquisition module 1202 is specifically used to receive a first computing power announcement sent by the neighboring computing power node, the first computing power announcement carrying the computing power information of the neighboring computing power node.

[0406] In one embodiment, the acquisition module 1202 is specifically used to send a first computing power information request to the neighboring computing power node; and to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the first computing power information request.

[0407] In one embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement.

[0408] If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

[0409] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the acquisition module 1202 is further configured to determine that the neighboring computing power node does not support shared computing power and acquire the computing power information of other neighboring computing power nodes if it receives a response rejection message sent by the neighboring computing power node.

[0410] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the acquisition module 1202 is further configured to determine that the neighboring computing power node does not support shared computing power if it does not receive the computing power information sent by the neighboring computing power node within a preset time period, and to acquire the computing power information of other neighboring computing power nodes.

[0411] In one embodiment, the acquisition module 1202 is specifically used to monitor the computing power information of the neighboring computing power nodes in real time or periodically.

[0412] In one embodiment, the acquisition module 1202 is specifically used to read the computing power information of the neighboring computing power nodes from a first storage location. The first storage location stores a mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power nodes.

[0413] In one embodiment, the acquisition module 1202 is specifically used to receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

[0414] In one embodiment, the acquisition module 1202 is further configured to send a first computing power discovery request to the master computing power node or the first NF, wherein the first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0415] In one embodiment, the device further includes:

[0416] The task decomposition module is used to decompose the computing power task corresponding to the computing power resource request into multiple computing power sub-tasks.

[0417] The sending module is used to send the task decomposition information corresponding to the multiple computing power subtasks to the neighboring computing power nodes.

[0418] In one embodiment,

[0419] The receiving module 1201 is further configured to receive task decomposition information corresponding to multiple computing subtasks sent by the master control computing power node, wherein the multiple computing subtasks are obtained by the master control computing power node decomposing the computing power task corresponding to the computing power resource request; or...

[0420] The receiving module 1201 is further configured to receive task decomposition information corresponding to multiple computing power subtasks sent by the first NF, wherein the multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

[0421] In one embodiment, the task breakdown information includes at least one of the following:

[0422] The computing power task identifier of the computing power task;

[0423] The computing power requirements of the computing power task;

[0424] The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

[0425] In one embodiment, the receiving module 1201 is further configured to receive a subtask acceptance response returned by the neighboring computing power node in response to the task decomposition information, the subtask acceptance response carrying the computing power information of the neighboring computing power node.

[0426] In one embodiment, the sending module is further configured to send computing power task decomposition negotiation confirmation information to the neighboring computing power nodes.

[0427] In one embodiment, the receiving module 1201 is further configured to receive a subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

[0428] Specific limitations regarding the computing power negotiation device used for the target computing power node can be found in the limitations of the computing power negotiation method used for the target computing power node above, and will not be repeated here. Each module in the aforementioned computing power negotiation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the target computing power node, or stored in software in the memory of the target computing power node, so that the processor can call and execute the operations corresponding to each module.

[0429] In one embodiment, such as Figure 13 As shown, a computing power negotiation device is provided for a first NF, the device comprising:

[0430] Sending module 1301 is used to send computing resource requests to the target computing power node;

[0431] The receiving module 1302 is used to receive a computing resource response sent by the target computing power node in response to the computing resource request. The computing resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing resource request.

[0432] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0433] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0434] In one embodiment, the device further includes:

[0435] The acquisition module is used to acquire the computing power information of the neighboring computing power nodes;

[0436] The sending module 1301 is also used to send the computing power information of the neighboring computing power nodes to the target computing power node.

[0437] In one embodiment, before obtaining the computing power information of the neighboring computing power nodes, the receiving module 1302 is further configured to receive a second computing power discovery request sent by the target computing power node, the second computing power discovery request being used to request the computing power information of the neighboring computing power nodes.

[0438] In one embodiment, the acquisition module is specifically used to receive a second computing power announcement sent by the neighboring computing power node, the second computing power announcement carrying the computing power information of the neighboring computing power node.

[0439] In one embodiment, the acquisition module is specifically used to send a second computing power information request to the neighboring computing power node; and to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the second computing power information request.

[0440] In one embodiment, the acquisition module is specifically used to monitor the computing power information of the neighboring computing power nodes in real time or periodically.

[0441] In one embodiment, the acquisition module is specifically used to read the computing power information of the neighboring computing power nodes from a second storage location. The second storage location stores a mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF historically monitoring the neighboring computing power node.

[0442] In one embodiment, the device further includes:

[0443] A generation module is used to generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

[0444] In one embodiment, the device further includes:

[0445] The task decomposition module is used to decompose the computing power task corresponding to the computing power resource request into multiple computing power sub-tasks.

[0446] The sending module 1301 is further configured to send the task decomposition information corresponding to the plurality of computing power subtasks to the neighboring computing power nodes and the target computing power node.

[0447] In one embodiment, the sending module 1301 is further configured to send the computing power resource response to the second NF, wherein the computing power resource response is used by the second NF to send the computing power resource response to the third NF, and wherein the computing power resource response is used by the third NF to establish a service session that reaches the target computing power node through the neighboring computing power nodes.

[0448] Specific limitations regarding the computing power negotiation device used in the first NF can be found in the limitations of the computing power negotiation method used in the first NF above, and will not be repeated here. Each module in the aforementioned computing power negotiation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the first NF, or stored in software in the memory of the first NF, so that the processor can call and execute the operations corresponding to each module.

[0449] In one embodiment, such as Figure 14 As shown, a computing power negotiation device is provided for a third NF, the device comprising:

[0450] The receiving module 1401 is used to receive a computing power resource response sent by the second NF. The computing power resource response is sent by the target computing power node to the first NF according to the computing power information of the neighboring computing power nodes, and then forwarded by the first NF to the second NF. The computing power information of the neighboring computing power nodes is obtained by the target computing power node when the computing power requirement corresponding to the computing power resource request is not met.

[0451] The session establishment module 1402 is used to establish a service session that reaches the target computing power node through the neighboring computing power nodes based on the computing power resource response.

[0452] Specific limitations regarding the computing power negotiation device used in the third NF can be found in the limitations of the computing power negotiation method used in the third NF above, and will not be repeated here. Each module in the aforementioned computing power negotiation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the third NF, or stored in software in the memory of the third NF, so that the processor can call and execute the operations corresponding to each module.

[0453] Figure 15 This is a schematic diagram of the structure of a target computing node provided in an embodiment of this application. The target computing node can be a UE (User Equipment). Figure 15 As shown, the target computing node includes a processor 1500, a transceiver 1510, and a memory 1520. The transceiver 1510 is used to receive and send data under the control of the processor 1500.

[0454] Among them, Figure 15 In this context, the bus architecture may include any number of interconnected buses and bridges, specifically linked together by various circuits of one or more processors represented by processor 1500 and memory represented by memory 1520.

[0455] The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further here. The bus interface provides the interface.

[0456] The transceiver 1510 may consist of multiple components, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, and other transmission media. For different user equipment, the user interface 1530 may also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0457] The processor 1500 is responsible for managing the bus architecture and general processing, while the memory 1520 can store computer programs and data used by the processor 1500 during operation.

[0458] Optionally, the processor 1500 can be a CPU (Central Processing Unit), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or CPLD (Complex Programmable Logic Device), and the processor 1500 can also adopt a multi-core architecture.

[0459] The processor 1500 executes the computing power negotiation method for the target computing power node provided in this application embodiment by calling the program stored in the memory 1520 according to the obtained executable instructions. The processor 1500 and the memory 1520 can also be physically arranged separately.

[0460] Processor 1500 is used to read computer programs from memory 1520 and perform the following operations:

[0461] Control the transceiver 1510 to receive the computing resource request sent by the first NF;

[0462] If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, then obtain the computing power information of the neighboring computing power nodes;

[0463] Based on the computing power information of the neighboring computing power nodes, the transceiver 1510 is controlled to send a computing power resource response to the first NF.

[0464] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0465] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0466] In one embodiment, the computing power information includes a computing power node identifier and computing power attribute information, wherein the computing power attribute information includes at least one of the following:

[0467] Computing node types;

[0468] The service location range of computing power nodes;

[0469] Computing node service time;

[0470] Supported business types;

[0471] Business identifiers that support the business;

[0472] Supported application types;

[0473] Supported application identifiers;

[0474] Support capability information;

[0475] Calculate force and force information;

[0476] Description of computing power usage.

[0477] In one embodiment, the computing resource request includes computing service type requirements and / or computing resource requirements.

[0478] In one embodiment, the processor 1500 is configured to read the computer program in the memory 1520 and specifically perform the following operations:

[0479] The transceiver 1510 is controlled to receive a first computing power notification sent by the neighboring computing power node, the first computing power notification carrying the computing power information of the neighboring computing power node.

[0480] In one embodiment, the processor 1500 is configured to read the computer program in the memory 1520 and specifically perform the following operations:

[0481] Control the transceiver 1510 to send a first computing power information request to the neighboring computing power node;

[0482] The transceiver 1510 is controlled to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the first computing power information request.

[0483] In one embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement.

[0484] If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

[0485] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the processor 1500 reads the computer program in the memory 1520 and further performs the following operations:

[0486] If a response rejection message is received from the neighboring computing power node, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0487] In one embodiment, after sending the first computing power information request to the neighboring computing power node, the processor 1500 reads the computer program in the memory 1520 and further performs the following operations:

[0488] If no computing power information is received from the neighboring computing power node within a preset time period, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0489] In one embodiment, the processor 1500 is configured to read the computer program in the memory 1520 and specifically perform the following operations:

[0490] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0491] In one embodiment, the processor 1500 is configured to read the computer program in the memory 1520 and specifically perform the following operations:

[0492] The target computing node reads the computing power information of the neighboring computing power node from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power node.

[0493] In one embodiment, the processor 1500 is configured to read the computer program in the memory 1520 and specifically perform the following operations:

[0494] The transceiver 1510 is controlled to receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

[0495] In one embodiment, the processor 1500 is configured to read a computer program from the memory 1520 and further perform the following operations:

[0496] The transceiver 1510 is controlled to send a first computing power discovery request to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0497] In one embodiment, the processor 1500 is configured to read a computer program from the memory 1520 and further perform the following operations:

[0498] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0499] The transceiver 1510 is controlled to send the task decomposition information corresponding to the multiple computing subtasks to the neighboring computing nodes.

[0500] In one embodiment, the processor 1500 is configured to read a computer program from the memory 1520 and further perform the following operations:

[0501] The transceiver 1510 is controlled to receive task decomposition information corresponding to multiple computing subtasks sent by the master computing power node. These multiple computing subtasks are obtained by the master computing power node decomposing the computing power task corresponding to the computing power resource request; or...

[0502] The transceiver 1510 is controlled to receive task decomposition information corresponding to multiple computing power subtasks sent by the first NF. The multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

[0503] In one embodiment, the task breakdown information includes at least one of the following:

[0504] The computing power task identifier of the computing power task;

[0505] The computing power requirements of the computing power task;

[0506] The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

[0507] In one embodiment, the processor 1500 is configured to read a computer program from the memory 1520 and further perform the following operations:

[0508] The transceiver 1510 is controlled to receive the subtask acceptance response returned by the neighboring computing power node in response to the task decomposition information. The subtask acceptance response carries the computing power information of the neighboring computing power node.

[0509] In one embodiment, the processor 1500 is configured to read a computer program from the memory 1520 and further perform the following operations:

[0510] The transceiver 1510 is controlled to send computing task decomposition negotiation confirmation information to the neighboring computing power nodes.

[0511] In one embodiment, the processor 1500 is configured to read a computer program from the memory 1520 and further perform the following operations:

[0512] The transceiver 1510 is controlled to receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

[0513] Figure 16 This is a schematic diagram illustrating the structure of a network function provided in an embodiment of this application. The network function may include a processor 1600, a transceiver 1610, and a memory 1620. The transceiver 1610 is used to receive and transmit data under the control of the processor 1600.

[0514] Among them, Figure 16 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 1600 and memory represented by memory 1620 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides the interface.

[0515] The transceiver 1610 may consist of multiple components, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, etc. The processor 1600 is responsible for managing the bus architecture and general processing, while the memory 1620 can store computer programs and data used by the processor 1600 during operation.

[0516] The processor 1600 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor 1600 can also adopt a multi-core architecture.

[0517] The network function can be a first NF (such as the CCF mentioned above), wherein the processor 1600 reads the program stored in the memory 1620 and executes the following steps:

[0518] Control the transceiver 1610 to send a computing resource request to the target computing node;

[0519] The transceiver 1610 is controlled to receive the computing resource response sent by the target computing power node in response to the computing resource request. The computing resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing resource request.

[0520] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0521] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0522] In one embodiment, the processor 1600 is configured to read a computer program from the memory 1620 and further perform the following operations:

[0523] The system acquires the computing power information of the neighboring computing power nodes and controls the transceiver 1610 to send the computing power information of the neighboring computing power nodes to the target computing power node.

[0524] In one embodiment, before acquiring the computing power information of the neighboring computing power nodes, the processor 1600 reads the computer program in the memory 1620 and further performs the following operations:

[0525] The transceiver 1610 is controlled to receive a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0526] In one embodiment, the processor 1600 is configured to read the computer program in the memory 1620 and specifically perform the following operations:

[0527] The transceiver 1610 is controlled to receive a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

[0528] In one embodiment, the processor 1600 is configured to read the computer program in the memory 1620 and specifically perform the following operations:

[0529] Control the transceiver 1610 to send a second computing power information request to the neighboring computing power node;

[0530] The transceiver 1610 is controlled to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the second computing power information request.

[0531] In one embodiment, the processor 1600 is configured to read the computer program in the memory 1620 and specifically perform the following operations:

[0532] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0533] In one embodiment, the processor 1600 is configured to read the computer program in the memory 1620 and specifically perform the following operations:

[0534] The computing power information of the neighboring computing power nodes is read from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the network function historically monitoring the neighboring computing power node.

[0535] In one embodiment, the processor 1600 is configured to read a computer program from the memory 1620 and further perform the following operations:

[0536] Generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

[0537] In one embodiment, the processor 1600 is configured to read a computer program from the memory 1620 and further perform the following operations:

[0538] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0539] The transceiver 1610 is controlled to send the task decomposition information corresponding to the multiple computing subtasks to the neighboring computing nodes and the target computing node.

[0540] In one embodiment, the processor 1600 is configured to read a computer program from the memory 1620 and further perform the following operations:

[0541] The transceiver 1610 is controlled to send the computing resource response to the second NF. The computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

[0542] The network function can also be a third NF (such as the AF or SMF mentioned above), wherein the processor 1600 reads the program stored in the memory 1620 and executes the following steps:

[0543] The transceiver 1610 is controlled to receive the computing power resource response sent by the second NF. The computing power resource response is sent by the target computing power node to the first NF according to the computing power information of the neighboring computing power nodes, and then forwarded by the first NF to the second NF. The computing power information of the neighboring computing power nodes is obtained by the target computing power node when the computing power requirement corresponding to the computing power resource request is not met.

[0544] Based on the computing power resource response, a service session is established to reach the target computing power node via the neighboring computing power nodes.

[0545] In one embodiment, a computer-readable storage medium is provided, which may be any available medium or data storage device that can be accessed by a processor, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO), etc.), optical memory (e.g., CD, DVD, BD, HVD, etc.), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0546] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0547] Receive the computing resource request sent by the first NF;

[0548] If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, then obtain the computing power information of the neighboring computing power nodes;

[0549] Based on the computing power information of the neighboring computing power nodes, a computing power resource response is sent to the first NF.

[0550] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0551] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0552] In one embodiment, the computing power information includes a computing power node identifier and computing power attribute information, wherein the computing power attribute information includes at least one of the following:

[0553] Computing node types;

[0554] The service location range of computing power nodes;

[0555] Computing node service time;

[0556] Supported business types;

[0557] Business identifiers that support the business;

[0558] Supported application types;

[0559] Supported application identifiers;

[0560] Support capability information;

[0561] Calculate force and force information;

[0562] Description of computing power usage.

[0563] In one embodiment, the computing resource request includes computing service type requirements and / or computing resource requirements.

[0564] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0565] The system receives a first computing power notification sent by the neighboring computing power node, the first computing power notification carrying the computing power information of the neighboring computing power node.

[0566] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0567] Send a first computing power information request to the neighboring computing power nodes;

[0568] Receive the computing power information of the neighboring computing power nodes sent in response to the first computing power information request.

[0569] In one embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement.

[0570] If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

[0571] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0572] If a response rejection message is received from the neighboring computing power node, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0573] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0574] If no computing power information is received from the neighboring computing power node within a preset time period, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0575] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0576] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0577] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0578] The target computing node reads the computing power information of the neighboring computing power node from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power node.

[0579] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0580] Receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

[0581] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0582] A first computing power discovery request is sent to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0583] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0584] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0585] The task decomposition information corresponding to the multiple computing subtasks is sent to the neighboring computing nodes.

[0586] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0587] The system receives task decomposition information corresponding to multiple computing subtasks sent by the master computing power node. These multiple computing subtasks are obtained by the master computing power node decomposing the computing power task corresponding to the computing power resource request; or...

[0588] The system receives task decomposition information corresponding to multiple computing power subtasks sent by the first NF, wherein the multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

[0589] In one embodiment, the task breakdown information includes at least one of the following:

[0590] The computing power task identifier of the computing power task;

[0591] The computing power requirements of the computing power task;

[0592] The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

[0593] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0594] The system receives a subtask acceptance response from the neighboring computing power node in response to the task decomposition information. The subtask acceptance response carries the computing power information of the neighboring computing power node.

[0595] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0596] Send computing task decomposition negotiation confirmation information to the neighboring computing power nodes.

[0597] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0598] Receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

[0599] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0600] Send a computing resource request to the target computing node;

[0601] The target computing power node receives a computing power resource response sent in response to the computing power resource request. The computing power resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing power resource request.

[0602] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0603] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0604] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0605] Obtain the computing power information of the neighboring computing power nodes and send the computing power information of the neighboring computing power nodes to the target computing power node.

[0606] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0607] The system receives a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0608] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0609] The system receives a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

[0610] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0611] Send a second computing power information request to the neighboring computing power nodes;

[0612] Receive the computing power information of the neighboring computing power node sent in response to the second computing power information request.

[0613] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0614] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0615] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0616] The computing power information of the neighboring computing power nodes is read from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF historically monitoring the neighboring computing power node.

[0617] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0618] Generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

[0619] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0620] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0621] The task decomposition information corresponding to the multiple computing power subtasks is sent to the neighboring computing power nodes and the target computing power node.

[0622] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0623] The computing resource response is sent to the second NF, and the computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

[0624] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0625] The target computing node receives a computing resource response from the second NF. The computing resource response is sent to the first NF by the target computing node based on the computing power information of the neighboring computing nodes, and then forwarded to the second NF by the first NF. The computing power information of the neighboring computing nodes is obtained by the target computing node when it does not meet the computing power requirements corresponding to the computing resource request.

[0626] Based on the computing power resource response, a service session is established to reach the target computing power node via the neighboring computing power nodes.

[0627] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0628] Receive the computing resource request sent by the first NF;

[0629] If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, then obtain the computing power information of the neighboring computing power nodes;

[0630] Based on the computing power information of the neighboring computing power nodes, a computing power resource response is sent to the first NF.

[0631] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0632] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0633] In one embodiment, the computing power information includes a computing power node identifier and computing power attribute information, wherein the computing power attribute information includes at least one of the following:

[0634] Computing node types;

[0635] The service location range of computing power nodes;

[0636] Computing node service time;

[0637] Supported business types;

[0638] Business identifiers that support the business;

[0639] Supported application types;

[0640] Supported application identifiers;

[0641] Support capability information;

[0642] Calculate force and force information;

[0643] Description of computing power usage.

[0644] In one embodiment, the computing resource request includes computing service type requirements and / or computing resource requirements.

[0645] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0646] The system receives a first computing power notification sent by the neighboring computing power node, the first computing power notification carrying the computing power information of the neighboring computing power node.

[0647] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0648] Send a first computing power information request to the neighboring computing power nodes;

[0649] Receive the computing power information of the neighboring computing power nodes sent in response to the first computing power information request.

[0650] In one embodiment, when the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement.

[0651] If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

[0652] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0653] If a response rejection message is received from the neighboring computing power node, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0654] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0655] If no computing power information is received from the neighboring computing power node within a preset time period, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

[0656] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0657] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0658] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0659] The target computing node reads the computing power information of the neighboring computing power node from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power node.

[0660] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0661] Receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

[0662] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0663] A first computing power discovery request is sent to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0664] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0665] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0666] The task decomposition information corresponding to the multiple computing subtasks is sent to the neighboring computing nodes.

[0667] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0668] The system receives task decomposition information corresponding to multiple computing subtasks sent by the master computing power node. These multiple computing subtasks are obtained by the master computing power node decomposing the computing power task corresponding to the computing power resource request; or...

[0669] The system receives task decomposition information corresponding to multiple computing power subtasks sent by the first NF, wherein the multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

[0670] In one embodiment, the task breakdown information includes at least one of the following:

[0671] The computing power task identifier of the computing power task;

[0672] The computing power requirements of the computing power task;

[0673] The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

[0674] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0675] The system receives a subtask acceptance response from the neighboring computing power node in response to the task decomposition information. The subtask acceptance response carries the computing power information of the neighboring computing power node.

[0676] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0677] Send computing task decomposition negotiation confirmation information to the neighboring computing power nodes.

[0678] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0679] Receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

[0680] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0681] Send a computing resource request to the target computing node;

[0682] The target computing power node receives a computing power resource response sent in response to the computing power resource request. The computing power resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing power resource request.

[0683] In one embodiment, if the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

[0684] In one embodiment, if the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

[0685] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0686] Obtain the computing power information of the neighboring computing power nodes and send the computing power information of the neighboring computing power nodes to the target computing power node.

[0687] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0688] The system receives a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

[0689] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0690] The system receives a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

[0691] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0692] Send a second computing power information request to the neighboring computing power nodes;

[0693] Receive the computing power information of the neighboring computing power node sent in response to the second computing power information request.

[0694] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0695] The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

[0696] In one embodiment, when the computer program is executed by the processor, it specifically implements the following steps:

[0697] The computing power information of the neighboring computing power nodes is read from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF historically monitoring the neighboring computing power node.

[0698] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0699] Generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

[0700] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0701] The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks;

[0702] The task decomposition information corresponding to the multiple computing power subtasks is sent to the neighboring computing power nodes and the target computing power node.

[0703] In one embodiment, the computer program, when executed by a processor, further performs the following steps:

[0704] The computing resource response is sent to the second NF, and the computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

[0705] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0706] The target computing node receives a computing resource response from the second NF. The computing resource response is sent to the first NF by the target computing node based on the computing power information of the neighboring computing nodes, and then forwarded to the second NF by the first NF. The computing power information of the neighboring computing nodes is obtained by the target computing node when it does not meet the computing power requirements corresponding to the computing resource request.

[0707] Based on the computing power resource response, a service session is established to reach the target computing power node via the neighboring computing power nodes.

[0708] Figure 17 This is a schematic structural diagram of the chip according to an embodiment of this application. Figure 17 The chip 1700 shown includes a processor 1710, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0709] Optionally, such as Figure 17 As shown, chip 1700 may further include memory 1720. Processor 1710 can retrieve and run computer programs from memory 1720 to implement the methods described in this embodiment.

[0710] The memory 1720 can be a separate device independent of the processor 1710, or it can be integrated into the processor 1710.

[0711] Optionally, the chip 1700 may also include an input interface 1730. The processor 1710 can control the input interface 1730 to communicate with other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0712] Optionally, the chip 1700 may also include an output interface 1740. The processor 1710 can control the output interface 1740 to communicate with other devices or chips, specifically, to output information or data to other devices or chips.

[0713] Optionally, the chip 1700 can be applied to the passive IoT terminal, base station or core network equipment in the embodiments of this application, and the chip 1700 can implement the corresponding processes implemented in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0714] It should be understood that the chip 1700 mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0715] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0716] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0717] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A computing power negotiation method, characterized in that, For target computing nodes, the method includes: Receive the computing resource request sent by the first NF; If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, then obtain the computing power information of the neighboring computing power nodes; Based on the computing power information of the neighboring computing power nodes, a computing power resource response is sent to the first NF.

2. The method according to claim 1, characterized in that, If the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

3. The method according to claim 1, characterized in that, If the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

4. The method according to any one of claims 1-3, characterized in that, The computing power information includes computing power node identifiers and computing power attribute information, wherein the computing power attribute information includes at least one of the following: Computing node types; The service location range of computing power nodes; Computing node service time; Supported business types; Business identifiers that support the business; Supported application types; Supported application identifiers; Support capability information; Calculate force and force information; Description of computing power usage.

5. The method according to claim 1, characterized in that, The computing power resource request includes computing power service type requirements and / or computing power resource requirements.

6. The method according to claim 1, characterized in that, The acquisition of computing power information of neighboring computing power nodes includes: The system receives a first computing power notification sent by the neighboring computing power node, the first computing power notification carrying the computing power information of the neighboring computing power node.

7. The method according to claim 1, characterized in that, The acquisition of computing power information of neighboring computing power nodes includes: Send a first computing power information request to the neighboring computing power nodes; Receive the computing power information of the neighboring computing power nodes sent in response to the first computing power information request.

8. The method according to claim 7, characterized in that, When the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement; If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

9. The method according to claim 7, characterized in that, After sending the first computing power information request to the neighboring computing power node, the method further includes: If a response rejection message is received from the neighboring computing power node, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

10. The method according to claim 7, characterized in that, After sending the first computing power information request to the neighboring computing power node, the method further includes: If no computing power information is received from the neighboring computing power node within a preset time period, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

11. The method according to claim 1, characterized in that, The acquisition of computing power information of neighboring computing power nodes includes: The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

12. The method according to claim 1, characterized in that, The acquisition of computing power information of neighboring computing power nodes includes: The target computing node reads the computing power information of the neighboring computing power node from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power node.

13. The method according to claim 1, characterized in that, The acquisition of computing power information of neighboring computing power nodes includes: Receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

14. The method according to claim 13, characterized in that, The method further includes: A first computing power discovery request is sent to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

15. The method according to claim 3, characterized in that, The method further includes: The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks; The task decomposition information corresponding to the multiple computing subtasks is sent to the neighboring computing nodes.

16. The method according to claim 3, characterized in that, The method further includes: The system receives task decomposition information corresponding to multiple computing subtasks sent by the master computing power node. These multiple computing subtasks are obtained by the master computing power node decomposing the computing power task corresponding to the computing power resource request; or... The system receives task decomposition information corresponding to multiple computing power subtasks sent by the first NF, wherein the multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

17. The method according to claim 15 or 16, characterized in that, The task breakdown information includes at least one of the following: The computing power task identifier of the computing power task; The computing power requirements of the computing power task; The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

18. The method according to claim 15, characterized in that, The method further includes: The system receives a subtask acceptance response from the neighboring computing power node in response to the task decomposition information. The subtask acceptance response carries the computing power information of the neighboring computing power node.

19. The method according to claim 18, characterized in that, The method further includes: Send computing task decomposition negotiation confirmation information to the neighboring computing power nodes.

20. The method according to claim 15, characterized in that, The method further includes: Receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

21. A computing power negotiation method, characterized in that, For the first NF, the method includes: Send a computing resource request to the target computing node; The target computing power node receives a computing power resource response sent in response to the computing power resource request. The computing power resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing power resource request.

22. The method according to claim 21, characterized in that, If the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

23. The method according to claim 21, characterized in that, If the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

24. The method according to claim 21, characterized in that, The method further includes: Obtain the computing power information of the neighboring computing power nodes and send the computing power information of the neighboring computing power nodes to the target computing power node.

25. The method according to claim 24, characterized in that, Before obtaining the computing power information of the neighboring computing power nodes, the method further includes: The system receives a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

26. The method according to claim 24, characterized in that, The step of obtaining the computing power information of the neighboring computing power nodes includes: The system receives a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

27. The method according to claim 24, characterized in that, The step of obtaining the computing power information of the neighboring computing power nodes includes: Send a second computing power information request to the neighboring computing power nodes; Receive the computing power information of the neighboring computing power node sent in response to the second computing power information request.

28. The method according to claim 24, characterized in that, The step of obtaining the computing power information of the neighboring computing power nodes includes: The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

29. The method according to claim 24, characterized in that, The step of obtaining the computing power information of the neighboring computing power nodes includes: The computing power information of the neighboring computing power nodes is read from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF historically monitoring the neighboring computing power node.

30. The method according to claim 24, characterized in that, The method further includes: Generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

31. The method according to claim 23, characterized in that, The method further includes: The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks; The task decomposition information corresponding to the multiple computing power subtasks is sent to the neighboring computing power nodes and the target computing power node.

32. The method according to claim 21, characterized in that, The method further includes: The computing resource response is sent to the second NF, and the computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

33. A computing power negotiation method, characterized in that, For the third NF, the method includes: The target computing node receives a computing resource response from the second NF. The computing resource response is sent to the first NF by the target computing node based on the computing power information of the neighboring computing nodes, and then forwarded to the second NF by the first NF. The computing power information of the neighboring computing nodes is obtained by the target computing node when it does not meet the computing power requirements corresponding to the computing resource request. Based on the computing power resource response, a service session is established to reach the target computing power node via the neighboring computing power nodes.

34. A computing power negotiation device, characterized in that, For a target computing node, the device includes: The receiving module is used to receive the computing resource request sent by the first NF; The acquisition module is used to acquire computing power information of neighboring computing power nodes if the target computing power node does not meet the computing power requirements corresponding to the computing power resource request. The response module is used to send a computing resource response to the first NF based on the computing power information of the neighboring computing power nodes.

35. The apparatus according to claim 34, characterized in that, If the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

36. The apparatus according to claim 34, characterized in that, If the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

37. The apparatus according to any one of claims 34-36, characterized in that, The computing power information includes computing power node identifiers and computing power attribute information, wherein the computing power attribute information includes at least one of the following: Computing node types; The service location range of computing power nodes; Computing node service time; Supported business types; Business identifiers that support the business; Supported application types; Supported application identifiers; Support capability information; Calculate force and force information; Description of computing power usage.

38. The apparatus according to claim 34, characterized in that, The computing power resource request includes computing power service type requirements and / or computing power resource requirements.

39. The apparatus according to claim 34, characterized in that, The acquisition module is specifically used to receive a first computing power announcement sent by the neighboring computing power node, wherein the first computing power announcement carries the computing power information of the neighboring computing power node.

40. The apparatus according to claim 34, characterized in that, The acquisition module is specifically used to send a first computing power information request to the neighboring computing power node; and to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the first computing power information request.

41. The apparatus according to claim 40, characterized in that, When the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement; If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

42. The apparatus according to claim 40, characterized in that, After sending the first computing power information request to the neighboring computing power node, the acquisition module is further configured to determine that the neighboring computing power node does not support shared computing power and acquire the computing power information of other neighboring computing power nodes if it receives a response rejection message sent by the neighboring computing power node.

43. The apparatus according to claim 40, characterized in that, After sending the first computing power information request to the neighboring computing power node, the acquisition module is further configured to determine that the neighboring computing power node does not support shared computing power if it does not receive the computing power information sent by the neighboring computing power node within a preset time period, and to acquire the computing power information of other neighboring computing power nodes.

44. The apparatus according to claim 34, characterized in that, The acquisition module is specifically used to monitor the computing power information of the neighboring computing power nodes in real time or periodically.

45. The apparatus according to claim 34, characterized in that, The acquisition module is specifically used to read the computing power information of the neighboring computing power nodes from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power nodes.

46. ​​The apparatus according to claim 34, characterized in that, The acquisition module is specifically used to receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

47. The apparatus according to claim 46, characterized in that, The acquisition module is further configured to send a first computing power discovery request to the master computing power node or the first NF, wherein the first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

48. The apparatus according to claim 36, characterized in that, The device further includes: The task decomposition module is used to decompose the computing power task corresponding to the computing power resource request into multiple computing power sub-tasks. The sending module is used to send the task decomposition information corresponding to the multiple computing power subtasks to the neighboring computing power nodes.

49. The apparatus according to claim 36, characterized in that, The receiving module is further configured to receive task decomposition information corresponding to multiple computing subtasks sent by the master control computing power node, wherein the multiple computing subtasks are obtained by the master control computing power node decomposing the computing power task corresponding to the computing power resource request; or... The receiving module is further configured to receive task decomposition information corresponding to multiple computing power subtasks sent by the first NF, wherein the multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

50. The apparatus according to claim 48 or 49, characterized in that, The task breakdown information includes at least one of the following: The computing power task identifier of the computing power task; The computing power requirements of the computing power task; The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

51. The apparatus according to claim 48, characterized in that, The receiving module is further configured to receive a subtask acceptance response returned by the neighboring computing power node in response to the task decomposition information, wherein the subtask acceptance response carries the computing power information of the neighboring computing power node.

52. The apparatus according to claim 51, characterized in that, The sending module is also used to send computing power task decomposition negotiation confirmation information to the neighboring computing power nodes.

53. The apparatus according to claim 48, characterized in that, The receiving module is also used to receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

54. A computing power negotiation device, characterized in that, For the first NF, the device includes: The sending module is used to send computing resource requests to the target computing power node; The receiving module is configured to receive a computing resource response sent by the target computing power node in response to the computing resource request. The computing resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing resource request.

55. The apparatus according to claim 54, characterized in that, If the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

56. The apparatus according to claim 54, characterized in that, If the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

57. The apparatus according to claim 54, characterized in that, The device further includes: The acquisition module is used to acquire the computing power information of the neighboring computing power nodes; The sending module is also used to send the computing power information of the neighboring computing power nodes to the target computing power node.

58. The apparatus according to claim 57, characterized in that, Before obtaining the computing power information of the neighboring computing power nodes, the receiving module is further configured to receive a second computing power discovery request sent by the target computing power node, the second computing power discovery request being used to request the computing power information of the neighboring computing power nodes.

59. The apparatus according to claim 57, characterized in that, The acquisition module is specifically used to receive a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

60. The apparatus according to claim 57, characterized in that, The acquisition module is specifically used to send a second computing power information request to the neighboring computing power node; and to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the second computing power information request.

61. The apparatus according to claim 57, characterized in that, The acquisition module is specifically used to monitor the computing power information of the neighboring computing power nodes in real time or periodically.

62. The apparatus according to claim 57, characterized in that, The acquisition module is specifically used to read the computing power information of the neighboring computing power nodes from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the first NF historically monitoring the neighboring computing power node.

63. The apparatus according to claim 57, characterized in that, The device further includes: A generation module is used to generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

64. The apparatus according to claim 56, characterized in that, The device further includes: The task decomposition module is used to decompose the computing power task corresponding to the computing power resource request into multiple computing power sub-tasks. The sending module is also used to send the task decomposition information corresponding to the multiple computing power subtasks to the neighboring computing power nodes and the target computing power node.

65. The apparatus according to claim 54, characterized in that, The sending module is also used to send the computing power resource response to the second NF, the computing power resource response being used by the second NF to send the computing power resource response to the third NF, the computing power resource response being used by the third NF to establish a service session that reaches the target computing power node through the neighboring computing power nodes.

66. A computing power negotiation device, characterized in that, For use in a third NF, the device includes: The receiving module is used to receive the computing power resource response sent by the second NF. The computing power resource response is sent by the target computing power node to the first NF according to the computing power information of the neighboring computing power nodes, and then forwarded by the first NF to the second NF. The computing power information of the neighboring computing power nodes is obtained by the target computing power node when the computing power requirement corresponding to the computing power resource request is not met. The session establishment module is used to establish a service session that reaches the target computing power node through the neighboring computing power nodes based on the computing power resource response.

67. A target computing power node, characterized in that, Includes memory, transceiver, and processor: A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: Control the transceiver to receive the computing resource request sent by the first NF; If the target computing power node does not meet the computing power requirements corresponding to the computing power resource request, then obtain the computing power information of the neighboring computing power nodes; Based on the computing power information of the neighboring computing power nodes, the transceiver is controlled to send a computing power resource response to the first NF.

68. The target computing node according to claim 67, characterized in that, If the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

69. The target computing node according to claim 67, characterized in that, If the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

70. The target computing node according to any one of claims 67-69, characterized in that, The computing power information includes computing power node identifiers and computing power attribute information, wherein the computing power attribute information includes at least one of the following: Computing node types; The service location range of computing power nodes; Computing node service time; Supported business types; Business identifiers that support the business; Supported application types; Supported application identifiers; Support capability information; Calculate force and force information; Description of computing power usage.

71. The target computing node according to claim 67, characterized in that, The computing power resource request includes computing power service type requirements and / or computing power resource requirements.

72. The target computing node according to claim 67, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: The transceiver is controlled to receive a first computing power notification sent by the neighboring computing power node, the first computing power notification carrying the computing power information of the neighboring computing power node.

73. The target computing node according to claim 67, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: Control the transceiver to send a first computing power information request to the nearby computing power node; The transceiver is controlled to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the first computing power information request.

74. The target computing node according to claim 73, characterized in that, When the first computing power information request carries a computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power node to return computing power information corresponding to the computing power discovery requirement; If the first computing power information request does not carry the computing power discovery requirement, the first computing power information request is used to instruct the neighboring computing power nodes to return all computing power information.

75. The target computing node according to claim 73, characterized in that, After sending the first computing power information request to the neighboring computing power node, the processor reads the computer program in the memory and further performs the following operations: If a response rejection message is received from the neighboring computing power node, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

76. The target computing node according to claim 73, characterized in that, After sending the first computing power information request to the neighboring computing power node, the processor reads the computer program in the memory and further performs the following operations: If no computing power information is received from the neighboring computing power node within a preset time period, it is determined that the neighboring computing power node does not support shared computing power, and the computing power information of other neighboring computing power nodes is obtained.

77. The target computing node according to claim 67, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

78. The target computing node according to claim 67, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: The target computing node reads the computing power information of the neighboring computing power node from the first storage location. The first storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the target computing power node through historical monitoring of the neighboring computing power node.

79. The target computing node according to claim 67, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: The transceiver is controlled to receive computing power information of the neighboring computing power nodes sent by the master computing power node or the first NF.

80. The target computing node according to claim 79, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The transceiver is controlled to send a first computing power discovery request to the master computing power node or the first NF. The first computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

81. The target computing node according to claim 69, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks; The transceiver is controlled to send the task decomposition information corresponding to the multiple computing subtasks to the neighboring computing nodes.

82. The target computing node according to claim 69, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The transceiver is controlled to receive task decomposition information corresponding to multiple computing subtasks sent by the master computing power node. The multiple computing subtasks are obtained by the master computing power node decomposing the computing power task corresponding to the computing power resource request. or, The transceiver is controlled to receive task decomposition information corresponding to multiple computing power subtasks sent by the first NF. The multiple computing power subtasks are obtained by the first NF decomposing the computing power task corresponding to the computing power resource request.

83. The target computing node according to claim 81 or 82, characterized in that, The task breakdown information includes at least one of the following: The computing power task identifier of the computing power task; The computing power requirements of the computing power task; The computing power subtask information list includes computing power node identifiers, computing power subtask identifiers for each computing power subtask, computing power requirement information for each computing power subtask, and network requirement information for each computing power subtask.

84. The target computing node according to claim 81, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The transceiver is controlled to receive the subtask acceptance response returned by the neighboring computing power node in response to the task decomposition information. The subtask acceptance response carries the computing power information of the neighboring computing power node.

85. The target computing node according to claim 84, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The transceiver is controlled to send computing task decomposition negotiation confirmation information to the neighboring computing power nodes.

86. The target computing node according to claim 81, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The transceiver is controlled to receive the subtask rejection response returned by the neighboring computing power node in response to the task decomposition information.

87. A network function, characterized in that, Includes memory, transceiver, and processor: A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: Control the transceiver to send a computing resource request to the target computing node; The transceiver is controlled to receive the computing resource response sent by the target computing power node in response to the computing resource request. The computing resource response is sent by the target computing power node based on the computing power information of neighboring computing power nodes. The computing power information of neighboring computing power nodes is obtained by the target computing power node when it does not meet the computing power requirements corresponding to the computing resource request.

88. The network function according to claim 87, characterized in that, If the target computing power node does not meet all the computing power requirements corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes.

89. The network function according to claim 87, characterized in that, If the target computing power node does not meet part of the computing power requirement corresponding to the computing power resource request, the computing power resource response includes the computing power information of the neighboring computing power nodes and the computing power information of the target computing power node.

90. The network function according to claim 87, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The system acquires the computing power information of the neighboring computing power nodes and controls the transceiver to send the computing power information of the neighboring computing power nodes to the target computing power node.

91. The network function according to claim 90, characterized in that, Before acquiring the computing power information of the neighboring computing power nodes, the processor reads the computer program in the memory and also performs the following operations: The transceiver is controlled to receive a second computing power discovery request sent by the target computing power node. The second computing power discovery request is used to request the computing power information of the neighboring computing power nodes.

92. The network function according to claim 90, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: The transceiver is controlled to receive a second computing power notification sent by the neighboring computing power node, the second computing power notification carrying the computing power information of the neighboring computing power node.

93. The network function according to claim 90, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: Control the transceiver to send a second computing power information request to the nearby computing power node; The transceiver is controlled to receive the computing power information of the neighboring computing power node sent by the neighboring computing power node in response to the second computing power information request.

94. The network function according to claim 90, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: The computing power information of the neighboring computing power nodes is monitored in real time or periodically.

95. The network function according to claim 90, characterized in that, The processor is used to read the computer program in the memory and specifically perform the following operations: The computing power information of the neighboring computing power nodes is read from the second storage location. The second storage location stores the mapping relationship between the computing power node identifier of the neighboring computing power node and the computing power information of the neighboring computing power node. The computing power information of the neighboring computing power node is obtained by the network function historically monitoring the neighboring computing power node.

96. The network function according to claim 90, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: Generate proximity relationships for the neighboring computing power nodes, wherein the proximity relationships include the mapping relationship between the neighboring computing power nodes and the target computing power node.

97. The network function according to claim 89, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The computing power task corresponding to the computing power resource request is decomposed into multiple computing power sub-tasks; The transceiver is controlled to send the task decomposition information corresponding to the multiple computing subtasks to the neighboring computing nodes and the target computing node.

98. The network function according to claim 87, characterized in that, The processor is used to read the computer program in the memory and also performs the following operations: The transceiver is controlled to send the computing resource response to the second NF. The computing resource response is used by the second NF to send the computing resource response to the third NF. The computing resource response is used by the third NF to establish a service session that reaches the target computing node through the neighboring computing nodes.

99. A network function, characterized in that, Includes memory, transceiver, and processor: A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: The transceiver is controlled to receive the computing power resource response sent by the second NF. The computing power resource response is sent by the target computing power node to the first NF according to the computing power information of the neighboring computing power nodes, and then forwarded by the first NF to the second NF. The computing power information of the neighboring computing power nodes is obtained by the target computing power node when the computing power requirement corresponding to the computing power resource request is not met. Based on the computing power resource response, a service session is established to reach the target computing power node via the neighboring computing power nodes.

100. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 33.

101. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 33.

Images