Communication method, device and system, and storage medium

Abstract

The present application relates to the technical field of communications. Disclosed are a communication method and apparatus, and a computer-readable storage medium. The communication method comprises: a network device receiving first information sent by at least one first terminal, wherein the first information is configured to indicate manufacturer information corresponding to an artificial intelligence (AI) model of the at least one first terminal. In the embodiments of the present disclosure, by means of receiving manufacturer information corresponding to AI model training provided by at least one first terminal, a network device can determine a terminal that sends a dataset used for the AI model training, thereby avoiding repeated sending of a training dataset of an AI model, and improving the utilization rate of radio resources.

Description

Communication methods, devices, systems and storage media Technical Field

[0001] This disclosure relates to the field of communication technology, and more specifically, to a communication method, device, system, and storage medium. Background Technology

[0002] With the development of technology, artificial intelligence (AI) and machine learning (ML) have been applied to the field of communication to improve communication performance. AI datasets can be transmitted between the sending and receiving ends for training purposes. Summary of the Invention

[0003] This disclosure provides a communication method, device, system, and storage medium.

[0004] A first aspect of this disclosure provides a communication method, the method being executed by a second terminal, the method comprising:

[0005] Send a first message to the network device, the first message being used to instruct the second terminal's artificial intelligence (AI) model to train the corresponding manufacturer information.

[0006] A second aspect of this disclosure provides a communication method, the method being executed by a network device, the method comprising:

[0007] The network device receives first information sent by at least one first terminal, the first information being used to indicate the manufacturer information corresponding to the artificial intelligence (AI) model of the at least one first terminal.

[0008] A third aspect of this disclosure provides a terminal, including:

[0009] The first transceiver module is used to send first information to the network device, wherein the first information is used to instruct the artificial intelligence (AI) model training of the second terminal to provide the corresponding manufacturer information.

[0010] A fourth aspect of this disclosure provides a network device, including:

[0011] The second transceiver module is used to receive first information sent by at least one first terminal, the first information being used to indicate the manufacturer information corresponding to the artificial intelligence (AI) model of the at least one first terminal.

[0012] A fifth aspect of this disclosure provides a terminal, including:

[0013] One or more processors;

[0014] The terminal is used to execute the optional implementation of the first aspect described above.

[0015] A sixth aspect of this disclosure provides a network device, including:

[0016] One or more processors;

[0017] The network device is used to perform an optional implementation of the second aspect described above.

[0018] A seventh aspect of this disclosure provides a communication system including a terminal and a network device, wherein the terminal is used to implement the method described in the optional embodiments of the first aspect, and the network device is used to implement the method described in the optional embodiments of the second aspect.

[0019] According to an eighth aspect of the present disclosure, a computer-readable storage medium is provided that stores executable instructions which are loaded and executed by the processor to implement the method described in the optional embodiments of the first or second aspect.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0022] Figure 1 is a schematic diagram of a wireless communication system according to an exemplary embodiment;

[0023] Figure 2a is a flowchart illustrating a communication method according to an exemplary embodiment;

[0024] Figure 2b is a flowchart illustrating a communication method according to an exemplary embodiment;

[0025] Figure 2c is a flowchart illustrating a communication method according to an exemplary embodiment;

[0026] Figure 2d is a flowchart illustrating a communication method according to an exemplary embodiment;

[0027] Figure 2e is a flowchart illustrating a communication method according to an exemplary embodiment;

[0028] Figure 3a is a flowchart illustrating the communication method according to an embodiment of this disclosure;

[0029] Figure 3b is a flowchart illustrating the communication method according to an embodiment of this disclosure;

[0030] Figure 4a is a flowchart illustrating the communication method according to an embodiment of this disclosure;

[0031] Figure 4b is a flowchart illustrating the communication method according to an embodiment of this disclosure;

[0032] Figure 5a is a flowchart illustrating the communication method according to an embodiment of this disclosure;

[0033] Figure 5b is a schematic diagram illustrating manufacturer information according to an embodiment of this disclosure;

[0034] Figure 5c is a flowchart illustrating the communication method according to an embodiment of this disclosure;

[0035] Figure 6a is a schematic diagram of the structure of the terminal proposed in an embodiment of this disclosure;

[0036] Figure 6b is a schematic diagram of the structure of the network device proposed in an embodiment of this disclosure;

[0037] Figure 7a is a schematic diagram of the structure of the communication device proposed in an embodiment of this disclosure;

[0038] Figure 7b is a schematic diagram of the chip structure proposed in an embodiment of this disclosure. Detailed Implementation

[0039] This disclosure provides communication methods, devices, communication systems, and storage media.

[0040] In a first aspect, embodiments of this disclosure propose a communication method, which is executed by a second terminal, and the method includes:

[0041] Send a first message to the network device, the first message being used to instruct the second terminal's artificial intelligence (AI) model to train the corresponding manufacturer information.

[0042] In the above embodiments, by providing the network device with manufacturer information related to AI model training through the terminal, the network device can determine the terminal that should send the AI ​​model training dataset based on the information, thereby avoiding duplicate transmission of AI datasets and improving the utilization rate of wireless resources.

[0043] In conjunction with some embodiments of the first aspect, in some embodiments, the manufacturer information corresponding to the second terminal includes: manufacturer identifier and AI training identifier.

[0044] In the above embodiments, the manufacturer's information includes a manufacturer identifier and an AI training identifier, which can identify terminals with the same hardware or using the same AI training server.

[0045] In conjunction with some embodiments of the first aspect, some embodiments further include:

[0046] Receive the training dataset sent by the network device;

[0047] The training dataset can be any of the following:

[0048] The dataset corresponding to the AI ​​model;

[0049] The dataset corresponding to one AI use case of the AI ​​model;

[0050] The dataset corresponding to one AI function of the AI ​​model;

[0051] The dataset corresponding to one AI use case of one AI function of the AI ​​model.

[0052] In conjunction with some embodiments of the first aspect, in some embodiments, the manufacturer information corresponding to the second terminal includes information of one manufacturer or information of multiple manufacturers.

[0053] In conjunction with some embodiments of the first aspect, in some embodiments, the manufacturer information corresponding to the second terminal is reported by the first terminal based on the following granularity: terminal, chip, AI use case, AI function, AI model.

[0054] In the above embodiments, the way the terminal reports manufacturer information related to AI model training is flexible, so as to better adapt to the power consumption requirements of the terminal.

[0055] In conjunction with some embodiments of the first aspect, in some embodiments, sending the first information includes:

[0056] The first information is sent to the access network device via a Radio Link Control (RRC) message.

[0057] In the above embodiments, the terminal can provide (e.g., proactively provide) manufacturer information related to AI model training to the access network device serving it. This allows the network device to determine the terminal that should send the AI ​​model training dataset based on the information, thereby avoiding duplicate transmission of AI datasets and improving the utilization of wireless resources.

[0058] In conjunction with some embodiments of the first aspect, in some embodiments, before sending the first information to the access network device, the method further includes:

[0059] The system receives a first message sent by the network device, the first message being used to configure information on AI functions and / or AI use cases corresponding to the training of the AI ​​model.

[0060] In the above embodiments, the terminal can provide the access network device with the corresponding manufacturer information related to AI model training based on the AI ​​function or AI use case information configured in the access network device. This enables the access network device to obtain the specific manufacturer information related to AI model training, thereby sending the AI ​​model training-related dataset to the specific terminal, effectively avoiding the repeated sending of AI datasets and improving the utilization rate of wireless resources.

[0061] In conjunction with some embodiments of the first aspect, in some embodiments, sending the first information includes:

[0062] The first information is sent to the core network device via a non-access stratum (NAS) message, wherein the first information is sent by the core network device to the access network device.

[0063] In the above embodiments, the terminal can forward manufacturer information related to AI model training to the access network device through the core network device serving it. This allows the access network device to determine the terminal that sends the AI ​​model training dataset based on the information, thereby avoiding duplicate transmission of AI datasets and improving the utilization rate of wireless resources.

[0064] In conjunction with some embodiments of the first aspect, in some embodiments, receiving the training dataset sent by the network device includes:

[0065] Receive all data of the training dataset and the identifier of the training dataset sent by the access network device; or;

[0066] The second terminal receives a first identifier, a portion of the training dataset, and an identifier of the training dataset sent by the access network device. The first identifier is used to indicate the portion of the training dataset received by the second terminal.

[0067] In the above embodiments, when the terminal is a specific terminal determined by the access network device based on the acquired AI model training-related manufacturer information, it can receive the AI ​​model training dataset sent by the access network device, avoiding repeated transmission of AI datasets and improving the utilization rate of wireless resources.

[0068] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0069] A third message is sent to the network device, the third message indicating that the training of the AI ​​model associated with the training dataset of the AI ​​model has been completed.

[0070] In the above embodiments, the terminal can avoid the problem of repeatedly sending AI training datasets by sending information indicating that the training of the AI ​​model has been completed.

[0071] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0072] After a first duration, the network device receives the training dataset retransmitted by the network device, wherein the network device did not receive a training completion message from the second terminal during the first duration.

[0073] In conjunction with some embodiments of the first aspect, in some embodiments, before sending the third information to the network device, the method further includes:

[0074] AI model training is performed based on the aforementioned training dataset; or...

[0075] The training dataset is sent to the OTT server corresponding to the second terminal, and the third information sent by the server is received.

[0076] In the above embodiments, the terminal can train the AI ​​model based on the received AI model training dataset, or it can send the received AI model training dataset to an associated server for AI model training, so as to reduce the power consumption of the terminal.

[0077] In conjunction with some embodiments of the first aspect, in some embodiments, the access network device is the access network device before the second terminal hands over, and the method further includes:

[0078] If the second terminal switches access network devices after receiving the training dataset, a fourth message is sent to the new access network device after the second terminal switches. The fourth message indicates that the training of the AI ​​model corresponding to the training dataset has been completed.

[0079] In conjunction with some embodiments of the first aspect, in some embodiments, the fourth information includes the identifier of the access network device before the handover, and the fourth information is sent by the access network device after the handover to the access network device before the handover.

[0080] In the above embodiments, if the terminal switches before and after AI training, the terminal may carry the identifier of the access network device that served the terminal before the switch in the information indicating that the training of the AI ​​model has been completed when sending the information to the first access network device that is currently providing services to it. This allows the first access network device to forward the information indicating that the training of the AI ​​model has been completed to the access network device before the switch.

[0081] Secondly, embodiments of this disclosure provide a communication method, executed by a network device, the method comprising:

[0082] The network device receives first information sent by at least one first terminal, the first information being used to indicate the manufacturer information corresponding to the artificial intelligence (AI) model of the at least one first terminal.

[0083] In the above embodiments, the network device can determine the terminal that sent the training dataset of the AI ​​model by receiving manufacturer information corresponding to the AI ​​model training provided by at least one first terminal, thereby avoiding the repeated transmission of the training dataset of the AI ​​model and improving the utilization rate of wireless resources.

[0084] In conjunction with some embodiments of the second aspect, in some embodiments, the manufacturer information corresponding to the first terminal includes: manufacturer identifier and AI training identifier.

[0085] In conjunction with some embodiments of the second aspect, some embodiments further include:

[0086] Based on the first information, a training dataset is sent to a second terminal, wherein the second terminal is one or more of the at least one first terminal.

[0087] In conjunction with some embodiments of the second aspect, in some embodiments, the training dataset is any one of the following:

[0088] The dataset corresponding to the AI ​​model;

[0089] The dataset corresponding to one AI use case of the AI ​​model;

[0090] The dataset corresponding to one AI function of the AI ​​model;

[0091] The dataset corresponding to one AI use case of one AI function of the AI ​​model.

[0092] In conjunction with some embodiments of the second aspect, in some embodiments, the manufacturer information corresponding to the first terminal is reported by the first terminal based on the following granularity: terminal, chip, AI use case, AI function, AI model.

[0093] In conjunction with some embodiments of the second aspect, in some embodiments, the network device is an access network device, and before receiving the first information sent by the terminal, the method further includes:

[0094] A first message is sent to the terminal, the first message being used to configure information on AI functions and / or AI use cases related to the training of the AI ​​model.

[0095] In conjunction with some embodiments of the second aspect, in some embodiments, when the number of the second terminal is one, the step of sending the training dataset to the second terminal according to the first information includes:

[0096] Based on the first information, send all the data of the training dataset and the identifier of the training dataset to the second terminal;

[0097] When there are multiple second terminals, the step of sending the training dataset to the second terminals according to the first information includes:

[0098] Based on the first information, all the data of the training dataset is sent to the plurality of second terminals.

[0099] In conjunction with some embodiments of the second aspect, in some embodiments, the network device is an access network device, and further includes:

[0100] Send the first information to the core network equipment.

[0101] In conjunction with some embodiments of the second aspect, in some embodiments, sending all the data of the training dataset to the plurality of second terminals based on the first information includes:

[0102] Based on the first information, a portion of the training dataset, the identifier of the training dataset, and a first identifier are sent to each of the plurality of second terminals, wherein the first identifier is the identifier of the portion.

[0103] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0104] The system receives a third message sent by the first terminal, the third message indicating that the training of the AI ​​model associated with the training dataset has been completed.

[0105] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0106] If the network device does not receive a training completion message from the second terminal within a first time period during which the training dataset is sent to the second terminal, the network device will resend the training dataset.

[0107] In conjunction with some embodiments of the second aspect, in some embodiments, the access network device is the access network device before the second terminal hands over, and the method further includes:

[0108] When the second terminal switches access network devices after receiving the training dataset, it receives fourth information sent by the access network device after the second terminal switches. The fourth information is used to indicate that the training of the AI ​​model corresponding to the training dataset has been completed.

[0109] In conjunction with some embodiments of the second aspect, in some embodiments, the fourth information includes the identifier of the access network device prior to the handover.

[0110] In conjunction with some embodiments of the second aspect, in some embodiments, the network device is the access network device before the terminal handover, and the method further includes:

[0111] The first information is sent to the access network device after the second terminal is switched.

[0112] In conjunction with some embodiments of the second aspect, in some embodiments, the network device is a core network device, and the method further includes:

[0113] Send the first information to the access network device; and / or,

[0114] Store the first information.

[0115] Thirdly, embodiments of this disclosure provide a terminal, including:

[0116] The first transceiver module is used to send first information to the network device, wherein the first information is used to instruct the artificial intelligence (AI) model training of the second terminal to provide the corresponding manufacturer information.

[0117] Fourthly, embodiments of this disclosure provide a network device, including:

[0118] The second transceiver module is used to receive first information sent by at least one first terminal, the first information being used to indicate the manufacturer information corresponding to the artificial intelligence (AI) model of the at least one first terminal.

[0119] Fifthly, embodiments of this disclosure provide a terminal, including:

[0120] One or more processors;

[0121] The terminal executes the method described in the optional implementation of the first aspect.

[0122] According to a sixth aspect of the embodiments of this disclosure, a network device is provided, comprising:

[0123] One or more processors;

[0124] The network device performs the method described in the optional implementation of the second aspect.

[0125] In a seventh aspect, embodiments of this disclosure provide a communication system including a terminal and a network device, wherein the terminal is used to implement the method described in the optional implementation of the first aspect, and the network device is used to implement the method described in the optional implementation of the second aspect.

[0126] Eighthly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the method as described in the optional embodiments of the first or second aspect.

[0127] Ninthly, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the method as described in the optional implementation of the first or second aspect.

[0128] In a tenth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in an optional implementation of the first or second aspect.

[0129] Eleventhly, embodiments of this disclosure provide a chip or chip system including processing circuitry for performing the method described in an optional implementation of the first or second aspect above.

[0130] Understandably, the aforementioned devices, communication equipment, communication systems, storage media, program products, and computer programs for random access are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here. The communication equipment can be a terminal or a network device.

[0131] This disclosure provides communication methods, apparatus, devices, systems, and storage media.

[0132] In some embodiments, the terms "communication method" and "for random access" can be used interchangeably, the terms "apparatus for random access" and "information processing apparatus" and "communication apparatus" can be used interchangeably, and the terms "information processing system" and "communication system" can be used interchangeably.

[0133] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of the embodiments disclosed. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0134] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0135] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the embodiments of this disclosure.

[0136] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0137] In the embodiments disclosed herein, "multiple" refers to two or more.

[0138] In some embodiments, the terms “at least one of”, “at least one of”, “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0139] The descriptions in this disclosure, such as "at least one of A, B, C..." or "A and / or B and / or C...", include the case where any one of A, B, C... exists alone, as well as the case where any combination of any of A, B, C... exists alone. Each case can exist alone. For example, "at least one of A, B, C" includes the cases of A alone, B alone, C alone, A and B combination, A and C combination, B and C combination, and A and B and C combination. For example, A and / or B includes the cases of A alone, B alone, and A and B combination.

[0140] In some embodiments, the notation "in one case A, in another case B" or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: A is executed regardless of B, i.e., A is executed in some embodiments; B is executed regardless of A, i.e., B is executed in some embodiments; A and B are selectively executed, i.e., A and B are selected for execution in some embodiments; A and B are both executed, i.e., A and B are executed in some embodiments. The same applies when there are more branches such as A, B, and C.

[0141] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. As another example, if the object being described is "information", then "first configuration" and "second configuration" can be the same information or different information, and their content can be the same or different.

[0142] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0143] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0144] 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,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0145] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0146] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0147] 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", and "client" can be used interchangeably.

[0148] In some embodiments, the access network device, core network device, or network device can be replaced by a terminal. For example, various embodiments of this disclosure can also be applied to structures that replace communication between the access network device, core network device, or network device and the terminal with communication between multiple terminals (e.g., also referred to as 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. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "side").

[0149] For example, uplink channels and downlink channels can be replaced with side channels, and uplink links and downlink links can be replaced with side links.

[0150] In some embodiments, terms such as “uplink”, “uplink”, and “physical uplink” can be used interchangeably, as can terms such as “downlink”, “downlink”, and “physical downlink”, and terms such as “sidelink”, “sidelink”, “sidelink communication”, “sidelink communication”, “direct connection”, “direct link”, “direct communication”, and “direct link communication”.

[0151] In some embodiments, the terms “downlink control information (DCI),” “downlink (DL) assignment,” “DL DCI,” “uplink (UL) grant,” and “UL DCI” can be used interchangeably.

[0152] In some embodiments, terms such as "physical downlink shared channel (PDSCH)" and "DL data" can be used interchangeably, as can terms such as "physical uplink shared channel (PUSCH)" and "UL data".

[0153] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values ​​(e.g., a comparison with a predetermined value), but is not limited thereto.

[0154] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0155] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0156] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0157] Figure 1 is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0158] As shown in Figure 1, the communication system 100 includes a terminal 101 and a network device 102.

[0159] In some embodiments, terminal 101 includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0160] In some embodiments, network device 102 may include at least one of access network device and core network device.

[0161] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), wireless backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a wireless fidelity (WiFi) system.

[0162] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0163] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0164] In some embodiments, the access network device may be a single device, multiple devices, or a group of devices, including all or part of a first network element, a second network element, etc. Network elements may be virtual or physical. Network devices may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC).

[0165] In some embodiments, a core network device may be a single device comprising one or more network elements, or it may be multiple devices or a group of devices, each comprising all or part of the aforementioned one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), or a Next Generation Core (NGC).

[0166] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0167] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1 are illustrative. The communication system may include all or some of the main bodies in FIG1, or may include other main bodies outside of FIG1. ​​The number and form of each main body are arbitrary. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0168] The embodiments disclosed herein 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), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, utilizing other systems for random access, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0169] Machine learning algorithms are one of the most important methods for implementing artificial intelligence technology. Machine learning can obtain models from large amounts of training data, and these models can then be used to predict events. In many fields, machine learning models can achieve very accurate predictions.

[0170] In 5G systems, AI can be used for prediction and reasoning to improve system performance.

[0171] AI datasets can be transferred between the terminal and network devices for training. For example, in the CSI compression use case, a two-sided model is employed. The network device can provide the terminal with a dataset containing N1 samples, each sample including {target CSI, CSI feedback}, corresponding to the input and output of the nominal encoder, respectively. N1 can reach 600,000, and each sample can have 3,000 bits, resulting in a dataset size of 600K * (2000 bits + 1000 bits) / (8 bits / Byte) = 225MB.

[0172] When an AI model is trained on an OTT server, the terminal needs to transmit the AI ​​data to the OTT server. The terminal can also receive the trained AI model from the OTT server.

[0173] AI datasets can be very large, ranging from hundreds of megabytes. Current technology cannot distinguish between terminals with identical hardware (including AI hardware and / or wireless communication hardware) or using the same AI training server during AI training. Therefore, it's possible to transmit the same AI dataset to multiple terminals with identical hardware or using the same AI training server. This leads to a waste of wireless resources.

[0174] The method provided in this disclosure allows the network side to send AI datasets to specific terminals by instructing the manufacturer information related to AI training, thereby avoiding the repeated sending of AI datasets and improving the utilization rate of wireless resources.

[0175] Based on the aforementioned wireless communication system, various embodiments of the communication method proposed in this disclosure will be described in detail below.

[0176] Figure 2a is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2a, the communication method is used in a communication system 100, and the method includes:

[0177] S201, At least one first terminal sends first information to the network device.

[0178] In some embodiments, the first information is used to indicate manufacturer information related to the training of an artificial intelligence (AI) model for at least one first terminal.

[0179] In some embodiments, the manufacturer information corresponding to the first terminal may include: manufacturer ID and AI training ID.

[0180] In some embodiments, the manufacturer associated with AI model training depends on the specific implementation of model training in the terminal. Optionally, the manufacturer associated with AI model training can be a terminal manufacturer, or a chip manufacturer of the AI ​​model, or a modem manufacturer of wireless communication, or a system-on-chip (SoC) manufacturer of wireless communication.

[0181] In some embodiments, the manufacturer identifier can be a string or a number. Optionally, the manufacturer identifier can be assigned by an entity (e.g., 3GPP, or IANA (Internet Assigned Numbers Authority)).

[0182] In some embodiments, the AI ​​training identifier may be assigned by the manufacturer corresponding to the manufacturer identifier. Optionally, the AI ​​training identifier may be associated with the product model, product version, AI training server used, etc.

[0183] In some embodiments, the manufacturer information corresponding to the first terminal includes information about one manufacturer or information about multiple manufacturers.

[0184] In some embodiments, the manufacturer information corresponding to the first terminal is reported by the first terminal based on one of the following granularities: terminal, chip, AI use case, AI function, AI model.

[0185] In some embodiments, if a terminal reports only one piece of manufacturer information related to AI model training, it can be understood as reporting at the terminal level.

[0186] In some embodiments, a terminal reporting a piece of manufacturer information related to AI model training for an AI use case can be understood as reporting based on the granularity of the AI ​​use case.

[0187] In some embodiments, a terminal reports a piece of manufacturer information related to AI model training for an AI function. The manufacturer information is associated with the AI ​​model corresponding to the AI ​​function, which can be understood as reporting based on the granularity of the AI ​​function.

[0188] In some embodiments, a terminal reports a piece of manufacturer information related to the training of an AI model for an AI model. The manufacturer information is associated with the AI ​​model, which can be understood as reporting at the granularity of the AI ​​model.

[0189] In some embodiments, manufacturer information related to AI model training may include:

[0190] Manufacturer information related to the training of an AI model corresponding to the terminal; or,

[0191] At least one set of information corresponding to the terminal;

[0192] Each of at least one set of information includes any of the following:

[0193] An AI use case and manufacturer information related to the training of an AI model corresponding to that AI use case;

[0194] Information about the manufacturer associated with an AI function and the training of the corresponding AI model;

[0195] An AI model identifier and manufacturer information related to the training of the AI ​​model corresponding to that AI model identifier.

[0196] In some embodiments, manufacturer information related to AI model training can be reported to network devices at the terminal level. Optionally, a terminal may report only one instance of manufacturer information related to AI model training.

[0197] In some embodiments, manufacturer information related to AI model training can also be reported based on AI use case / functionality / AI model identifier. Optionally, a terminal can report one or more pairs of information to the network device, wherein each pair of information includes: an AI use case / functionality / model identifier and the corresponding manufacturer information related to AI model training.

[0198] In some embodiments, the network device may be an access network device or a core network device.

[0199] In some embodiments, step S201 may include:

[0200] At least one first terminal sends first information to the access network device.

[0201] In some embodiments, the first information can be sent to the access network device via a Radio Resource Control (RRC) message. Optionally, the terminal can send manufacturer information related to AI model training to the access network device via an RRC message.

[0202] In some embodiments, the first information can be sent to the access network device via a UE capability message. Optionally, the terminal can send manufacturer information related to AI model training to the access network device via a UE capability message.

[0203] In some embodiments, prior to step S201, the following may also be included:

[0204] Receive the first message sent by the access network device.

[0205] In some embodiments, the first message is used to configure information related to AI functions or AI use cases associated with AI model training.

[0206] In some embodiments, the terminal may send manufacturer information related to AI model training to the access network device in response to a first message sent by the access network device.

[0207] In some embodiments, the first message may be an RRC reconfiguration message (RRCReconfiguration message), and the first information may be sent to the access network device via an RRC reconfiguration complete message (RRCReconfigurationComplete message).

[0208] In some embodiments, after receiving configuration information for AI functions or AI use cases related to AI model training from the access network device, the terminal sends manufacturer information related to AI model training to the access network device.

[0209] In some embodiments, step S201 may include:

[0210] The terminal sends the first information to the core network equipment.

[0211] In some embodiments, the first information may be included in the registration request of the Non-Access Stratum (NAS) message. Optionally, the terminal may send manufacturer information related to AI model training to the core network device via the registration request of the NAS message.

[0212] In some embodiments, the core network equipment may be a core network element, core network function, core network function entity, etc., but is not limited thereto. Optionally, the core network equipment may be an Access and Mobility Management Function (AMF).

[0213] S202. The network device determines the second terminal based on the first information.

[0214] In some embodiments, the second terminal may be one or more of at least one first terminal.

[0215] In some embodiments, a network device may select one or more terminals as a second terminal from a first terminal that reports manufacturer information related to the training of the same AI model.

[0216] It should be understood that in the embodiments disclosed herein, "multiple" can be understood as two or more.

[0217] In some embodiments, the network device is an access network device. When the access network device receives manufacturer information related to AI model training sent by multiple first terminals, if the received manufacturer information related to AI model training contains the same manufacturer information, one or more terminals can be selected as second terminals from the first terminals that sent the same manufacturer information.

[0218] In some embodiments, a second terminal may be selected from a plurality of first terminals that transmit the same manufacturer information based on signal quality. Optionally, the terminal with the best signal quality may be selected from a plurality of first terminals that transmit the same manufacturer information as the second terminal, or at least two first terminals whose signal quality exceeds a threshold may be selected from a plurality of first terminals that transmit the same manufacturer information as the second terminal.

[0219] In some embodiments, step S202 may be omitted. For example, the network device can directly send the second information to at least one first terminal based on the first information, that is, directly execute step S203. The second terminal is the same as the first terminal.

[0220] S203. The network device sends the second information to the determined second terminal.

[0221] In some embodiments, the network device may send the training dataset of the AI ​​model to the second terminal. Optionally, the training dataset may be carried via second information.

[0222] In some embodiments, the second information may include: the training dataset of the AI ​​model and the identifier of the training dataset.

[0223] In some embodiments, the second information may include: a first identifier, a portion of the data in the training dataset of the AI ​​model, and an identifier for the training dataset. Optionally, the first identifier is used to indicate a portion of the data in the training dataset of the AI ​​model. Optionally, the first identifier is used to uniquely identify a portion of the data in the training dataset of the AI ​​model.

[0224] In some embodiments, if the training dataset of an AI model is split and sent to multiple terminals by a network device, a first identifier can be used to identify the different parts of the training dataset after splitting. Optionally, the first identifier can be implemented by combining the identifier of the training dataset with encoding, numbering, or indexing.

[0225] In some embodiments, when there is only one second terminal, step S203 may include sending the training dataset to the second terminal. Optionally, all data of the training dataset and the identifier of the training dataset may be sent to the second terminal.

[0226] In some embodiments, when there are multiple second terminals, step S203 may include: sending the training dataset to the second terminals. Optionally, all data of the training dataset may be sent to multiple second terminals.

[0227] In some embodiments, a portion of the training dataset, an identifier of the training dataset, and a first identifier are sent to each of the plurality of second terminals. Optionally, the first identifier is the identifier of the portion.

[0228] In some embodiments, the training dataset for an AI model may include the training data required to train the AI ​​model.

[0229] Optionally, the training dataset can be any of the following:

[0230] The dataset corresponding to the AI ​​model;

[0231] A dataset corresponding to an AI use case of an AI model;

[0232] The dataset corresponding to one AI function of an AI model;

[0233] A dataset corresponding to an AI use case for an AI function of an AI model.

[0234] In some embodiments, the network device may send the training dataset of the AI ​​model and related information to at least one selected second terminal.

[0235] In some embodiments, the relevant information of the training dataset of the AI ​​model can be the identifier of the AI ​​training dataset and / or a first identifier. Optionally, the identifier of the AI ​​training dataset can be the identifier of the AI ​​model corresponding to the training dataset of the AI ​​model, or the identifier of the AI ​​use case or AI function corresponding to the AI ​​model.

[0236] In some embodiments, if the network device selects a first terminal as a second terminal in step S202, the network device can send the training dataset of the AI ​​model and the identifier of the training dataset to the selected second terminal.

[0237] In some embodiments, if the network device selects multiple first terminals as second terminals in step S202, the network device can send the training dataset of the AI ​​model and the identifier of the training dataset to any one of the multiple second terminals (e.g., terminal #1). Optionally, other terminals among the selected multiple second terminals can be used as candidate terminals. If the network device does not receive (e.g., does not receive within a preset time period (which may correspond to the first duration mentioned above, but is not limited to) the information indicating that the training of the AI ​​model related to the training dataset of the AI ​​model has been completed from terminal #1, another second terminal (e.g., terminal #2) can be selected from the candidate terminals to send the training dataset of the AI ​​model and the identifier of the training dataset. Alternatively, the network device can resend the training dataset and the identifier of the training dataset to terminal #1 until it receives the information indicating that the training of the AI ​​model has been completed.

[0238] In some embodiments, the network device may send a first identifier and a portion of the training dataset of the AI ​​model, as well as the identifier of the training dataset, to at least one selected second terminal.

[0239] In some embodiments, if the network device selects multiple first terminals as second terminals in step S202, the network device splits the training dataset of the AI ​​model and sends it to the multiple second terminals. In order to ensure that the device performing AI model training can determine that the split training data belongs to the training dataset of the same AI model, it is also necessary to send a first identifier to the multiple second terminals to indicate (or identify) a portion of the data in the training dataset of the AI ​​model.

[0240] For example, assuming the network device selects terminals #1, #2, #3, and #4 from the first terminals as the second terminals, and the identifier of the training dataset for AI model #1 is the identifier of the AI ​​model (e.g., ID #1), then: the training dataset for AI model #1 is split and sent to terminals #1, #2, #3, and #4. For example: terminal #1 receives ID #1, the first training data in the training dataset of AI model #1, and its first identifier ID #1a1; terminal #2 receives ID #1, the second training data in the training dataset of AI model #1, and its first identifier ID #1a2; terminal #3 receives ID #1, the third training data in the training dataset of AI model #1, and its first identifier ID #1a3; and terminal #4 receives ID #1, the fourth training data in the training dataset of AI model #1, and its first identifier ID #1a4. It should be understood that the amount of training data sent to terminals #1, #2, #3, and #4 can be the same or different, and this embodiment does not limit this.

[0241] It should be understood that network devices can send training datasets of different AI models to a selected terminal. The identifier of the training dataset is used to distinguish different AI models, and the first identifier is used to distinguish which AI model's training dataset the identified data belongs to.

[0242] It should be understood that in some embodiments, after the first terminal reports the first information to the network device, the step of receiving the training dataset sent by the network device may be omitted. Optionally, if the first terminal is not selected as the second terminal by the network device after reporting the first information, it will not receive the training dataset sent by the network device. In this case, steps S203 and S204 are omitted.

[0243] S204. The network device receives the third information sent by the second terminal.

[0244] In some embodiments, the third information is used to indicate that the training of the AI ​​model associated with the training dataset of the AI ​​model has been completed.

[0245] In some embodiments, the third information may include information related to the training data of the AI ​​model. Optionally, this information may be an identifier of the AI ​​training dataset. For example, the identifier of the AI ​​model corresponding to the AI ​​model's training dataset, or the identifier of the AI ​​use case or AI function corresponding to the AI ​​model.

[0246] In some embodiments, by carrying relevant information about the training data of the AI ​​model in the third information, the network device can obtain which training dataset of the AI ​​model has been trained, thereby avoiding the repeated transmission of the training dataset of the AI ​​model.

[0247] In some embodiments, if a network device sends a training dataset of an AI model to a selected second terminal, the second terminal can train the AI ​​model based on the received training dataset and send third information to the network device after completing the training.

[0248] For example, if the second terminal receives the training dataset corresponding to the identifier (e.g., ID#2) of the AI ​​model, it will train based on the training dataset and, after training is completed, send third information carrying ID#2 to the network device so that the network device can obtain that the AI ​​model corresponding to the training dataset of the AI ​​model corresponding to ID#2 has been trained.

[0249] In some embodiments, if a network device sends a training dataset of an AI model to a selected second terminal, the second terminal can send the received training dataset of the AI ​​model and the identifier of the training dataset to the corresponding OTT (Over The Top) server for AI model training, and after training is completed, forward the third information from the OTT server to the network device.

[0250] In some embodiments, if the network device sends a training dataset of an AI model (e.g., sending a portion of the training dataset of the AI ​​model to each of the selected second terminals), the identifier of the training dataset, and a first identifier, then each second terminal can send the received portion of the training dataset of the AI ​​model, the identifier of the training dataset, and the first identifier to the corresponding OTT server (multiple second terminals correspond to the same OTT server) for AI model training, and after completing the training, forward the third information from the OTT server to the network device.

[0251] It should be noted that step S204 is an optional step.

[0252] In some embodiments, the method described above may further include:

[0253] The network device resends the training dataset.

[0254] In some embodiments, if the network device does not receive a training completion message from the second terminal within a first period of time during which the training dataset is sent to the terminal, the network device resends the training dataset.

[0255] In some embodiments, the second terminal receives the training dataset resent by the network device after a first duration. Optionally, the network device does not receive a message from the second terminal indicating that the training dataset has been trained within the first duration.

[0256] In some embodiments, the names of information, etc., are not limited to those described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", and "data" can be used interchangeably.

[0257] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0258] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0259] In some embodiments, terms such as “in the case of,” “when,” “when,” “if,” “if,” etc., can be used interchangeably.

[0260] The method involved in the embodiments of this disclosure may include at least one of steps S201 to S204. For example, step S201 may be implemented as a standalone embodiment, steps S201 and S202 may be implemented as standalone embodiments, and steps S201, S202 and S203 may be implemented as standalone embodiments, but are not limited thereto.

[0261] In some embodiments, step S202 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0262] In some embodiments, step S203 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0263] In some embodiments, step S204 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0264] Figure 2b is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2b, the communication method is used in a communication system 100, and the method includes:

[0265] S211. At least one first terminal sends first information to the access network device.

[0266] In some embodiments, the first information is used to indicate manufacturer information related to the training of an artificial intelligence (AI) model for at least one first terminal.

[0267] In this embodiment, the content related to the first information can be referred to the relevant description of the first information in step S201 of Figure 2a above, and will not be repeated here.

[0268] In some embodiments, the first terminal may report a capability message carrying first information to the access network device. Optionally, the first terminal may send manufacturer information related to AI model training to the access network device through the capability message of the first terminal.

[0269] In some embodiments, the first terminal may report an RRC message carrying first information to the access network device. Optionally, the first terminal may send manufacturer information related to AI model training to the access network device via the RRC message.

[0270] In some embodiments, prior to step S211, the following may also be included:

[0271] S210, The access network device sends a first message to at least one first terminal.

[0272] In some embodiments, the first message is used to configure information related to AI functions and / or AI use cases associated with AI model training.

[0273] In some embodiments, the first terminal may send manufacturer information related to AI model training to the access network device in response to a first message sent by the access network device.

[0274] In some embodiments, the first message may be an RRC reconfiguration message (RRCReconfiguration message), and the first information may be sent to the access network device via an RRC reconfiguration complete message (RRCReconfigurationComplete message).

[0275] In some embodiments, after receiving configuration information for AI functions and / or AI use cases related to AI model training from the access network device, the first terminal sends manufacturer information related to AI model training to the access network device.

[0276] S212. The access network device determines the second terminal based on the first information.

[0277] Optionally, the second terminal may be one or more of at least one of the first terminals.

[0278] The optional implementation of step S212 can be found in the optional implementation of step S202 in Figure 2a, and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0279] S213. The access network device sends the second information to the determined second terminal.

[0280] In some embodiments, the access network device sends a training dataset to the second terminal.

[0281] The optional implementation of step S213 can be found in the optional implementation of step S203 in Figure 2a, and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0282] In some embodiments, after receiving the second information, the second terminal can train an AI model based on the second information, i.e., execute step S213a-1. Alternatively, the second terminal can forward the second information to the server, and the server can train the AI ​​model, i.e., execute steps S213a-2 to S214a.

[0283] S213a-1, the second terminal can train an AI model based on the second information.

[0284] In some embodiments, if the second terminal is one of at least one of the first terminals determined by the access network device in step S212, the second terminal can train the AI ​​model based on all the data in the received training dataset of the AI ​​model.

[0285] S213a-2, The second terminal sends the second information to its corresponding server.

[0286] In some embodiments, if the second terminal is one of the at least one first terminal determined by the access network device in step S212, the second terminal can send all the data of the received training dataset of the AI ​​model to its corresponding server.

[0287] In some embodiments, if the second terminal is one of multiple terminals among at least one first terminal determined by the access network device in step S212, the second information sent to each second terminal includes a first identifier and a portion of the data in the training dataset of the AI ​​model, as well as the identifier of the training dataset. Then each second terminal can send the received first identifier, the portion of the data in the training dataset of the AI ​​model, and the identifier of the training dataset to its corresponding server.

[0288] In some embodiments, the server may be an OTT server.

[0289] S213b: The server trains the AI ​​model based on the second information.

[0290] In some embodiments, the server can train the AI ​​model based on all the data in the received training dataset of the AI ​​model and the identifier of the training dataset.

[0291] In some embodiments, the server may determine all the data of the training dataset of the AI ​​model corresponding to the received multiple "first identifiers and partial data in the training dataset of the AI ​​model" and the identifier of the training dataset, and then train the AI ​​model based on the determined all data.

[0292] For example, suppose the identifier of the training dataset of AI model #1 is the identifier of the AI ​​model (e.g., ID #1), and the server receives partial data and their first identifiers from the training dataset of AI model #1 sent by terminals #1, #2, #3, and #4 respectively (e.g., the first training data and its first identifier ID #1a1 sent by terminal #1, the second training data and its first identifier ID #1a2 sent by terminal #2, the third training data and its first identifier ID #1a3 sent by terminal #3, and the fourth training data and its first identifier sent by terminal #4). Given ID#1a4 and the identifier of the AI ​​model #1 (e.g., the identifier of the AI ​​model, i.e., ID#1), the server can determine, based on the received ID#1 and the first identifiers ID#1a1, ID#1a2, ID#1a3, and ID#1a4, that the first training data, second training data, third training data, and fourth training data from terminals #1, #2, #3, and #4 belong to the training dataset of AI model #1, and perform AI model training based on the first training data, second training data, third training data, and fourth training data.

[0293] For example, assume that the identifier of the training dataset of AI model #1 is the identifier of the AI ​​model (e.g., ID#1), and the identifier of the training dataset of AI model #2 is the identifier of the AI ​​model (e.g., ID#2). The server receives partial data from the training dataset of AI model #1 and its first identifier (e.g., the first training data and its first identifier ID#1a1 sent by terminal #1, the second training data and its first identifier ID#1a2 sent by terminal #2), as well as the identifier ID#1 of AI model #1, sent by terminal #1 and terminal #2 respectively. The server also receives partial data from the training dataset of AI model #2 and its first identifier (e.g., the third training data and its first identifier ID#1b1 sent by terminal #3, the fourth training data and its first identifier ID#1b2 sent by terminal #4), as well as the identifier ID#2 of AI model #2, sent by terminal #3 and terminal #4 respectively. The server can then determine, based on the received ID#1 and the first identifiers ID#1a1 and ID#1a2, that the first and second training data from terminals #1 and #2 belong to the training dataset of AI model #1, and train the AI ​​model based on the first and second training data to obtain AI model #1. The server can also determine, based on the received ID#2 and the first identifiers ID#1b1 and ID#1b2, that the third and fourth training data from terminals #3 and #4 belong to the training dataset of AI model #2, and train the AI ​​model based on the third and fourth training data to obtain AI model #2.

[0294] In some embodiments, if the second information includes a portion of the training dataset of the AI ​​model, the second information may further include indication information to indicate whether the portion of data includes the last data of the corresponding training dataset.

[0295] In some embodiments, the server may determine whether it has received all the data of the dataset for the corresponding AI model based on the indication information in the second information.

[0296] In some embodiments, the indication information can be indicated using a 1-bit method. Optionally, 1 indicates that the current part of the data contains the last sample of the corresponding AI training dataset, and 0 indicates that the current part of the data does not contain the last sample of the corresponding AI training dataset. Alternatively, 0 indicates that the current part of the data contains the last sample of the corresponding AI training dataset, and 1 indicates that the current part of the data does not contain the last sample of the corresponding AI training dataset.

[0297] S214a, The server sends third information to the second terminal.

[0298] In some embodiments, after the server completes the training of the AI ​​model based on the received training dataset of the AI ​​model, it can send feedback to the terminal indicating that the AI ​​model training has been completed, so that the terminal can report back to the access network device whether the AI ​​model training has been completed.

[0299] S214. The terminal sends third information to the access network equipment.

[0300] The optional implementation of step S214 can be found in the optional implementation of step S204 in Figure 2a, and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0301] In some embodiments, after step S211, the following may also be included:

[0302] S211a, The access network device sends the first information to the core network device.

[0303] In some embodiments, after receiving manufacturer information related to model training reported by a terminal, the access network device may send the manufacturer information related to model training to the core network device.

[0304] In some embodiments, the core network equipment may be a core network element, core network function, core network function entity, etc., but is not limited thereto. Optionally, the core network equipment may be an Access and Mobility Management Function (AMF).

[0305] In some embodiments, after step S211a, the following may also be included:

[0306] S211b, the core network equipment stores the first information.

[0307] In some embodiments, the core network device may store the received model training-related manufacturer information. Optionally, the core network device may store the received model training-related manufacturer information in the context of the terminal, but is not limited thereto.

[0308] The method involved in the embodiments of this disclosure may include at least one of steps S210 to S214. For example, step S211 can be implemented as an independent embodiment, steps S211 and S211a can be implemented as independent embodiments, steps S211 and S211b can be implemented as independent embodiments, steps S211, S212, and S213 can be implemented as independent embodiments, steps S211, S212, S213, S213a-1, and S214 can be implemented as independent embodiments, steps S211, S212, S213, S213a-2, S213b, S214a, and S214 can be implemented as independent embodiments, and steps S210 and S211 can be implemented as independent embodiments. The implementation can be carried out using the following embodiments: steps S210, S211, and S211a can be implemented as independent embodiments; steps S210, S211, and S211b can be implemented as independent embodiments; steps S210, S211, S212, and S213 can be implemented as independent embodiments; steps S210, S211, S212, S213, S213a-1, and S214 can be implemented as independent embodiments; and steps S210, S211, S212, S213, S213a-2, S213b, S214a, and S214 can be implemented as independent embodiments, but are not limited thereto.

[0309] In some embodiments, step S210 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0310] In some embodiments, step S211a is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0311] In some embodiments, step S211b is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0312] In some embodiments, step S212 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0313] In some embodiments, step S213 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0314] In some embodiments, step S213a-1 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0315] In some embodiments, steps S213a-2 to S214a are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0316] In some embodiments, step S214 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0317] Figure 2c is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2c, the communication method is used in a communication system 100, and the method includes:

[0318] S221. At least one first terminal sends first information to the access network device.

[0319] The optional implementation of step S221 can be found in the optional implementation of step S211 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0320] In some embodiments, prior to step S221, the following may also be included:

[0321] S220, The access network device sends a first message to at least one first terminal.

[0322] The optional implementation of step S220 can be found in the optional implementation of step S210 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0323] S222. The access network device determines the second terminal based on the first information.

[0324] The optional implementation of step S222 can be found in the optional implementation of step S202 in Figure 2a and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0325] S223. The access network device sends the second information to the determined second terminal.

[0326] The optional implementation of step S223 can be found in the optional implementation of step S203 in Figure 2a and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0327] In some embodiments, after receiving the second information, the second terminal may execute step S223a-1, or steps S223a-2 to S224a.

[0328] S223a-1, the second terminal can train an AI model based on the second information.

[0329] The optional implementation of step S223a-1 can be found in the optional implementation of step S213a-1 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0330] S223a-2, The second terminal sends the second information to its corresponding server.

[0331] The optional implementation of step S223a-2 can be found in the optional implementation of step S213a-2 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0332] S223b: The server trains the AI ​​model based on the second information.

[0333] The optional implementation of step S223b can be found in the optional implementation of step S213b in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0334] S224a, The server sends third information to the second terminal.

[0335] The optional implementation of step S224a can be found in the optional implementation of step S214a in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0336] S224b: The second terminal sends the fourth information to the first access network device.

[0337] In some embodiments, the first access network device is the serving access network device after the second terminal switches over. Optionally, if the second terminal switches over after receiving the second information sent by the access network device, the second terminal can send a fourth information to the first access network device currently providing services to it after training the AI ​​model based on the training dataset of the AI ​​model, or after receiving the third information from its associated server, to indicate that the AI ​​model training related to the training dataset of the AI ​​model has been completed.

[0338] In some embodiments, the fourth information may include the identifier of the access network device that provided services to the second terminal before the handover.

[0339] S224c, The access network device receives the fourth information sent by the first access network device.

[0340] In some embodiments, the first access network device may determine the recipient of the fourth information based on the identifier of the access network device included in the fourth information, and forward the fourth information to that recipient. Optionally, after receiving the fourth information sent by the second terminal, the first access network device may forward the fourth information to the access network device before the second terminal switched.

[0341] In some embodiments, after step S221, the following may also be included:

[0342] S221a, The access network device sends the first information to the first access network device.

[0343] In some embodiments, after receiving manufacturer information related to AI model training reported by at least one first terminal, if the first terminal has switched over, the access network device can send the manufacturer information related to AI model training from the first terminal to the switched first access network device.

[0344] The method involved in the embodiments of this disclosure may include at least one of steps S220 to S224c. For example, step S221 can be implemented as an independent embodiment, steps S221 and S221a can be implemented as independent embodiments, steps S221, S222, and S223 can be implemented as independent embodiments, steps S221, S222, S223, S223a-1, and S224b can be implemented as independent embodiments, steps S221, S222, S223, S223a-2, S223b, S224a, and S224b can be implemented as independent embodiments, steps S220 and S221 can be implemented as independent embodiments, steps S220, S221, and S221a can be implemented as independent embodiments, and steps S220, S221, and S224c can be implemented as independent embodiments. 2. Steps S223, S220, S221, S222, S223, S223a-1, and S224b can be implemented as independent embodiments, as can steps S220, S221, S222, S223, S223a-2, S223b, S224a, and S224b, as can steps S221, S222, S223, S223a-1, S224b, and S224c, as can steps S221, S222, S223, S223a-2, S223b, S224a, S224b, and S224c, can be implemented as independent embodiments, but are not limited thereto.

[0345] In some embodiments, step S220 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0346] In some embodiments, step S221a is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0347] In some embodiments, step S222 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0348] In some embodiments, step S223 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0349] In some embodiments, step S223a-1 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0350] In some embodiments, steps S223a-2 to S224a are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0351] In some embodiments, step S224b is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0352] In some embodiments, step S224c is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0353] Figure 2d is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2d, the communication method is used in a communication system 100, and the method includes:

[0354] S231. At least one first terminal sends first information to the core network equipment.

[0355] In some embodiments, the first information is used to indicate manufacturer information related to the training of an artificial intelligence (AI) model for at least one first terminal.

[0356] In this embodiment, the content related to the first information can be referred to the relevant description of the first information in step S201 of Figure 2a above, and will not be repeated here.

[0357] In some embodiments, the first terminal can send first information to the core network device via NAS messages. Optionally, the first terminal can send manufacturer information related to AI model training to the core network device via a registration request in a NAS message.

[0358] In some embodiments, the core network equipment may be a core network element, core network function, core network function entity, etc., but is not limited thereto. Optionally, the core network equipment may be an Access and Mobility Management Function (AMF).

[0359] S231a, The core network equipment sends the first information to the access network equipment.

[0360] In some embodiments, after receiving the manufacturer information related to AI model training sent by the first terminal, the core network device can forward the manufacturer information related to AI model training to the access network device, so that the access network device can select the terminal based on the manufacturer information related to AI model training. This can avoid sending the same training dataset corresponding to the same AI model to multiple terminals with the same hardware or using the same AI training server, thereby improving the utilization rate of wireless resources.

[0361] In some embodiments, after step S231a, the following may also be included:

[0362] S231b, the core network equipment stores the first information.

[0363] The optional implementation of step S231b can be found in the optional implementation of step S211b in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0364] S232. The access network device determines the second terminal based on the first information.

[0365] The optional implementation of step S232 can be found in the optional implementation of step S202 in Figure 2a and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0366] S233. The access network device sends the second information to the determined second terminal.

[0367] The optional implementation of step S233 can be found in the optional implementation of step S203 in Figure 2a and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0368] In some embodiments, after receiving the second information, the second terminal may execute step S233a-1, or steps S233a-2 to S234a.

[0369] S233a-1, the second terminal can train an AI model based on the second information.

[0370] The optional implementation of step S233a-1 can be found in the optional implementation of step S213a-1 in Figure 2b, and other related parts in the embodiments involved in Figure 2b, which will not be repeated here.

[0371] S233a-2, The second terminal sends the second information to its corresponding server.

[0372] The optional implementation of step S233a-2 can be found in the optional implementation of step S213a-2 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0373] S233b: The server trains the AI ​​model based on the second information.

[0374] The optional implementation of step S233b can be found in the optional implementation of step S213b in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0375] S234a, The server sends third information to the second terminal.

[0376] The optional implementation of step S234a can be found in the optional implementation of step S214a in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0377] S234. The second terminal sends third information to the access network equipment.

[0378] The optional implementation of step S234 can be found in the optional implementation of step S214 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0379] The method involved in the embodiments of this disclosure may include at least one of steps S231 to S234. For example, step S231 may be implemented as an independent embodiment, steps S231 and S231a may be implemented as independent embodiments, steps S231 and S231b may be implemented as independent embodiments, steps S231, S231a, S232, and S233 may be implemented as independent embodiments, steps S231, S231a, S232, S233, S233a-1, and S234 may be implemented as independent embodiments, and steps S231, S231a, S232, S233, S233a-2, S233b, S234a, and S234 may be implemented as independent embodiments, but are not limited thereto.

[0380] In some embodiments, step S231a is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0381] In some embodiments, step S231b is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0382] In some embodiments, step S232 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0383] In some embodiments, step S233 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0384] In some embodiments, step S233a-1 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0385] In some embodiments, steps S233a-2 to S234a are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0386] In some embodiments, step S234 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0387] Figure 2e is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2e, the communication method is used in a communication system 100, and the method includes:

[0388] S241. At least one first terminal sends first information to the core network equipment.

[0389] The optional implementation of step S241 can be found in the optional implementation of step S231 in Figure 2d, and other related parts in the embodiment involved in Figure 2d, which will not be repeated here.

[0390] S241a, The core network equipment sends the first information to the access network equipment.

[0391] The optional implementation of step S241a can be found in the optional implementation of step S231a in Figure 2d, and other related parts in the embodiment involved in Figure 2d, which will not be repeated here.

[0392] In some embodiments, after step S241a, the following may also be included:

[0393] S241b, the core network equipment stores the first information.

[0394] The optional implementation of step S241b can be found in the optional implementation of step S211b in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0395] In some embodiments, after step S241a, the following may also be included:

[0396] S241c, The access network device sends the first information to the first access network device.

[0397] The optional implementation of step S241c can be found in the optional implementation of step S211a in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0398] S242. The access network device determines the second terminal based on the first information.

[0399] The optional implementation of step S242 can be found in the optional implementation of step S202 in Figure 2a and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0400] S243. The access network device sends the second information to the determined second terminal.

[0401] The optional implementation of step S243 can be found in the optional implementation of step S203 in Figure 2a and other related parts in the embodiment involved in Figure 2a, which will not be repeated here.

[0402] In some embodiments, after receiving the second information, the second terminal may execute step S243a-1, or steps S243a-2 to S244a.

[0403] S243a-1, the second terminal can train AI models based on the second information.

[0404] The optional implementation of step S243a-1 can be found in the optional implementation of step S213a-1 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0405] S243a-2, The second terminal sends the second information to its corresponding server.

[0406] The optional implementation of step S243a-2 can be found in the optional implementation of step S213a-2 in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0407] S243b: The server trains the AI ​​model based on the second information.

[0408] The optional implementation of step S243b can be found in the optional implementation of step S213b in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0409] S244a, The server sends third information to the second terminal.

[0410] The optional implementation of step S244a can be found in the optional implementation of step S214a in Figure 2b, and other related parts in the embodiment involved in Figure 2b, which will not be repeated here.

[0411] S244b: The second terminal sends the fourth information to the first access network device.

[0412] The optional implementation of step S244b can be found in the optional implementation of step S224b in Figure 2c, and other related parts in the embodiment involved in Figure 2c, which will not be repeated here.

[0413] S244c: The access network device receives the fourth information sent by the first access network device.

[0414] The optional implementation of step S244c can be found in the optional implementation of step S224c in Figure 2c, and other related parts in the embodiment involved in Figure 2c, which will not be repeated here.

[0415] The method involved in the embodiments of this disclosure may include at least one of steps S241 to S244c. For example, step S241 can be implemented as an independent embodiment, steps S241 and S241a can be implemented as independent embodiments, steps S241 and S241b can be implemented as independent embodiments, steps S241, S241a, S242, and S243 can be implemented as independent embodiments, steps S241, S241a, S242, S243, S243a-1, and S244b can be implemented as independent embodiments, and steps S241, S241a, and S242 can be implemented as independent embodiments. Steps S243, S243a-2, S243b, S244a, and S244b can be implemented as independent embodiments, as can steps S241, S241a, and S241c, as can steps S241, S241a, S242, S243, S243a-1, S244b, and S244c, as can steps S241, S241a, S242, S243, S243a-2, S243b, S244a, S244b, and S244c, as can steps S241, S241a, S242, S243, S243a-2, S243b, S244a, S244b, and S244c, but are not limited thereto.

[0416] In some embodiments, step S241a is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0417] In some embodiments, step S241b is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0418] In some embodiments, step S241c is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0419] In some embodiments, step S242 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0420] In some embodiments, step S243 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0421] In some embodiments, step S243a-1 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0422] In some embodiments, steps S243a-2 to S244a are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0423] In some embodiments, step S244b is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0424] In some embodiments, step S244c is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0425] It should be understood that Figures 2a-2e in this disclosure are merely exemplary figures and do not constitute a limitation on the solution of this embodiment. In some embodiments, the second terminal may be exactly the same as at least one first terminal. Optionally, if at least one first terminal that reports the first information is selected by the network device as the second terminal, then at least one first terminal and the second terminal in Figures 2a-2e can be represented by a single "box". That is, the terminal that reports the first information to the network device can also receive the second information sent by the network device.

[0426] Figure 3a is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3a, the communication method can be executed by terminal 101, and the method includes:

[0427] S301, Send the first message.

[0428] In some embodiments, at least one first terminal may send first information to a network device (e.g., an access network device or a core network device).

[0429] The optional implementations of step S301 can be found in the optional implementations of step S201 in Figure 2a, step S211 in Figure 2b, step S221 in Figure 2c, step S231 in Figure 2d, step S241 in Figure 2e, and other related parts in the embodiments involved in Figures 2a to 2e, which will not be repeated here.

[0430] In some embodiments, the first information is used to indicate the manufacturer information corresponding to the training of the artificial intelligence (AI) model of at least one first terminal.

[0431] In some embodiments, the manufacturer information corresponding to the first terminal includes: manufacturer identifier and AI training identifier.

[0432] In some embodiments, the manufacturer information corresponding to the first terminal includes: information of one manufacturer or information of multiple manufacturers.

[0433] In some embodiments, the manufacturer information corresponding to the first terminal is reported by the first terminal based on one of the following granularities: terminal, chip, AI use case, AI function, AI model.

[0434] In some embodiments, the network device of the second terminal is determined based on first information reported by at least one first terminal. Optionally, the second terminal is one or more of at least one first terminal. It should be understood that at least one first terminal includes the second terminal, and in some embodiments, step S301 may also include: the second terminal sending the first information to the network device. Optionally, the first information is used to indicate the manufacturer information corresponding to the AI ​​model training of the second terminal.

[0435] S302, Receive the second information.

[0436] In some embodiments, the second terminal may receive second information from the network device. Optionally, the network device may be an access network device.

[0437] In some embodiments, if the number of second terminals is one, the second information may include: the training dataset of the AI ​​model and the identifier of the training dataset.

[0438] In some embodiments, if there are multiple second terminals, the second information received by each second terminal may include: a first identifier, a portion of the data in the training dataset of the AI ​​model, and an identifier for the training dataset. Optionally, the first identifier is used to indicate a portion of the data in the training dataset of the AI ​​model.

[0439] The optional implementations of step S302 can be found in the optional implementations of step S203 in Figure 2a, step S213 in Figure 2b, step S223 in Figure 2c, step S233 in Figure 2d, step S243 in Figure 2e, and other related parts in the embodiments involved in Figures 2a to 2e, which will not be repeated here.

[0440] S303, Send the third message.

[0441] In some embodiments, the second terminal sends third information to the network device.

[0442] In some embodiments, the third information is used to indicate that the training of the AI ​​model associated with the training dataset of the AI ​​model has been completed.

[0443] The optional implementations of step S303 can be found in the optional implementations of step S204 in Figure 2a, step S214 in Figure 2b, step S234 in Figure 2d, and other related parts in the embodiments involved in Figures 2a, 2b, and 2d, which will not be repeated here.

[0444] In some embodiments, the second terminal may send third information to the access network device.

[0445] In some embodiments, after step S302, if the second terminal switches access network devices after receiving the training dataset, the above method may further include: sending fourth information.

[0446] In some embodiments, the fourth information is used to indicate that training of the AI ​​model associated with the training dataset of the AI ​​model has been completed. Optionally, the fourth information may include the identifier of the access network device before the handover.

[0447] In some embodiments, if the second terminal performs a handover after receiving the second information, it sends the fourth information to the first access network device after the handover.

[0448] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S224b in Figure 2c, the optional implementation methods of step S244b in Figure 2e, and other related parts in the embodiments involved in Figures 2c and 2e, which will not be repeated here.

[0449] In some embodiments, prior to step S303, the following may also be included:

[0450] The second terminal trains the AI ​​model based on the received second information, including the training dataset and the identifier of the training dataset.

[0451] The above-mentioned optional implementations can be found in the optional implementations of step S213a-1 in Figure 2b, step S223a-1 in Figure 2c, step S233a-1 in Figure 2d, step S243a-1 in Figure 2e, and other related parts in the embodiments involved in Figures 2b to 2e, which will not be repeated here.

[0452] In some embodiments, prior to step S303, the following may also be included:

[0453] The second terminal sends the received second information, including the training dataset and its identifier, to its associated server for training the AI ​​model, and receives feedback from the server indicating that training is complete; or,

[0454] The second terminal sends the received second information, including the first identifier, a portion of the training dataset, and the identifier of the training dataset, to its associated server for training the AI ​​model, and receives feedback from the server indicating that the training is complete.

[0455] The above-mentioned optional implementations can be found in the optional implementations of steps S213a-2 to S214a in Figure 2b, the optional implementations of steps S223a-2 to S224a in Figure 2c, the optional implementations of steps S233a-2 to S234a in Figure 2d, the optional implementations of steps S243a-2 to S244a in Figure 2e, and other related parts in the embodiments involved in Figures 2b to 2e, which will not be repeated here.

[0456] The method involved in the embodiments of this disclosure may include at least one of steps S301 to S303. For example, step S301 may be implemented as a separate embodiment, and steps S301 and S302 may be implemented as separate embodiments, but are not limited thereto.

[0457] In some embodiments, step S302 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0458] In some embodiments, step S303 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0459] Figure 3b is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3b, the communication method can be executed by terminal 101, and the method includes:

[0460] S311, Send the first message.

[0461] In some embodiments, the terminal (which may be the first terminal or the second terminal in the above embodiments) sends first information to the network device.

[0462] In some embodiments, the first information is used to indicate manufacturer information related to the training of the terminal's artificial intelligence (AI) model.

[0463] The optional implementations of step S311 can be found in the optional implementations of step S201 in Figure 2a, step S211 in Figure 2b, step S221 in Figure 2c, step S231 in Figure 2d, step S241 in Figure 2e, step S301 in Figure 3a, and other related parts in the embodiments involved in Figures 2a-2e and 3a, which will not be repeated here.

[0464] In some embodiments, the manufacturer information corresponding to the terminal includes: manufacturer identifier and AI training identifier.

[0465] In some embodiments, the manufacturer information corresponding to the terminal includes information from one manufacturer or information from multiple manufacturers.

[0466] In some embodiments, the manufacturer information corresponding to the terminal is reported by the terminal based on one of the following granularities: terminal, chip, AI use case, AI function, AI model.

[0467] In some embodiments, sending the first information includes sending the first information to an access network device. Optionally, the first information is sent to the access network device via a Radio Link Control (RRC) message.

[0468] In some embodiments, before sending the first information to the access network device, the method may further include:

[0469] Receive the first message sent by the access network device.

[0470] Optionally, the first message is used to configure information about AI functions and / or AI use cases related to the training of the AI ​​model.

[0471] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S210 in Figure 2b, the optional implementation methods of step S220 in Figure 2c, and other related parts in the embodiments involved in Figures 2b and 2c, which will not be repeated here.

[0472] In some embodiments, sending the first information includes: sending the first information to a core network device. Optionally, the first information is sent by the core network device to an access network device. Optionally, the first information is sent to the core network device via a Non-Access Stratum (NAS) message.

[0473] In some embodiments, the method further includes: a second terminal receiving a training dataset sent by the network device.

[0474] In some embodiments, the second terminal receives second information sent by the access network device.

[0475] In some embodiments, if the number of second terminals is one, the second information may include: the training dataset of the AI ​​model and the identifier of the training dataset.

[0476] In some embodiments, if there are multiple second terminals, the second information received by each second terminal may include: a first identifier, a portion of the data in the training dataset of the AI ​​model, and an identifier for the training dataset. Optionally, the first identifier is used to indicate a portion of the data in the training dataset of the AI ​​model.

[0477] In some embodiments, the second terminal is determined by the access network device based on the received first information. Optionally, the second terminal includes a terminal that sends manufacturer information related to the same AI model training.

[0478] The above optional implementations can be found in the optional implementations of step S203 in Figure 2a, step S213 in Figure 2b, step S223 in Figure 2c, step S233 in Figure 2d, step S243 in Figure 2e, step S302 in Figure 3a, and other related parts in the embodiments involved in Figures 2a and 3a, which will not be repeated here.

[0479] In some embodiments, the method further includes: the second terminal sending third information. Optionally, the second terminal sends the third information to a network device.

[0480] In some embodiments, the third information is used to indicate that the training of the AI ​​model associated with the training dataset of the AI ​​model has been completed.

[0481] The above-mentioned optional implementations can be found in the optional implementations of step S204 in Figure 2a, step S214 in Figure 2b, step S234 in Figure 2d, step S303 in Figure 3a, and other related parts in the embodiments involved in Figures 2a, 2b, 2d, and 3a, which will not be repeated here.

[0482] In some embodiments, the method further includes:

[0483] After a first duration, the network device receives the training dataset retransmitted by the network device, wherein the network device did not receive a training completion message from the second terminal during the first duration.

[0484] In some embodiments, before the second terminal sends the third information, the method further includes:

[0485] The AI ​​model is trained based on the training dataset of the AI ​​model.

[0486] The above-mentioned optional implementations can be found in the optional implementations of step S213a-1 in Figure 2b, step S223a-1 in Figure 2c, step S233a-1 in Figure 2d, step S243a-1 in Figure 2e, and other related parts in the embodiments involved in Figures 2b to 2e, which will not be repeated here.

[0487] In some embodiments, before the second terminal sends the third information, the method further includes:

[0488] Send the second information to the server associated with the second terminal; and,

[0489] Receive the third information sent by the server.

[0490] The above-mentioned optional implementations can be found in the optional implementations of steps S213a-2 to S214a in Figure 2b, the optional implementations of steps S223a-2 to S224a in Figure 2c, the optional implementations of steps S233a-2 to S234a in Figure 2d, the optional implementations of steps S243a-2 to S244a in Figure 2e, and other related parts in the embodiments involved in Figures 2b to 2e, which will not be repeated here.

[0491] In some embodiments, the access network device is the access network device before the second terminal hands over, and the method further includes:

[0492] When the second terminal receives the training dataset and switches access network devices, a fourth message is sent to the access network device after the second terminal switches. The fourth message is used to indicate that the training of the AI ​​model corresponding to the training dataset has been completed.

[0493] In some embodiments, the fourth information includes the identifier of the access network device before the terminal handover.

[0494] In some embodiments, the fourth information is sent by the access network device after the second terminal switches to the access network device before the second terminal switches.

[0495] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S224b in Figure 2c, the optional implementation methods of step S244b in Figure 2e, and other related parts in the embodiments involved in Figures 2c and 2e, which will not be repeated here.

[0496] Figure 4a is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4a, the method involved in this embodiment is executed by network device 102, and the method includes:

[0497] S401, Receive first information.

[0498] In some embodiments, the network device receives first information sent / reported by at least one first terminal. Optionally, if the at least one first terminal includes the second terminal mentioned above, the network device may receive the first information reported by the second terminal.

[0499] In some embodiments, the network device may be an access network device or a core network device, and this embodiment does not limit this.

[0500] In some embodiments, the first information is used to indicate manufacturer information related to the training of the terminal's artificial intelligence (AI) model.

[0501] The optional implementations of step S401 can be found in the optional implementations of step S201 in Figure 2a, step S211 in Figure 2b, step S221 in Figure 2c, step S231 in Figure 2d, step S241 in Figure 2e, step S301 in Figure 3a, and other related parts in the embodiments involved in Figures 2a-2e and 3a, which will not be repeated here.

[0502] In some embodiments, the manufacturer information includes: manufacturer identifier and AI training identifier.

[0503] S402. Based on the first information, determine the second terminal.

[0504] In some embodiments, the second terminal includes a terminal that sends manufacturer information related to the same AI model training.

[0505] In some embodiments, a network device (e.g., an access network device) selects a first terminal that sends manufacturer information related to the same AI model training as a second terminal based on the received first information.

[0506] The optional implementations of step S402 can be found in the optional implementations of step S202 in Figure 2a, step S212 in Figure 2b, step S222 in Figure 2c, step S232 in Figure 2d, step S242 in Figure 2e, and other related parts in the embodiments involved in Figures 2a to 2e, which will not be repeated here.

[0507] S403, Send the training dataset to the second terminal.

[0508] In some embodiments, the second terminal may be one or more of at least one first terminal.

[0509] In some embodiments, if there is only one second terminal, the second information may include: all the data of the training dataset of the AI ​​model and the identifier of the training dataset.

[0510] In some embodiments, there are multiple second terminals, and all data of the training dataset is sent to the multiple second terminals. Optionally, the second information sent to each of the multiple second terminals may include: a first identifier, a portion of the data in the training dataset of the AI ​​model, and an identifier of the training dataset. Optionally, the first identifier is used to indicate a portion of the data in the training dataset of the AI ​​model.

[0511] Optionally, each of the plurality of second terminals receives a portion of the training dataset, an identifier of the training dataset, and a first identifier, wherein the first identifier is the identifier of the portion.

[0512] The optional implementations of step S403 can be found in the optional implementations of step S203 in Figure 2a, the optional implementations of step S213 in Figure 2b, the optional implementations of step S223 in Figure 2c, the optional implementations of step S233 in Figure 2d, the optional implementations of step S243 in Figure 2e, the optional implementations of step S302 in Figure 3a, and other related parts in the embodiments involved in Figures 2a to 2e and Figure 3a, which will not be repeated here.

[0513] S404, Receive third information.

[0514] In some embodiments, third information sent by a second terminal is received.

[0515] In some embodiments, the third information is used to indicate that the training of the AI ​​model associated with the training dataset of the AI ​​model has been completed.

[0516] The optional implementations of step S404 can be found in the optional implementations of step S204 in Figure 2a, step S214 in Figure 2b, step S234 in Figure 2d, step S303 in Figure 3a, and other related parts in the embodiments involved in Figures 2a, 2b, 2d, and 3a, which will not be repeated here.

[0517] In some embodiments, the access network device is the access network device before the second terminal switches. After step S403, if the second terminal switches the access network device after receiving the training dataset, the above method may further include: receiving fourth information sent by the access network device after the second terminal switches.

[0518] In some embodiments, the fourth information is used to indicate that training of the AI ​​model associated with the training dataset of the AI ​​model has been completed. Optionally, the fourth information may include the identifier of the access network device before the handover.

[0519] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S224b in Figure 2c, the optional implementation methods of step S244b in Figure 2e, and other related parts in the embodiments involved in Figures 2c and 2e, which will not be repeated here.

[0520] The method involved in the embodiments of this disclosure may include at least one of steps S401 to S404. For example, step S401 may be implemented as a standalone embodiment, steps S401 and S402 may be implemented as standalone embodiments, and steps S401, S402 and S403 may be implemented as standalone embodiments, but are not limited thereto.

[0521] In some embodiments, step S402 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0522] In some embodiments, step S403 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0523] In some embodiments, step S404 is optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0524] Figure 4b is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4b, the method involved in this embodiment is executed by network device 102, and the method includes:

[0525] S411, Obtain first information.

[0526] In some embodiments, acquiring the first information can be understood as receiving the first information. Optionally, the network device may receive the first information sent by a terminal. Optionally, the network device may receive the first information sent by at least one first terminal.

[0527] In some embodiments, the first information is used to indicate manufacturer information related to the training of an artificial intelligence (AI) model for at least one first terminal.

[0528] The optional implementations of step S411 can be found in the optional implementations of step S201 in Figure 2a, step S211 in Figure 2b, step S221 in Figure 2c, step S231 in Figure 2d, step S241 in Figure 2e, step S401 in Figure 4a, and other related parts in the embodiments involved in Figures 2a-2e and Figure 4a, which will not be repeated here.

[0529] In some embodiments, the manufacturer information corresponding to the at least one first terminal includes: manufacturer identifier and AI training identifier.

[0530] In some embodiments, the manufacturer information corresponding to the first terminal includes information about one manufacturer or information about multiple manufacturers.

[0531] In some embodiments, the manufacturer information corresponding to the first terminal is reported by the first terminal based on one of the following granularities: terminal, chip, AI use case, AI function, AI model.

[0532] In some embodiments, if the network device is an access network device, the method further includes the following steps before step S411:

[0533] Send the first message to the terminal.

[0534] Optionally, the first message is used to configure information about AI functions or AI use cases related to the training of the AI ​​model.

[0535] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S210 in Figure 2b, the optional implementation methods of step S220 in Figure 2c, and other related parts in the embodiments involved in Figures 2b and 2c, which will not be repeated here.

[0536] In some embodiments, if the network device is an access network device, the method further includes:

[0537] The first information is sent to the first access network device, which is the service access network device after the terminal has switched.

[0538] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S221a in Figure 2c, and other related parts in the embodiments involved in Figure 2c, which will not be repeated here.

[0539] In some embodiments, if the network device is an access network device, the method further includes: sending the first information to a core network device.

[0540] Optionally, the first information can be sent to the core network equipment via a non-access stratum (NAS) message.

[0541] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S211a in Figure 2b, and other related parts in the embodiments involved in Figure 2b, which will not be repeated here.

[0542] In some embodiments, the method further includes:

[0543] Based on the first information, a training dataset is sent to a second terminal, wherein the second terminal is one or more of the at least one first terminal.

[0544] In some embodiments, the training dataset is any one of the following:

[0545] The dataset corresponding to the AI ​​model;

[0546] The dataset corresponding to one AI use case of the AI ​​model;

[0547] The dataset corresponding to one AI function of the AI ​​model;

[0548] The dataset corresponding to one AI use case of one AI function of the AI ​​model.

[0549] In some embodiments, the method further includes:

[0550] Based on the first information, at least one first terminal is identified; second information is sent to at least one first terminal.

[0551] In some embodiments, the first terminal includes a terminal that sends manufacturer information related to the same AI model training.

[0552] In some embodiments, the second information may include: the training dataset of the AI ​​model and the identifier of the training dataset.

[0553] In some embodiments, the second information may include: a first identifier, a portion of the data in the training dataset of the AI ​​model, and an identifier for the training dataset. Optionally, the first identifier is used to indicate a portion of the data in the training dataset of the AI ​​model.

[0554] The above-mentioned optional implementation methods can be referred to in the optional implementation methods of steps S202 and S203 in Figure 2a, the optional implementation methods of steps S212 and S213 in Figure 2b, the optional implementation methods of steps S222 and S223 in Figure 2c, the optional implementation methods of steps S232 and S233 in Figure 2d, the optional implementation methods of steps S242 and S243 in Figure 2e, the optional implementation methods of steps S402 and S403 in Figure 4a, and other related parts in the embodiments involved in Figures 2a to 2e and Figure 4a, which will not be repeated here.

[0555] In some embodiments, the method further includes:

[0556] If the network device does not receive a training completion message from the second terminal within a first time period during which the training dataset is sent to the second terminal, the network device will resend the training dataset.

[0557] In some embodiments, the method further includes: receiving third information sent by the second terminal.

[0558] In some embodiments, the third information is used to indicate that the training of the AI ​​model associated with the training dataset of the AI ​​model has been completed.

[0559] The above-mentioned optional implementations can be found in the optional implementations of step S204 in Figure 2a, step S214 in Figure 2b, step S234 in Figure 2d, step S404 in Figure 4a, and other related parts in the embodiments involved in Figures 2a, 2b, 2d, and 4a, which will not be repeated here.

[0560] In some embodiments, the access network device is the access network device before the second terminal hands over, and the method further includes:

[0561] If the second terminal switches access network devices after receiving the training dataset, it receives the fourth information sent by the access network device after the second terminal switches.

[0562] In some embodiments, the fourth information is used to indicate that the training of the AI ​​model corresponding to the training dataset has been completed.

[0563] In some embodiments, the fourth information includes the identifier of the access network device before the terminal handover.

[0564] The above-mentioned optional implementation methods can be found in the optional implementation methods of step S224b in Figure 2c, the optional implementation methods of step S244b in Figure 2e, and other related parts in the embodiments involved in Figures 2c and 2e, which will not be repeated here.

[0565] In some embodiments, the network device is a core network device, and the method further includes:

[0566] Send the first information to the access network device; and / or,

[0567] Store the first information.

[0568] The above optional implementation methods can be found in the optional implementation methods of steps S231a and S231b in Figure 2d, the optional implementation methods of steps S241a and S241b in Figure 2e, and other related parts in the embodiments involved in Figures 2d and 2e, which will not be repeated here.

[0569] Figure 5a is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 5a, the method involved in this embodiment of the present disclosure is used in a communication system 100, and the method includes:

[0570] S501, At least one first terminal sends first information to the network device.

[0571] Optional implementations of step S501 can be found in step S201 of Figure 2a, step S211 of Figure 2b, step S221 of Figure 2c, step S231 of Figure 2d, step S241 of Figure 2e, step S301 of Figure 3a, step S311 of Figure 3b, step S401 of Figure 4a, step S411 of Figure 4b, and other related parts in the embodiments involved in Figures 2a-2e, 3a-3b, and 4a-4b, which will not be repeated here.

[0572] S502, The network device sends the second information to the second terminal.

[0573] The optional implementations of step S502 can be found in step S203 of Figure 2a, step S213 of Figure 2b, step S223 of Figure 2c, step S233 of Figure 2d, step S243 of Figure 2e, optional implementations of step S403 of Figure 4a, and other related parts in the embodiments involved in Figures 2a-2e and Figure 4a, which will not be repeated here.

[0574] This disclosure also provides an optional implementation in which the network side can send AI datasets to specific terminals by instructing the manufacturer information related to AI training, thereby avoiding the repeated sending of AI datasets and improving the utilization of wireless resources.

[0575] In some embodiments, the terminal instructs the network device on manufacturer information related to AI training.

[0576] In some embodiments, manufacturer information may include a manufacturer ID and an AI training ID, as shown in Figure 5b.

[0577] In some embodiments, the manufacturer associated with AI training depends on the specific implementation of AI training in the terminal. Optionally, the manufacturer associated with AI training may be a terminal manufacturer, a modem or system-on-chip (SoC) manufacturer for wireless communication, or an AI chip manufacturer, but is not limited to these.

[0578] In some embodiments, the manufacturer identifier can be a string or a number.

[0579] In some embodiments, the manufacturer identifier may be assigned by an entity, such as 3GPP or the Internet Assigned Numbers Authority (IANA).

[0580] In some embodiments, the AI ​​training identifier is assigned by the manufacturer (corresponding to the manufacturer identifier). Optionally, the AI ​​training identifier is associated with the model number of the relevant product, the version of the product, the AI ​​training server used, etc.

[0581] In some embodiments, terminals with the same AI hardware may use different AI training servers due to differences in geographical location. Different terminal devices (e.g., different terminal models) may share the same AI chip, and therefore can have the same manufacturer identifier and AI training identifier. How the AI ​​training identifier is specifically assigned to the terminal depends on the manufacturer's implementation and deployment (e.g., the deployment of the AI ​​training server).

[0582] In some embodiments, the manufacturer identifier may be a Private Enterprise Number as defined by IANA.

[0583] In some embodiments, manufacturer information related to AI training can be reported at the terminal level. Optionally, a terminal may report only one piece of manufacturer information related to AI training.

[0584] In some embodiments, AI training-related manufacturer information can also be reported based on AI use case / functionality / AI model identifier. Optionally, a terminal reports one or more pairs of information, each pair including: an AI use case / functionality / AI model identifier and the corresponding AI training-related manufacturer information.

[0585] In some embodiments, the network device can be an access network device, in which case the terminal sends the manufacturer information related to AI training to the access network device.

[0586] In some embodiments, the terminal sends AI training-related manufacturer information to the access network device via RRC messages.

[0587] In some embodiments, the terminal sends AI training-related manufacturer information to the access network device via UE capability.

[0588] In some embodiments, after receiving configuration signaling for relevant AI functions from the access network device (e.g., RRCReconfiguration message), the terminal sends AI training-related manufacturer information to the access network device (e.g., via RRCReconfigurationComplete message).

[0589] In some embodiments, during a handover scenario, the serving access network device (e.g., the source base station) before the terminal switches can send the terminal's AI training-related manufacturer information to the serving access network device (e.g., the destination base station) after the terminal switches.

[0590] In some embodiments, the access network device can send the manufacturer information related to the AI ​​training of the terminal to the core network element / function.

[0591] In some embodiments, the aforementioned core network element / function may be an AMF. Optionally, access network equipment (e.g., a base station) may send manufacturer information related to the AI ​​training of the terminal to the AMF via NGAP signaling.

[0592] In some embodiments, the network device can be a core network element / function, in which case the terminal sends the manufacturer information related to AI training to the core network element / function.

[0593] In some embodiments, the terminal sends AI training-related manufacturer information to core network elements / functions via Non-Access Stratum (NAS) messages.

[0594] In some embodiments, the aforementioned core network element / function is the AMF. Optionally, the terminal sends AI training-related manufacturer information to the AMF in the NAS message Registration Request.

[0595] In some embodiments, core network elements / functions send manufacturer information related to AI training of the terminal to access network devices.

[0596] In some embodiments, if the core network element / function mentioned above is an AMF, then the AMF sends the manufacturer information related to the AI ​​training of the terminal to the access network equipment (e.g., a base station) via NGAP signaling.

[0597] In some embodiments, core network elements / functions store the manufacturer information related to the AI ​​training of the terminal in the terminal's UE context.

[0598] In some embodiments, the aforementioned core network element / function is an AMF. During the handover process, when the source AMF (also referred to as the initial AMF) creates the terminal's context at the destination AMF, and during the inter PLMN handover procedure, when the initial AMF relocates the terminal's context to the destination AMF, the source AMF / initial AMF provides the destination AMF with manufacturer information related to AI training. For example, the manufacturer information related to AI training is used as input for service operations.

[0599] In some embodiments, the network device selects terminals to send the AI ​​training dataset. Optionally, for terminals reporting the same AI training-related manufacturer information, the network device may select one or more terminals to send the AI ​​training dataset.

[0600] In some embodiments, a network device can split an AI training dataset and send it to multiple terminals.

[0601] In some embodiments, when AI training associated with the AI ​​training dataset is completed, the terminal indicates to the network device that the AI ​​training associated with the AI ​​training dataset has ended.

[0602] In the above embodiments, the purpose of sending instructions is to prevent some errors from occurring, such as: if the corresponding AI training is not completed, the network device needs to resend the relevant AI training dataset.

[0603] In some embodiments, the AI ​​training described above can be performed by the terminal or by a server associated with the terminal (e.g., an OTT server).

[0604] In some embodiments, when a network device sends an AI training dataset to a terminal, it indicates relevant information about the dataset. This information includes the identifier of the AI ​​training dataset, such as the AI ​​use case / functionality (e.g., CSI compression) corresponding to the AI ​​training dataset, or the identifier of the model corresponding to the AI ​​training dataset. When the terminal indicates to the network device that AI training related to the AI ​​training dataset has ended, the terminal indicates the identifier of the corresponding AI training dataset.

[0605] In some embodiments, the network device can be an access network device, in which case the terminal indicates to the access network device that the AI ​​training related to the AI ​​training dataset has ended. Optionally, the terminal indicates that the AI ​​training related to the AI ​​training dataset has ended via an RRC message.

[0606] In some embodiments, when the terminal's current serving access network device is not the same access network device that initially sent the AI ​​training dataset due to a handover, the terminal indicates that the AI ​​training related to the AI ​​training dataset has ended, and simultaneously indicates the identifier of the access network device that initially sent the AI ​​training dataset. The current serving access network device forwards the information indicating that the AI ​​training related to the terminal's AI training dataset has ended to the access network device that initially sent the AI ​​training dataset. Optionally, the current serving access network device sends the information to the access network device that initially sent the AI ​​training dataset via XnAP signaling.

[0607] In some embodiments, as shown in FIG5c, the terminal indicates to the network device manufacturer information related to AI training, and indicates to the network device that AI training related to the AI ​​training dataset has ended.

[0608] S51, The terminal (which may correspond to at least one of the first terminals mentioned above) instructs the network device on manufacturer information related to AI training.

[0609] S52. The network device selects a terminal (which may correspond to the second terminal mentioned above) based on the received manufacturer information.

[0610] S53. The network device sends the AI ​​training dataset to the selected terminal (which can correspond to the second terminal mentioned above).

[0611] S54. If AI training is performed by an OTT server associated with the terminal (which can correspond to the second terminal mentioned above), then the terminal (which can correspond to the second terminal mentioned above) sends the AI ​​training dataset to the OTT server.

[0612] S55 and OTT servers use the received AI training dataset for AI training.

[0613] S56, the OTT server sends the trained AI model to the terminal (which can correspond to the second terminal mentioned above).

[0614] S57. The terminal (which can correspond to the second terminal mentioned above) indicates to the network device that the AI ​​training related to the AI ​​training dataset has ended.

[0615] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0616] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functions of some or all of the units or modules can be achieved through the design of the hardware circuits. The aforementioned hardware circuits can be understood as one or more processors. For example, in one implementation, the aforementioned hardware circuit is an application-specific integrated circuit (ASIC). The functions of some or all of the aforementioned units or modules are achieved through the design of the logical relationships between the components within the circuit. As another example, in another implementation, the aforementioned hardware circuit can be implemented through a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functions of some or all of the aforementioned units or modules.

[0617] All units or modules of the above devices can be implemented entirely through processor-invoked software, entirely through hardware circuits, or partially through processor-invoked software with the remainder implemented through hardware circuits. In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be hardware circuits designed for artificial intelligence, which can be understood as ASICs, such as Neural Network Processing Units (NPUs), Tensor Processing Units (TPUs), and Deep Learning Processing Units (DPUs).

[0618] Figure 6a is a schematic diagram of the structure of a terminal proposed in an embodiment of this disclosure. As shown in Figure 6a, the terminal may include at least one of a first transceiver module 611, a first processing module 612, etc.

[0619] In some embodiments, the first transceiver module 611 is used to send first information to the network device, the first information being used to instruct the manufacturer information corresponding to the training of the artificial intelligence (AI) model of the second terminal.

[0620] Optionally, the first transceiver module 611 described above is used to execute the steps related to transmitting and receiving signaling executed by the terminal in any of the above methods, such as: at least one of the steps S201, S203, and S204 shown in FIG2a, steps S210, S211, S213, S213a-2, S214a, and S214 shown in FIG2b, steps S220, S221, S223, S223a-2, S224a, and S224b shown in FIG2c, steps S231, S233, S233a-2, S234a, and S234 shown in FIG2d, and steps S241, S243, S243a-2, S244a, and S244b shown in FIG2e, which will not be described in detail here.

[0621] Optionally, the first processing module 612 is used to execute the information processing-related steps performed by the terminal in any of the above methods, such as at least one of step S213a-1 shown in FIG2b, step S223a-1 shown in FIG2c, step S233a-1 shown in FIG2d, and step S243a-1 shown in FIG2e, which will not be described in detail here.

[0622] Figure 6b is a schematic diagram of the network device proposed in an embodiment of this disclosure. As shown in Figure 6b, the network device includes at least one of a second transceiver module 621, a second processing module 622, etc.

[0623] In some embodiments, the second transceiver module 621 is used to receive first information sent by at least one first terminal, the first information being used to indicate the manufacturer information corresponding to the artificial intelligence (AI) model of the at least one first terminal.

[0624] Optionally, the second transceiver module 621 described above is used to execute the steps related to sending and receiving signaling performed by the network device in any of the above methods, such as at least one of the following: steps S201, S203, and S204 shown in FIG2a; steps S210, S211, S211a, S213, and S214 shown in FIG2b; steps S220, S221, S221a, S223, S224b, and S224c shown in FIG2c; steps S231, S233, and S234 shown in FIG2d; and steps S241, S241a, S241c, S243, S244b, and S244c shown in FIG2e. These will not be elaborated further here.

[0625] Optionally, the first processing module 622 is used to execute the information processing-related steps performed by the sending end in any of the above methods, such as: at least one of step S202 shown in FIG2a, step S212 shown in FIG2b, step S222 shown in FIG2c, step S232 shown in FIG2d, and step S242 shown in FIG2e, which will not be described in detail here.

[0626] Optionally, the first processing module 622 is used to execute the information storage-related steps performed by the sending end in any of the above methods, such as: at least one of step S211b shown in FIG2b, step S231b shown in FIG2d, and step S241b shown in FIG2e, which will not be described in detail here.

[0627] Figure 7a is a schematic diagram of the structure of the communication device 7100 proposed in an embodiment of this disclosure. The communication device 7100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 7100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0628] As shown in Figure 7a, the communication device 7100 includes one or more processors 7101. The processor 7101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. The processor 7101 is used to invoke instructions to cause the communication device 7100 to execute any of the above methods.

[0629] In some embodiments, the communication device 7100 further includes one or more transceivers 7103. When the communication device 7100 includes one or more transceivers 7103, the transceivers 7103 perform communication steps such as sending and / or receiving in the above-described method (e.g., steps S201, S203, S204 shown in FIG. 2a; steps S210, S211, S211a, S213, S213a-2, S214a, S214 shown in FIG. 2b; steps S220, S221, S221a, S223, S223a-2, S224a, S224b, S224c shown in FIG. 2d; steps S231, S233, S233a-2, S234a, S234 shown in FIG. 2e). At least one of the steps S241, S241a, S241c, S243, S243a-2, S244a, S244b, and S244c shown in FIG. 2, but not limited thereto, is performed by processor 7101. Other steps (e.g., at least one of step S202 shown in FIG. 2a, steps S212, S211b, and S213a-1 shown in FIG. 2b, steps S222 and S223a-1 shown in FIG. 2c, steps S231b, S232, and S233a-1 shown in FIG. 2d, and steps S241b, S242, and S243a-1 shown in FIG. 2e, but not limited thereto) are executed by processor 7101. In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated together. Optionally, terms such as transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface can be used interchangeably; terms such as transmitter, transmitter unit, transmitter, and transmitter circuit can be used interchangeably; and terms such as receiver, receiver unit, receiver, and receiver circuit can be used interchangeably.

[0630] In some embodiments, the communication device 7100 further includes one or more memories 7102 for storing instructions. Optionally, all or part of the memories 7102 may also be located outside the communication device 7100.

[0631] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0632] Optionally, the communication device 7100 further includes one or more interface circuits 7104, which are connected to the memory 7102. The interface circuits 7104 can be used to receive signals from the memory 7102 or other devices, and can be used to send signals to the memory 7102 or other devices. For example, the interface circuits 7104 can read instructions stored in the memory 7102 and send the instructions to the processor 7101.

[0633] The communication device 7100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 7100 described in this disclosure is not limited thereto, and the structure of the communication device 7100 may not be limited by FIG. 7a. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: (1) an independent integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0634] Figure 7b is a schematic diagram of the structure of the chip 7200 proposed in an embodiment of this disclosure. For cases where the communication device 7100 can be a chip or a chip system, please refer to the schematic diagram of the chip 7200 shown in Figure 7b, but it is not limited thereto.

[0635] Chip 7200 includes one or more processors 7201. Chip 7200 is used to perform any of the above methods.

[0636] In some embodiments, chip 7200 further includes one or more interface circuits 7202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 7200 further includes one or more memories 7203 for storing data. Optionally, all or part of the memories 7203 may be located outside of chip 7200. Optionally, interface circuit 7202 is connected to memory 7203, and interface circuit 7202 can be used to receive data from memory 7203 or other devices, and interface circuit 7202 can be used to send data to memory 7203 or other devices. For example, interface circuit 7202 can read data stored in memory 7203 and send the data to processor 7201.

[0637] In some embodiments, the interface circuit 7202 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., at least one of steps S201, S203, S204 shown in FIG. 2a, steps S210, S211, S211a, S213, S213a-2, S214a, S214 shown in FIG. 2b, steps S220, S221, S221a, S223, S223a-2, S224a, S224b, S224c shown in FIG. 2c, steps S231, S233, S233a-2, S234a, S234 shown in FIG. 2d, steps S241, S241a, S241c, S243, S243a-2, S244a, S244b, S244c shown in FIG. 2e, but not limited thereto). The interface circuit 7202 performing the communication steps such as sending and / or receiving in the above method refers to, for example, the interface circuit 7202 performing data interaction between the processor 7201, the chip 7200, the memory 7203, or the transceiver device. In some embodiments, the processor 7201 performs at least one of other steps (e.g., at least one of step S202 shown in FIG. 2a, steps S212, S211b, S213a-1 shown in FIG. 2b, steps S222, S223a-1 shown in FIG. 2c, steps S231b, S232, S233a-1 shown in FIG. 2d, and steps S241b, S242, S243a-1 shown in FIG. 2e, but is not limited thereto).

[0638] This disclosure also provides a program product that, when executed by the communication device 7100, causes the communication device 7100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0639] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0640] The technical solutions described in the embodiments of this disclosure can be combined arbitrarily without conflict.

[0641] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0642] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A communication method, characterized in that, The method is performed by a network device, and the method includes: The network device receives first information sent by at least one first terminal, the first information being used to indicate the manufacturer information corresponding to the artificial intelligence (AI) model of the at least one first terminal.

2. The method according to claim 1, characterized in that, Also includes: Based on the first information, a training dataset is sent to a second terminal, wherein the second terminal is one or more of the at least one first terminal.

3. The method according to claim 2, characterized in that, The training dataset is any one of the following: The dataset corresponding to the AI ​​model; The dataset corresponding to one AI use case of the AI ​​model; The dataset corresponding to one AI function of the AI ​​model; The dataset corresponding to one AI use case of one AI function of the AI ​​model.

4. The method according to any one of claims 1-3, characterized in that, The manufacturer information corresponding to the first terminal includes information from one manufacturer or information from multiple manufacturers.

5. The method according to any one of claims 1-4, characterized in that, The manufacturer information corresponding to the first terminal is reported by the first terminal based on one of the following granularities: terminal, chip, AI use case, AI function, AI model.

6. The method according to any one of claims 1-5, characterized in that, The manufacturer information corresponding to the first terminal includes: manufacturer identifier and AI training identifier.

7. The method according to any one of claims 2-6, characterized in that, When the number of the second terminal is one, the step of sending the training dataset to the second terminal according to the first information includes: Based on the first information, send all the data of the training dataset and the identifier of the training dataset to the second terminal; When there are multiple second terminals, the step of sending the training dataset to the second terminals according to the first information includes: Based on the first information, all the data of the training dataset is sent to the plurality of second terminals.

8. The method according to claim 7, characterized in that, The step of sending all the data of the training dataset to the plurality of second terminals according to the first information includes: Based on the first information, a portion of the training dataset, the identifier of the training dataset, and a first identifier are sent to each of the plurality of second terminals, wherein the first identifier is the identifier of the portion.

9. The method according to any one of claims 2-8, characterized in that, The method further includes: The system receives a third message sent by the second terminal, the third message indicating that the training of the AI ​​model corresponding to the training dataset has been completed.

10. The method according to any one of claims 2-8, characterized in that, The method further includes: If the network device does not receive a training completion message from the second terminal within a first time period during which the training dataset is sent to the second terminal, the network device will resend the training dataset.

11. The method according to any one of claims 1-10, characterized in that, The network device is an access network device, and before receiving the first information sent by the terminal, the method further includes: Send a first message to the at least one first terminal, the first message being used to configure information on the AI ​​functions and / or AI use cases corresponding to the AI ​​training.

12. The method according to any one of claims 2-11, characterized in that, The access network device is the access network device used before the second terminal hands over, and the method further includes: When the second terminal switches access network devices after receiving the training dataset, it receives fourth information sent by the access network device after the second terminal switches. The fourth information is used to indicate that the training of the AI ​​model corresponding to the training dataset has been completed.

13. The method according to claim 12, characterized in that, The fourth piece of information includes the identifier of the access network device before the handover.

14. The method according to any one of claims 1-10, characterized in that, The network device is the access network device before the terminal switches over, and the method further includes: The first information is sent to the access network device after the second terminal is switched.

15. The method according to any one of claims 1-11, characterized in that, The network device is an access network device, and the method further includes: Send the first information to the core network equipment.

16. The method according to any one of claims 1-10, characterized in that, The network device is a core network device, and the method further includes: Send the first information to the access network device; and / or, Store the first information.

17. A communication method, characterized in that, The method is executed by a second terminal, and the method includes: Send a first message to the network device, the first message being used to instruct the second terminal's artificial intelligence (AI) model to train the corresponding manufacturer information.

18. The method according to claim 17, characterized in that, Also includes: Receive the training dataset sent by the network device; The training dataset can be any of the following: The dataset corresponding to the AI ​​model; The dataset corresponding to one AI use case of the AI ​​model; The dataset corresponding to one AI function of the AI ​​model; The dataset corresponding to one AI use case of one AI function of the AI ​​model.

19. The method according to claim 17 or 18, wherein the manufacturer information corresponding to the second terminal includes information of one manufacturer or information of multiple manufacturers.

20. The method according to any one of claims 17-19, characterized in that, The manufacturer information corresponding to the second terminal is reported by the second terminal based on one of the following granularities: terminal, chip, AI use case, AI function, AI model.

21. The method according to any one of claims 17-20, characterized in that, The manufacturer information corresponding to the second terminal includes: manufacturer identifier and AI training identifier.

22. The method according to any one of claims 18-21, characterized in that, The training dataset sent by the network device includes: Receive all data of the training dataset and the identifier of the training dataset sent by the access network device; or; The second terminal receives a first identifier, a portion of the training dataset, and an identifier of the training dataset sent by the access network device. The first identifier is used to indicate the portion of the training dataset received by the second terminal.

23. The method according to any one of claims 18-22, characterized in that, The method further includes: A third message is sent to the network device, the third message indicating that the training of the AI ​​model associated with the training dataset of the AI ​​model has been completed.

24. The method according to any one of claims 18-22, characterized in that, The method further includes: After a first duration, the network device receives the training dataset retransmitted by the network device, wherein the network device did not receive a training completion message from the second terminal during the first duration.

25. The method according to claim 23 or 24, characterized in that, Before sending the third information to the network device, the method further includes: AI model training is performed based on the aforementioned training dataset; or... The training dataset is sent to the OTT server corresponding to the second terminal, and the third information sent by the OTT server is received.

26. The method according to any one of claims 17-25, characterized in that, The sending of the first information includes: The first information is sent to the access network device via a Radio Link Control (RRC) message.

27. The method according to any one of claims 17-26, characterized in that, Before sending the first message to the network device, it also includes: The system receives a first message sent by the network device, the first message being used to configure information on AI functions and / or AI use cases corresponding to the training of the AI ​​model.

28. The method according to any one of claims 18-27, characterized in that, The access network device is the access network device used before the second terminal hands over, and the method further includes: When the second terminal receives the training dataset and switches access network devices, a fourth message is sent to the access network device after the second terminal switches. The fourth message is used to indicate that the training of the AI ​​model corresponding to the training dataset has been completed.

29. The method according to claim 28, characterized in that, The fourth information includes the identifier of the access network device before the handover, and the fourth information is sent by the access network device after the handover to the access network device before the handover.

30. The method according to any one of claims 17-25, characterized in that, The sending of the first information includes: The first information is sent to the core network device via a non-access stratum (NAS) message, wherein the first information is sent by the core network device to the access network device.

31. A communication device, characterized in that, The communication device is used to perform the communication method according to any one of claims 1-16, or any one of claims 17-30.

32. A communication system, characterized in that, include: A terminal and a network device, wherein the terminal is used to implement the method of any one of claims 1 to 16, and the network device is used to implement the method of any one of claims 17 to 30.

33. A computer storage medium, characterized in that, The computer-readable storage medium stores executable instructions that are loaded and executed by a processor to implement the method as claimed in any one of claims 1 to 16, or any one of claims 17 to 30.

34. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the programs or instructions is executed by the communication device, it implements the steps of the method according to any one of claims 1-16 or 17-30.

Images