Communication method, communication device, communication system, storage medium, and program product

Abstract

The embodiment of the invention relates to a communication method, communication equipment, a communication system, a storage medium and a program product. The communication method can be executed by a first node, and the method comprises the following steps: obtaining first information, the first information being used for requesting a first artificial intelligence (AI) reasoning service; determining a second node for providing the first AI reasoning service according to the first information; and sending second information, wherein the second information is used for indicating the second node to provide the first AI reasoning service. According to the method and the device, the second node is matched with the first information, so that the second node can meet the requirements of the first AI reasoning service on the computing power and the resources and does not bring extra delay.

Description

Communication method, communication device, communication system, storage medium and program product TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and in particular to a communication method, a communication device, a communication system, a storage medium and a program product. BACKGROUND

[0002] With the progress of communication technology, artificial intelligence (AI) models, machine learning (ML) models or other models are introduced in communication systems. Through these models, data reasoning or prediction can be performed in scenarios such as autonomous driving, medical assistance, cross-device computing, digital twinning, etc.

[0003] SUMMARY

[0004] In the process of model reasoning, on the one hand, due to the limited computing capability of the terminal, the terminal cannot support reasoning services beyond its own computing capability; on the other hand, although a third-party server can be used to provide reasoning services for the terminal, this will also bring additional delay, affecting user experience.

[0005] The present disclosure provides a communication method, a communication device, a communication system, a storage medium and a program product.

[0006] According to a first aspect of the present disclosure, a communication method is provided, which is performed by a first node, and the method comprises: obtaining first information, the first information being used to request a first artificial intelligence (AI) reasoning service; determining, according to the first information, a second node used to provide the first AI reasoning service; and sending second information, the second information being used to instruct the second node to provide the first AI reasoning service.

[0007] According to a second aspect of the present disclosure, a communication method is provided, which is performed by a second node, and the method comprises: receiving second information sent by a first node, the second information being used to instruct the second node to provide a first AI reasoning service, the second node being determined by the first node according to first information, the first information being used to request the first AI reasoning service.

[0008] According to a third aspect of the present disclosure, a communication method is provided, which is performed by a fourth node, and the method comprises: sending first information to a first node, the first information being used to request a first AI reasoning service, the first AI reasoning service being provided by a second node, the second node being determined by the first node according to the first information.

[0009] According to a fourth aspect of embodiments of the present disclosure, a first node is provided, including: a first transceiver configured to obtain first information, the first information being used to request a first artificial intelligence, AI, inference service; and transmit second information, the second information being used to indicate that a second node provides the first AI inference service; and a first processing module configured to determine, according to the first information, the second node used to provide the first AI inference service.

[0010] According to a fifth aspect of embodiments of the present disclosure, a second node is provided, including: a second transceiver configured to receive second information transmitted by a first node, the second information being used to indicate that the second node provides a first AI inference service, the second node being determined by the first node according to first information, the first information being used to request the first AI inference service.

[0011] According to a sixth aspect of embodiments of the present disclosure, a fourth node is provided, including: a third transceiver configured to transmit first information to a first node, the first information being used to request a first AI inference service, the first AI inference service being provided by a second node, the second node being determined by the first node according to the first information.

[0012] According to a seventh aspect of embodiments of the present disclosure, a communication device is provided, including: one or more processors; and wherein the communication device is configured to perform the communication method according to any one of the first aspect to the third aspect.

[0013] According to an eighth aspect of embodiments of the present disclosure, a communication system is provided, including a first node, a second node, and a fourth node; the first node is configured to implement the communication method according to the first aspect; the second node is configured to implement the communication method according to the second aspect; and the fourth node is configured to implement the communication method according to the third aspect.

[0014] According to a ninth aspect of embodiments of the present disclosure, a storage medium is provided, the storage medium storing instructions, when the instructions are executed on a communication device, causing the communication device to perform the communication method according to any one of the first aspect to the third aspect.

[0015] According to a tenth aspect of embodiments of the present disclosure, a computer program product is provided, including a computer program, when the computer program is executed by a processor, implementing the communication method according to any one of the first aspect to the third aspect.

[0016] According to an eleventh aspect of embodiments of the present disclosure, a computer program is provided, the computer program including code, when the code is executed by a processor, implementing the communication method according to any one of the first aspect to the third aspect.

[0017] According to a twelfth aspect of the embodiments of the present disclosure, a chip or a chip system is provided, which includes processing circuitry configured to perform the communication method according to any one of the first aspect to the third aspect.

[0018] According to the embodiments of the present disclosure, the first node determines the second node for providing the first AI inference service according to the first information for requesting the first AI inference service, and then sends the second information to instruct the second node to provide the first AI inference service. Since the second node is matched with the first information, the second node can meet the requirements of the first AI inference service for computing capability and resources, and will not bring additional delay. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following describes the drawings required for the embodiments, and the following drawings are only some embodiments of the present disclosure, and do not specifically limit the protection scope of the present disclosure.

[0020] FIG. 1A is a schematic architecture diagram of a communication system according to an embodiment of the present disclosure.

[0021] FIG. 1B is a service architecture schematic diagram of an AI inference service facing 6G according to an embodiment of the present disclosure.

[0022] FIG. 2 is an interaction schematic diagram of a communication method according to an embodiment of the present disclosure.

[0023] FIG. 3A is a flow schematic diagram of an AIISF performing a communication method according to an embodiment of the present disclosure.

[0024] FIG. 3B is a flow schematic diagram of an inference node A performing a communication method according to an embodiment of the present disclosure.

[0025] FIG. 3C is a flow schematic diagram of a terminal A performing a communication method according to an embodiment of the present disclosure.

[0026] FIG. 4A is a flow schematic diagram of a first node performing a communication method according to an embodiment of the present disclosure.

[0027] FIG. 4B is a flow schematic diagram of a second node performing a communication method according to an embodiment of the present disclosure.

[0028] FIG. 4C is a flow schematic diagram of a fourth node performing a communication method according to an embodiment of the present disclosure.

[0029] FIG. 5A is a structural schematic diagram of a first node according to an embodiment of the present disclosure.

[0030] FIG. 5B is a structural schematic diagram of a second node according to an embodiment of the present disclosure.

[0031] FIG. 5C is a structural schematic diagram of a fourth node according to an embodiment of the present disclosure.

[0032] FIG. 6 is a structural schematic diagram of a communication device according to an embodiment of the present disclosure.

[0033] FIG. 7 is a structural schematic diagram of a chip according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] Embodiments of the present disclosure provide a communication method, a communication device, a communication system, a storage medium and a program product.

[0035] In a first aspect, embodiments of the present disclosure provide a communication method performed by a first node, the method comprising: obtaining first information, the first information being used to request a first artificial intelligence (AI) inference service; determining, according to the first information, a second node used to provide the first AI inference service; and sending second information, the second information being used to instruct the second node to provide the first AI inference service.

[0036] In embodiments of the present disclosure, the first node determines the second node that meets the requirements of the first information, and controls the second node to provide the first AI inference service through the second information. In this way, the second node can meet the requirements of the first AI inference service on computing power and resources, and will not bring additional delay.

[0037] In some embodiments in combination with the first aspect, in some embodiments, the first information comprises at least one of: first indication information used to indicate a fourth node requesting the first AI inference service; second indication information used to indicate quality requirements of the first AI inference service; third indication information used to indicate model requirements of the first AI inference service; fourth indication information used to indicate a type of the first AI inference service; fifth indication information used to indicate a location of the fourth node; and sixth indication information used to indicate a service area of the first AI inference service.

[0038] In some embodiments in combination with the first aspect, in some embodiments, determining, according to the first information, the second node used to provide the first AI inference service comprises: determining, according to the first information and third information associated with a plurality of third nodes, the second node from the plurality of third nodes; wherein the plurality of third nodes are nodes used to provide AI inference services.

[0039] In some embodiments in combination with the first aspect, in some embodiments, the third information comprises at least one of: seventh indication information used to indicate support capabilities of the third node for different types of AI inference services; eighth indication information used to indicate support capabilities of the third node for AI models; ninth indication information used to indicate resources of the third node for processing AI inference services; and tenth indication information used to indicate a location of the third node.

[0040] In some embodiments of the first aspect, according to the first information, the second node for providing the first AI inference service is determined, including: according to the first information and eleventh indication information, the second node is determined; wherein the eleventh indication information is used to indicate a mapping relationship between the type of the AI inference service and the second node.

[0041] In some embodiments of the first aspect, the method further includes one of: according to the first information, a first inference method adopted by the first AI inference service is determined; according to the first information and twelfth indication information, the first inference method adopted by the first AI inference service is determined; wherein the twelfth indication information is used to indicate a mapping relationship between the type of the AI inference service and the inference method.

[0042] In the embodiments of the present disclosure, the first information is not only used to determine the matched second node, but also used to determine the appropriate first inference method, so that the second node can provide the first AI inference service more quickly, and the user experience is improved.

[0043] In some embodiments of the first aspect, the second information is further used to indicate that the second node provides the first AI inference service by adopting the first inference method.

[0044] In some embodiments of the first aspect, the number of the second nodes is multiple, and the method further includes: determining multiple inference tasks associated with the first AI inference service; and assigning the multiple inference tasks to the multiple second nodes.

[0045] In the embodiments of the present disclosure, the first AI inference service is completed by the multiple second nodes, which can further improve the speed of the second node to provide the first AI inference service, and improve the user experience of the terminal.

[0046] In some embodiments of the first aspect, the second information includes at least one of: the first information; thirteenth indication information used to indicate the first AI inference service; fourteenth indication information used to indicate the multiple inference tasks associated with the first AI inference service; and fifteenth indication information used to indicate the first inference method adopted by the first AI inference service.

[0047] In some embodiments of the first aspect, the second information is further used to request the establishment of a data connection between the second node and a fourth node.

[0048] In some embodiments of the first aspect, the method further includes: receiving fourth information sent by the second node, the fourth information being used to indicate an access address of the second node; and sending fifth information to the fourth node, the fifth information including the fourth information.

[0049] In some embodiments of the first aspect, the number of the second nodes is multiple, and the fifth information further includes: sixteenth indication information, used to indicate a mapping relationship between the inference task associated with the first AI inference service and the second nodes.

[0050] In some embodiments of the first aspect, the first node and the second node are deployed on a same device.

[0051] In the second aspect, the embodiments of the present disclosure provide a communication method, executed by a second node, and the method includes: receiving second information sent by a first node, the second information being used to indicate that the second node provides a first AI inference service, and the second node being determined by the first node according to first information, the first information being used to request the first AI inference service.

[0052] In some embodiments of the second aspect, the first information includes at least one of: first indication information, used to indicate a fourth node requesting the first AI inference service; second indication information, used to indicate a quality requirement of the first AI inference service; third indication information, used to indicate a model requirement of the first AI inference service; fourth indication information, used to indicate a type of the first AI inference service; fifth indication information, used to indicate a location of the fourth node; and sixth indication information, used to indicate a service area of the first AI inference service.

[0053] In some embodiments of the second aspect, the second node is determined by the first node from a plurality of third nodes according to the first information and third information associated with the plurality of third nodes, and the plurality of third nodes are nodes used to provide AI inference services.

[0054] In some embodiments of the second aspect, the third information includes at least one of: seventh indication information, used to indicate a support capability of the second node for different types of AI inference services; eighth indication information, used to indicate a support capability of the second node for AI models; ninth indication information, used to indicate a resource of the second node for processing AI inference services; and tenth indication information, used to indicate a location of the second node.

[0055] In some embodiments of the second aspect, the second node is determined by the first node according to the first information and eleventh indication information, and the eleventh indication information is used to indicate a mapping relationship between a type of the AI inference service and the second node.

[0056] In some embodiments of the second aspect, the second information is further used to indicate that the second node provides the first AI inference service by using a first inference method.

[0057] In some embodiments of the second aspect, in some embodiments, the first inference method is obtained based on the first information, or the first inference method is obtained based on the first information and twelfth indication information, the twelfth indication information being used to indicate a mapping relationship between a type of the AI inference service and the inference method.

[0058] In some embodiments of the second aspect, in some embodiments, the second information is further used to request the establishment of the data connection between the second node and the fourth node.

[0059] In some embodiments of the second aspect, in some embodiments, the second information includes at least one of the following: the first information; thirteenth indication information used to indicate the first AI inference service; fourteenth indication information used to indicate a plurality of inference tasks associated with the first AI inference service; and fifteenth indication information used to indicate the first inference method adopted by the first AI inference service.

[0060] In some embodiments of the second aspect, in some embodiments, the method further includes: sending fourth information to the first node, the fourth information being used to indicate an access address of the second node.

[0061] In some embodiments of the second aspect, in some embodiments, the method further includes: receiving inference data sent by the fourth node; and performing AI inference based on the inference data to obtain an inference result.

[0062] In some embodiments of the second aspect, in some embodiments, the method further includes: sending the inference result to the fourth node, the inference result being used by the fourth node to determine the first inference result of the first AI inference service.

[0063] In some embodiments of the second aspect, in some embodiments, the first node and the second node are deployed on the same device.

[0064] In a third aspect, the embodiments of the present disclosure provide a communication method, the method being performed by a fourth node, and the method further includes: sending first information to a first node, the first information being used to request a first AI inference service, the first AI inference service being provided by a second node, the second node being determined by the first node according to the first information.

[0065] In some embodiments of the third aspect, in some embodiments, the first information includes at least one of the following: first indication information used to indicate the fourth node requesting the first AI inference service; second indication information used to indicate a quality requirement of the first AI inference service; third indication information used to indicate a model requirement of the first AI inference service; fourth indication information used to indicate a type of the first AI inference service; fifth indication information used to indicate a location of the fourth node; and sixth indication information used to indicate a service area of the first AI inference service.

[0066] In some embodiments of the third aspect, in some embodiments, the second node is determined by the first node from a plurality of third nodes according to the first information and third information associated with the plurality of third nodes, the plurality of third nodes being nodes for providing the AI inference service.

[0067] In some embodiments of the third aspect, in some embodiments, the third information includes at least one of: seventh indication information indicating support capabilities of the third node for different types of AI inference services; eighth indication information indicating support capabilities of the third node for AI models; ninth indication information indicating resources of the third node for processing the AI inference service; and tenth indication information indicating a location of the third node.

[0068] In some embodiments of the third aspect, in some embodiments, the second node is determined by the first node according to the first information and eleventh indication information indicating a mapping relationship between a type of the AI inference service and the second node.

[0069] In some embodiments of the third aspect, in some embodiments, the method further includes: receiving fifth information sent by the first node, the fifth information including fourth information indicating an access address of the second node; and sending inference data to the second node based on the fifth information.

[0070] In some embodiments of the third aspect, in some embodiments, the number of the second nodes is a plurality, and the fifth information further includes: sixteenth indication information indicating a mapping relationship between an inference task associated with the first AI inference service and the second node.

[0071] In some embodiments of the third aspect, in some embodiments, the method further includes: receiving inference results sent by the second node; and determining a first inference result of the first AI inference service based on the inference results.

[0072] In some embodiments of the third aspect, in some embodiments, the number of the second nodes is a plurality, and the first inference result is determined based on inference results sent by the plurality of second nodes.

[0073] In some embodiments of the third aspect, in some embodiments, the method further includes: merging the inference results sent by the plurality of second nodes to obtain the first inference result.

[0074] In a fourth aspect, the embodiments of the present disclosure provide a first node, including: a first receiving module configured to obtain first information, the first information being used to request a first artificial intelligence (AI) inference service; and send second information, the second information being used to indicate that a second node provides the first AI inference service; and a first processing module configured to determine the second node for providing the first AI inference service according to the first information.

[0075] In some embodiments of the fourth aspect, in some embodiments, the first information comprises at least one of: first indication information indicating a fourth node requesting the first AI inference service; second indication information indicating a quality requirement of the first AI inference service; third indication information indicating a model requirement of the first AI inference service; fourth indication information indicating a type of the first AI inference service; fifth indication information indicating a location of the fourth node; and sixth indication information indicating a service area of the first AI inference service.

[0076] In some embodiments of the fourth aspect, in some embodiments, the first processing module is further configured to determine the second node from the plurality of third nodes according to the first information and third information associated with the plurality of third nodes, wherein the plurality of third nodes are nodes configured to provide AI inference services.

[0077] In some embodiments of the fourth aspect, in some embodiments, the third information comprises at least one of: seventh indication information indicating support capabilities of the third node for different types of AI inference services; eighth indication information indicating support capabilities of the third node for AI models; ninth indication information indicating resources of the third node for processing AI inference services; and tenth indication information indicating a location of the third node.

[0078] In some embodiments of the fourth aspect, in some embodiments, the first processing module is further configured to determine the second node according to the first information and eleventh indication information, wherein the eleventh indication information indicates a mapping relationship between a type of the AI inference service and the second node.

[0079] In some embodiments of the fourth aspect, in some embodiments, the first processing module is further configured to determine one of: a first inference method adopted by the first AI inference service according to the first information; and a first inference method adopted by the first AI inference service according to the first information and twelfth indication information, wherein the twelfth indication information indicates a mapping relationship between a type of the AI inference service and the inference method.

[0080] In some embodiments of the fourth aspect, in some embodiments, the second information further indicates that the second node provides the first AI inference service using the first inference method.

[0081] In some embodiments of the fourth aspect, in some embodiments, the number of the second nodes is a plurality, and the first processing module is further configured to determine a plurality of inference tasks associated with the first AI inference service, and assign the plurality of inference tasks to the plurality of second nodes.

[0082] In some embodiments of the fourth aspect, in some embodiments, the second information comprises at least one of the following: the first information; thirteenth indication information for indicating the first AI inference service; fourteenth indication information for indicating a plurality of inference tasks associated with the first AI inference service; and fifteenth indication information for indicating a first inference method adopted by the first AI inference service.

[0083] In some embodiments of the fourth aspect, in some embodiments, the second information is further used to request the second node to establish a data connection with the fourth node.

[0084] In some embodiments of the fourth aspect, in some embodiments, the first transceiver module is further configured to: receive fourth information sent by the second node, the fourth information being used to indicate an access address of the second node; and send fifth information to the fourth node, the fifth information comprising the fourth information.

[0085] In some embodiments of the fourth aspect, in some embodiments, the number of the second nodes is a plurality, and the fifth information further comprises sixteenth indication information for indicating a mapping relationship between an inference task associated with the first AI inference service and the second nodes.

[0086] In the fifth aspect, the embodiments of the present disclosure provide a second node, comprising: a second transceiver module configured to receive second information sent by a first node, the second information being used to indicate that the second node provides a first AI inference service, and the second node being determined by the first node according to first information, the first information being used to request the first AI inference service.

[0087] In some embodiments of the fifth aspect, in some embodiments, the first information comprises at least one of the following: first indication information for indicating a fourth node requesting the first AI inference service; second indication information for indicating a quality requirement of the first AI inference service; third indication information for indicating a model requirement of the first AI inference service; fourth indication information for indicating a type of the first AI inference service; fifth indication information for indicating a location of the fourth node; and sixth indication information for indicating a service area of the first AI inference service.

[0088] In some embodiments of the fifth aspect, in some embodiments, the second node is determined by the first node from a plurality of third nodes according to the first information and third information associated with the plurality of third nodes, the plurality of third nodes being nodes for providing AI inference services.

[0089] In some embodiments of the fifth aspect, in some embodiments, the third information includes at least one of: seventh indication information indicating support capabilities of the second node for different types of AI inference services; eighth indication information indicating support capabilities of the second node for AI models; ninth indication information indicating resources of the second node for processing AI inference services; and tenth indication information indicating a location of the second node.

[0090] In some embodiments of the fifth aspect, in some embodiments, the second node is determined by the first node according to the first information and eleventh indication information, the eleventh indication information indicating a mapping relationship between the type of the AI inference service and the second node.

[0091] In some embodiments of the fifth aspect, in some embodiments, the second information further indicates that the second node provides the first AI inference service using the first inference method.

[0092] In some embodiments of the fifth aspect, in some embodiments, the first inference method is obtained based on the first information, or the first inference method is obtained based on the first information and twelfth indication information, the twelfth indication information indicating a mapping relationship between the type of the AI inference service and the inference method.

[0093] In some embodiments of the fifth aspect, in some embodiments, the second information further requests the second node to establish a data connection with the fourth node.

[0094] In some embodiments of the fifth aspect, in some embodiments, the second information includes at least one of: the first information; thirteenth indication information indicating the first AI inference service; fourteenth indication information indicating a plurality of inference tasks associated with the first AI inference service; and fifteenth indication information indicating the first inference method used by the first AI inference service.

[0095] In some embodiments of the fifth aspect, in some embodiments, the second transceiver is further configured to: send, to the first node, fourth information indicating an access address of the second node.

[0096] In some embodiments of the fifth aspect, in some embodiments, the second transceiver is further configured to: receive inference data sent by the fourth node; and perform AI inference based on the inference data to obtain an inference result.

[0097] In some embodiments of the fifth aspect, in some embodiments, the second transceiver is further configured to: send, to the fourth node, the inference result, the inference result being used by the fourth node to determine a first inference result of the first AI inference service.

[0098] In a sixth aspect, the embodiments of the present disclosure provide a fourth node, comprising: a third transceiver configured to send first information to a first node, the first information being used to request a first AI inference service, the first AI inference service being provided by a second node, the second node being determined by the first node according to the first information.

[0099] In some embodiments in combination with the sixth aspect, in some embodiments, the first information comprises at least one of: first indication information used to indicate the fourth node requesting the first AI inference service; second indication information used to indicate quality requirements of the first AI inference service; third indication information used to indicate model requirements of the first AI inference service; fourth indication information used to indicate a type of the first AI inference service; fifth indication information used to indicate a location of the fourth node; and sixth indication information used to indicate a service area of the first AI inference service.

[0100] In some embodiments in combination with the sixth aspect, in some embodiments, the second node is determined by the first node from a plurality of third nodes according to the first information and third information associated with the plurality of third nodes, the plurality of third nodes being nodes used to provide AI inference services.

[0101] In some embodiments in combination with the sixth aspect, in some embodiments, the third information comprises at least one of: seventh indication information used to indicate support capabilities of the third node for different types of AI inference services; eighth indication information used to indicate support capabilities of the third node for AI models; ninth indication information used to indicate resources of the third node for processing AI inference services; and tenth indication information used to indicate a location of the third node.

[0102] In some embodiments in combination with the sixth aspect, in some embodiments, the second node is determined by the first node according to the first information and eleventh indication information, the eleventh indication information being used to indicate a mapping relationship between a type of the AI inference service and the second node.

[0103] In some embodiments in combination with the sixth aspect, in some embodiments, the third transceiver is further configured to: receive fifth information sent by the first node, the fifth information comprising fourth information, the fourth information being used to indicate an access address of the second node; and send inference data to the second node based on the fifth information.

[0104] In some embodiments in combination with the sixth aspect, in some embodiments, the number of the second nodes is a plurality, and the fifth information further comprises: sixteenth indication information used to indicate a mapping relationship between an inference task associated with the first AI inference service and the second nodes.

[0105] In some embodiments combined with the sixth aspect, in some embodiments, the third transceiving module is further configured to: receive the inference result sent by the second node; and determine the first inference result of the first AI inference service based on the inference result.

[0106] In some embodiments combined with the sixth aspect, in some embodiments, the number of the second nodes is a plurality, and the first inference result is determined based on inference results sent by the plurality of second nodes.

[0107] In some embodiments combined with the sixth aspect, in some embodiments, the fourth node further comprises a third processing module, and the third processing module is further configured to combine the inference results sent by the plurality of second nodes to obtain the first inference result.

[0108] In a seventh aspect, the embodiments of the present disclosure provide a communication device, comprising: one or more processors; wherein the communication device is configured to perform the communication method according to any one of the first aspect to the third aspect.

[0109] In an eighth aspect, the embodiments of the present disclosure provide a communication system, comprising: a first node, a second node and a fourth node; the first node is configured to implement the communication method according to the first aspect; the second node is configured to implement the communication method according to the second aspect; and the fourth node is configured to implement the communication method according to the third aspect.

[0110] In a ninth aspect, the embodiments of the present disclosure provide a storage medium, and the storage medium stores instructions, when the instructions are executed on a communication device, the communication device performs the communication method according to any one of the first aspect to the third aspect.

[0111] In a tenth aspect, the embodiments of the present disclosure provide a program product, and the program product, when executed by a communication device, causes the communication device to perform the communication method according to any one of the first aspect to the third aspect.

[0112] In an eleventh aspect, the embodiments of the present disclosure provide a computer program, when executed on a computer, causes the computer to perform the method described in the optional implementation manner of any one of the first aspect to the third aspect.

[0113] In a twelfth aspect, the embodiments of the present disclosure provide a chip or chip system. The chip or chip system comprises processing circuitry configured to perform the method described in the optional implementation manner of any one of the first aspect to the third aspect.

[0114] It can be understood that the above-mentioned communication device, communication system, storage medium, program product, computer program, chip or chip system are all used to perform the method proposed in the embodiments of the present disclosure. Therefore, the beneficial effects that can be achieved thereby can refer to the beneficial effects in the corresponding method, which will not be described here again.

[0115] The embodiments of the present disclosure provide a communication method, a communication device, a communication system, a storage medium and a program product. In some embodiments, the communication method and the AI inference method, the processing method of the AI inference service, and the like can be replaced with each other, and the AI inference system, the communication system, the AI inference service processing system, and the like can be replaced with each other.

[0116] The embodiments of the present disclosure are not exhaustive, but are only a part of the embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing part of the steps in an embodiment can also be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, part or all of the steps of different embodiments can be combined arbitrarily, an embodiment can be combined with the optional implementation manners of other embodiments.

[0117] In the embodiments of the present disclosure, the terms and / or descriptions between the embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0118] The terms used in the embodiments of the present disclosure are only for the purpose of describing the specific embodiments, and not as a limitation on the present disclosure.

[0119] In the embodiments of the present disclosure, unless otherwise specified, the elements expressed in singular form, such as "one", "one", "the", "the above", "the", "the above", "this", etc. can represent "one and only one", and can also represent "one or more", "at least one", etc. For example, in the case of using articles such as "a", "an", "the" in English, the noun after the article can be understood as singular expression, and can also be understood as plural expression.

[0120] In the embodiments of the present disclosure, "a plurality of" means two or more.

[0121] In some embodiments, the terms "at least one of", "one or more", "a plurality of", "multiple", and the like can be replaced with each other.

[0122] In some embodiments, "at least one of A, B", "A and / or B", "in one case A, in another case B", "responsive to case A, responsive to case B" and the like, can be interpreted to include both cases, A and B, in some embodiments, A (A is performed regardless of B), in some embodiments, B (B is performed regardless of A), in some embodiments, selected from the group consisting of A and B (the selection between A and B is an option), in some embodiments, A and B (both A and B are performed).

[0123] In some embodiments, "A or B" and the like, can be interpreted to include both cases, A and B, in some embodiments, A (A is performed regardless of B), in some embodiments, B (B is performed regardless of A), in some embodiments, selected from the group consisting of A and B (the selection between A and B is an option).

[0124] In some embodiments, the prefix words "first", "second" and the like in the disclosure do not limit the position, order, priority, number or content of the described objects, and the description of the described objects should be understood in the context of the claims or embodiments, and should not be construed as redundant limitations. For example, the described object is "field", and the ordinal words before "field" in "first field" and "second field" do not limit the position or order between "fields", and "first" and "second" do not limit whether the "fields" modified by them are in the same message or not, nor do they limit the order of "first field" and "second field". For another example, the described object is "level", and the ordinal words before "level" in "first level" and "second level" do not limit the priority between "levels". For another example, the number of described objects is not limited by ordinal words, and can be one or more. For example, "first device", where the number of "devices" can be one or more. In addition, objects modified by different prefix words can be the same or different, for example, the described object is "device", and "first device" and "second device" can be the same device or different devices, and their types can be the same or different; for another example, the described object is "information", and "first information" and "second information" can be the same information or different information, and their contents can be the same or different.

[0125] In some embodiments, "including A", "containing A", "for indicating A", "carrying A" can be interpreted as directly carrying A, or indirectly indicating A.

[0126] In some embodiments, the terms "in response to", "in response to determining", "in the case of", "when", "when", "if", "if" and the like can be replaced with each other.

[0127] In some embodiments, the terms "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not lower than", "above", and the like can be replaced with each other, and the terms "less than", "less than or equal to", "not greater than", "fewer than", "fewer than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", "below", and the like can be replaced with each other.

[0128] In some embodiments, an apparatus and the like can be interpreted as an entity, and can also be interpreted as virtual, and the name thereof is not limited to the name recited in the embodiments, and the terms "apparatus", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject", and the like can be replaced with each other.

[0129] In some embodiments, "network" can be interpreted as an apparatus (for example, an access network device, a core network device, and the like) included in the network.

[0130] In some embodiments, the terms “network devices,” “access network devices (AN devices),” “radio access network devices (RAN devices),” “base stations (BSs),” “radio base stations,” “fixed stations,” “nodes,” “access network nodes,” “access points,” “transmission points (TPs),” “reception points (RPs),” “transmission / reception points (TRPs),” “panels,” “antenna panels,” “antenna arrays,” “cells,” “macro cells,” “small cells,” “femtocells,” “pico cells,” “sectors,” “cell groups,” “serving cells,” “carriers,” “component carriers,” “bandwidth parts (BWPs),” and the like can be used interchangeably.

[0131] In some embodiments, the terms "terminal," "terminal device," "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," and so on can be replaced with each other.

[0132] In some embodiments, the access network device, the core network device, or the network device can be replaced with a terminal. For example, the embodiments of the present disclosure can also be applied to a structure in which communication between the access network device, the core network device, or the network device and the terminal is replaced with communication between a plurality of terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the terminal can also be configured to have all or part of the functions of the access network device. In addition, the terms "uplink," "downlink," and the like can also be replaced with terms corresponding to the inter-terminal communication (e.g., "side"). For example, the uplink channel, the downlink channel, and the like can be replaced with the side channel, and the uplink, the downlink, and the like can be replaced with the sidelink.

[0133] In some embodiments, the terminal can be replaced with the access network device, the core network device, or the network device. In this case, the access network device, the core network device, or the network device can also be configured to have all or part of the functions of the terminal.

[0134] In some embodiments, the data, information, etc. can be obtained in compliance with the laws and regulations of the country in which the location is situated.

[0135] In some embodiments, the data, information, etc. can be obtained after obtaining the consent of the user.

[0136] In addition, each element, each row, or each column in the table of the embodiments of the present disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0137] FIG. 1A is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG. 1A, the communication system 100 includes a first node 101, a third node 102, and a fourth node 103.

[0138] In some embodiments, the first node is configured to manage an AI model inference service function (AiISF).

[0139] In some embodiments, the first node is configured to obtain an AI inference service request.

[0140] In some embodiments, the first node is configured to determine an inference method based on the AI inference service request.

[0141] In some embodiments, the first node is configured to determine a node that provides an AI inference service based on the AI inference service request.

[0142] In some embodiments, the first node is configured to determine a plurality of inference tasks associated with the AI inference service.

[0143] In some embodiments, the first node is configured to assign the plurality of inference tasks to a plurality of nodes that provide the AI inference service.

[0144] In some embodiments, the first node is configured to initiate establishment of a data connection between a node that requests the AI inference service and a node that provides the AI inference service.

[0145] In some embodiments, the name of the first node is not limited, and it is, for example, “AiISF”, “inference service management node”, “AI inference management node”, “model inference management node”, “network data analytics function (NWDAF)”, etc.

[0146] In some embodiments, the third node is configured to provide an AI inference service.

[0147] In some embodiments, the third node is configured to establish a data connection with a node that requests the AI inference service.

[0148] In some embodiments, the third node is configured to provide an inference result to a node requesting an AI inference service.

[0149] In some embodiments, the third node can be dedicated to providing an AI inference service. In an example, the second node is an operator server dedicated to providing an AI inference service.

[0150] In some embodiments, the third node can provide other services in addition to an AI inference service. In an example, the second node is a network element providing a location management function (LMF), which can also provide an AI inference service.

[0151] In some embodiments, the third node is not limited in name, for example, “inference node”, “AI inference node”, “AI model inference node”, “inference execution node”, etc.

[0152] In some embodiments, the third node includes the second node, and the second node is one or more of the third node. The function of the second node is the same as that of the third node, which is not described here. The second node can be understood as a target inference node, and the third node can be understood as a candidate inference node.

[0153] In some embodiments, the fourth node is configured to request an AI inference service.

[0154] In some embodiments, the fourth node is configured to establish a data connection with a node providing an AI inference service.

[0155] In some embodiments, the fourth node is configured to send inference data to a node providing an AI inference service.

[0156] In some embodiments, the fourth node is configured to obtain an inference result of an AI inference service.

[0157] In some embodiments, the fourth node is not limited in name, for example, “request node”, “initiation node”, “inference request node”, “AI inference request node”, “model inference request node”, etc.

[0158] In some embodiments, the first node described above can be a core network device, an access network device, etc.

[0159] In some embodiments, the third node and the fourth node described above can be a terminal, an access network device, a core network device, etc.

[0160] In some embodiments, the first node, the third node and the fourth node described above can be deployed in one device, or can be respectively deployed in multiple devices, and each device is deployed with one or more nodes described above.

[0161] In some embodiments, the first node and the third node are deployed in the same device.

[0162] In an example, the first node and the third node are A1SFs.

[0163] In an example, the first node and the third node are NWDAFs.

[0164] In some embodiments, the terminal includes at least one of a mobile phone, a wearable device, an Internet of Things device, a communication-capable car, a smart car, a Pad, a wireless transceiver-equipped computer, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, a wireless terminal device in a smart home, and the like, but is not limited thereto.

[0165] In some embodiments, the access network device is at least one of a node or a device that accesses a terminal to a wireless network, and can include an evolved NodeB (eNB), a next generation eNB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an Open RAN, a Cloud RAN, a base station in other communication systems, an access node in a Wi-Fi system, and the like, but is not limited thereto.

[0166] In some embodiments, the technical solutions of the present disclosure can be applied to an Open RAN architecture, at this time, the interfaces between or within the network devices involved in the embodiments of the present disclosure can become internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0167] In some embodiments, the access network device can be composed of a central unit (CU) and a distributed unit (DU), where the CU can also be referred to as a control unit. The CU-DU structure can split the protocol layers of the network device, and some protocol layer functions are controlled by the CU, and the remaining or all protocol layer functions are distributed in the DU and controlled by the CU, but not limited thereto.

[0168] In some embodiments, the core network device can be one device including the first network element, or a plurality of devices or device groups each including the first network element. The network element can be virtual or physical. The core network includes at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0169] It can be understood that the communication system described in the embodiments of the present disclosure is for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and does not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. It can be known by those skilled in the art that, with the evolution of system architecture and the appearance of new business scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0170] The following embodiments of the present disclosure can be applied to the communication system 100 shown in FIG. 1A or part of the subject, but are not limited thereto. The subjects shown in FIG. 1A are examples, and the communication system can include all or part of the subjects in FIG. 1A, or include other subjects other than those in FIG. 1A. The number and form of each subject is arbitrary, and the connection relationship between each subject is an example. Each subject can not be connected or can be connected, and the connection can be in any way, can be direct connection or indirect connection, can be wired connection or wireless connection.

[0171] Embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (Bluetooth (registered trademark)), Public Land Mobile Network (PLMN) network, Device-to-Device (D2D) system, Machine to Machine (M2M) system, Internet of Things (IoT) system, Vehicle-to-Everything (V2X), system using other communication methods, next-generation system expanded based on them, and the like. Further, a plurality of systems can be combined (for example, combination of LTE or LTE-A and 5G, and the like).

[0172] Hereinafter, terms related to the present disclosure are explained and interpreted.

[0173] FIG. IB is a service architecture diagram of an AI inference service oriented to 6G, according to an embodiment of the present disclosure. As shown in FIG. IB, the service architecture includes a 6G access network device (RAN), a 6G access and mobility management function (AMF), a 6G session management function (SMF), an AiISF, a 6G inference network function (inference NF), a 6G network function 1 with inference capability (NF1 with inference capability), a 6G network function 2 with inference capability (NF2 with inference capability), and a 6G network function 3 with inference capability (NF3 with inference capability).

[0174] In some embodiments, the 6G inference NF is a 6G network element dedicated to providing AI model inference services.

[0175] In some embodiments, the 6G NF1 with inference capability, the 6G NF2 with inference capability, and the 6G NF3 with inference capability are 6G network elements that have other functions and also have AI model inference capabilities.

[0176] In an example, the 6G NF1 with inference capability is an LMF with inference capability.

[0177] In an example, the 6G NF2 with inference capability is an analytics data repository function (ADRF) with inference capability.

[0178] In some embodiments, AI model inference of a terminal can be performed locally at the terminal, but due to limited computing power and computing resources of the terminal, the terminal cannot support inference services that exceed the computing power and computing resources of the terminal. For this case, although a third-party server (e.g., a non-operator server) can be used to provide inference services for the terminal, this will also cause delay and affect user experience.

[0179] The embodiment of the disclosure provides a communication method, a communication device, a communication system, a storage medium and a program product. A first node determines a second node for providing a first AI inference service according to first information used for requesting the first AI inference service, and then sends second information to instruct the second node to provide the first AI inference service. Since the second node is determined based on the first information, that is, the second node matches the requirements of the first information, the second node can meet the requirements of the first AI inference service for computing power and resources, and will not bring additional delay.

[0180] FIG. 2 is a first interaction schematic diagram of a communication method provided by an embodiment of the disclosure. As shown in FIG. 2, the embodiment of the disclosure relates to a communication method. The communication method is performed by the communication system 100, and includes steps S2101 to S2110.

[0181] In the embodiment of the disclosure, the process of providing the AI inference service is illustrated by taking the first node as the AiISF, the second node as the inference node A, the third node as the inference node, and the fourth node as the terminal A as an example.

[0182] In step S2101, the terminal A sends first information.

[0183] In some embodiments, the terminal A can be one terminal, or one or more terminals in a terminal group.

[0184] In some embodiments, the AiISF receives the first information.

[0185] In some embodiments, the first information is used to request a first AI inference service.

[0186] In some embodiments, the first AI inference service can be a positioning service, for example, inferring the moving track of object A at a future time based on the moving track and the current position of object A at a historical time.

[0187] In some embodiments, the first AI inference service can be a measurement service, for example, inferring the measurement result of cell A at a current time based on the measurement result of cell A at a historical time. For example, inferring the measurement result of cell A based on the measurement result of the neighboring cell of cell A. For example, inferring the channel state information (CSI) of channel A at a current time based on the CSI of channel A at a historical time.

[0188] In some embodiments, the first AI inference service can also be an image recognition service, a voice recognition service, a user behavior prediction service, a data repair service, etc.

[0189] In some embodiments, the number of first AI inference services can be one or more.

[0190] In some embodiments, in a case that terminal A requests multiple first AI inference services, terminal A can send one first information to request the multiple first AI inference services, or terminal A can send multiple first information, each of which is used to request one first AI inference service.

[0191] In some embodiments, the first information is carried in a first message, which is an inference service request message.

[0192] In some embodiments, the first information is used to indicate at least one of the following: terminal A requesting the first AI inference service, quality requirement of the first AI inference service, model requirement of the first AI inference service, type of the first AI inference service, location of the terminal requesting the first AI inference service, service area of the first AI inference service.

[0193] In some embodiments, terminal A requesting the first AI inference service can be indicated by first indication information. In an example, the first indication information is identification information (e.g., UE ID) of terminal A. In an example, the first indication information is identification information (e.g., UE group ID) of a terminal group to which terminal A belongs.

[0194] In some embodiments, the name of the first indication information is not limited, which is, for example, “requester identification information”, “device identification information”, “identification information”, etc.

[0195] In some embodiments, the quality requirement of the first AI inference service can be indicated by second indication information. In some embodiments, the quality of service (QoS) of the first AI inference service can be indicated by the second indication information.

[0196] In some embodiments, the name of the second indication information is not limited, which is, for example, “quality requirement information”, “quality information”, “service quality information”, etc.

[0197] In an embodiment, the second indication information includes at least one of the following: latency information, bandwidth information, transmission rate information, packet loss rate information, data privacy information.

[0198] In some embodiments, the model requirement of the first AI inference service can be indicated by third indication information.

[0199] In some embodiments, the name of the third indication information is not limited, which is, for example, “model requirement information”, “model information”, “model indication information”, etc.

[0200] In some embodiments, the third indication information comprises at least one of the following: model identification information, model version information, model function information, model structure information, model size information, inference accuracy information, and inference speed information.

[0201] In some embodiments, the type of the first AI inference service can be indicated by the fourth indication information.

[0202] In some embodiments, the name of the fourth indication information is not limited, which is, for example, “service type information”, “type information”, “type indication information”, and the like.

[0203] In some embodiments, the type of the first AI inference service can be associated with the quality requirement of the first AI inference service. The quality requirement of the first AI inference service can be determined by the type of the first AI inference service, and the type of the first AI inference service can be determined by the quality requirement of the first AI inference service. It can be understood that different types of AI inference services correspond to different quality requirements. In other words, the fourth indication information is associated with the second indication information.

[0204] In some embodiments, the location of the terminal A requesting the first AI inference service can be indicated by the fifth indication information.

[0205] In some embodiments, the name of the fifth indication information is not limited, which is, for example, “requester location information”, “device location information”, “location information”, and the like.

[0206] In some embodiments, the service area of the first AI inference service can be indicated by the sixth indication information.

[0207] In some embodiments, the name of the sixth indication information is not limited, which is, for example, “service area information”, “area information”, “service range information”, “area identification information”, and the like.

[0208] In some embodiments, the first information can comprise at least one of the following: the first indication information (denoted as requester identification information), the second indication information (denoted as quality requirement information), the third indication information (denoted as model requirement information), the fourth indication information (denoted as service type information), the fifth indication information (denoted as requester location information), and the sixth indication information (service area information).

[0209] In some embodiments, when the first information contains the service type information, the first information can not carry the quality requirement information.

[0210] In some embodiments, when the first information does not contain the quality requirement information, the AiISF can determine the quality requirement information according to the service type information.

[0211] In some embodiments, when the first information contains the requester identity information, the first information can not carry the requester location information.

[0212] In some embodiments, when the first information does not contain the requester location information, the AiISF can determine the requester location information according to the requester identity information.

[0213] In some embodiments, when the fourth node and the first node are deployed in the same device, step S2101 can be omitted.

[0214] In an example, the fourth node and the first node are both AiISFs, in which case, the AiISF requests the first AI inference service, determines the first information, and performs step S2102 according to the first information.

[0215] In step S2102, the AiISF determines the inference node A.

[0216] In some embodiments, the inference node A is used to provide the first AI inference service, and the number of inference node A can be one or more.

[0217] In some embodiments, the AiISF can determine the inference node A that meets the requirements of the first information according to the first information.

[0218] In some embodiments, when the first information contains the requester identity information or the requester location information, the AiISF can determine the inference node closest to the location of the terminal A as the inference node A, and the AiISF can also determine a first region with the location of the terminal A as the center and a first value as the radius according to the location of the terminal A, and determine the inference nodes in the first region as the inference node A.

[0219] In some embodiments, when the first information contains the quality requirement information, the number of inference node A is determined. When the first information contains the quality requirement information and the requester location information, the inference node A is determined.

[0220] In some embodiments, when the first information contains the service type information, the number of inference node A is determined. When the first information contains the service type information and the requester location information, the inference node A is determined.

[0221] In some embodiments, the AiISF can determine the inference node A according to the first information and the eleventh indication information.

[0222] In some embodiments, the eleventh indication information can be configured by a network device or specified by a protocol.

[0223] In some embodiments, the eleventh indication information can be used to indicate a mapping relationship between the type of the AI inference service and the inference node, in which case the AiISF can determine, from the mapping relationship, the inference node A corresponding to the type of the first AI inference service.

[0224] In an example, assuming that there are four types of AI inference services (e.g., type 1, type 2, type 3, and type 4) and a total of four inference nodes (e.g., inference node A1, inference node A2, inference node A3, and inference node A4), the mapping relationship between the type of the AI inference service and the inference node is shown in Table 1 below:

[0225] Table 1

[0226] In some embodiments, the eleventh indication information can be used to indicate a mapping relationship between the type of the AI inference service and the inference node, in which case the AiISF can determine, from the mapping relationship, the inference node A corresponding to the type of the first AI inference service.

[0227] In some embodiments, the eleventh indication information can be used to indicate a mapping relationship between the type of the AI inference service and the inference node, in which case the AiISF can determine, from the mapping relationship, the inference node A corresponding to the type of the first AI inference service.

[0228] In some embodiments, the eleventh indication information can be used to indicate a mapping relationship between the type of the AI inference service and the inference node, in which case the AiISF can determine, from the mapping relationship, the inference node A corresponding to the type of the first AI inference service.

[0229] In some embodiments, the AiISF can determine the inference node A from the plurality of inference nodes according to the first information and third information associated with the plurality of inference nodes.

[0230] In some embodiments, the AiISF can request the plurality of inference nodes to obtain the third information.

[0231] In some embodiments, the AiISF can also request a network storage (NRF) network element to obtain the third information of the inference node.

[0232] In some embodiments, the third information is used to indicate at least one of the following: support capability of the inference node for different types of AI inference services, support capability of the inference node for AI models, resources of the inference node for processing AI inference services, location of the inference node, inference node, and support capability of the inference node for inference methods.

[0233] In some embodiments, the support capability of the inference node for different types of AI inference services can be indicated by the seventh indication information.

[0234] In some embodiments, the name of the seventh indication information is not limited, which is, for example, “type support information”, “capability information”, “service support information”, etc.

[0235] In an example, assuming that there are three types (e.g., type 1, type 2, type 3) of AI inference services, the seventh indication information indicates that the inference node A1 supports type 1 and type 2 AI inference services, in which case it can be considered that the inference node A1 does not support type 3 AI inference service. In an example, the type support information further indicates that the inference node A2 does not support type 1 AI inference service, in which case it can be considered that the inference node A2 supports type 2 and type 3 AI inference services.

[0236] In some embodiments, the support capability of the inference node for AI models can be indicated by the eighth indication information.

[0237] In some embodiments, the name of the eighth indication information is not limited, which is, for example, “model support information”, “model capability information”, “capability information”, etc.

[0238] In an example, the eighth indication information indicates that the inference node A1 supports AI model A and AI model B. In an example, the eighth indication information further indicates that the inference node A2 does not support AI model A and AI model C.

[0239] In some embodiments, the eighth indication information can also be used to indicate the support capability of the inference node for different types of AI models. In some embodiments, different types of AI models can be divided based on model structure, or can be divided based on model function, or can be divided based on the data type processed by the model.

[0240] In an example, the eighth indication information indicates that the inference node A1 supports type 1, type 2 and type 3 AI models. In an example, the model support information further indicates that the inference node A2 does not support type 2 AI model.

[0241] In some embodiments, the resources of the inference node for processing AI inference services can be indicated by the ninth indication information.

[0242] In some embodiments, the name of the ninth indication information is not limited, which is, for example, “resource information”, “AI resource information”, “service resource information”, etc.

[0243] In some embodiments, the ninth indication information includes at least one of the following: storage resource information, computing resource information.

[0244] In some embodiments, the ninth indication information is further used to indicate a resource that is idle in resources of the inference node processing the AI inference service.

[0245] In some embodiments, the location of the inference node can be indicated by the tenth indication information.

[0246] In some embodiments, the name of the tenth indication information is not limited, which is, for example, “inference party location information”, “inference location information”, “device location information”, “location information”, etc.

[0247] In some embodiments, the inference node can be indicated by inference party identification information.

[0248] In some embodiments, the name of the inference party identification information is not limited, which is, for example, “inference indication information”, “device identification information”, “inference device identification information”, “device identification information”, etc.

[0249] In an example, the inference party identification information is the ID of the inference node.

[0250] In some embodiments, the support capability of the inference node for the inference method can be indicated by inference method support information.

[0251] In some embodiments, the name of the inference method support information is not limited, which is, for example, “method support information”, “inference capability information”, “capability information”, etc.

[0252] In an example, the inference method support information is used to indicate that the inference node A1 supports inference method 1 and inference method 2. In an example, the inference method support information is also used to indicate that the inference node A2 does not support inference method 3.

[0253] In some embodiments, the third information includes at least one of the following: seventh indication information (denoted as type support information), eighth indication information (denoted as model support information), ninth indication information (denoted as resource information), tenth indication information (denoted as inference party location information), inference party identification information, inference method support information.

[0254] In some embodiments, in the case that the third information does not contain the inference party location information, the AiISF can determine the inference party location information according to the inference party identification information.

[0255] In some embodiments, in the case that the first information includes quality requirement information and requestor location information, and the third information includes inference party location information and resource information, the AiISF can determine the inference node A that meets the requirements of the first information from the plurality of inference nodes according to the third information.

[0256] In an example, assuming that the quality requirement information indicates that the time delay of the first AI inference service is less than a first threshold value, the AiISF can calculate the distance between each inference node and terminal A according to the inference party location information and the requester location information, determine the idle resources of each inference node that can currently process the AI inference service according to the resource information, and based on this, select an inference node A from the plurality of inference nodes that is less than a second threshold value in distance and has idle resources greater than a third threshold value.

[0257] In some embodiments, in a case where the first information includes model requirement information and the third information includes model support information, the AiISF can determine an inference node A that meets the requirements of the first information from the plurality of inference nodes according to the third information.

[0258] In an example, assuming that the model requirement information indicates that the model of the first AI inference service is AI model C, the AiISF can determine an inference node A that supports AI model C from the plurality of inference nodes according to the model support information.

[0259] In some embodiments, in a case where the first information includes service type information and the third information includes type support information, the AiISF can determine an inference node A that meets the requirements of the first information from the plurality of inference nodes according to the third information.

[0260] In an example, assuming that the service type information indicates that the type of the first AI inference service is type 1, the AiISF can determine an inference node A that supports processing AI inference services of type 1 from the plurality of inference nodes according to the type support information.

[0261] In some embodiments, the AiISF can determine a first inference method used by the first AI inference service according to the first information.

[0262] In some embodiments, the first inference method can be used to determine the inference node A.

[0263] In some embodiments, the first inference method can be used to determine the number of inference nodes A.

[0264] In some embodiments, the AiISF determines the inference node A according to the first inference method, the first information, and the third information. In an example, the AiISF can determine an inference node A that meets the requirements of the first information and supports the first inference method from the plurality of inference nodes according to the third information.

[0265] In some embodiments, the first inference method is one of: a centralized inference method, a distributed inference method, and a federated learning inference method. The centralized inference method is to concentrate the AI inference service in one inference node for execution. The distributed inference method is to distribute multiple inference tasks associated with the AI inference service to multiple nodes for execution. The federated learning inference method is a special distributed inference method that allows inference through federated learning while keeping user data localized, thereby ensuring the privacy of user data.

[0266] In an example, in a case where the AiISF determines, according to the first information, that the first AI inference service has a small amount of data, a low requirement for real-time performance, and a small model, the first inference method can be determined as the centralized inference method.

[0267] In an example, in a case where the AiISF determines, according to the first information, that the first AI inference service has a large amount of data, a high requirement for real-time performance, and a large model, the first inference method can be determined as the distributed inference method.

[0268] In an example, in a case where the AiISF determines, according to the first information, that the first AI inference service requires data privacy protection, the first inference method can be determined as the federated learning inference method.

[0269] In an example, in a case where the first inference method is determined as the centralized inference method, the AiISF can determine the number of inference nodes A to be one.

[0270] In an example, in a case where the first inference method is determined as the distributed inference method or the federated learning inference method, the AiISF can determine the number of inference nodes A to be multiple.

[0271] In some embodiments, the AiISF can determine the first inference method adopted by the first AI inference service according to the first information and preconfigured twelfth indication information.

[0272] In some embodiments, the twelfth indication information is used to indicate a mapping relationship between the type of the AI inference service and the inference method.

[0273] In some embodiments, the twelfth indication information is used to indicate a mapping relationship between the type of the model adopted by the AI inference service and the inference method.

[0274] In some embodiments, in a case where the AiISF determines multiple inference methods according to the first information, the AiISF can determine one inference method from the multiple inference methods as the first inference method based on the eleventh indication information.

[0275] In step S2103, the AiISF assigns the first AI inference service to the inference node A.

[0276] In some embodiments, in the case where the number of first AI inference services is one and the number of inference nodes A is one, inference node A can independently complete the first AI inference service.

[0277] In some embodiments, in the case where the number of first AI inference services is one and the number of inference nodes A is multiple, AiISF determines the multiple inference tasks associated with the first AI inference service and assigns the multiple inference tasks to the multiple inference nodes A, at this time, each inference node A only processes a part of the inference tasks.

[0278] In some embodiments, in the case where the number of first AI inference services is multiple and the number of inference nodes A is one, inference node A can independently complete the multiple first AI inference services.

[0279] In some embodiments, in the case where the number of first AI inference services is multiple and the number of inference nodes A is multiple, AiISF can assign the multiple first AI inference services to the multiple inference nodes A according to the inference node A corresponding to each first AI inference service determined in step S2102. In the case where one of the multiple first AI inference services corresponds to multiple inference nodes A, AiISF determines the multiple inference tasks associated with the first AI inference service and assigns the multiple inference tasks to the multiple inference nodes A.

[0280] In an example, case 1, AiISF determines that first AI inference service 1 corresponds to inference node A1, first AI inference service 2 corresponds to inference node A1, and first AI inference service 3 corresponds to inference node A2, in this case, AiISF directly assigns the multiple first AI inference services according to the determined inference node A.

[0281] Case 2, AiISF determines that first AI inference service 1 corresponds to inference node A1, first AI inference service 2 corresponds to inference node A1 and inference node A2, and first AI inference service 3 corresponds to inference node A2, in this case, AiISF assigns first AI inference service 1 to inference node A1, assigns first AI inference service 2 to inference node A2, and determines that first AI inference service 2 is associated with 3 tasks (for example, task 1, task 2 and task 3), assigns task 1 and task 2 to inference node A1, and assigns task 3 to inference node A2.

[0282] In some embodiments, the above-mentioned embodiments of determining the multiple inference tasks associated with the first AI inference service can be understood as splitting the first AI inference service into multiple inference tasks, or decomposing the first AI inference service into multiple inference tasks.

[0283] In some embodiments, the above-mentioned embodiment that the AiISF assigns the first AI inference service to the inference node A can be understood as that the AiISF establishes a mapping relationship between the first AI inference service and the inference node A, or the AiISF establishes a mapping relationship between the plurality of inference tasks associated with the first AI inference service and the inference node A.

[0284] In some embodiments, the AiISF can assign the plurality of inference tasks to the plurality of inference nodes A evenly. In other words, the number of inference tasks assigned to each inference node A is equal.

[0285] In step S2104, the AiISF sends the second information.

[0286] In some embodiments, in the case that the number of inference nodes A is more than one, the AiISF can send one second information to each of the plurality of inference nodes A, or the AiISF can send a plurality of second information to one inference node A1 of the plurality of inference nodes A, and the inference node A1 sends the second information to other inference nodes A.

[0287] In some embodiments, the inference node A receives the second information.

[0288] In some embodiments, the second information can be used to instruct the inference node A to provide the first AI inference service.

[0289] In some embodiments, the second information can be used to instruct the inference node A to provide the first AI inference service by using the first inference method.

[0290] In some embodiments, the second information can be used to request the inference node A to establish a data connection with the terminal A.

[0291] In some embodiments, the second information is carried in a second message, for example, a data connection establishment request message.

[0292] In some embodiments, the second information includes one of the following: the first information, thirteenth indication information (denoted as service identification information), fourteenth indication information (denoted as task identification information), and fifteenth indication information (denoted as method identification information).

[0293] In some embodiments, the service identification information is used to indicate the first AI inference service. In an example, the service identification information is an ID of the first AI inference service. In an example, the service identification information is an ID of the terminal A that requests the first AI inference service.

[0294] In some embodiments, the task identification information is used to indicate a plurality of inference tasks associated with the first AI inference service. In an example, the task identification information is an ID of the inference task.

[0295] In some embodiments, the method identification information is used to indicate the first inference method. In an example, the method identification information is an ID of the first inference method.

[0296] In some embodiments, the service identification information, the task identification information, and the method identification information are configured by the AiISF.

[0297] In some embodiments, in a case where the first node and the second node are deployed on the same device, step S2104 can be omitted. In an example, the first node and the second node are both AiISFs, and step S2104 is omitted.

[0298] In step S2105, the inference node A sends fourth information.

[0299] In some embodiments, the AiISF receives the fourth information.

[0300] In some embodiments, the fourth information is used to indicate that the inference node A agrees to provide the first AI inference service.

[0301] In some embodiments, the fourth information is used to indicate that the inference node A agrees to provide the first AI inference service using the first inference method.

[0302] In some embodiments, the fourth information is used to indicate that the inference node A agrees to establish a data connection with the terminal A.

[0303] In some embodiments, the fourth information is used to indicate an access address of the inference node A. In an example, the access address of the inference node A includes at least one of: an IP address, a port.

[0304] In some embodiments, the fourth information is carried in a third message. The third message is a response message of the second message, and the third message is, for example, a data connection establishment response message.

[0305] In some embodiments, in a case where the second node and the first node are deployed on the same device, step S2105 can be omitted. In an example, the first node and the second node are both AiISFs, and step S2105 is omitted.

[0306] In step S2106, the AiISF sends fifth information.

[0307] In some embodiments, the terminal A receives the fifth information. The terminal A is a terminal that requests the first AI inference service.

[0308] In some embodiments, the fifth information is used to indicate that the inference node A agrees to provide the first AI inference service.

[0309] In some embodiments, the fifth information is used to indicate the access address of the inference node A.

[0310] In some embodiments, the fifth information is used for the terminal A to send inference data (denoted as inference data A) of the first AI inference service to the inference node A. In some embodiments, the inference data is input data of a model associated with the first AI inference service.

[0311] In some embodiments, the fifth information is used to indicate a mapping relationship between the first AI inference service and the inference node A.

[0312] In some embodiments, the fifth information is used to indicate a mapping relationship between a plurality of inference tasks associated with the first AI inference service and the inference node A.

[0313] In some embodiments, the fifth information includes the fourth information, in which case the fourth information is used to indicate the access address of the inference node A.

[0314] In some embodiments, in the case where the number of inference nodes A is multiple, the fifth information further includes sixteenth indication information.

[0315] In some embodiments, the sixteenth indication information can be used to indicate a mapping relationship between the first AI inference service and the inference node A. In some embodiments, the sixteenth indication information can also be used to indicate a mapping relationship between a plurality of inference tasks associated with the first AI inference service and the inference node A.

[0316] In some embodiments, the fifth information is carried in a fourth message, for example, an inference service response message.

[0317] In some embodiments, in the case where the fourth node and the first node are deployed on the same device, step S2106 can be omitted.

[0318] In an example, the fourth node and the first node are both AiISFs, and step S2106 is omitted.

[0319] In step S2107, the terminal A sends the inference data A based on the fifth information.

[0320] In some embodiments, the terminal A directly sends the inference data A based on a data connection between the terminal A and the inference node A.

[0321] In some embodiments, the inference node A receives the inference data A. In some embodiments, the inference node A receives the inference data A through the data connection with the terminal A.

[0322] In some embodiments, in a case where the fifth information includes the fourth information, the terminal A sends the inference data A to the inference node A indicated by the access address indicated by the fourth information.

[0323] In some embodiments, in a case where the fifth information includes the fourth information and the sixteenth indication information, the terminal A distributes the inference data A of each first AI inference service to the corresponding access address or splits and distributes the inference data A of one first AI inference service to the corresponding access address according to the indication of the sixteenth indication information.

[0324] In some embodiments, in a case where the number of inference nodes A is one, the terminal A sends the inference data A to the inference node A.

[0325] In some embodiments, in a case where the number of inference nodes A is multiple and the number of first AI inference services is one, the terminal A splits and distributes the inference data A to the corresponding inference node A according to the mapping relationship between the multiple inference tasks associated with the first AI inference service and the multiple inference nodes A.

[0326] In an example, it is assumed that the number of inference nodes A determined by the AiISF is 3 (for example, inference node A1, inference node A2, and inference node A3), and the AiISF determines that the first AI inference service is associated with 4 inference tasks (for example, task 1, task 2, task 3, and task 4). The mapping relationship between the inference tasks and the 3 inference nodes is shown in Table 2 below, inference node A1 is assigned to process task 1 and task 2, inference node A2 is assigned to process task 3, and inference node A3 is assigned to process task 4. In this case, the terminal A splits the inference data A into inference data a1 of task 1, inference data a2 of task 2, inference data a3 of task 3, and inference data a4 of task 4, and sends inference data a1 and a2 to inference node A1, inference data a3 to inference node A2, and inference data a4 to inference node A3.

[0327] Table 2

[0328] In some embodiments, in the case where the number of inference nodes A is multiple and the number of first AI inference services is multiple, if each inference node A is allocated a complete first AI inference service or services, the terminal A distributes each inference data A to the corresponding inference node A according to the mapping relationship between the multiple first AI inference services and the multiple inference nodes A. If there is a first AI inference service among the multiple first AI inference services that is allocated to multiple inference nodes A for completion, the terminal A splits the inference data of the first AI inference service and distributes it to the corresponding inference nodes.

[0329] In some embodiments, in the case where the fourth node and the first node are deployed on the same device, for example, the fourth node is an AISF, the execution subject of step S2107 can be replaced by the AISF.

[0330] In step S2108, the inference node A performs AI inference based on the inference data A to obtain an inference result.

[0331] In some embodiments, the inference node A performs AI inference on the inference data A using the first inference method to obtain an inference result.

[0332] In some embodiments, the inference node A uses the first inference method and inputs the inference data A into the model A to obtain the inference result output by the model A.

[0333] In some embodiments, the model A is a model associated with the first AI inference service. In some embodiments, the model A can be an AI model, an ML model, or other models.

[0334] In some embodiments, in the case where the second node and the first node are deployed on the same device, for example, the second node is an AISF, the execution subject of step S2108 can be replaced by the AISF.

[0335] In step S2109, the inference node A sends the inference result.

[0336] In some embodiments, the inference node A directly sends the inference result to the terminal A through a data connection with the terminal A.

[0337] In some embodiments, the terminal A receives the inference result. In some embodiments, the terminal A receives the inference result through a data connection with the inference node A.

[0338] In some embodiments, in the case where the number of inference nodes A is one, the inference result obtained by the inference node A is the first inference result of the first AI inference service.

[0339] In some embodiments, in the case that the number of inference nodes A is multiple and the number of the first AI inference services is one, the inference result obtained by each inference node A is used to determine the first inference result of the first AI inference service.

[0340] In some embodiments, in the case that the number of inference nodes A is multiple and the number of the first AI inference services is multiple, if each inference node A is assigned a complete one or more first AI inference services, the inference result obtained by each inference node A is the first inference result of the one or more first AI inference services. If one of the multiple first AI inference services is assigned to be completed by multiple inference nodes A, the inference results obtained by the multiple inference nodes A are used to determine the first inference result of the first AI inference service.

[0341] In some embodiments, in the case that the second node and the first node are deployed on the same device, for example, the second node is an AiISF, the execution subject of step S2108 can be replaced by the AiISF.

[0342] In step S2110, the terminal A determines the first inference result of the first AI inference service based on the inference results sent by the multiple inference nodes A.

[0343] In some embodiments, since the multiple inference tasks associated with the first AI inference service are assigned to the multiple inference nodes A for execution, each inference node A only processes a part of the first AI inference service, and therefore the terminal A combines the inference results obtained by the multiple inference nodes A to obtain the first inference result.

[0344] In an example, the number of first AI inference services is 3 (for example, service 1, service 2 and service 3), and the number of inference nodes A is 2 (for example, inference node A1 and inference node A2). If the AiISF assigns service 1 to inference node A1, assigns service 3 to inference node A2, splits service 2 into task 1, task 2 and task 3, and assigns task 1 and task 2 to inference node A1 and task 3 to inference node A2. In this case, inference node A1 sends the inference result of service 1, the inference result of task 1 and the inference result of task 2 to the terminal A, and inference node A2 sends the inference result of service 3 and the inference result of task 3 to the terminal A. The terminal A obtains the inference results of service 1 and service 3, and combines the inference result of task 1, the inference result of task 2 and the inference result of task 3 to obtain the inference result of service 2.

[0345] In some embodiments, in the case that the number of inference nodes A is one, step S2110 can be omitted, in which case the inference result sent by the inference node A is the first inference result of the first AI inference service.

[0346] In some embodiments, in the case where the plurality of inference nodes A are all allocated the complete one or more first AI inference services, step S2110 can be omitted, in which case the inference result sent by the plurality of inference nodes A is the first inference result of the plurality of first AI inference services.

[0347] In some embodiments, in the case where the fourth node and the first node are deployed on the same device, for example, the fourth node is an AiISF, the execution subject of step S2110 can be replaced by the AiISF.

[0348] The communication method related to the embodiments of the present disclosure can include at least one of steps S2101 to S2110. For example, step S2101 can be implemented as an independent embodiment. For example, step S2102 can be implemented as an independent embodiment. For example, step S2103 can be implemented as an independent embodiment. For example, step S2104 can be implemented as an independent embodiment. For example, step S2105 can be implemented as an independent embodiment. For example, step S2106 can be implemented as an independent embodiment. For example, step S2107 can be implemented as an independent embodiment. For example, step S2108 can be implemented as an independent embodiment. For example, step S2109 can be implemented as an independent embodiment. For example, step S2110 can be implemented as an independent embodiment. For example, step S2102 and step S2103 can be combined to be implemented as an independent embodiment. For example, step S2103 and step S2104 can be combined to be implemented as an independent embodiment. For example, step S2104, step S2105 and step S2106 can be combined to be implemented as an independent embodiment. For example, step S2107, step S2108 and step S2109 can be combined to be implemented as an independent embodiment. For example, step S2109 and step S2110 can be combined to be implemented as an independent embodiment.

[0349] In some embodiments, the terms “AI inference service”, “AI model inference service”, “model inference service”, “inference service” and the like can be replaced with each other.

[0350] In some embodiments, the names of information and the like are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", "chip", and the like can be replaced with each other.

[0351] In some embodiments, terms such as "carrying", "including", "containing", "packaging", and the like can be replaced with each other.

[0352] In some embodiments, terms such as "radio", "wireless", "radio access network (RAN)", "access network (AN)", "RAN-based", and the like can be replaced with each other.

[0353] In some embodiments, "acquire", "obtain", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be replaced with each other, which can be interpreted as receiving from other subjects, acquiring from protocols, acquiring from higher layers, obtaining by processing oneself, implementing autonomously, and the like.

[0354] In some embodiments, terms such as "send", "transmit", "report", "transmit", "request", "bidirectional transmission", "send and / or receive" can be replaced with each other.

[0355] In some embodiments, terms such as "issue", "return", "feedback", "response", "reply" can be replaced with each other.

[0356] In some embodiments, the terms "certain", "preset", "pre-set", "set", "indicated", "a certain", "any", "first", and the like can be replaced with each other, "certain A", "preset A", "pre-set A", "set A", "indicated A", "a certain A", "any A", "first A" can be interpreted as A predetermined in a protocol or the like, can be interpreted as A obtained by setting, configuring, or indicating, or the like, can be interpreted as certain A, a certain A, any A, or first A, and the like, but are not limited thereto.

[0357] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), can be made by a true or false value (Boolean value) represented by true or false, can be made by comparison of numerical values (for example, comparison with a predetermined value), but is not limited thereto.

[0358] FIG. 3A is a flow diagram of a communication method performed by an AiISF according to an embodiment of the present disclosure. As shown in FIG. 3A, the present embodiment of the present disclosure relates to a communication method performed by an AiISF. The above-mentioned communication method comprises steps S3101 to S3106.

[0359] In step S3101, first information is received.

[0360] The optional implementation of step S3101 can refer to the optional implementation of step S2101 of FIG. 2, other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0361] In step S3102, an inference node A is determined.

[0362] The optional implementation of step S3102 can refer to the optional implementation of step S2102 of FIG. 2, other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0363] In step S3103, the first AI inference service is assigned to the inference node A.

[0364] The optional implementation of step S3103 can refer to the optional implementation of step S2103 of FIG. 2, other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0365] In step S3104, second information is sent.

[0366] The optional implementation of step S3104 can refer to the optional implementation of step S2104 of FIG. 2, other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0367] In step S3105, the fourth information is received.

[0368] Optional implementation of step S3105 can refer to optional implementation of step S2105 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0369] In step S3106, the fifth information is sent.

[0370] Optional implementation of step S3106 can refer to optional implementation of step S2106 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0371] FIG. 3B is a flow diagram of a communication method performed by an inference node A, according to an embodiment of the present disclosure. As shown in FIG. 3B, the present embodiment of the present disclosure relates to a communication method, which is performed by an inference node A. The above-mentioned communication method comprises steps S3201 to S3205.

[0372] In step S3201, the second information is received.

[0373] Optional implementation of step S3201 can refer to optional implementation of step S2104 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0374] In step S3202, the fourth information is sent.

[0375] Optional implementation of step S3202 can refer to optional implementation of step S2105 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0376] In step S3203, inference data A is received.

[0377] Optional implementation of step S3203 can refer to optional implementation of step S2107 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0378] In step S3204, AI inference is performed based on the inference data A, to obtain an inference result.

[0379] Optional implementation of step S3204 can refer to optional implementation of step S2108 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0380] In step S3205, the inference result is sent.

[0381] The optional implementation manner of step S3205 can refer to the optional implementation manner of step S2109 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and so on, details are not repeated here.

[0382] FIG. 3C is a flow diagram of a communication method performed by a terminal A according to an embodiment of the present disclosure. As shown in FIG. 3C, the embodiment of the present disclosure relates to a communication method, which is performed by a terminal A. The above-mentioned communication method comprises steps S3301 to S3305.

[0383] In step S3301, first information is sent.

[0384] The optional implementation manner of step S3301 can refer to the optional implementation manner of step S2101 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and so on, details are not repeated here.

[0385] In step S3302, fifth information is received.

[0386] The optional implementation manner of step S3302 can refer to the optional implementation manner of step S2106 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and so on, details are not repeated here.

[0387] In step S3303, inference data A is sent based on the fifth information.

[0388] The optional implementation manner of step S3303 can refer to the optional implementation manner of step S2107 in FIG. 2, other associated parts in the embodiments involved in FIG. 2.

[0389] In step S3304, inference results are received.

[0390] The optional implementation manner of step S3304 can refer to the optional implementation manner of step S2109 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and so on, details are not repeated here.

[0391] In step S3305, based on the inference results sent by the plurality of inference nodes A, a first inference result of the first AI inference service is determined.

[0392] The optional implementation manner of step S3305 can refer to the optional implementation manner of step S2110 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and so on, details are not repeated here.

[0393] FIG. 4A is a flow diagram of a communication method performed by a first node according to an embodiment of the present disclosure. As shown in FIG. 4A, the embodiment of the present disclosure relates to a communication method, which is performed by a first node. The above-mentioned communication method comprises steps S4101 to S4103.

[0394] In step S4101, first information is acquired.

[0395] The optional implementation of step S4101 can refer to the optional implementation of step S2101 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0396] In step S4102, the second node is determined.

[0397] The optional implementation of step S4102 can refer to the optional implementation of step S2102 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0398] In step S4103, the second information is sent.

[0399] The optional implementation of step S4103 can refer to the optional implementation of step S2104 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0400] FIG. 4B is a flow diagram of a communication method performed by a second node according to an embodiment of the present disclosure. As shown in FIG. 4B, the embodiment of the present disclosure relates to a communication method, which is performed by a second node. The above-mentioned communication method comprises step S4201.

[0401] In step S4201, the second information is received.

[0402] The optional implementation of step S4201 can refer to the optional implementation of step S2104 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0403] FIG. 4C is a flow diagram of a communication method performed by a fourth node according to an embodiment of the present disclosure. As shown in FIG. 4C, the embodiment of the present disclosure relates to a communication method, which is performed by a fourth node. The above-mentioned communication method comprises step S4301.

[0404] In step S4301, the first information is sent.

[0405] The optional implementation of step S4301 can refer to the optional implementation of step S2101 in FIG. 2, other associated parts in the embodiments involved in FIG. 2, and the like, which will not be repeated here.

[0406] In the following, the technical solutions of the embodiments of the present disclosure are exemplarily described through specific embodiments.

[0407] In some embodiments, the AI model inference on the UE side can be performed locally on the UE, but due to the limited computing capability of the UE, the UE cannot support services that require higher computing resources beyond the computing resources of the UE.

[0408] In some embodiments, the third-party server can perform AI model inference for the UE, which can reduce the computational resource requirement for the UE, but it will bring additional delay, which can negatively impact the user experience.

[0409] In some embodiments, a framework is proposed for a 6G network to provide AI model inference service to a UE, by defining a new AiISF to implement the following functions: (1) select inference nodes for inference service requests from the UE. (2) assign inference tasks for each selected inference node. (3) trigger to initiate data connection(s) for transferring inference input data and inference results between the UE and the inference node(s). The UE is responsible for merging the inference results from multiple inference nodes.

[0410] In some embodiments, the AiISF is responsible for selecting inference nodes and assigning / creating inference tasks for each selected inference node, and supports initiating data connection establishment between the UE and the inference nodes (similar to PDU session). The UE merges the inference results from multiple inference nodes.

[0411] In some embodiments, the UE sends an inference service request to the AiISF through the 6G RAN, including UE ID, inference service requirements, AI model metadata. In some embodiments, the inference service requirements include: latency, data rate. In some embodiments, the AI model metadata includes AI model ID, version, size.

[0412] In some embodiments, the AiISF determines to accept the request and determines the inference method, whether to use a central inference method, or use a FL inference method, a distributed inference method, or other pre-configured or defined methods. Based on the selected inference method, the AiISF selects inference nodes and assigns a task ID for each inference node.

[0413] In some embodiments, the AiISF requests to establish data connections between the UE and the inference nodes, sends inference task ID, AI model metadata, inference service requirements.

[0414] In some embodiments, the data connection establishment response sends the IP address / port information of the inference node.

[0415] In some embodiments, the AiISF sends an inference service response message to the 6G RAN, including the IP address / port information of the inference node.

[0416] In some embodiments, based on the message from the AiISF, specific resources are established between the UE and the RAN. In addition, the inference task ID and the corresponding inference node information are sent to the UE.

[0417] In some embodiments, the UE sends, to the inference node, inference input data according to the inference task ID via the established data connection.

[0418] In some embodiments, the inference node obtains the inference result by performing inference on the AI model.

[0419] In some embodiments, the inference node sends the inference result to the UE.

[0420] In some embodiments, the UE merges inference results from multiple inference nodes.

[0421] Embodiments of the present disclosure also propose a device for implementing any of the above methods, for example, a terminal including units or modules for implementing each step performed by the terminal in any of the above methods. For another example, another network device is also proposed, including units or modules for implementing each step performed by the network device (such as an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0422] It should be understood that the division of each unit or module in the above apparatus is only a logical function division, and all or part of them can be integrated into a physical entity or physically separated in actual implementation. In addition, the units or modules in the apparatus can be implemented in the form of processor calling software: for example, the apparatus includes a processor, the processor is connected with a memory, the memory stores instructions, and the processor calls the instructions stored in the memory to realize the functions of any of the above methods or the units or modules of the above apparatus, wherein the processor is a general processor such as a central processing unit (CPU) or a microprocessor, and the memory is a memory in the apparatus or a memory outside the apparatus. Alternatively, the units or modules in the apparatus can be implemented in the form of hardware circuit, and the functions of part or all of the units or modules can be realized by the design of the hardware circuit. The above hardware circuit can be understood as one or more processors; for example, in one implementation, the above hardware circuit is an application-specific integrated circuit (ASIC), and the functions of part or all of the units or modules are realized by the design of the logical relationship between the elements in the circuit; for another example, in another implementation, the above hardware circuit is a programmable logic device (PLD), and a field programmable gate array (FPGA) is taken as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to realize the functions of part or all of the units or modules. All units or modules of the above apparatus can be all implemented in the form of processor calling software, or all implemented in the form of hardware circuit, or part implemented in the form of processor calling software and the remaining part implemented in the form of hardware circuit.

[0423] In the embodiments of the present disclosure, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and running capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), a digital signal processor (DSP), and the like. In another implementation, the processor can implement certain functions through a logical relationship of hardware circuits, and the logical relationship of the hardware circuits is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In the reconfigurable hardware circuit, the processor loads a configuration document to implement the configuration of the hardware circuit. It can be understood that the processor loads instructions to implement the functions of the above part or all units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), and the like.

[0424] FIG. 5A is a structural schematic diagram of a first node according to an embodiment of the present disclosure. As shown in FIG. 5A, the first node 5100 can include a first transceiver module 5101 and a first processing module 5102. In some embodiments, the first transceiver module 5101 is configured to obtain first information, the first information being used to request a first artificial intelligence (AI) inference service; and transmit second information, the second information being used to instruct a second node to provide the first AI inference service. The first processing module 5102 is configured to determine, according to the first information, the second node used to provide the first AI inference service. In some embodiments, the first transceiver module 5101 is configured to perform at least one of the communication steps (for example, steps S3101, S3104, and S3105, but not limited thereto) performed by the first node in any of the above methods, such as transmitting and / or receiving. Details are not described herein again.

[0425] FIG. 5B is a schematic structural diagram of the second node, according to an embodiment of the present disclosure. As shown in FIG. 5B, the second node 5200 can include a second transceiver module 5201. In some embodiments, the second transceiver module 5201 is configured to receive second information sent by the first node, the second information being used to indicate that the second node provides the first AI inference service, and the second node being determined by the first node according to the first information, the first information being used to request the first AI inference service. In some embodiments, the second transceiver module 5201 can be configured to perform at least one of the communication steps (for example, step S3201, step S3202, but not limited to) performed by the second node in any of the above methods, and details are not described herein again.

[0426] FIG. 5C is a schematic structural diagram of the fourth node, according to an embodiment of the present disclosure. As shown in FIG. 5C, the fourth node 5300 can include a third transceiver module 5301. In some embodiments, the third transceiver module 5301 is configured to send first information to the first node, the first information being used to request the first AI inference service, and the first AI inference service being provided by the second node, the second node being determined by the first node according to the first information. In some embodiments, the third transceiver module 5301 described above is configured to perform at least one of the communication steps (for example, step S3301, step S3302, but not limited to) performed by the fourth node in any of the above methods, and details are not described herein again.

[0427] In some embodiments, the transceiver module described above can include a sending module and / or a receiving module. The sending module and the receiving module can be separate or integrated together. Alternatively, the transceiver module described above can be replaced by a transceiver.

[0428] FIG. 6 is a schematic structural diagram of a communication device, according to an embodiment of the present disclosure. The communication device 6100 can be any one of the first node, the second node, and the fourth node, can be a chip, a chip system, or a processor supporting the first node to implement any of the above methods, can be a chip, a chip system, or a processor supporting the second node to implement any of the above methods, and can be a chip, a chip system, or a processor supporting the fourth node to implement any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments, and details can be referred to the descriptions in the above method embodiments.

[0429] As shown in FIG. 6, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general processor or a special-purpose processor, etc., such as a baseband processor or a central processor. The baseband processor can be used to process communication protocols and communication data, and the central processor can be used to control a communication apparatus (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process data of the programs. Optionally, the communication device 6100 is configured to perform any of the above methods. Optionally, the one or more processors 6101 are configured to invoke instructions to cause the communication device 6100 to perform any of the above methods.

[0430] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps (e.g., step S3101, step S3201, step S3301, but not limited to this) in the above methods, and the processor 6101 performs at least one of the other steps (e.g., step S3102, step S3204, step S3303, but not limited to this). In an optional embodiment, the transceiver 6102 can include a receiver and / or a transmitter, which can be separate or integrated together. Optionally, the terms transceiver, transceiving unit, transceiver, transceiving circuit, interface circuit, interface, etc. can be replaced with each other, and the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced with each other, and the terms receiver, receiving unit, receiver, receiving circuit, etc. can be replaced with each other.

[0431] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data. Optionally, all or part of the memory 6103 can also be outside the communication device 6100. In an optional embodiment, the communication device 6100 can include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6103, and the interface circuit 6104 can be used to receive data from the memory 6103 or other devices, and can be used to send data to the memory 6103 or other devices. For example, the interface circuit 6104 can read data stored in the memory 6103 and send the data to the processor 6101.

[0432] The communication device 6100 described in the above embodiments can be a network device or a terminal, but the scope of the communication device 6100 described in the present disclosure is not limited thereto, and the structure of the communication device 6100 can not be limited to that of FIG. 6. The communication device can be a standalone device or can be part of a larger device. For example, the communication device can be: 1) a standalone integrated circuit (IC), or a chip, or a chip system or subsystem; (2) a set of one or more ICs, which can optionally also include storage components for storing data, programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, a smart terminal device, a cellular phone, a wireless device, a handset, a mobile unit, a vehicle-mounted device, a network device, a cloud device, an artificial intelligence device, and the like; (6) others, and the like.

[0433] FIG. 7 is a structural schematic diagram of a chip according to an embodiment of the present disclosure. For the case where the communication device 6100 can be a chip or a chip system, the structural schematic diagram of the chip 7100 shown in FIG. 7 can be referred to, but is not limited thereto.

[0434] The chip 7100 includes one or more processors 7101. The chip 7100 is configured to perform any of the above methods.

[0435] In some embodiments, the chip 7100 further includes one or more interface circuits 7102. Optionally, the terms interface circuit, interface, transceiver pin, and the like can be replaced with each other. In some embodiments, the chip 7100 further includes one or more memories 7103 for storing data. Optionally, all or part of the memory 7103 can be outside the chip 7100. Optionally, the interface circuit 7102 is connected with the memory 7103, and the interface circuit 7102 can be configured to receive data from the memory 7103 or other devices, and the interface circuit 7102 can be configured to send data to the memory 7103 or other devices. For example, the interface circuit 7102 can read data stored in the memory 7103 and send the data to the processor 7101.

[0436] In some embodiments, the interface circuit 7102 performs at least one of the communication steps (for example, step S3101, step S3201, step S3301, but not limited thereto) of sending and / or receiving in the above methods. The interface circuit 7102 performing the communication steps such as sending and / or receiving in the above methods means that the interface circuit 7102 performs data interaction between the processor 7101, the chip 7100, the memory 7103, or a transceiver device. In some embodiments, the processor 7101 performs at least one of the other steps (for example, step S3102, step S3204, step S3303, but not limited thereto).

[0437] The modules and / or devices described in each embodiment of the virtual device, the physical device, the chip, etc. can be combined or separated as appropriate. Alternatively, some or all of the steps can be performed cooperatively by a number of modules and / or devices, which are not limited here.

[0438] The embodiments of the present disclosure further provide a storage medium, and the storage medium stores instructions. When the instructions run on the communication device 6100, the communication device 6100 performs any one of the above methods. Alternatively, the storage medium is an electronic storage medium. Alternatively, the storage medium is a computer readable storage medium, but is not limited to this, and it can also be a storage medium readable by other devices. Alternatively, the storage medium can be a non-transitory storage medium, but is not limited to this, and it can also be a transitory storage medium.

[0439] The embodiments of the present disclosure further provide a program product, and the program product is executed by the communication device 6100, so that the communication device 6100 performs any one of the above methods. Alternatively, the program product is a computer program product.

[0440] The embodiments of the present disclosure further provide a computer program, and when the computer program runs on a computer, the computer executes any one of the above methods.

[0441] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The present disclosure is intended to cover any and all variations of the present application which become apparent to those skilled in the art from this description which is to be regarded in an illustrative rather than a restrictive sense. The true scope and spirit of the application is indicated by the following claims.

[0442] It should be understood that the application is not limited to the precise construction that has been described above and illustrated in the accompanying drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application should be limited only by the appended claims.

Claims

A communication method performed by a first node, the method comprising: obtaining first information, the first information being used for requesting a first artificial intelligence (AI) inference service; determining, according to the first information, a second node for providing the first AI inference service; sending second information, the second information being used for instructing the second node to provide the first AI inference service. The method of claim 1, wherein, The first information comprises at least one of: first indication information, used for indicating a fourth node requesting the first AI inference service; second indication information, used for indicating a quality requirement of the first AI inference service; third indication information, used for indicating a model requirement of the first AI inference service; fourth indication information, used for indicating a type of the first AI inference service; fifth indication information, used for indicating a location of the fourth node; sixth indication information, used for indicating a service area of the first AI inference service. The method according to claim 1 or 2, wherein The determining, according to the first information, of the second node for providing the first AI inference service comprises: determining, according to the first information and third information associated with a plurality of third nodes, the second node from the plurality of third nodes, wherein the plurality of third nodes are nodes for providing AI inference services. The method of claim 3, wherein, The third information comprises at least one of: seventh indication information, used for indicating support capabilities of the third node for different types of AI inference services; eighth indication information, used for indicating support capabilities of the third node for AI models; ninth indication information, used for indicating resources of the third node for processing the AI inference service; tenth indication information, used for indicating a location of the third node. The method according to claim 1 or 2, wherein The determining, according to the first information, of the second node for providing the first AI inference service comprises: determining, according to the first information and eleventh indication information, the second node; wherein the eleventh indication information is used for indicating a mapping relationship between a type of AI inference service and a second node. The method according to any one of claims 1 to 5, wherein The method further comprises one of: determining, according to the first information, a first inference method adopted by the first AI inference service; determining, according to the first information and twelfth indication information, a first inference method adopted by the first AI inference service; wherein the twelfth indication information is used for indicating a mapping relationship between a type of AI inference service and an inference method. The method of claim 6, wherein, The second information is further used for instructing the second node to provide the first AI inference service by using the first inference method. The method according to any one of claims 1 to 7, wherein The number of the second nodes is a plurality, and the method further comprises: determining a plurality of inference tasks associated with the first AI inference service; allocating the plurality of inference tasks to the plurality of second nodes. The method according to any one of claims 1 to 8, wherein The second information comprises at least one of: the first information; thirteenth indication information, used for indicating the first AI inference service; fourteenth indication information, used for indicating the plurality of inference tasks associated with the first AI inference service; fifteenth indication information, used for indicating the first inference method adopted by the first AI inference service. The method according to any one of claims 1 to 9, wherein The second information is further used for requesting a data connection to be established between the second node and a fourth node. The method of claim 10, wherein, The method further comprises: receive fourth information sent by the second node, the fourth information being used for indicating an access address of the second node; send fifth information to the fourth node, the fifth information comprising the fourth information. The method of claim 11, wherein, The number of the second nodes is multiple, and the fifth information further comprises: sixteenth indication information used for indicating a mapping relationship between the first AI inference service and the second nodes. The method according to any one of claims 1 to 12, wherein The first node and the second node are deployed on a same device. A communication method performed by a second node, the method comprising: receiving second information sent by a first node, the second information being used for indicating that the second node provides a first AI inference service, and the second node being determined by the first node according to first information, the first information being used for requesting the first AI inference service. The method of claim 14, wherein, The first information comprises at least one of: first indication information used for indicating a fourth node requesting the first AI inference service; second indication information used for indicating a quality requirement of the first AI inference service; third indication information used for indicating a model requirement of the first AI inference service; fourth indication information used for indicating a type of the first AI inference service; fifth indication information used for indicating a location of the fourth node; sixth indication information used for indicating a service area of the first AI inference service. The method according to claim 14 or 15, wherein The second node is determined by the first node from a plurality of third nodes according to the first information and third information associated with the plurality of third nodes, and the plurality of third nodes are nodes used for providing AI inference services. The method of claim 16, wherein, The third information comprises at least one of: seventh indication information used for indicating a support capability of the second node for different types of AI inference services; eighth indication information used for indicating a support capability of the second node for AI models; ninth indication information used for indicating a resource of the second node for processing the AI inference service; tenth indication information used for indicating a location of the second node. The method according to claim 14 or 15, wherein The second node is determined by the first node according to the first information and eleventh indication information, and the eleventh indication information is used for indicating a mapping relationship between a type of AI inference service and a second node. The method according to any one of claims 14 to 18, wherein The second information is further used for indicating that the second node provides the first AI inference service by using a first inference method. The method of claim 19, wherein, The first inference method is obtained based on the first information, or the first inference method is obtained based on the first information and twelfth indication information, and the twelfth indication information is used for indicating a mapping relationship between a type of the AI inference service and an inference method. The method according to any one of claims 14 to 20, wherein The second information is further used for requesting that the second node and a fourth node establish a data connection. The method according to any one of claims 14 to 21, wherein The second information comprises at least one of: the first information; thirteenth indication information used for indicating the first AI inference service; fourteenth indication information used for indicating a plurality of inference tasks associated with the first AI inference service; fifteenth indication information used for indicating a first inference method used by the first AI inference service. The method according to any one of claims 14 to 22, wherein The method further comprises: The fourth information is used to indicate an access address of the second node. The method according to any one of claims 14 to 23, wherein The method further includes: receiving inference data sent by a fourth node; performing AI inference based on the inference data to obtain an inference result. The method of claim 24, wherein, The method further includes: sending the inference result to the fourth node, the inference result being used by the fourth node to determine a first inference result of the first AI inference service. The method according to any one of claims 14 to 25, wherein The first node and the second node are deployed on a same device. A communication method, performed by a fourth node, the method further includes: sending first information to a first node, the first information being used to request a first AI inference service, the first AI inference service being provided by a second node, the second node being determined by the first node according to the first information. The method of claim 27, wherein, The first information includes at least one of: first indication information used to indicate a fourth node requesting the first AI inference service; second indication information used to indicate a quality requirement of the first AI inference service; third indication information used to indicate a model requirement of the first AI inference service; fourth indication information used to indicate a type of the first AI inference service; fifth indication information used to indicate a location of the fourth node; sixth indication information used to indicate a service area of the first AI inference service. The method of claim 27 or 28, wherein, The second node is determined by the first node from a plurality of third nodes according to the first information and third information associated with the plurality of third nodes, the plurality of third nodes being nodes used to provide AI inference services. The method of claim 29, wherein, The third information includes at least one of: seventh indication information used to indicate support capabilities of the third node for different types of AI inference services; eighth indication information used to indicate support capabilities of the third node for AI models; ninth indication information used to indicate resources of the third node for processing the AI inference service; tenth indication information used to indicate a location of the third node. The method of claim 27 or 28, wherein, The second node is determined by the first node according to the first information and eleventh indication information, the eleventh indication information being used to indicate a mapping relationship between a type of AI inference service and a second node. The method of any one of claims 27 to 31, wherein The method further includes: receiving fifth information sent by the first node, the fifth information including fourth information, the fourth information being used to indicate an access address of the second node; based on the fifth information, sending inference data to the second node. The method of claim 32, wherein, The number of the second nodes is a plurality, and the fifth information further includes: sixteenth indication information used to indicate a mapping relationship between an inference task associated with the first AI inference service and a second node. The method of any one of claims 27 to 33, wherein The method further includes: receiving an inference result sent by the second node; based on the inference result, determining a first inference result of the first AI inference service. The method of claim 34, wherein, The number of the second nodes is a plurality, and the first inference result is determined based on inference results sent by a plurality of second nodes. The method of claim 35, wherein, The method further includes: merging the inference results sent by the plurality of second nodes to obtain the first inference result. A first node includes: The first transceiver module is configured to obtain first information, the first information being used to request a first artificial intelligence (AI) inference service; The second transceiver module is configured to send second information, the second information being used to instruct a second node to provide the first AI inference service; The first processing module is configured to determine, according to the first information, the second node used to provide the first AI inference service. A second node comprises: The second transceiver module is configured to receive second information sent by a first node, the second information being used to instruct the second node to provide a first AI inference service, the second node being determined by the first node according to first information, the first information being used to request the first AI inference service. A fourth node comprises: The third transceiver module is configured to send first information to a first node, the first information being used to request a first AI inference service, the first AI inference service being provided by a second node, the second node being determined by the first node according to the first information. A communication device comprises: One or more processors; The communication device is configured to perform the communication method in any one of claims 1 to 36. A communication system comprises a first node, a second node and a fourth node; The first node is configured to implement the communication method in any one of claims 1 to 13; the second node is configured to implement the communication method in any one of claims 14 to 26; and the fourth node is configured to implement the communication method in any one of claims 27 to 36. A storage medium stores instructions, when the instructions are executed on a communication device, the communication device performs the communication method in any one of claims 1 to 36. A computer program product comprises a computer program, when the computer program is executed by a processor, the communication method in any one of claims 1 to 36 is implemented.

Images