Communication method and apparatus

Abstract

A communication method and apparatus, which are applied in the technical field of communications, are used for adapting the receiving capability of a terminal device for an AI model, and can reduce the waste of transmission resources. The method comprises: a first communication apparatus receiving first information from a second communication apparatus, wherein the first information is used for indicating the receiving capability of the second communication apparatus for an AI model, and the first information can be used for determining a first AI model to be applied to the second communication apparatus and a transmission mode of the first AI model; and on the basis of the first information, sending the first AI model to the second communication apparatus.

Description

Communication method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on March 28, 2024, with application number 202410366730.7 and application name "A Communication Method and Device", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of communication technology, and in particular to a communication method and device. Background Art

[0004] Artificial intelligence (AI) technology, first proposed in the 1950s, simulates the human brain to perform complex calculations. With advances in data storage and computing power, AI is increasingly being used. The Third Generation Partnership Project (3GPP) has proposed applying AI to New Radio (NR) systems. By intelligently collecting and analyzing data, it can improve network performance and user experience.

[0005] Currently, terminal devices can obtain AI models from the network to implement AI functions. However, different terminal devices have different reception capabilities for AI models. This can lead to the problem that the network-side AI model (and / or the AI ​​model transmission method) may not be adapted to the terminal device's reception capabilities, resulting in a waste of transmission resources. Summary of the Invention

[0006] The embodiments of the present application provide a communication method and apparatus for adapting the terminal device's receiving capability for an AI model, thereby reducing the waste of transmission resources.

[0007] In a first aspect, the present application provides a communication method, which can be performed by a first communication device, or can also be performed by a device including the first communication device, or can also be performed by a chip (or, chip system) or other functional module, which chip or functional module can implement the functions of the first communication device, for example, the chip or functional module is set in the first communication device. The first communication device can be a network-side device, for example, the first communication device can be an access network device, or can also be a core network device, or can also be a third-party device, without limitation.

[0008] Taking the first communication device as the execution subject as an example, the method may include: the first communication device receives first information from the second communication device, the first information is used to indicate the second communication device's receiving capability for the AI ​​model, and the first information is used to determine the first AI model to be applied by the second communication device and the transmission method of the first AI model; and, sending the first AI model to the second communication device according to the first information.

[0009] In an embodiment of the present application, a first communication device receives first information from a second communication device, where the first information is used to indicate the second communication device's receiving capability for an AI model. Based on the first information, the first communication device can determine a suitable first AI model and a transmission method for the first AI model. Because the determination of the first AI model and the transmission method of the first AI model takes into account the second communication device's receiving capability for the AI ​​model, the first AI model and the transmission method of the first AI model can adapt to the receiving capability of the second communication device, thereby avoiding the problem of wasting transmission resources due to a mismatch between the AI ​​model and / or the transmission method of the AI ​​model and the receiving capability of the second communication device.

[0010] In one possible implementation, the first information may indicate the receiving capability of the second communication device for the AI ​​model through one or more of the following: the architecture of the AI ​​model supported by the second communication device; the transmission format of the AI ​​model supported by the second communication device; the identifier of the AI ​​model supported by the second communication device; a first parameter, wherein the first parameter is a relevant parameter applied to the first architecture, and the first architecture is the architecture of the AI ​​model supported by the second communication device and known to the first communication device; or, a first identifier, wherein the first identifier is used to indicate the second architecture and the relevant parameters applied to the second architecture, and the second architecture belongs to the architecture of the AI ​​model supported by the second communication device.

[0011] Through the above implementation method, the first information can indicate the receiving capability of the second communication device corresponding to the AI ​​model through the architecture, transmission format, or parameters of the AI ​​model supported by the second communication device.

[0012] In one possible implementation, the first communication device may further send second information to the second communication device, where the second information is used to indicate the transmission capability of the first communication device for the AI ​​model.

[0013] Through the above implementation method, the first communication device can also inform the second communication device of its own transmission capability for the AI ​​model, so that the second communication device can refer to the transmission capability of the first communication device for the AI ​​model when sending the first information, thereby reducing the transmission of invalid information by the second communication device.

[0014] In one possible implementation, the second information may indicate the transmission capability of the first communication device for the AI ​​model through one or more of the following: the architecture of the AI ​​model supported for transmission by the first communication device; the transmission format of the AI ​​model supported for transmission by the first communication device; the identifier of the AI ​​model supported for transmission by the first communication device; a second parameter, wherein the second parameter is a relevant parameter applied to a third architecture, and the third architecture is the architecture of the AI ​​model supported for transmission by the first communication device that is known to the second communication device; or, a second identifier, wherein the second identifier is used to indicate a fourth architecture and relevant parameters applied to the fourth architecture, and the fourth architecture belongs to the architecture of the AI ​​model supported for transmission by the first communication device.

[0015] Through the above implementation method, the second information can indicate the transmission capability of the first communication device corresponding to the AI ​​model through the architecture, transmission format, or parameters of the AI ​​model supported by the first communication device.

[0016] In a possible implementation, the second information may also be used to indicate a communication range to which the transmission capability of the first communication device for the AI ​​model is applicable.

[0017] Through the above implementation method, within different communication ranges, the transmission capabilities of the first communication device corresponding to the AI ​​model can be different or the same, and the implementation method is flexible.

[0018] In one possible implementation, the first communication device sends the first AI model to the second communication device based on the first information. Specifically, the first communication device receives third information from the second communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model; and sends the first AI model to the second communication device based on the first information and the third information.

[0019] Through the above implementation method, when determining the first AI model and the transmission method of the first AI model, the first communication device can not only consider the second communication device's receiving capability for the AI ​​model but also the second communication device's transmission requirements for the AI ​​model, so as to adapt the second communication device's receiving capability and transmission requirements corresponding to the AI ​​model.

[0020] In one possible implementation, the first communication device sends the first AI model to the second communication device. Specifically, it can be: the first communication device sends the architecture and third parameters of the first AI model to the second communication device, where the third parameters are relevant parameters of the architecture applied to the first AI model; or, the first communication device sends the identifier of the architecture of the first AI model and the third parameter to the second communication device, where the third parameters are relevant parameters of the architecture applied to the first AI model; or, the first communication device sends fourth information to the second communication device, where the fourth information includes the identifier and / or the third identifier of the first AI model, where the third identifier is used to indicate the architecture and third parameters of the first AI model, and the third parameters are relevant parameters of the architecture applied to the first AI model.

[0021] Through the above implementation, the first communication device can send the first AI model to the second communication device in a variety of ways, and the implementation method is flexible.

[0022] In one possible implementation, the first communication device sends the first AI model to the second communication device, specifically: the first communication device sends part of the information of the first AI model to the second communication device through a control surface, and sends the remaining information of the first AI model except the part of the information to the second communication device through a user surface.

[0023] Through the above implementation, part of the information in the first AI model is transmitted via the control plane, while the remaining information is transmitted via the user plane, fully leveraging the advantages of both control and user plane transmission. For example, control plane transmission generally has a higher priority, and transmitting part of the information in the first AI model via the control plane can ensure the transmission priority of this part of information and reduce the transmission latency of this part of information.

[0024] In one possible implementation, the first communication device may further send fifth information to the second communication device, where the fifth information indicates whether the second communication device is permitted to modify the first AI model. Optionally, when the fifth information indicates that the second communication device is permitted to modify the first AI model, the fifth information further indicates conditions for registering the modified AI model and / or a registration method for the modified AI model.

[0025] Through the above implementation, the first communication device can indicate whether to allow the second communication device to modify the first AI model. If modification is allowed, the first communication device can also indicate the conditions under which the modified AI model needs to be registered and / or the registration method of the modified AI model.

[0026] In a possible implementation, the first communication device may further send information indicating that the first AI model has not been transmitted and / or transmission progress information of the first AI model to the second communication device.

[0027] In one possible implementation, the first communication device may also send sixth information to the second communication device, where the sixth information is used to instruct the second communication device to record seventh information, where the seventh information is used to indicate that the first AI model has not completed transmission, or the seventh information is transmission progress information of the first AI model.

[0028] In one possible implementation, the first communication device may further send eighth information to the second communication device, where the eighth information is used to indicate that the second communication device is allowed to send the seventh information to a third communication device, where the cell of the third communication device is the cell after the second communication device performs a cell handover, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission anomaly occurs. Optionally, the eighth information may also be used to indicate the communication range of the third communication device.

[0029] Through the above implementation method, the first communication device sends the eighth information to the second communication device, so that when the transmission of the first AI model is interrupted (for example, the second communication device performs cell switching, or the transmission of the first AI model is abnormal, etc.), the second communication device can send the seventh information to the third communication device to enable the third communication device to determine that the second communication device has a need to transmit the first AI model.

[0030] In one possible implementation, the seventh information is the transmission progress information of the first AI model. The first communication device may also send ninth information to the third communication device, and the ninth information is used to instruct the third communication device to obtain the transmission progress information of the first AI model from the second communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

[0031] Through the above implementation method, the first communication device sends the ninth information to the third communication device, so that the third communication device can obtain the transmission progress information of the first AI model from the second communication device.

[0032] In another possible implementation, the first communication device may also send transmission progress information of the first AI model to a third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

[0033] Through the above implementation, the first communication device can also send the transmission progress information of the first AI model to the third communication device. For example, if the second communication device records the information that the first AI model has not completed transmission but does not record the transmission progress information of the first AI model, the first communication device can send the transmission progress information of the first AI model to the third communication device.

[0034] In a possible implementation, the first communication device may receive a first request message from the third communication device, where the first request message is used to request transmission progress information of the first AI model.

[0035] Through the above implementation method, the first communication device can actively send the transmission progress information of the first AI model to the third communication device, or can also send the transmission progress information of the first AI model to the third communication device in response to the first request message of the third communication device. The implementation method is flexible.

[0036] In one possible implementation, the transmission progress information of the first AI model may include one or more of the following: transmission progress information of the architecture of the first AI model; transmission progress information of a third parameter, where the third parameter is a relevant parameter applied to the architecture of the first AI model; or information indicating information that has not been transmitted in the first AI model.

[0037] In one possible implementation, the first communication device may also send the first information and / or third information to the third communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

[0038] In one possible implementation, the first AI model transmission is abnormal, and the first communication device re-establishes a connection with the second communication device. The first communication device may also determine the cause of the first AI model transmission abnormality; adjust the transmission method of the information that has not been transmitted in the first AI model according to the cause of the first AI model transmission abnormality; and send the information that has not been transmitted in the first AI model to the second communication device according to the adjusted transmission method.

[0039] Through the above implementation method, if the first AI model transmission is abnormal, after the first communication device re-establishes the connection with the second communication device, the first communication device can adjust the transmission method of the information that has not been transmitted in the first AI model according to the cause of the first AI model transmission abnormality, thereby improving the transmission reliability of the AI ​​model.

[0040] In a second aspect, the present application provides a communication method, which can be performed by a second communication device, or can also be performed by a device including the second communication device, or can also be performed by a chip (or, chip system) or other functional module, which chip or functional module can implement the functions of the second communication device, for example, the chip or functional module is provided in the second communication device. The second communication device can be a terminal-side device, for example, the second communication device can be a terminal device, without limitation.

[0041] Taking the second communication device as the execution subject as an example, the method may include: the second communication device sends first information to the first communication device, the first information is used to indicate the second communication device's receiving capability for the AI ​​model, and the first information is used to determine the first AI model to be applied by the second communication device and the transmission method of the first AI model; and, receiving the first AI model from the first communication device.

[0042] In one possible implementation, the first information may indicate the receiving capability of the second communication device for the AI ​​model through one or more of the following: the architecture of the AI ​​model supported by the second communication device; the transmission format of the AI ​​model supported by the second communication device; the identifier of the AI ​​model supported by the second communication device; a first parameter, wherein the first parameter is a relevant parameter applied to the first architecture, and the first architecture is the architecture of the AI ​​model supported by the second communication device and known to the first communication device; or, a first identifier, wherein the first identifier is used to indicate the second architecture and the relevant parameters applied to the second architecture, and the second architecture belongs to the architecture of the AI ​​model supported by the second communication device.

[0043] In one possible implementation, the second communication device may also receive second information from the first communication device, where the second information is used to indicate the transmission capability of the first communication device for the AI ​​model; and determine the first information based on the second information.

[0044] In one possible implementation, the second information may indicate the transmission capability of the first communication device for the AI ​​model through one or more of the following: the architecture of the AI ​​model supported for transmission by the first communication device; the transmission format of the AI ​​model supported for transmission by the first communication device; the identifier of the AI ​​model supported for transmission by the first communication device; a second parameter, wherein the second parameter is a relevant parameter applied to a third architecture, and the third architecture is the architecture of the AI ​​model supported for transmission by the first communication device that is known to the second communication device; or, a second identifier, wherein the second identifier is used to indicate a fourth architecture and relevant parameters applied to the fourth architecture, and the fourth architecture belongs to the architecture of the AI ​​model supported for transmission by the first communication device.

[0045] In a possible implementation, the second information may also be used to indicate a communication range to which the transmission capability of the first communication device for the AI ​​model is applicable.

[0046] In one possible implementation, the second communication device may further send third information to the first communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model.

[0047] In one possible implementation, the second communication device receives the first AI model from the first communication device. Specifically, it may be that: the second communication device receives the architecture and third parameter of the first AI model from the first communication device, where the third parameter is a relevant parameter of the architecture applied to the first AI model; or, the second communication device receives the identifier and third parameter of the architecture of the first AI model from the first communication device, where the third parameter is a relevant parameter of the architecture applied to the first AI model; or, the second communication device receives fourth information from the first communication device, where the fourth information includes the identifier and / or third identifier of the first AI model, where the third identifier is used to indicate the architecture and third parameter of the first AI model, and the third parameter is a relevant parameter of the architecture applied to the first AI model.

[0048] In one possible implementation, the second communication device receives the first AI model from the first communication device, specifically: the second communication device receives partial information of the first AI model from the first communication device through a control plane, and receives the remaining information of the first AI model from the first communication device except the partial information through a user plane.

[0049] In one possible implementation, the second communication device may further receive fifth information from the first communication device, where the fifth information indicates whether the second communication device is permitted to modify the first AI model. Optionally, when the fifth information indicates that the second communication device is permitted to modify the first AI model, the fifth information further indicates conditions for registering the modified AI model and / or a registration method for the modified AI model.

[0050] In a possible implementation, the second communication device may further receive information indicating that the first AI model has not completed transmission and / or transmission progress information of the first AI model from the first communication device.

[0051] In one possible implementation, the second communication device may also receive sixth information from the first communication device, where the sixth information is used to instruct the second communication device to record seventh information, where the seventh information is used to indicate that the first AI model has not completed transmission, or the seventh information is transmission progress information of the first AI model.

[0052] In one possible implementation, the second communication device may further receive eighth information from the first communication device, the eighth information being used to indicate that the second communication device is permitted to send the seventh information to a third communication device, where the cell of the third communication device is the cell to which the second communication device is connected after a cell handover, or the cell of the third communication device is the cell that provided service to the second communication device after an abnormal transmission of the first AI model occurred. Optionally, the eighth information may also be used to indicate the communication range of the third communication device.

[0053] In one possible implementation, the second communication device may also send the seventh information to the third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

[0054] In one possible implementation, the seventh information is the transmission progress information of the first AI model, and the second communication device may also receive a second request message from the third communication device, where the second request message is used to request the transmission progress information of the first AI model.

[0055] In a possible implementation, the second communication device may also receive information in the first AI model that has not been completely transmitted from the third communication device.

[0056] In one possible implementation, the transmission progress information of the first AI model may include one or more of the following: transmission progress information of the architecture of the first AI model; transmission progress information of a third parameter, where the third parameter is a relevant parameter applied to the architecture of the first AI model; or information indicating information that has not been transmitted in the first AI model.

[0057] In one possible implementation, the second communication device may also send the first information and / or third information to the third communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

[0058] The technical effects that can be achieved by the above-mentioned second aspect and any possible implementation thereof can be referred to the technical effects that can be achieved by the above-mentioned first aspect and any possible implementation thereof, and no further details will be given.

[0059] In a third aspect, the present application provides a communication method, which can be performed by a third communication device, or can also be performed by a device including the third communication device, or can also be performed by a chip (or, chip system) or other functional module, which chip or functional module can implement the functions of the third communication device, for example, the chip or functional module is provided in the third communication device. The third communication device can be a network-side device, for example, the third communication device can be an access network device, without limitation.

[0060] Taking a third communication device as an example, the method may include: the third communication device receiving transmission progress information of a first AI model to be applied by a second communication device; receiving first information indicating the second communication device's ability to receive the AI ​​model; and, based on the first information and the transmission progress information of the first AI model, transmitting to the second communication device information that has not yet been transmitted the information in the first AI model. Alternatively, the third communication device receives transmission progress information of the first AI model to be applied by the second communication device; and, based on the transmission progress information of the first AI model, transmitting to the second communication device information that has not yet been transmitted the information in the first AI model.

[0061] Exemplarily, the third communication device receiving the transmission progress information of the first AI model may specifically include: the third communication device may receive the transmission progress information of the first AI model from the first communication device or the second communication device.

[0062] In the above embodiment, if the transmission of the first AI model is interrupted (for example, due to a cell handover by the second communication device or an abnormal transmission of the first AI model), the third communication device can obtain the transmission progress information of the first AI model and resume transmission based on the first information and the transmission progress information of the first AI model, eliminating the need to retransmit the first AI model. This improves the utilization of transmission resources. Furthermore, the resumption of transmission of the first AI model takes into account the second communication device's reception capability for the AI ​​model. Therefore, the resumption of transmission of the first AI model can be adapted to the second communication device's reception capability, thereby reducing the waste of transmission resources.

[0063] In one possible implementation, the first information may indicate the receiving capability of the second communication device for the AI ​​model through one or more of the following: the architecture of the AI ​​model supported by the second communication device; the transmission format of the AI ​​model supported by the second communication device; the identifier of the AI ​​model supported by the second communication device; a first parameter, wherein the first parameter is a relevant parameter applied to the first architecture, and the first architecture is the architecture of the AI ​​model supported by the second communication device and known to the first communication device; or, a first identifier, wherein the first identifier is used to indicate the second architecture and the relevant parameters applied to the second architecture, and the second architecture belongs to the architecture of the AI ​​model supported by the second communication device.

[0064] In one possible implementation, the third communication device sends the information in the first AI model that has not been transmitted to the second communication device based on the first information and the transmission progress information of the first AI model. Specifically, the third communication device receives third information, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model; and sends the information in the first AI model that has not been transmitted to the second communication device based on the first information, the third information, and the transmission progress information of the first AI model.

[0065] In a possible implementation, the third communication device may further receive seventh information from the second communication device, where the seventh information is used to indicate that the first AI model has not completed transmission.

[0066] In a possible implementation, the third communication device may further send a first request message to the first communication device, where the first request message is used to request transmission progress information of the first AI model.

[0067] In a possible implementation, the third communication device may further send a second request message to the first communication device, where the second request message is used to request transmission progress information of the first AI model.

[0068] In one possible implementation, the third communication device may also receive ninth information from the first communication device, wherein the ninth information is used to instruct the third communication device to obtain transmission progress information of the first AI model from the second communication device, wherein the cell of the first communication device is the cell before the second communication device performs cell switching, or the cell of the first communication device is the cell that provides services to the second communication device before the transmission of the first AI model is abnormal.

[0069] In one possible implementation, the third communication device may further determine a cause of the transmission abnormality of the first AI model based on the transmission progress information of the first AI model; and determine a transmission method for the information that has not been transmitted in the first AI model based on the cause of the transmission abnormality of the first AI model, the first information, and the transmission progress information of the first AI model.

[0070] In a possible implementation, the third communication device may further determine, based on the transmission progress information of the first AI model, to send the untransmitted information of the first AI model to the second communication device.

[0071] The technical effects that can be achieved by any possible implementation method of the third aspect mentioned above can be referred to the technical effects that can be achieved by any possible implementation method of the first aspect mentioned above, and no further details will be given.

[0072] In a fourth aspect, the present application provides a communication method, which can be performed by a fourth communication device, or can also be performed by a device including a fourth communication device, or can also be performed by a chip (or, chip system) or other functional module, which can implement the functions of the fourth communication device, for example, the chip or functional module is set in the fourth communication device. The fourth communication device can be a network side device, for example, the fourth communication device can be a core network device, or can also be a third-party device, without limitation.

[0073] Taking the fourth communication device as the execution subject as an example, the method may include: the fourth communication device receives first information from the second communication device, the first information is used to indicate the second communication device's receiving capability for the AI ​​model, and the first information is used to determine the first AI model to be applied by the second communication device and the transmission method of the first AI model; and, sending the first AI model to the second communication device according to the first information.

[0074] In one possible implementation, the first information may indicate the receiving capability of the second communication device for the AI ​​model through one or more of the following: the architecture of the AI ​​model supported by the second communication device; the transmission format of the AI ​​model supported by the second communication device; the identifier of the AI ​​model supported by the second communication device; a first parameter, wherein the first parameter is a relevant parameter applied to the first architecture, and the first architecture is the architecture of the AI ​​model supported by the second communication device and known to the fourth communication device; or, a first identifier, wherein the first identifier is used to indicate the second architecture and the relevant parameters applied to the second architecture, and the second architecture belongs to the architecture of the AI ​​model supported by the second communication device.

[0075] In one possible implementation, the fourth communication device may further send second information to the second communication device, where the second information is used to indicate the transmission capability of the fourth communication device for the AI ​​model.

[0076] In one possible implementation, the second information may indicate the transmission capability of the fourth communication device for the AI ​​model through one or more of the following: the architecture of the AI ​​model supported for transmission by the fourth communication device; the transmission format of the AI ​​model supported for transmission by the fourth communication device; the identifier of the AI ​​model supported for transmission by the fourth communication device; a second parameter, wherein the second parameter is a relevant parameter applied to the third architecture, and the third architecture is the architecture of the AI ​​model supported for transmission by the fourth communication device known to the second communication device; or, a second identifier, wherein the second identifier is used to indicate the fourth architecture and the relevant parameters applied to the fourth architecture, and the fourth architecture belongs to the architecture of the AI ​​model supported for transmission by the fourth communication device.

[0077] In a possible implementation, the second information may also be used to indicate a communication range to which the transmission capability of the fourth communication device for the AI ​​model is applicable.

[0078] In one possible implementation, the fourth communication device sends the first AI model to the second communication device based on the first information. Specifically, the fourth communication device receives third information from the second communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model; and sends the first AI model to the second communication device based on the first information and the third information.

[0079] In one possible implementation, the fourth communication device sends the first AI model to the second communication device, which may be: the fourth communication device sends the architecture and third parameters of the first AI model to the second communication device, where the third parameters are relevant parameters of the architecture applied to the first AI model; or, the fourth communication device sends the identifier of the architecture of the first AI model and the third parameter to the second communication device, where the third parameters are relevant parameters of the architecture applied to the first AI model; or, the fourth communication device sends fourth information to the second communication device, where the fourth information includes the identifier and / or the third identifier of the first AI model, where the third identifier is used to indicate the architecture and third parameters of the first AI model, and the third parameters are relevant parameters of the architecture applied to the first AI model.

[0080] In one possible implementation, the fourth communication device sends the first AI model to the second communication device, specifically: the fourth communication device sends part of the information of the first AI model to the second communication device through a control surface, and sends the remaining information of the first AI model except the part of the information to the second communication device through a user surface.

[0081] In one possible implementation, the first AI model is carried by a non-access stratum (NAS) message, and the NAS message reaches the second communication device through the first communication device. The fourth communication device may also send tenth information to the first communication device, where the tenth information is used to indicate that the NAS message carries an AI model, wherein the first communication device provides access services for the second communication device.

[0082] Through the above implementation, the first AI model is carried by the NAS message, and the fourth communication device can send the tenth information to the first communication device, so that the first communication device can determine that the NAS message carries the AI ​​model.

[0083] In one possible implementation, the fourth communication device may further send fifth information to the second communication device, where the fifth information indicates whether the second communication device is permitted to modify the first AI model. Optionally, when the fifth information indicates that the second communication device is permitted to modify the first AI model, the fifth information further indicates conditions for registering the modified AI model and / or a registration method for the modified AI model.

[0084] In a possible implementation, the fourth communication device may further send information indicating that the first AI model has not been transmitted and / or transmission progress information of the first AI model to the second communication device.

[0085] In one possible implementation, the fourth communication device may also send sixth information to the second communication device, where the sixth information is used to instruct the second communication device to record seventh information, where the seventh information is used to indicate that the first AI model has not completed transmission, or the seventh information is transmission progress information of the first AI model.

[0086] In one possible implementation, the fourth communication device may further send eighth information to the second communication device, where the eighth information is used to indicate that the second communication device is allowed to send the seventh information to the third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission anomaly occurs. Optionally, the eighth information may also be used to indicate the communication range of the third communication device.

[0087] In one possible implementation, the seventh information is the transmission progress information of the first AI model, and the fourth communication device may also send ninth information to the third communication device, where the ninth information is used to instruct the third communication device to obtain the transmission progress information of the first AI model from the second communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

[0088] In another possible implementation, the fourth communication device may also send transmission progress information of the first AI model to the third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

[0089] In a possible implementation, the fourth communication device may receive a first request message from the third communication device, where the first request message is used to request transmission progress information of the first AI model.

[0090] In one possible implementation, the transmission progress information of the first AI model may include one or more of the following: transmission progress information of the architecture of the first AI model; transmission progress information of a third parameter, where the third parameter is a relevant parameter applied to the architecture of the first AI model; or information indicating information that has not been transmitted in the first AI model.

[0091] In one possible implementation, the fourth communication device may also send the first information and / or third information to the third communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

[0092] The technical effects that can be achieved by the above-mentioned fourth aspect and any possible implementation thereof can be referred to the technical effects that can be achieved by the above-mentioned first aspect and any possible implementation thereof, and no further details will be given.

[0093] In a fifth aspect, the present application provides a communication device, which can be used to execute the method described in the first aspect and any possible implementation thereof. The communication device can be, for example, a first communication device.

[0094] In a possible implementation, the communication device may include a baseband device and a radio frequency device.

[0095] In another possible implementation, the communication device may include a processing module (sometimes also referred to as a processing unit) and a transceiver module (sometimes also referred to as a transceiver unit). The transceiver module can implement both sending and receiving functions. When the transceiver module implements the sending function, it may be referred to as a sending module (sometimes also referred to as a sending unit); when the transceiver module implements the receiving function, it may be referred to as a receiving module (sometimes also referred to as a receiving unit). The sending module and the receiving module may be the same functional module, referred to as a transceiver module, which is capable of both sending and receiving functions; alternatively, the sending module and the receiving module may be different functional modules, with the transceiver module being a general term for these functional modules.

[0096] In a sixth aspect, the present application provides a communication device, which can be used to execute the method described in the second aspect and any possible implementation thereof. The communication device can be, for example, the second communication device.

[0097] In a possible implementation, the communication device may include a baseband device and a radio frequency device.

[0098] In another possible implementation, the communication device may include a processing module (sometimes also referred to as a processing unit) and a transceiver module (sometimes also referred to as a transceiver unit). The transceiver module can implement both sending and receiving functions. When the transceiver module implements the sending function, it may be referred to as a sending module (sometimes also referred to as a sending unit); when the transceiver module implements the receiving function, it may be referred to as a receiving module (sometimes also referred to as a receiving unit). The sending module and the receiving module may be the same functional module, referred to as a transceiver module, which is capable of both sending and receiving functions; alternatively, the sending module and the receiving module may be different functional modules, with the transceiver module being a general term for these functional modules.

[0099] In a seventh aspect, the present application provides a communication device, which can be used to execute the method described in the third aspect and any possible implementation thereof. The communication device can be, for example, the third communication device.

[0100] In a possible implementation, the communication device may include a baseband device and a radio frequency device.

[0101] In another possible implementation, the communication device may include a processing module (sometimes also referred to as a processing unit) and a transceiver module (sometimes also referred to as a transceiver unit). The transceiver module can implement both sending and receiving functions. When the transceiver module implements the sending function, it may be referred to as a sending module (sometimes also referred to as a sending unit); when the transceiver module implements the receiving function, it may be referred to as a receiving module (sometimes also referred to as a receiving unit). The sending module and the receiving module may be the same functional module, referred to as a transceiver module, which is capable of both sending and receiving functions; alternatively, the sending module and the receiving module may be different functional modules, with the transceiver module being a general term for these functional modules.

[0102] In an eighth aspect, the present application provides a communication device, which can be used to execute the method described in the fourth aspect and any possible implementation thereof. The communication device can be, for example, the fourth communication device.

[0103] In a possible implementation, the communication device may include a baseband device and a radio frequency device.

[0104] In another possible implementation, the communication device may include a processing module (sometimes also referred to as a processing unit) and a transceiver module (sometimes also referred to as a transceiver unit). The transceiver module can implement both sending and receiving functions. When the transceiver module implements the sending function, it may be referred to as a sending module (sometimes also referred to as a sending unit); when the transceiver module implements the receiving function, it may be referred to as a receiving module (sometimes also referred to as a receiving unit). The sending module and the receiving module may be the same functional module, referred to as a transceiver module, which is capable of both sending and receiving functions; alternatively, the sending module and the receiving module may be different functional modules, with the transceiver module being a general term for these functional modules.

[0105] In a ninth aspect, the present application provides a communication system, which includes one or more of the following: the communication device described in the fifth aspect, the communication device described in the sixth aspect, the communication device described in the seventh aspect, or the communication device described in the eighth aspect.

[0106] In a tenth aspect, the present application further provides a communication device, which may include one or more processors configured to execute the method described in any one of the first to fourth aspects and any possible implementation thereof.

[0107] Optionally, the communication device may also include a memory, wherein the memory is used to store one or more computer programs or instructions, and the one or more processors are used to execute the one or more computer programs or instructions stored in the memory, so that the communication device performs the method described in any one of the first to fourth aspects above and any possible implementation methods thereof.

[0108] In the eleventh aspect, the present application also provides a computer-readable storage medium, which is used to store a computer program. When the computer program is run on a computer, the computer executes the method described in any one of the first to fourth aspects above and any possible implementation method thereof.

[0109] In the twelfth aspect, the present application also provides a computer program product, which includes a computer program. When the computer program is run on a computer, it enables the computer to execute the method described in any one of the above-mentioned aspects 1 to 4 and any possible implementation method thereof.

[0110] In a thirteenth aspect, the present application further provides a chip system, comprising a processor configured to execute the method described in any one of the first to fourth aspects and any possible implementation thereof. Optionally, the chip system may be composed of a chip, or the chip system may also include a chip and other discrete devices.

[0111] The technical effects that can be achieved by the above-mentioned fifth to thirteenth aspects and any possible implementation methods thereof may refer to the technical effects that can be achieved by the above-mentioned first to fourth aspects and any possible implementation methods thereof, and no repetition will be given. BRIEF DESCRIPTION OF THE DRAWINGS

[0112] FIG1( a ) is a schematic diagram of the architecture of a communication system used in an embodiment of the present application;

[0113] Figure 1(b) is a schematic diagram of an access network device;

[0114] FIG1( c ) is a schematic diagram of the architecture of another communication system used in an embodiment of the present application;

[0115] Figure 2 is a schematic diagram of an architecture for AI applications in NR;

[0116] FIG3 is a flow chart of a first communication method provided in an embodiment of the present application;

[0117] FIG4 is a flow chart of a second communication method provided in an embodiment of the present application;

[0118] FIG5 is a schematic diagram of a flow chart of a third communication method provided in an embodiment of the present application;

[0119] FIG6 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0120] FIG7 is a schematic structural diagram of another communication device provided in an embodiment of the present application;

[0121] FIG8 is a schematic structural diagram of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0122] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. The technical solutions of the embodiments of the present application can be applied to various communication systems, for example, universal mobile telecommunications system (UMTS), wireless local area network (WLAN), short-range wireless communication systems (such as sidelink, wireless fidelity (Wi-Fi), Bluetooth, etc.), wired networks, vehicle-to-everything (V2X) communication systems, device-to-device (D2D) communication systems, Internet of Vehicles communication systems, 4th generation (4G) mobile communication systems (such as long term evolution (LTE) systems), LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, worldwide interoperability for microwave access (WiMAX) communication systems, fifth generation (5G) mobile communication systems (such as new radio (NR) systems), future communication systems (such as sixth generation (6G) systems), and the like. Generation (6G) mobile communication systems), or other similar communication systems, etc., without limitation. It should be understood that when the technical solutions of the embodiments of the present application are applied to other communication systems, the devices, components, modules, etc. in the embodiments of the present application can be replaced with corresponding devices, components, and modules in other communication systems without limitation.

[0123] This application will present various aspects, embodiments, or features in the context of systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that each system may include additional devices, components, modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in conjunction with the figures. Furthermore, combinations of these aspects may also be used.

[0124] Figure 1(a) is a schematic diagram of the architecture of a communication system used in an embodiment of the present application. The communication system 1000 shown in Figure 1(a) includes an access network 100 and a core network 200. Exemplarily, the communication system 1000 also includes the Internet 300. Among them, the access network 100 may include at least one access network device (such as 110a and 110b in Figure 1(a)), and may also include at least one terminal device (such as 120a-120j in Figure 1(a)). The terminal device is connected to the access network device wirelessly, and the access network device is connected to the core network wirelessly or wired. The core network device and the access network device can be independent and different physical devices, or the functions of the core network device and the logical functions of the access network device can be integrated into the same physical device, or the functions of some core network devices and some access network devices can be integrated into one physical device. Terminal devices and terminal devices, as well as access network devices and access network devices, can be connected to each other by wire or wirelessly. FIG1( a ) is only a schematic diagram. The communication system may further include other access network devices, such as wireless relay devices and wireless backhaul devices, which are not shown in FIG1( a ).

[0125] Access network equipment is the access network equipment that terminal devices use to access the communication system via wired or wireless means. Access network equipment can be a base station, such as an evolved NodeB (eNodeB), a transmission reception point (TRP), a next-generation NodeB (gNB) in a 5G mobile communication system, a next-generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a Wi-Fi system. It can also be a module or unit that performs some of the functions of a base station, such as a centralized unit (CU) or a distributed unit (DU). The CU performs the functions of the base station's radio resource control protocol and packet data convergence protocol (PDCP), as well as the service data adaptation protocol (SDAP). The DU performs the functions of the base station's radio link control layer and medium access control (MAC) layer, as well as some or all of the physical layer. For detailed descriptions of each of the above protocol layers, please refer to the relevant technical specifications of 3GPP. The access network device may be a macro base station (such as 110a in FIG1(a)), a micro base station or an indoor station (such as 110b in FIG1(a)), a relay node or a donor node, etc. The embodiments of the present application do not limit the specific technology and specific device form used by the access network device.

[0126] A terminal device is a device with wireless transceiver capabilities that can send signals to or receive signals from an access network device. Terminal devices include but are not limited to terminal devices, terminals, user equipment (UE), mobile stations, mobile terminals, etc. Terminal devices can be widely used in various scenarios, such as D2D communication, V2X communication, machine-type communication (MTC), Internet of Things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. The terminal device can specifically be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a wearable device, a vehicle, an airplane, a ship, a robot, a robotic arm, a smart home device, etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the terminal device.

[0127] The access network equipment or terminal equipment can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; on water; or on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the access network equipment and terminal equipment.

[0128] The roles of access network devices and terminal devices can be relative. For example, the helicopter or drone 120i in Figure 1(a) can be configured as a mobile access network device. For terminal devices 120j that access the access network 100 via 120i, terminal device 120i is an access network device. However, for access network device 110a, 120i is a terminal device, meaning that communication between 110a and 120i occurs via a wireless air interface protocol. Of course, communication between 110a and 120i can also occur via an interface protocol between access network devices. In this case, relative to 110a, 120i is also an access network device. Therefore, both access network devices and terminal devices can be collectively referred to as communication devices. 110a and 110b in Figure 1(a) can be referred to as communication devices with access network device functionality, while 120a-120j in Figure 1(a) can be referred to as communication devices with terminal device functionality.

[0129] Access network devices and terminal devices, access network devices and access network devices, and terminal devices and terminal devices can communicate through authorized spectrum, unauthorized spectrum, or both. They can communicate through spectrum below 6 gigahertz (GHz), spectrum above 6 GHz, or spectrum below 6 GHz and spectrum above 6 GHz. The embodiments of this application do not limit the spectrum resources used for wireless communications.

[0130] In the embodiments of the present application, the functions of the access network device may also be performed by a module (such as a chip) in the access network device, or by a control subsystem that includes the functions of the access network device. The control subsystem that includes the functions of the access network device here may be a control center in the above-mentioned application scenarios such as smart grid, industrial control, smart transportation, and smart city. The functions of the terminal device may also be performed by a module (such as a chip or modem) in the terminal device, or by a device that includes the functions of the terminal device.

[0131] In this application, an access network device sends downlink signals or downlink information to a terminal device, and the downlink information is carried on a downlink channel. A terminal device sends uplink signals or uplink information to the access network device, and the uplink information is carried on an uplink channel. To communicate with the access network device, the terminal device needs to establish a wireless connection with the cell controlled by the access network device. The cell with which the terminal device has established a wireless connection is called the serving cell of the terminal device.

[0132] The core network 200 includes one or more core network devices. Taking the 5G core network as an example, the core network devices include, but are not limited to, one or more of the following network elements: an authentication server function (AUSF) network element, a unified data management (UDM) network element, a unified data repository (UDR) network element, a network repository function (NRF) network element, a network exposure function (NEF) network element, an application function (AF) network element, a policy control function (PCF) network element, an access and mobility management function (AMF) network element, a session management function (SMF) network element, a user plane function (UPF) network element, a binding support function (BSF) network element, a network data analytics function (NWDAF) network element, or a location management function (LMF). Each core network element can work independently or be combined to implement certain control functions. For example, AMF, SMF and PCF can be combined together as a core network device.

[0133] Figure 1(b) shows a schematic diagram of an access network device. As shown in Figure 1(b), the access network device includes one or more CUs, one or more DUs, and one or more radio units (RUs). For clarity, Figure 1(b) shows only one CU, one DU, and one RU. The CU is used to connect to the core network and one or more DUs. For example, the CU and one or more DUs are connected via an F1 interface. For example, the CU may have some of the core network's functions.

[0134] The CU and DU can be configured according to the protocol layer functions of the wireless network they implement. For example, the CU is configured to implement the functions of the packet data convergence protocol (PDCP) layer and the protocol layers above it (such as the radio resource control (RRC) layer and / or the service data adaptation protocol (SDAP) layer, etc.); the DU is configured to implement the functions of the protocol layers below the PDCP layer (such as the radio link control (RLC) layer, the medium access control (MAC) layer, and / or the physical (PHY) layer, etc.). For another example, the CU is configured to implement the functions of the protocol layers above the PDCP layer (such as the RRC layer and / or the SDAP layer), and the DU is configured to implement the functions of the PDCP layer and the protocol layers below it (such as the RLC layer, the MAC layer, and / or the PHY layer, etc.).

[0135] The above configuration of CU and DU is only an example, and the functions of CU and DU can also be configured as needed. For example, the CU or DU can be configured to have the functions of more protocol layers, or the CU or DU can be configured to have partial processing functions of the protocol layer. For example, some functions of the RLC layer and the functions of the protocol layers above the RLC layer are set in the CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer are set in the DU. For another example, the functions of the CU or DU can be divided according to the service type or other system requirements, such as by delay, and the functions whose processing time needs to meet the smaller delay requirement are set in the DU, and the functions that do not need to meet the delay requirement are set in the CU.

[0136] The functions of the CU can be implemented by a single entity or by different entities. For example, the functions of the CU can be further divided, such as separating the control plane (CP) and the user plane (UP), namely the CU control plane (CU-CP) and the CU user plane (CU-UP). For example, the CU-CP and CU-UP can be implemented by different functional entities and connected via an E1 interface. The CU-CP and CU-UP can be coupled with the DU to jointly perform the functions of the access network device.

[0137] For example, the CU-CP may further include CU-CP1 and CU-CP2. For example, CU-CP1 is responsible for determining the interaction strategy between the CU and DU, while CU-CP2 is responsible for generating specific control plane messages. For another example, CU-CP1 includes various radio resource management functions, while CU-CP2 only includes RRC and PDCP-C functions.

[0138] The RU may be included in a radio frequency device or a radio frequency unit, for example, in a remote radio unit (RRU), an active antenna unit (AAU) or a remote radio head (RRH).

[0139] The DU and RU can work together to implement the functions of the PHY layer. A DU can be connected to one or more RUs. The functions of the DU and RU can be configured in various ways according to the design. For example, the DU is configured to implement the baseband function, and the RU is configured to implement the mid-RF function. For another example, the DU is configured to implement the high-layer functions in the PHY layer, and the RU is configured to implement the low-layer functions in the PHY layer or to implement the low-layer functions and the RF functions. The high-layer functions in the physical layer may include a part of the functions of the physical layer, which is closer to the MAC layer, and the low-layer functions in the physical layer may include another part of the functions of the physical layer, which is closer to the mid-RF side.

[0140] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (open RAN, ORAN) system, CU may also be called open CU (O-CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0141] Furthermore, a terminal device can achieve wireless access through a single access network device, or through multiple access network devices. In other words, multiple access network devices collaborate to assist the terminal device in achieving wireless access, with different access network devices implementing portions of the base station's functionality, as shown in Figure 1(c). Figure 1(c) uses two gNBs as an example.

[0142] The communication system and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. A person skilled in the art will appreciate that, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0143] The following first explains the technical features involved in the embodiments of the present application. It should be noted that these explanations are intended to make the embodiments of the present application easier to understand and should not be regarded as limiting the scope of protection claimed by the present application.

[0144] 1. AI Application Framework in NR

[0145] 3GPP has proposed applying AI to NR systems. Through intelligent data collection and analysis, network performance and user experience can be improved. 3GPP has initially defined an AI application framework for NR, as shown in Figure 2. The data source stores data from the gNB, gNB-CU, gNB-DU, UE, or other management entities. The data source serves as a database for AI model training and data analysis and inference. For example, "Data Collection" in Figure 2 represents the data source. The model training host analyzes the training data provided by the data source to generate an optimal AI model. For example, the "Model Training" box in Figure 2 represents the model training host. The model inference host uses this AI model to generate AI-based predictions about network operation based on the data provided by the data source, or guide network policy adjustments. For example, the "Model Inference" box in Figure 2 represents the model inference host. These policy adjustments are centrally planned by the actor entity and sent to multiple network entities for execution. Furthermore, after the network applies the adjusted policy, specific network performance information is re-entered and stored in the data source.

[0146] 2. AI capabilities, or AI application scenarios, or AI-based use cases

[0147] AI application scenarios may include, but are not limited to, one or more of the following: energy saving, load balancing, mobility optimization, channel status information reference signal (CSI-RS) feedback enhancement, beam management enhancement, or positioning accuracy enhancement. These are described below.

[0148] (1) Energy saving

[0149] Access network equipment can predict its load based on its own and neighboring cell load, energy consumption, energy efficiency, and other information, as well as terminal trajectory and measurement results. Based on the prediction results, the access network equipment can take appropriate energy-saving measures in a timely manner, without impacting network coverage or user access. These energy-saving measures may include at least one of the following: cell deactivation, carrier shutdown, channel shutdown, time slot shutdown, or transmit power reduction.

[0150] (2) Load balancing

[0151] Access network equipment can predict its load based on its own and neighboring cell's load, energy consumption, energy efficiency, and other information, as well as terminal trajectories and measurement results. Based on these predictions, the access network equipment can handover some terminals to neighboring cells, or handover some terminals served by neighboring cells to its own cell. This ensures that the loads of all access network equipment in the network are consistent, preventing some access network equipment from being overloaded, impacting terminal services, while other access network equipment resources remain idle.

[0152] (3) Mobility Optimization

[0153] Access network equipment can predict a terminal's future trajectory based on its historical trajectory and measurement data. Based on this prediction, the equipment can determine in advance whether a terminal requires handover. It can also pre-configure the necessary handover information for terminals requiring handover and notify the target cell to prepare access resources for the terminal. This reduces handover delays and improves the success rate of terminal handovers.

[0154] (4) CSI-RS feedback enhancement

[0155] The access network equipment can provide the terminal with an encoder and quantization tool based on information such as the terminal's capabilities. The terminal compresses and quantizes the CSI-RS using this encoder and quantization tool and then sends the CSI-RS to the access network equipment. The access network equipment can use the CSI-RS to determine the terminal's channel quality.

[0156] (5) Enhanced beam management

[0157] The access network device can obtain full-beam scanning results from multiple terminals and train a sparse scanning matrix based on them. Then, after sending the sparse scanning matrix to terminal a, the access network device can obtain the sparse scanning results from terminal a and determine the optimal CSI-RS beam for terminal a based on the sparse scanning results.

[0158] (6) Positioning enhancement

[0159] Positioning enhancement is used to improve positioning accuracy. Positioning enhancement can include at least one of the following: positioning enhancement based on access network equipment, positioning enhancement based on positioning management function network elements, and positioning enhancement based on terminals.

[0160] 3. AI Model

[0161] An AI model, also referred to as a model, represents the mapping relationship between the model's input and output. An AI model can be a neural network, linear regression model, decision tree model, support vector machine (SVM), Bayesian network, Q-learning model, or other machine learning model.

[0162] AI models can be used to implement one or more of the following functions: data collection (collecting training data and / or inference data), data preprocessing, model training (also known as model learning), model information release (configuring model information), model verification, model inference, or inference result release. Inference can also be called prediction.

[0163] In the embodiments of the present application, an AI model can be used to implement the aforementioned AI functions. When the AI ​​model is located on the terminal side, for a certain functional module, the terminal may have multiple AI models that can implement the functions of the functional module. For example, for the CSI channel measurement result prediction function, the terminal may have multiple AI models that can provide prediction results.

[0164] 4. AI module

[0165] The AI ​​module can be a module with machine learning computing capabilities, used to acquire (or generate) AI models. In wireless communication systems, the AI ​​module can be located in the operations administration and maintenance (OAM) system, in the gNB (for example, in the CU within the gNB), in some UEs, or as a separate network element entity. The AI ​​module's primary function in wireless communication systems is to perform a series of AI computations, including model building, training approximation, and reinforcement learning, based on input data (in wireless communication systems, input data generally refers to network operation data provided by the RAN or monitored by OAM, such as network load and channel quality). The trained AI model provided by the AI ​​module has the ability to predict network changes on the RAN side and is typically used for load prediction and UE path prediction. Furthermore, the AI ​​module can use the trained model's predictions of RAN network performance to perform policy inference from the perspectives of network energy conservation and mobility optimization, thereby developing reasonable and efficient energy conservation and mobility optimization strategies.

[0166] When the AI ​​module is located in the OAM, its communication with the RAN-side gNB can reuse the current northbound interface. When the AI ​​module is located in the gNB or CU, it can reuse the current F1, Xn, and Uu interfaces. When the AI ​​module becomes an independent network element entity, it is necessary to re-establish communication links with the OAM and RAN sides, such as using wired or wireless links. When the CP and UP of the CU are separated, the CP is generally responsible for receiving the AI ​​model and subsequent AI reasoning and policy generation functions. When the CU-CP is further divided into CU-CP1 and CU-CP2, CU-CP1 is generally responsible for receiving the AI ​​model and subsequent AI reasoning functions, and generating specific interaction signaling, which is then sent by CU-CP2.

[0167] 5. Transmission method of AI model

[0168] The 3GPP standard defines the transmission methods of AI models on the air interface from the perspectives of RAN2 and RAN1 respectively. Among them, RAN2 focuses on the methods and paths for transmitting AI models. The planned AI model transmission methods include 8 types, as shown in Table 1. Among them, solutions 1a, 2a, and 3a are to transfer (or deliver) the AI ​​model to the UE through the control surface. Solutions 1b, 2b, and 3b are to transfer (or deliver) the AI ​​model to the UE through the user surface. Solutions 4a and 4b are to transfer (or deliver) the AI ​​model to the UE through a third-party server. The third-party server can be, for example, OAM or OTT (over the top), etc., without limitation. Optionally, solution 4a may transmit the AI ​​model to the UE through the Internet Protocol (IP) pipe or non-access stratum (NAS) signaling. Optionally, the transmission mode of solution 4b may be transparent or non-transparent to the 3GPP network (for example, the AI ​​model is transmitted as application layer data through the user plane) without restriction.

[0169] Table 1

[0170] RAN1 defines six AI model transmission methods based on the transmission format of the AI ​​model, as shown in Table 2. Among them, use case (case) y implements the transmission of the AI ​​model based on the top layer (for example, the application layer), and the AI ​​model is stored in a network outside the 3GPP network (outside the 3GPP network), that is, the content of the AI ​​model is not visible to the 3GPP network. Case z1 and case z2 are both based on a proprietary format (but the two methods are transmitted to the UE from different nodes respectively) to implement the transmission of the AI ​​model, that is, the AI ​​model will be transmitted on the air interface in a format that is not recognizable or readable by 3GPP. Case z3, case z4 and case z5 are all based on an open format to implement the transmission of the AI ​​model. Among them, open format refers to the compiled format of the AI ​​model, for example, based on Python, C++, or Open Neural Network Exchange (ONNX) and other compiled formats. In case z3, model training is performed by the UE side or neutral side node (i.e., other non-3GPP network side nodes), while in case z4 and case z5, model training is performed by the 3GPP network (NW) side. The difference between case z4 and case z5 is that in case z4, the UE side and the NW side have already interacted in advance about the architecture of the transmitted AI model, while in case z5, the architecture of the transmitted AI model is unknown. The architecture of the AI ​​model can be, for example, a fully connected model or a deep learning model, without limitation.

[0171] Table 2

[0172] Currently, terminal devices can obtain AI models from the network to implement AI functions. The standard only defines several potential model transmission formats from the perspectives of RAN1 and RAN2, but does not specify how to transmit the AI ​​model. Different terminal devices have different AI model reception capabilities, and there is a problem where the network-side AI model (and / or AI model transmission method) may not be adapted to the terminal device's reception capabilities, resulting in a waste of transmission resources.

[0173] In view of this, the embodiments of the present application provide a communication method and apparatus for adapting the terminal device's receiving capability for an AI model, thereby reducing the waste of transmission resources. The method and apparatus described in this application are based on the same technical concept. Since the method and apparatus solve the problem in a similar manner, the implementation of the apparatus and method can refer to each other, and the repetitions will not be repeated.

[0174] The following is an introduction to the technical terms involved in the embodiments of this application.

[0175] The first AI model may be an AI model to be applied by the second communication device. The present embodiment of the application does not limit the specific naming of the first AI model. For example, the first AI model may be generated by an AI module. For details about the AI ​​module, please refer to the aforementioned content and will not be described in detail. The present embodiment of the application does not limit the AI ​​function implemented by the first AI model. For details about the AI ​​function, please refer to the aforementioned content and will not be described in detail.

[0176] It should be pointed out that the embodiment of the present application takes the transmission of a single AI model as an example, but is not limited to the number of AI models transmitted simultaneously over the air interface. That is, the communication method provided in the embodiment of the present application is also suitable for scenarios where multiple AI models are transmitted over the air interface.

[0177] The first communication device can be used to send a first AI model. Exemplarily, the first communication device can be an access network device or a component in the access network device (for example, one or more of CU, CU-CP, CU-CP1, or CU-CP2, etc.); or, the first communication device can also be a core network device or a component in a core network device, and the core network device can be, for example, LMF, or other core network devices other than LMF; or, the first communication device can also be a third-party server or a component in a third-party server, and the third-party server can be, for example, OAM, or OTT, etc. The embodiment of the present application does not limit the specific implementation form of the first communication device.

[0178] The second communication device may be configured to receive the first AI model. The first AI model is applied to the second communication device to implement the corresponding AI function. The second communication device may be a terminal device or a component of a terminal device. The embodiments of the present application do not limit the specific implementation of the second communication device.

[0179] The third communication device can be used to execute the retransmission of the first AI model. For example, the first communication device sends the first AI model to the second communication device. During this process, the transmission of the first AI model may be interrupted (for example, the second communication device performs cell switching, or the transmission of the first AI model is abnormal, etc.), and then the third communication device can execute the retransmission of the first AI model. Exemplarily, the third communication device can be an access network device or a component in the access network device (for example, one or more of CU, CU-CP, CU-CP1, or CU-CP2, etc.); or, the third communication device can also be a core network device or a component in a core network device, and the core network device can be, for example, LMF, or other core network devices other than LMF; or, the third communication device can also be a third-party server or a component in a third-party server, and the third-party server can be, for example, OAM, or OTT, etc. The embodiment of the present application does not limit the specific implementation form of the third communication device.

[0180] In one embodiment, the third communication device and the first communication device may be the same communication device. For example, if the first communication device is a core network device, and the second communication device performs a cell handover during the transmission of the first AI model, the core network device may execute the continued transmission of the first AI model. For another example, if the first communication device is an access network device and the transmission of the first AI model is abnormal, the second communication device may re-establish a connection with the access network device, and the access network device may execute the continued transmission of the first AI model.

[0181] In another embodiment, the third communication device and the first communication device may be different communication devices. For example, the first communication device is access network device 1, and the third communication device is access network device 2. During the transmission of the first AI model, if the second communication device switches from the cell provided by access network device 1 to the cell of access network device 2, access network device 2 can then perform the continued transmission of the first AI model.

[0182] The fourth communication device can be used to send the first AI model. Exemplarily, the fourth communication device can be a core network device or a component in the core network device. The core network device can be, for example, LMF, or other core network devices other than LMF; or, the fourth communication device can also be a third-party server or a component in a third-party server. The third-party server can be, for example, OAM, or OTT. The embodiment of the present application does not limit the specific implementation form of the fourth communication device. In other words, when the first communication device is not an access network device, the fourth communication device can be the first communication device. The relationship between the fourth communication device and the third communication device can refer to the description of the first communication device and the third communication device, and will not be repeated.

[0183] Figure 3 is a flow chart of a first communication method provided in an embodiment of the present application. The method may include the following steps.

[0184] S301: The second communication device sends first information to the first communication device.

[0185] Accordingly, the first communication device receives the first information from the second communication device.

[0186] In one embodiment, the second communication device may proactively send the first information to the first communication device. For example, the second communication device may send the first information to the first communication device via a UE capability reporting mechanism. For another example, the second communication device may send the first information to the first communication device via a UE assistance information (UAI) reporting mechanism.

[0187] In another embodiment, the second communication device may also send the first information to the first communication device in response to the request of the first communication device. For example, the first communication device may send a third request message to the second communication device, and the third request message may be used to request the first information (or the third request message may be used to request information about the second communication device's ability to receive the AI ​​model); accordingly, the second communication device may send the first information to the first communication device according to the third request message. Optionally, the first information may be carried by an RRC message without limitation.

[0188] It should be noted that if the first communication device is not an access network device (or, in other words, the first communication device is a fourth communication device), for example, the first communication device is a core network device or a third-party server, then the second communication device can send the first information to the first communication device (or the fourth communication device) through the access network device that provides access services for the second communication device. In other words, the second communication device sends the first information, and the access network device that provides access services for the second communication device receives the first information and then forwards it to the first communication device (or the fourth communication device).

[0189] The first information is used to indicate the receiving capability of the second communication device for the AI ​​model. In other words, the first information is information about the receiving capability of the second communication device for the AI ​​model. Exemplarily, the first information may indicate the receiving capability of the second communication device for the AI ​​model through one or more of the following:

[0190] (1) The second communication device supports the architecture of the received AI model.

[0191] The architecture of the AI ​​model refers to architectures such as fully connected models, deep learning models, or convolutional neural network models, and is not restricted.

[0192] (2) The second communication device supports the transmission format of the received AI model.

[0193] The transmission format of AI models can be based on top-level transmission, private format transmission, or public format transmission. Among them, public format refers to the compiled format based on programming languages ​​such as Python, C++, or ONNX.

[0194] (3) The second communication device supports the identification of the received AI model.

[0195] The identifier of the AI ​​model is used to indicate the AI ​​model. For example, the first communication device and the second communication device pre-agreed on one or more AI models and configured corresponding identifiers, and then determined the one or more AI models through the identifiers.

[0196] (4) First parameter.

[0197] The first parameter is a parameter related to the first architecture. The first architecture may be an architecture of an AI model supported and received by the second communication device, known to the first communication device. Alternatively, the first architecture is an architecture of an AI model supported and received by the second communication device, agreed upon in advance by the first communication device and the second communication device.

[0198] Exemplarily, the first parameter may include but is not limited to one or more of the following: the maximum number of input parameters of the AI ​​model; the accuracy of the input parameters of the AI ​​model; the type of the input parameters of the AI ​​model (for example, integer or floating point number, etc.); the maximum number of output parameters of the AI ​​model; the accuracy of the output parameters of the AI ​​model; the type of the output parameters of the AI ​​model; the number of hidden layers of the AI ​​model (or the range of the number of hidden layers, for example, supporting 3 to 5 hidden layers); the specific value of the architecture of the AI ​​model (for example, the specific value can be expressed as 3-351, which means the AI ​​model There are 3 layers in total, with the number of nodes in each layer being 3, 5, and 1 respectively); the connection method of the nodes in the AI ​​model (for example, the connection method can be expressed as 12-24, which means that the second node of the first layer of the AI ​​model is connected to the fourth node of the second layer); the calculation (or storage) accuracy (or supported calculation method) supported by specific nodes (or weights) in the AI ​​model; the update frequency of the parameters (or architecture) of the AI ​​model (for example, supporting the update of the parameters or architecture of the AI ​​model every 5 seconds); or, information indicating whether the architecture of the AI ​​model and the parameters of the AI ​​model are supported to be transmitted separately, etc. The embodiments of the present application do not limit the specific implementation form of the first parameter.

[0199] For example, the computation (or storage) accuracy supported by a specific node (or weight) in an AI model can be expressed as abc, which means that the computation (or storage) accuracy supported by the b-th node (or weight) in the a-th layer of the AI ​​model is c. For another example, the computation methods supported by a specific node (or weight) in an AI model can be expressed as abc, which means that the computation method supported by the b-th node (or weight) in the a-th layer of the AI ​​model is the computation method identified by c (for example, convolution or multiplication).

[0200] Optionally, in the case where the architecture of the AI ​​model and the parameters of the AI ​​model are supported to be transmitted separately, the first parameter may further include information for indicating that the architecture of the AI ​​model is transmitted via the control plane, and / or information for indicating that the parameters of the AI ​​model are transmitted via the user plane. Alternatively, in the case where the architecture of the AI ​​model and the parameters of the AI ​​model are not supported to be transmitted separately, the first parameter may further include information for indicating that the AI ​​model is transmitted via the control plane or the user plane.

[0201] (5) First identification.

[0202] The first identifier can be used to indicate the second architecture and related parameters applied to the second architecture. The second architecture belongs to the architecture of the AI ​​model supported by the second communication device. For example, the first identifier can be a token, which is not limited. For example, the first communication device and the second communication device pre-agreed on a combination of parameters and architectures for a specific AI model, and assign identifiers to these combinations (for example, assigning tokens). For example, the second communication device supports token1 of the fully connected model, indicating that the second communication device supports the architecture and parameters corresponding to token1 under the fully connected model. Among them, the relevant parameters applied to the second architecture can refer to the content of the aforementioned first parameter and will not be repeated.

[0203] In an embodiment of the present application, the first information can be used to determine the first AI model to be applied by the second communication device, or the first information can be used to determine the transmission method of the first AI model, or the first information can be used to determine the first AI model and the transmission method of the first AI model. That is, in the process of determining the first AI model and in the process of determining the transmission method of the first AI model, the receiving capability of the second communication device for the AI ​​model can be considered, so that the first AI model sent by the first communication device can adapt to the receiving capability of the second communication device, thereby reducing the waste of transmission resources caused by the mismatch between the AI ​​model sent by the first communication device and the receiving capability of the second communication device. Among them, please refer to the aforementioned term explanation section for terms such as the first AI model, the first communication device, and the second communication device, and no further details will be given.

[0204] The transmission mode of the first AI model, which may also be referred to as the transmission scheme of the first AI model, is not limited. For example, the transmission mode of the first AI model may include but is not limited to one or more of the following: the transmission format of the first AI model (for example, based on top-level transmission, or based on private format transmission, or based on public format transmission, etc.); transmission of the first AI model through the control plane (or transmission of the first AI model through the user plane, or part of the information of the first AI model is transmitted through the control plane and the remaining information is transmitted through the user plane); quality of service (QoS); mapping method of QoS and data radio bearer (DRB); configuration of signaling radio bearer (SRB); segmentation information (for example, whether segmented transmission is performed, and specific segmentation information in the case of segmented transmission); or PDCP interpolation method, etc. The embodiment of the present application does not limit the specific implementation form of the transmission mode of the first AI model.

[0205] It should be pointed out that the determination of the first AI model and the determination of the transmission mode of the first AI model can be performed by the same communication device, or can also be performed by different communication devices. For example, the first communication device determines the first AI model and the transmission mode of the first AI model based on the first information. For another example, the first communication device is an access network device. After receiving the first information, the first communication device can send the first information to a fourth communication device (for example, a core network device, or a third-party server, etc.); the fourth communication device can determine the first AI model based on the first information, and send the first AI model to the first communication device; the first communication device receives the first AI model and determines the transmission mode of the first AI model based on the first information. Optionally, the determination of the transmission mode of the first AI model can be determined by one or more communication devices without limitation.

[0206] Furthermore, when the determination of the first AI model and the determination of the transmission mode of the first AI model are performed by the same communication device (for example, the first communication device), the determination of the first AI model and the determination of the transmission mode of the first AI model can be performed by different components (or different functional modules) in the communication device, or can also be performed by the same component (or the same functional module) in the communication device.

[0207] In one possible implementation, the first communication device may send the second information to the second communication device; accordingly, the second communication device receives the second information from the first communication device, which is not shown in Figure 3. For example, the first communication device may actively send the second information to the second communication device; or, the first communication device may also send the second information to the second communication device in response to the request of the second communication device. Optionally, the second information may be carried by a broadcast message, or may be carried by an RRC message, without limitation. Among them, the second information can be used to indicate the transmission capability (or sending capability) of the first communication device for the AI ​​model. In other words, the second information is information about the transmission capability (or sending capability) of the first communication device for the AI ​​model.

[0208] Exemplarily, the second information may indicate the first communication device's ability to receive an AI model through one or more of the following: the architecture of the AI ​​model supported for transmission by the first communication device, the transmission format of the AI ​​model supported for transmission by the first communication device, an identifier of the AI ​​model supported for transmission by the first communication device, a second parameter, or a second identifier. For details about the AI ​​model architecture, the AI ​​model transmission format, and the AI ​​model identifier, please refer to the relevant description of the first information and will not be repeated here. The second parameter is a parameter applicable to a third architecture. The third architecture may be an architecture of the AI ​​model supported for transmission by the first communication device, known to the second communication device. Alternatively, the third architecture may be an architecture of the AI ​​model supported for transmission by the first communication device, pre-agreed upon by the first communication device and the second communication device. The second parameter may refer to the description of the first parameter and will not be repeated here. The second identifier may be used to indicate a fourth architecture and related parameters applicable to the fourth architecture. The fourth architecture belongs to the architecture of the AI ​​model supported for transmission by the first communication device. For example, the second identifier may be a token, without limitation. For example, the first communication device and the second communication device pre-agreed upon a combination of parameters and architecture for a specific AI model, and these combinations may be assigned identifiers (e.g., tokens). The second identifier can be compared with the description of the first identifier, which will not be repeated here.

[0209] In one embodiment, the second information can be used to determine the first information. For example, the second communication device can send the first information to the first communication device based on the second information. For another example, the second communication device can determine the first information based on the second information, and send the first information to the first communication device. For example, assuming that the second information indicates that the AI ​​models supported by the first communication device for transmission include AI model 1 and AI model 3, and the AI ​​models supported by the second communication device for reception include AI model 1, AI model 2, and AI model 3, then the second communication device sends the first information to the first communication device based on the second information, and the first information can indicate that the AI ​​models supported by the second communication device for reception include AI model 1 and AI model 3. This embodiment can reduce the transmission of invalid information by the second communication device.

[0210] Optionally, the second information can also be used to indicate the communication range to which the transmission capability of the first communication device for the AI ​​model is applicable. This means that the transmission capability of the first communication device for the AI ​​model in different communication ranges can be the same or different, and the implementation method is flexible. The communication range can be divided, for example, by a public land mobile network (PLMN), or a cell, or a tracking area (TA), etc., without limitation. For example, the transmission capability of the first communication device corresponding to the AI ​​model includes transmission capability 1, transmission capability 2, and transmission capability 3, wherein transmission capability 1 is applicable to cell 1, transmission capability 2 is applicable to cell 2, and transmission capability 3 is applicable to cell 3.

[0211] S302: The first communication device sends the first AI model to the second communication device according to the first information.

[0212] Accordingly, the second communication device receives the first AI model from the first communication device.

[0213] The first communication device may determine the first AI model based on the first information and send the first AI model to the second communication device; or the first communication device may determine the transmission mode of the first AI model based on the first information and send the first AI model to the second communication device according to the transmission mode of the first AI model; or the first communication device may determine the first AI model and the transmission mode of the first AI model based on the first information and send the first AI model to the second communication device according to the transmission mode of the first AI model. For details on the determination of the first AI model and the transmission mode of the first AI model, please refer to the relevant content of S301 and will not be repeated here. It should be noted that if the first AI model is not determined by the first communication device, the first communication device may obtain the first AI model from other communication devices. The embodiments of the present application do not limit the specific implementation process of the first communication device obtaining the first AI model from other communication devices. If the transmission mode of the first AI model is not determined by the first communication device, the first communication device may obtain the transmission mode of the first AI model from other communication devices. The embodiments of the present application do not limit the specific implementation process of the first communication device obtaining the transmission mode of the first AI model from other communication devices.

[0214] In one embodiment, the first communication device may proactively send the first AI model to the second communication device. For example, after obtaining the first AI model and the transmission method of the first AI model, the first communication device may proactively (or when a transmission condition is met) send the first AI model to the second communication device.

[0215] In another embodiment, the first communication device may also send the first AI model to the second communication device in response to a request from the second communication device. For example, the second communication device may send a fourth request message to the first communication device, where the fourth request message may be used to request the first AI model (or, in other words, the fourth request message may be used to request an AI model for a first AI function, where the first AI model is used to implement the first AI function). Accordingly, the first communication device may send the first AI model to the second communication device in response to the fourth request message.

[0216] In one possible implementation, the second communication device may send third information to the first communication device, and the third information may be used to indicate the second communication device's transmission requirements for the AI ​​model (for example, the size of the AI ​​model, the transmission delay of the AI ​​model, etc., without limitation). The first communication device receives the third information from the second communication device, and sends the first AI model to the second communication device based on the third information and the first information. For example, the first communication device determines the first AI model based on the third information, or determines the transmission method of the first AI model based on the third information, or determines the transmission method of the first AI model and the first AI model based on the third information. Optionally, the third information may be a fourth request message, or the third information is included in the fourth request message, without limitation.

[0217] In the embodiment of the present application, the first communication device may send the first AI model to the second communication device in any of the following ways.

[0218] Method 1: The first communication device can send the architecture and third parameters of the first AI model to the second communication device. In response, the second communication device receives the architecture and third parameters of the first AI model from the first communication device. The third parameters may be parameters related to the architecture of the first AI model. For details, please refer to the description of the first parameters and will not be repeated here.

[0219] An AI model consists of an architecture and related parameters applied to the architecture. In Method 1, a first communication device may send the architecture and third parameters of the first AI model to a second communication device; the second communication device receives the architecture and third parameters of the first AI model and determines (or assembles, etc.) the first AI model based on the architecture and third parameters of the first AI model.

[0220] Method 2: The first communication device can send the identifier of the architecture of the first AI model and the third parameter to the second communication device. Correspondingly, the second communication device receives the identifier of the architecture of the first AI model and the third parameter from the first communication device. The third parameter may be a parameter related to the architecture of the first AI model. Please refer to the description of the first parameter for details and will not be repeated here.

[0221] Exemplarily, the architecture of the first AI model may belong to the architecture of an AI model supported and received by the second communication device, which is known to the first communication device; in other words, the architecture of the first AI model may belong to the architecture of an AI model supported and received by the second communication device, which is pre-agreed upon by the first communication device and the second communication device. The first communication device sends an identifier of the architecture of the first AI model and a third parameter to the second communication device; after the second communication device receives the identifier of the architecture of the first AI model and the third parameter, it can determine the architecture of the first AI model based on the identifier of the architecture of the first AI model, and determine the first AI model based on the architecture of the first AI model and the third parameter. Generally, the transmission resources required for the architecture of an AI model are greater than the transmission resources required for the identifier of the architecture of an AI model. Therefore, compared with method 1, this method 2 can save transmission resources.

[0222] Method 3: The first communication device may send fourth information to the second communication device; accordingly, the second communication device receives the fourth information from the first communication device. The fourth information may include the identifier of the first AI model, or the fourth information may include the third identifier, or the fourth information may include the identifier of the first AI model and the third identifier. The third identifier may be used to indicate the architecture and third parameter of the first AI model. For example, the third identifier may be a token. For details, please refer to the description of the first identifier and will not be repeated here. The third parameter may be a relevant parameter of the architecture applied to the first AI model. For details, please refer to the description of the first parameter and will not be repeated here.

[0223] In one embodiment, the first AI model may be an AI model known to the first communication device and supported by the second communication device; alternatively, the first AI model may be an AI model pre-agreed between the first and second communication devices and supported by the second communication device. The first communication device sends the first AI model identifier and third parameter to the second communication device; upon receiving the first AI model identifier and third parameter, the second communication device may determine the first AI model based on the first AI model identifier.

[0224] In one embodiment, the third identifier may be an identifier of a combination of parameters and architecture for a specific AI model that is pre-determined by the first communication device and the second communication device. The first communication device sends the third identifier to the second communication device; after receiving the third identifier, the second communication device can determine the combination of the architecture and the third parameter of the first AI model based on the third identifier, and determine the first AI model based on the architecture and the third parameter of the first AI model. Optionally, the number of third identifiers can be one or more, for example, the first communication device can send one or more tokens to the second communication device. Optionally, the first communication device can send information to the second communication device for indicating the conditions for starting the one or more tokens. The conditions for starting one or more tokens may include, but are not limited to: a cell, the communication environment of the cell, or the communication performance of the second communication device, etc., without limitation.

[0225] For example, the first communication device may send token 1 and token 2 to the second communication device, as well as information indicating that token 1 should be activated when the serving cell is cell 1 and that token 2 should be activated when the serving cell is cell 2. Accordingly, the second communication device receives token 1, token 2, and the information, and activates token 1 or token 2 or does not activate the token based on the information. Specifically, if the serving cell of the second communication device is cell 1, the second communication device activates token 1, i.e., obtains the AI ​​model corresponding to token 1; alternatively, if the serving cell of the second communication device is cell 2, the second communication device activates token 2, i.e., obtains the AI ​​model corresponding to token 2; alternatively, if the serving cell of the second communication device is neither cell 1 nor cell 2, the second communication device does not obtain the AI ​​models corresponding to token 1 and token 2.

[0226] Generally, the transmission resources required for the identification and / or token of the AI ​​model are less than the transmission resources required for the architecture of the AI ​​model (or the identification of the architecture of the AI ​​model) and the third parameter. Therefore, compared with method 1 and method 2, this method 3 can save transmission resources.

[0227] The first communication device can send the first AI model to the second communication device in any of the above-mentioned ways, and the implementation method is flexible. Based on any of the above-mentioned ways, in one possible implementation method, the first communication device can send the first AI model to the second communication device through the control plane; accordingly, the second communication device receives the first AI model from the first communication device through the control plane. For example, the first communication device sends the architecture and the third parameter of the first AI model to the second communication device through the control plane, or sends the identifier of the architecture and the third parameter of the first AI model to the second communication device through the control plane, or sends the fourth information to the second communication device through the control plane. Since the priority of control plane transmission is usually higher, transmitting the first AI model through the control plane can increase the transmission priority of the first AI model and reduce the transmission delay of the first AI model.

[0228] Alternatively, the first communication device may send the first AI model to the second communication device via the user plane; accordingly, the second communication device receives the first AI model from the first communication device via the user plane. For example, the first communication device sends the architecture and third parameters of the first AI model to the second communication device via the user plane, or sends the identifier of the architecture and third parameters of the first AI model to the second communication device via the user plane, or sends the fourth information to the second communication device via the user plane. Compared to control plane transmission, user plane transmission is not affected by cell switching, is more suitable for the transmission of larger AI models, and can ensure the transmission stability of the AI ​​model.

[0229] Alternatively, the first communication device may also send partial information of the first AI model to the second communication device through the control plane, and send the remaining information of the first AI model other than the partial information to the second communication device through the user plane; accordingly, the second communication device receives partial information of the first AI model from the first communication device through the control plane, and receives the remaining information of the first AI model other than the partial information from the first communication device through the user plane. Optionally, the partial information may be the architecture of the first AI model (or the identifier of the architecture of the first AI model), or the partial information may be partial information of the architecture of the first AI model, or the partial information may be a third parameter, or the partial information may be partial information in the third parameter, or the partial information may be partial information in the fourth information. The embodiment of the present application does not limit the specific implementation method of the partial information of the first AI model transmitted through the control plane. Optionally, the first communication device may also send information to the second communication device to indicate that the partial information is transmitted through the control plane and the remaining information is transmitted through the user plane.

[0230] In one possible implementation, the first AI model can be transmitted in segments. That is, the first communication device can divide the first AI model into multiple parts and send the multiple parts to the second communication device; accordingly, the second communication device can receive the multiple parts from the first communication device and determine the first AI model based on the multiple parts. For example, if the first AI model is large, the first communication device can transmit the first AI model in segments. Optionally, the QoS of the multiple parts can be the same or different. Optionally, the mapping method of the QoS of the multiple parts to the DRB can be the same or different. Optionally, the DRBs used by the multiple parts can be the same or different.

[0231] In one embodiment, the first communication device may send information indicating the transmission format of the first AI model to the second communication device; accordingly, the second communication device receives the information. For the transmission format of the first AI model, please refer to the description of the transmission format of the aforementioned AI model and will not be repeated here. Optionally, if transmitted via the control plane, the information may be carried by an RRC message, but is not limited to this.

[0232] It should be pointed out that if the first communication device is not an access network device (or the first communication device is a fourth communication device), for example, the first communication device is a core network device, or a third-party server, etc., then the first communication device (or the fourth communication device) can send the first AI model to the second communication device through the access network device that provides access services to the second communication device; accordingly, the second communication device receives the first AI model from the first communication device (or the fourth communication device) through the access network device that provides access services to itself.

[0233] Optionally, the first AI model may be carried by a NAS message, that is, the NAS message carries the first AI model. The NAS message reaches the second communication device through an access network device that provides access services to the second communication device. The first communication device (or the fourth communication device) may send tenth information to the access network device, where the tenth information may be used to indicate that the NAS message carries the AI ​​model. Accordingly, the access network device may receive the tenth information. Further, the access network device may determine that the NAS message carries the AI ​​model based on the tenth information.

[0234] At this point, the first AI model is transmitted to the second communication device.

[0235] Optionally, the above-mentioned first communication method may further include: the first communication device may send fifth information to the second communication device, and the fifth information may be used to indicate whether the second communication device is allowed to modify (or update, or adjust) the first AI model; accordingly, the second communication device receives the fifth information from the first communication device. After the second communication device receives the first AI model, it may adjust the architecture and / or parameters according to the operation status of the first AI model to obtain better benefits. Therefore, the first communication device may send the fifth information to the second communication device. Exemplarily, the value of the fifth information includes a first value and a second value, the first value may be used to indicate that the second communication device is allowed to modify the first AI model, and the second value may be used to indicate that the second communication device is not allowed to modify the first AI model. For example, the fifth information occupies 1 bit, the first value may be 1, and the second value may be 0; or, the first value may be 0, and the second value may be 1.

[0236] In one implementation, the fifth information may also be used to indicate information that can be modified in the first AI model, or information that cannot be modified in the first AI model, or information that can be modified in the first AI model and information that cannot be modified in the first AI model.

[0237] In one embodiment, the fifth information may also be used to indicate the conditions under which the modified AI model requires registration (identification), or the fifth information may also be used to indicate the registration method of the modified AI model, or the fifth information may also be used to indicate the conditions under which the modified AI model requires registration and the registration method of the modified AI model. The conditions under which the modified AI model requires registration may include one or more of the following: a change in the value of a specific node (or weight) in the AI ​​model, a change in the calculation method of a specific node (or weight) in the AI ​​model, a change in the connection method of the nodes in the AI ​​model, or a change in the information in the AI ​​model that is greater than or equal to a preset threshold (for example, if the architecture (or parameters) of the AI ​​model changes by 10%, the second communication device needs to re-register the modified AI model). The registration method of the modified AI model may include one or more of the following: the target node for registration of the modified AI model, information that needs to be indicated during registration (for example, 1 bit indicating a registration request, etc.), or information that needs to be provided during registration regarding changes in the AI ​​model. The embodiments of the present application do not limit the specific implementation of the conditions under which the modified AI model requires registration and the registration method of the modified AI model.

[0238] It can be understood that the fifth information can indicate through the first value that the second communication device is allowed to modify the first AI model, or the fifth information can also implicitly indicate through information that can be modified in the first AI model (or information that cannot be modified in the first AI model, or the conditions under which the modified AI model needs to be registered, or the registration method of the modified AI model, or multiple of the foregoing) that the second communication device is allowed to modify the first AI model.

[0239] Optionally, the above-mentioned first communication method may further include: the first communication device may send information indicating whether the first AI model has completed transmission to the second communication device; accordingly, the second communication device may receive the information indicating whether the first AI model has completed transmission. Alternatively, the first communication device may send transmission progress information of the first AI model to the second communication device; accordingly, the second communication device may receive the transmission progress information of the first AI model. Alternatively, the first communication device may send information indicating whether the first AI model has completed transmission and the transmission progress information of the first AI model to the second communication device; accordingly, the second communication device may receive the information indicating whether the first AI model has completed transmission and the transmission progress information of the first AI model.

[0240] Exemplarily, the transmission progress information of the first AI model may include one or more of the following:

[0241] (1) Transmission progress information of the architecture of the first AI model.

[0242] The transmission progress information of the architecture of the first AI model may include one or more of the following: the number of bits (or percentage) that have been transmitted and not transmitted of the architecture of the first AI model, the coordinates of nodes that have not been transmitted or have been transmitted (as shown in Table 3), or information about the architecture that has not been transmitted, etc., without limitation.

[0243] Table 3

[0244] (2) Transmission progress information of the third parameter.

[0245] The transmission progress information of the third parameter may include one or more of the following: the number of bits (or percentage) of the third parameter that have been transmitted and not transmitted, the weight coordinates of the incomplete transmission or completed transmission (as shown in Table 4), or information of the parameter that has not been transmitted, etc., without limitation.

[0246] Table 4

[0247] (3) Information used to indicate information that has not been completely transmitted in the first AI model.

[0248] The information used to indicate the information that has not been transmitted in the first AI model can be information about the architecture of the incomplete transmission (such as an identifier, etc.), or information about the parameters of the incomplete transmission, or a token (or token list, etc.) of the incomplete transmission, or a combination of multiple of the preceding items, without limitation.

[0249] Optionally, the transmission progress information of the first AI model may further include an identifier of the first AI model. Optionally, the transmission progress information of the first AI model may further include a transmission mode of the first AI model. Optionally, the transmission progress information of the first AI model may further include the first information, or the third information, or both the first and third information. This embodiment of the present application does not limit the specific implementation of the transmission progress information of the first AI model.

[0250] Optionally, the first communication method described above may further include: the first communication device may send sixth information to the second communication device, and the sixth information may be used to instruct the second communication device to record (or store, or retain) seventh information; accordingly, the second communication device receives the sixth information from the first communication device. The seventh information may be used to indicate that the first AI model has not completed the transmission, or the seventh information may be the transmission progress information of the first AI model, or the seventh information may include information indicating that the first AI model has not completed the transmission and the transmission progress information of the first AI model. Furthermore, during the transmission process of the first AI model, the second communication device may record the seventh information in response to the sixth information.

[0251] Optionally, the above-mentioned first communication method may further include: the first communication device may send eighth information to the second communication device, and the eighth information is used to indicate whether the second communication device is allowed to send the seventh information to the third communication device (the embodiment of the present application takes the eighth information as an example to indicate that the second communication device is allowed to send the seventh information to the third communication device); accordingly, the second communication device receives the eighth information from the first communication device. The cell of the third communication device is the cell after the second communication device performs cell switching. Alternatively, the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal. Optionally, the eighth information can also be used to indicate the communication range of the third communication device, or the eighth information can also be used to indicate the communication range of the target device of the seventh information. The communication range can be divided into granularities such as PLMN, cell, or TA, without limitation. For example, the eighth information is used to indicate that the second communication device is allowed to send the seventh information to the target device within PLMN 1 and PLMN2.

[0252] In the first communication method described above, a first communication device receives first information from a second communication device, where the first information indicates the second communication device's reception capability for the AI ​​model. Based on the first information, the first communication device can determine an appropriate first AI model and a transmission method for the first AI model. Because the determination of the first AI model and the transmission method of the first AI model takes into account the second communication device's reception capability for the AI ​​model, the first AI model and the transmission method of the first AI model are adaptable to the second communication device's reception capability, thereby avoiding the waste of transmission resources caused by a mismatch between the AI ​​model and / or the AI ​​model's transmission method and the second communication device's reception capability.

[0253] In the first communication method described above, the first AI model is successfully transmitted from the first communication device to the second communication device according to the first information. In another possible implementation method, the first AI model may be interrupted in transmission. For example, during the transmission of the first AI model, the second communication device performs cell switching, and the transmission of the first AI model is interrupted. For another example, during the transmission of the first AI model, the first AI model transmission is abnormal, and the transmission of the first model is interrupted. The first AI model transmission abnormality may be, for example, a radio link failure (RLF) between the first communication device and the second communication device. The embodiment of the present application does not limit the specific implementation method of the first AI model transmission abnormality. Next, the communication method provided by the embodiment of the present application under the first AI model transmission interruption is introduced in conjunction with Figures 4 and 5.

[0254] Figure 4 is a flow chart of a second communication method provided in an embodiment of the present application. In this embodiment, during the transmission of the first AI model, the second communication device performs a cell handover, and the transmission of the first AI model is interrupted. The method may include the following steps.

[0255] S401: The second communication device sends first information to the first communication device.

[0256] Accordingly, the first communication device receives the first information from the second communication device.

[0257] The first information is used to indicate the second communication device's ability to receive the AI ​​model. For example, the first information may be used to determine the first AI model to be applied by the second communication device, or the first information may be used to determine a transmission method for the first AI model, or the first information may be used to determine the first AI model and the transmission method for the first AI model.

[0258] Optionally, the first communication device may send second information to the second communication device; accordingly, the second communication device receives the second information from the first communication device. The second information may be used to indicate the transmission capability (or sending capability) of the first communication device for the AI ​​model. In other words, the second information is information about the transmission capability (or sending capability) of the first communication device for the AI ​​model. Exemplarily, the second information may be used to determine the first information.

[0259] For the specific implementation process of S401, please refer to the content of S301, which will not be repeated here.

[0260] S402: The first communication device sends sixth information to the second communication device.

[0261] Accordingly, the second communication device receives the sixth information from the first communication device.

[0262] S402 is an optional step, indicated by a dotted line in FIG4 . The sixth information may be used to instruct the second communication device to record (or store, or retain) the seventh information; accordingly, the second communication device receives the sixth information from the first communication device. The seventh information may be used to indicate that the first AI model has not completed the transmission, or the seventh information may be the transmission progress information of the first AI model, or the seventh information may include information indicating that the first AI model has not completed the transmission and the transmission progress information of the first AI model. For the transmission progress information of the first AI model, please refer to the aforementioned content and will not be repeated here.

[0263] For the sake of brevity, the following description takes as an example the seventh information being used to indicate that the first AI model has not completed transmission or the seventh information being transmission progress information of the first AI model.

[0264] In one embodiment, the first communication device may transmit eighth information to the second communication device, where the eighth information indicates whether the second communication device is permitted to transmit the seventh information to the third communication device. Accordingly, the second communication device receives the eighth information from the first communication device. For example, the eighth information may also be used to indicate the communication range of the third communication device, or the eighth information may be used to indicate the communication range of the target device of the seventh information. For details, please refer to the aforementioned content and will not be repeated here.

[0265] It should be noted that the execution order of S402 is an example, and the embodiments of the present application are not limited thereto. For example, the first communication device may also send the sixth information to the second communication device after S403. For another example, the first communication device may also send the sixth information to the second communication device during the transmission process of the first AI model.

[0266] S403: The first communication device sends the first AI model to the second communication device according to the first information.

[0267] For the specific implementation method of the first communication device sending the first AI model to the second communication device according to the first information, please refer to the content of S302, which will not be repeated here.

[0268] In this embodiment, during the transmission of the first AI model, the second communication device performs cell switching (i.e., executes S404), and the transmission of the first AI model is interrupted. This means that part of the information in the first AI model has been successfully transmitted to the second communication device. Therefore, S403 can also be expressed as: the first communication device sends part of the information in the first AI model to the second communication device according to the first information; accordingly, the second communication device receives the part of the information. For ease of understanding, the information in the first AI model that has been successfully transmitted to the second communication device before the transmission of the first AI model is interrupted will be recorded as information 1, and the information in the first AI model that has not been transmitted will be recorded as information 2. That is, S403 can also be expressed as: the first communication device sends information 1 in the first AI model to the second communication device according to the first information; accordingly, the second communication device receives information 1. Figure 4 shows an example of the first communication device sending information 1 in the first AI model to the second communication device according to the first information.

[0269] Optionally, the first communication device may send information indicating whether the first AI model has completed transmission to the second communication device; accordingly, the second communication device may receive the information indicating whether the first AI model has completed transmission. Alternatively, the first communication device may send transmission progress information of the first AI model to the second communication device; accordingly, the second communication device may receive the transmission progress information of the first AI model. Alternatively, the first communication device may send information indicating whether the first AI model has completed transmission and the transmission progress information of the first AI model to the second communication device; accordingly, the second communication device may receive the information indicating whether the first AI model has completed transmission and the transmission progress information of the first AI model. Specifically, please refer to the aforementioned content for the transmission progress information of the first AI model, which will not be repeated here.

[0270] S404: The second communication device performs cell switching.

[0271] For example, the first communication device is an access network device, and the second communication device can be switched from the cell of the first communication device to the cell of the third communication device. The embodiment of the present application specifically implements the cell switching of the second communication device.

[0272] In one embodiment, the seventh information is transmission progress information of the first AI model. The first communication device may send ninth information to the third communication device. This ninth information may be used to instruct the third communication device to obtain the transmission progress information of the first AI model from the second communication device. Accordingly, the third communication device receives the ninth information from the first communication device. For example, during a cell handover, the first communication device may send the ninth information to the third communication device.

[0273] In one embodiment, the first communication device may send the first information (and / or the third information) to the third communication device; accordingly, the third communication device receives the first information (and / or the third information) from the first communication device. For example, during a cell handover process, the first communication device may send the first information and / or the third information to the third communication device.

[0274] The transmission of the first AI model is interrupted due to a cell handover performed by the second communication device. Therefore, information 2 in the first AI model is not transmitted to the second communication device. The third communication device needs to obtain the transmission progress information of the first AI model to resume transmission of the first AI model. Specifically, the third communication device can obtain the transmission progress information of the first AI model according to S405, S406, or both S405 and S406, as indicated by the dotted line in FIG4 .

[0275] S405: The second communication device sends seventh information to the third communication device.

[0276] Accordingly, the third communication device receives the seventh information from the second communication device.

[0277] S405 is an optional step, indicated by a dotted line in Figure 4. Exemplarily, the second communication device may actively send the seventh information to the third communication device. For example, the second communication device may send the seventh information to the third communication device based on the eighth information. Alternatively, the second communication device may also send the seventh information to the third communication device in response to the request of the third communication device. For example, the third communication device may send a second request message to the second communication device, and the second request message is used to request the transmission progress information of the first AI model; the second communication device receives the second request message, and sends the seventh information to the third communication device based on the second request message, and the seventh information is the transmission progress information of the first AI model. For example, the third communication device may send the second request message to the second communication device based on the ninth information. Optionally, the seventh information may be carried by the RRC reconfiguration completion message, without limitation.

[0278] In one implementation, the second communication device may send the first information (and / or the third information) to the third communication device; correspondingly, the third communication device receives the first information (and / or the third information) from the first communication device.

[0279] If the seventh information is the transmission progress information of the first AI model, then S407 is executed. If the seventh information indicates that the first AI model has not completed transmission, then the third communication device determines that the second communication device has an incomplete transmission of the first AI model and obtains the transmission progress information of the first AI model, i.e., S406 is executed. It should be understood that the first communication device may also directly send the transmission progress information of the first AI model to the third communication device, without the second communication device sending the seventh information to the third communication device. For example, during a cell handover, the first communication device may send the transmission progress information of the first AI model to the third communication device.

[0280] S406: The first communication device sends transmission progress information of the first AI model to the third communication device.

[0281] Accordingly, the third communication device receives the transmission progress information of the first AI model from the first communication device.

[0282] S406 is an optional step, indicated by a dotted line in Figure 4. Exemplarily, the first communication device may actively send the transmission progress information of the first AI model to the third communication device. For example, during the cell switching process, the first communication device sends the transmission progress information of the first AI model to the third communication device. Alternatively, the first communication device may also send the transmission progress information of the first AI model to the third communication device in response to the request of the third communication device. For example, the third communication device may send a first request message to the first communication device, and the first request message is used to request the transmission progress information of the first AI model; the first communication device receives the first request message and sends the transmission progress information of the first AI model to the third communication device according to the first request message. For example, the seventh information is used to indicate that the first AI model has not completed the transmission, and the third communication device may send a first request message to the first communication device according to the seventh information.

[0283] S407: The third communication device sends information 2 in the first AI model to the second communication device.

[0284] Accordingly, the second communication device receives the information 2 from the third communication device.

[0285] Exemplarily, the second communication device sends information 2 to the second communication device based on the transmission progress information of the first AI model; or, the second communication device sends information 2 to the second communication device based on the first information (and / or the third information); or, the second communication device sends information 2 to the second communication device based on the transmission progress information of the first AI model and the first information (and / or the third information). For example, the third communication device can determine whether to resume transmission of the first AI model based on the transmission progress information of the first AI model. In an embodiment of the present application, the third communication device determines to resume transmission of the first AI model based on the transmission progress information of the first AI model, that is, determines to send information 2 in the first AI model to the second communication device. For another example, the third communication device can determine to resume transmission of the first AI model based on the transmission progress information of the first AI model and the first information (and / or the third information), that is, determines to send information 2 to the second communication device.

[0286] Optionally, the third communication device may determine the transmission mode of information 2. The transmission mode of information 2 may be determined by other communication devices and sent to the third communication device, or may be determined by the third communication device itself. For example, the third communication device may determine the transmission mode of information 2 based on the first information and / or the third information. The transmission mode of information 2 may be different from the transmission mode of information 1, or may be different. For example, the SRB priority during control plane transmission may be different. For another example, the QoS and DRB mapping methods during user plane transmission may be different.

[0287] After receiving information 2, the second communication device may obtain the first AI model based on information 1 and information 2. For example, the second communication device may assemble information 1 and information 2 to obtain the first AI model.

[0288] In the second communication method described above, if the transmission of the first AI model is interrupted due to a cell handover by the second communication device, the third communication device can obtain the transmission progress information of the first AI model and resume the transmission of the first AI model. This saves transmission resources compared to retransmitting the first AI model. Furthermore, the determination of the first AI model and the transmission method of the first AI model takes into account the second communication device's reception capability for the AI ​​model. Therefore, the first AI model and the transmission method of the first AI model can be adapted to the second communication device's reception capability, thereby avoiding the problem of wasted transmission resources due to a mismatch between the AI ​​model and / or the transmission method of the AI ​​model and the second communication device's reception capability.

[0289] The second communication method shown in Figure 4 is described by taking the first communication device as an access network device as an example, that is, taking solution 1a or solution 1b in Table 1 as an example. If the first communication device is not an access network device (that is, the first communication device is a fourth communication device), such as non-solution 1a and non-solution 1b in Table 1, after the second communication device performs cell switching, the first communication device can still provide the second communication device with AI model transmission (if it is not the first communication device, please refer to the content shown in Figure 4). In this case, the third communication device is the forwarding node of the AI ​​model, and the first communication device can send information 2 of the first AI model to the second communication device through the third communication device.

[0290] In one embodiment, the first communication device is not an access network device (i.e., the first communication device is a fourth communication device), the first AI model is based on control plane transmission or part of the information in the first AI model is based on control plane transmission, and the access network device that provides access services to the second communication device before cell switching (such as the fifth communication device) can send segmentation information (for example, the first AI model segmented transmission, the segmentation information can be the segmentation method of the NAS message in the fifth communication device) and / or the SRB mapping method to the third communication device. Accordingly,

[0291] The third communication device receives the segmentation information and / or the SRB mapping method, and forwards the information 2 from the first communication device to the second communication device based on the segmentation information and / or the SRB mapping method. Optionally, the fifth communication device may send a cached NAS message to the third communication device, where the NAS message carries information about the first AI model.

[0292] In one embodiment, the first communication device is not an access network device (i.e., the first communication device is a fourth communication device), the first AI model is based on user-plane transmission or the remaining information in the first AI model is based on user-plane transmission, and the fifth communication device can send the mapping method of QoS and DRB involved in the transmission of the first AI model to the third communication device. Accordingly, the third communication device receives the mapping method of QoS and DRB, and forwards information 2 from the fourth communication device to the second communication device based on the mapping method of QoS and DRB. Optionally, the fifth communication device can send the information of the first AI model cached by itself and the data forwarding method to the third communication device. Optionally, the fifth communication device can send information to the third communication device for indicating the mapping method of QoS and DRB and / or the data forwarding method for the transmission of the AI ​​model.

[0293] Optionally, the first communication device is not an access network device (i.e., the first communication device is a fourth communication device), and the third communication device may send a fifth request message to the first communication device, where the fifth request message is used to request information 2 of the first AI model. Accordingly, the first communication device receives the fifth request message and sends information 2 to the third communication device according to the fifth request message; the third communication device receives information 2 and forwards it to the second communication device. For example, the third communication device determines that it does not have the first AI model based on the transmission progress information of the first AI model and may send the fifth request message to the first communication device.

[0294] The above describes a scenario in which the first AI model is interrupted due to cell switching by the second communication device. Next, a scenario in which the first AI model is interrupted due to transmission abnormality is described, as shown in FIG5 .

[0295] FIG5 is a flow chart of a third communication method provided in an embodiment of the present application. In this embodiment, during the transmission of the first AI model, the first AI model transmission is abnormal and the transmission of the first AI model is interrupted. The method may include the following steps.

[0296] S501, S502, S503, and S506 in FIG5 correspond to S401, S402, S403, and S406 in FIG4 , except that:

[0297] S504: The first AI model transmission is abnormal, and the second communication device performs cell switching.

[0298] In this embodiment, during the transmission of the first AI model, the transmission of the first AI model is abnormal, and the transmission of the first AI model is interrupted. For example, an RLF occurs between the first communication device and the second communication device. The embodiment of the present application does not limit the specific cause of the abnormal transmission of the first AI model. For ease of understanding, the description is based on the example of an RLF occurring between the first communication device and the second communication device and the second communication device re-establishing the connection. For example, the second communication device can establish a connection with a third communication device. The third communication device can still be the first communication device, that is, the second communication device re-establishes a connection with the first communication device. Alternatively, the third communication device can also be a communication device other than the first communication device, that is, the second communication device performs a cell handover, and the cell of the third communication device is the cell after the second communication device performs the cell handover. Figure 5 shows an example of the abnormal transmission of the first AI model and the second communication device performing a cell handover. The embodiment of the present application describes the specific implementation process of the second communication device performing a cell handover.

[0299] In one embodiment, the seventh information is transmission progress information of the first AI model. The first communication device may send ninth information to the third communication device. This ninth information may be used to instruct the third communication device to obtain the transmission progress information of the first AI model from the second communication device. Accordingly, the third communication device receives the ninth information from the first communication device. For example, during a cell handover, the first communication device may send the ninth information to the third communication device.

[0300] In one embodiment, the first communication device may send the first information (and / or the third information) to the third communication device; accordingly, the third communication device receives the first information (and / or the third information) from the first communication device. For example, during a cell handover process, the first communication device may send the first information and / or the third information to the third communication device.

[0301] If the third communication device is the first communication device, then steps S507, S508, and S509 are executed. Alternatively, if the third communication device is a communication device other than the first communication device, then the transmission progress information of the first AI model may be obtained, and then steps S507, S508, and S509 are executed. Specifically, the third communication device may obtain the transmission progress information of the first AI model according to step S505, S506, or both S505 and S506, as indicated by dashed lines in FIG5 .

[0302] S505: The second communication device sends seventh information to the third communication device.

[0303] Accordingly, the third communication device receives the seventh information from the second communication device.

[0304] S505 is an optional step, indicated by a dotted line in FIG5 .

[0305] In one embodiment, the second communication device may proactively send the seventh information to the third communication device. For example, alternatively, the second communication device may send the seventh information to the third communication device in response to a request from the third communication device. For example, the second communication device may send the seventh information to the third communication device based on the eighth information. For another example, if the first AI model transmits abnormally, the second communication device may record an abnormality report, such as an RLF report, and send the abnormality report to the third communication device, where the abnormality report includes the seventh information.

[0306] In another embodiment, the second communication device may also send the seventh information to the third communication device in response to the request of the third communication device. For example, the third communication device may send a second request message to the second communication device, and the second request message is used to request the transmission progress information of the first AI model; the second communication device receives the second request message and sends the seventh information to the third communication device according to the second request message, and the seventh information is the transmission progress information of the first AI model. For example, the third communication device may send the second request message to the second communication device according to the ninth information. Optionally, the seventh information may be carried by the RRC reconfiguration completion message without limitation.

[0307] Optionally, the second communication device may send the first information (and / or the third information) to the third communication device; correspondingly, the third communication device receives the first information (and / or the third information) from the first communication device.

[0308] If the seventh information is the transmission progress information of the first AI model, then S507 is executed. If the seventh information indicates that the first AI model has not completed transmission, then the third communication device determines that the second communication device has an incomplete transmission of the first AI model and obtains the transmission progress information of the first AI model, i.e., S506 is executed. It should be understood that the first communication device may also directly send the transmission progress information of the first AI model to the third communication device, without the second communication device sending the seventh information to the third communication device. For example, during a cell handover, the first communication device may send the transmission progress information of the first AI model to the third communication device.

[0309] S507: The third communication device determines the reason for the abnormal transmission of the first AI model.

[0310] For example, the third communication device may determine the cause of the first AI model transmission anomaly based on the transmission progress information of the first AI model; alternatively, the third communication device may determine the cause of the first AI model transmission anomaly based on the anomaly report; alternatively, the third communication device may determine the cause of the first AI model transmission anomaly based on the transmission progress information and the anomaly report of the first AI model. The embodiments of the present application do not limit the process for analyzing the cause of the first AI model transmission anomaly.

[0311] Optionally, the third communication device can determine whether to resume transmission of the first AI model based on the transmission progress information of the first AI model. In the embodiment of the present application, the third communication device determines to resume transmission of the first AI model based on the transmission progress information of the first AI model, that is, determines to send information 2 in the first AI model to the second communication device. For another example, the third communication device can determine to resume transmission of the first AI model based on the transmission progress information of the first AI model and the first information (and / or the third information), that is, determines to send information 2 to the second communication device.

[0312] S508: The third communication device adjusts the transmission method of the information 2 in the first AI model according to the reason for the abnormal transmission of the first AI model.

[0313] The third communication device adjusts (or determines) the transmission mode of information 2 in the first AI model based on the cause of the transmission abnormality of the first AI model. This can reduce the occurrence of transmission abnormalities between the second communication device and the third communication device, and can improve the transmission reliability of the AI ​​model. Optionally, the third communication device can adjust (or determine) the transmission mode of information 2 in the first AI model based on the cause of the transmission abnormality of the first AI model and the first information (and / or the third information). Optionally, the third communication device can adjust (or determine) the transmission mode of information 2 in the first AI model based on the cause of the transmission abnormality of the first AI model and the transmission progress information of the first AI model. Optionally, the third communication device can adjust (or determine) the transmission mode of information 2 in the first AI model based on the cause of the transmission abnormality of the first AI model, the first information (and / or the third information) and the transmission progress information of the first AI model.

[0314] For example, if the anomaly report includes the time of transmission via the control plane, and the fifth communication device transmits via a higher-priority SRB, and the reason for the first AI model transmission anomaly is a late handover, the third communication device can lower the SRB priority used for transmission of message 2 when retransmitting. Alternatively, the third communication device can lower the SRB priority used for transmission of other AI models.

[0315] In another example, the first AI model is based on user plane transmission, and the third communication device can adjust the mapping method between QoS and DRB corresponding to information 2.

[0316] S509: The third communication device sends information 2 to the second communication device according to the adjusted transmission mode.

[0317] Accordingly, the second communication device receives the information 2 from the third communication device.

[0318] After receiving information 2, the second communication device may obtain the first AI model based on information 1 and information 2. For example, the second communication device may assemble information 1 and information 2 to obtain the first AI model.

[0319] It is understandable that in this embodiment, the third communication device may not determine the cause of the abnormal transmission of the first AI model. For example, the third communication device may directly send information 2 to the second communication device. Please refer to the description of S407 for the specific implementation process and will not be repeated here.

[0320] In the third communication method described above, the transmission of the first AI model is interrupted due to a transmission anomaly. The third communication device can obtain the transmission progress information of the first AI model and execute the continued transmission of the first AI model, which can save transmission resources compared to retransmitting the first AI model. The determination of the first AI model and the transmission mode of the first AI model takes into account the receiving capability of the second communication device for the AI ​​model. Therefore, the transmission mode of the first AI model and the first AI model can adapt to the receiving capability of the second communication device, thereby avoiding the problem of wasting transmission resources due to the mismatch between the AI ​​model and / or the transmission mode of the AI ​​model and the receiving capability of the second communication device. Furthermore, the third communication device adjusts the transmission mode of the information 2 in the first AI model according to the cause of the transmission anomaly of the first AI model, which can reduce the occurrence of transmission anomalies between the second communication device and the third communication device, and improve the transmission reliability of the AI ​​model.

[0321] In the embodiments provided in the present application, the methods provided in the embodiments of the present application are introduced from the perspectives of the first communication device, the second communication device, and the interaction with the third communication device. Among them, the steps performed by the communication device (for example, the first communication device, the second communication device, or the third communication device) can be implemented by different functional entities that constitute the communication device. The communication device (for example, the first communication device, the second communication device, or the third communication device) may include a hardware structure and / or a software module to implement the above-mentioned functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether a function of the above-mentioned functions is performed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.

[0322] The following describes the communication device used to implement the above method in the embodiment of the present application with reference to the accompanying drawings. Therefore, the above contents can be used in subsequent embodiments, and repeated contents will not be repeated.

[0323] Fig. 6 exemplarily shows a schematic structural diagram of a communication device 600. The communication device 600 can implement the functions or steps implemented by the first communication device, the second communication device, or the third communication device in the above-mentioned various method embodiments.

[0324] In one embodiment, the communication device 600 may include a processing module 601 and a transceiver module 602. The processing module 601 may be used to perform data processing, such as executing the various method embodiments described above. The processing module 601 may also be referred to as a processing unit. The processing module 601 may be implemented by at least one processor or processor-related circuitry. The transceiver module 602 may be used to implement corresponding communication functions, such as receiving or sending relevant data, information, or messages. The transceiver module 602 may also be referred to as a communication interface, a communication module, or a transceiver unit. The transceiver module 602 may be implemented by a transceiver or transceiver-related circuitry.

[0325] It should be noted that the communication device 600 may include the processing module 601 but not the transceiver module 602. Alternatively, the communication device 600 may include the transceiver module 602 but not the processing module 601. The specific implementation depends on whether the above solution executed by the communication device 600 includes both processing and transceiver operations.

[0326] Optionally, the transceiver module 602 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiment. The receiving module is used to perform the receiving operation in the above method embodiment.

[0327] It should be noted that the communication device 600 may include a sending module but not a receiving module. Alternatively, the communication device 600 may include a receiving module but not a sending module. The specific implementation depends on whether the above solution executed by the communication device 600 includes a sending action and a receiving action.

[0328] Optionally, the communication device 600 may further include a storage module, not shown in FIG6 . The storage module may be implemented by at least one memory. The storage module may be used to store instructions and / or data, and the processing module 601 may read the instructions and / or data in the storage module to enable the communication device 600 to implement the aforementioned method embodiment.

[0329] Optionally, the communication device 600 may be a chip system. The chip system may be composed of a chip, or may include a chip and other discrete components, without limitation. The transceiver module 602 may be an input and output interface of a chip (e.g., a baseband chip). The processing module 601 may be a processor of the chip system.

[0330] In a first implementation, the communication device 600 can implement the functions of a first communication device, and specifically can execute the following contents: a transceiver module 602 is used to receive first information from a second communication device, where the first information is used to indicate the second communication device's receiving capability for the AI ​​model, and the first information is used to determine the first AI model to be applied by the second communication device and the transmission method of the first AI model; and, sending the first AI model to the second communication device according to the first information.

[0331] In one possible implementation, the transceiver module 602 is further used to send second information to the second communication device, where the second information is used to indicate the transmission capability of the first communication device for the AI ​​model.

[0332] In one possible implementation, the transceiver module 602 is specifically configured for the first communication device to receive third information from the second communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model; and to send the first AI model to the second communication device based on the first information and the third information.

[0333] In one possible implementation, the transceiver module 602 is specifically configured to send the architecture and third parameters of the first AI model to the second communication device, where the third parameters are related parameters of the architecture applied to the first AI model; or, to send the identifier of the architecture of the first AI model and the third parameters to the second communication device, where the third parameters are related parameters of the architecture applied to the first AI model; or, to send fourth information to the second communication device, where the fourth information includes the identifier of the first AI model and / or the third identifier, where the third identifier is used to indicate the architecture and third parameters of the first AI model, and the third parameters are related parameters of the architecture applied to the first AI model.

[0334] In one possible implementation, the transceiver module 602 is specifically configured to send part of the information of the first AI model to the second communication device through a control surface, and send the remaining information of the first AI model except the part of the information to the second communication device through a user.

[0335] In a possible implementation, the transceiver module 602 is further configured to send fifth information to the second communication device, where the fifth information is used to indicate whether the second communication device is allowed to modify the first AI model.

[0336] In a possible implementation, the transceiver module 602 is further configured to send information indicating that the first AI model has not completed transmission and / or transmission progress information of the first AI model to the second communication device.

[0337] In one possible implementation, the transceiver module 602 is further used to send sixth information to the second communication device, where the sixth information is used to instruct the second communication device to record seventh information, where the seventh information is used to indicate that the first AI model has not completed transmission, or the seventh information is transmission progress information of the first AI model.

[0338] In one possible implementation, the transceiver module 602 is further configured to send eighth information to the second communication device, where the eighth information is used to indicate that the second communication device is allowed to send the seventh information to a third communication device, where the cell of the third communication device is the cell after the second communication device performs a cell handover, or the cell of the third communication device is the cell that provides service to the second communication device after the first AI model transmission anomaly occurs. Optionally, the eighth information may also be used to indicate the communication range of the third communication device.

[0339] In one possible implementation, the seventh information is the transmission progress information of the first AI model. The transceiver module 602 is also used to send ninth information to the third communication device, and the ninth information is used to instruct the third communication device to obtain the transmission progress information of the first AI model from the second communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

[0340] In another possible implementation, the transceiver module 602 is further used to send transmission progress information of the first AI model to a third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

[0341] In a possible implementation, the transceiver module 602 is further configured to receive a first request message from the third communication device, where the first request message is used to request transmission progress information of the first AI model.

[0342] In one possible implementation, the transceiver module 602 is further used to send the first information and / or third information to a third communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

[0343] In one possible implementation, the first AI model experiences a transmission anomaly, and the first communication device reestablishes a connection with the second communication device. Processing module 601 is configured to determine a cause of the first AI model transmission anomaly and adjust a transmission method for information not yet fully transmitted in the first AI model based on the cause of the first AI model transmission anomaly. Transceiver module 602 is further configured to send the information not yet fully transmitted in the first AI model to the second communication device using the adjusted transmission method.

[0344] In a second implementation, the communication device 600 can implement the functions of a second communication device, and specifically can execute the following contents: a transceiver module 602 is used to send first information to a first communication device, where the first information is used to indicate the second communication device's receiving capability for the AI ​​model, and the first information is used to determine the first AI model to be applied by the second communication device and the transmission method of the first AI model; and, receive the first AI model from the first communication device.

[0345] In one possible implementation, the transceiver module 602 is further used to receive second information from the first communication device, where the second information is used to indicate the transmission capability of the first communication device for the AI ​​model; and the processing module 601 is used to determine the first information based on the second information.

[0346] In one possible implementation, the transceiver module 602 is further used to send third information to the first communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model.

[0347] In one possible implementation, the transceiver module 602 is specifically configured to receive the architecture and third parameter of the first AI model from the first communication device, where the third parameter is a parameter related to the architecture applied to the first AI model; or, receive the identifier and third parameter of the architecture of the first AI model from the first communication device, where the third parameter is a parameter related to the architecture applied to the first AI model; or, receive fourth information from the first communication device, where the fourth information includes the identifier and / or third identifier of the first AI model, where the third identifier is used to indicate the architecture and third parameter of the first AI model, and the third parameter is a parameter related to the architecture applied to the first AI model.

[0348] In one possible implementation, the transceiver module 602 is specifically configured to receive partial information of the first AI model from the first communication device through a control plane, and receive remaining information other than the partial information in the first AI model from the first communication device through a user plane.

[0349] In one possible implementation, the transceiver module 602 is further configured to receive fifth information from the first communication device, where the fifth information indicates whether the second communication device is permitted to modify the first AI model. Optionally, when the fifth information indicates that the second communication device is permitted to modify the first AI model, the fifth information further indicates conditions for registering the modified AI model and / or a method for registering the modified AI model.

[0350] In a possible implementation, the transceiver module 602 is further configured to receive information indicating that the first AI model has not completed transmission and / or transmission progress information of the first AI model from the first communication device.

[0351] In one possible implementation, the transceiver module 602 is further used to receive sixth information from the first communication device, where the sixth information is used to instruct the second communication device to record seventh information, where the seventh information is used to indicate that the first AI model has not completed transmission, or the seventh information is transmission progress information of the first AI model.

[0352] In one possible implementation, the transceiver module 602 is further configured to receive eighth information from the first communication device, the eighth information being used to indicate that the second communication device is permitted to send the seventh information to a third communication device, where the cell of the third communication device is the cell after the second communication device performs a cell handover, or the cell of the third communication device is the cell that provides service to the second communication device after an abnormality in the transmission of the first AI model occurs. Optionally, the eighth information may also be used to indicate the communication range of the third communication device.

[0353] In one possible implementation, the transceiver module 602 is further used to send the seventh information to a third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

[0354] In one possible implementation, the seventh information is the transmission progress information of the first AI model. The transceiver module 602 is further used to receive a second request message from the third communication device, where the second request message is used to request the transmission progress information of the first AI model.

[0355] In a possible implementation, the transceiver module 602 is further configured to receive untransmitted information in the first AI model from the third communication device.

[0356] In one possible implementation, the transceiver module 602 is further used to send the first information and / or third information to a third communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

[0357] In a third implementation, the communication device 600 can implement the functions of a third communication device, and specifically can execute the following contents: a transceiver module 602 is used to receive the transmission progress information of the first AI model to be applied by the second communication device; receive first information, where the first information is used to indicate the receiving capability of the second communication device for the AI ​​model; and send information in the first AI model that has not been transmitted to the second communication device based on the first information and the transmission progress information of the first AI model.

[0358] In one possible implementation, the transceiver module 602 is specifically used to receive third information, where the third information is used to indicate the transmission requirement of the second communication device for the AI ​​model; and send information in the first AI model that has not been transmitted to the second communication device based on the first information, the third information, and the transmission progress information of the first AI model.

[0359] In a possible implementation, the transceiver module 602 is further configured to receive seventh information from the second communication device, where the seventh information is used to indicate that the first AI model has not completed transmission.

[0360] In a possible implementation, the transceiver module 602 is further configured to send a first request message to the first communication device, where the first request message is used to request transmission progress information of the first AI model.

[0361] In a possible implementation, the transceiver module 602 is further configured to send a second request message to the first communication device, where the second request message is used to request transmission progress information of the first AI model.

[0362] In one possible implementation, the transceiver module 602 is further used to receive ninth information from the first communication device, where the ninth information is used to instruct the third communication device to obtain transmission progress information of the first AI model from the second communication device, wherein the cell of the first communication device is the cell before the second communication device performs cell switching, or the cell of the first communication device is the cell that provides services to the second communication device before the transmission of the first AI model is abnormal.

[0363] In one possible implementation, processing module 601 is configured to determine a cause of a transmission exception of the first AI model based on the transmission progress information of the first AI model; and determine a transmission method for information that has not been completely transmitted in the first AI model based on the cause of the transmission exception of the first AI model, the first information, and the transmission progress information of the first AI model.

[0364] In a possible implementation, the processing module 601 is further configured to determine, based on the transmission progress information of the first AI model, whether to send the untransmitted information of the first AI model to the second communication device.

[0365] It should be understood that a more detailed description of how each module performs the corresponding process can be directly obtained by referring to the relevant descriptions in the aforementioned method embodiments. For the sake of brevity, it is not repeated here.

[0366] As shown in Figure 7, an embodiment of the present application provides a schematic structural diagram of a communication device 700. The communication device 700 may include a processor 720 for implementing or supporting the communication device 700 in implementing the functions of the first communication device, the second communication device, or the third communication device in any method embodiment of the present application. For details, please refer to the detailed description of the aforementioned method embodiment, which is not repeated here. For example, the processor 720 is used to read and execute program instructions through a communication interface so that the communication device 700 implements the corresponding method. The processor 720 may include one or more processors without limitation.

[0367] It should be noted that the functional modules mentioned above can be implemented by hardware or by a combination of hardware and software, without limitation. Also, when the communication device 700 includes only the processor 720, the communication device 700 can be a chip or a chip system.

[0368] For example, the communication device 700 may be a chip system, wherein the chip system may be composed of a chip, or may include a chip and other discrete devices, without limitation.

[0369] Optionally, the communication device 700 may further include a memory 730 for storing program instructions and / or data. The memory 730 is coupled to the processor 720. Coupling can be understood as an indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, for information exchange between the devices, units, or modules. The processor 720 may operate in conjunction with the memory 730. The processor 720 and the memory 730 may be integrated or separately configured.

[0370] Furthermore, the processor 720 is configured to execute program instructions stored in the memory 730 so that the communication device 700 implements a corresponding method.

[0371] One or more memories in memory 730 may be included in the processor, or memory 730 may exist independently, such as an off-chip memory, connected to processor 720 via a communication bus (represented by a thick line 740 in FIG. 7 ). Memory 730 and processor 720 may also be integrated together.

[0372] Optionally, the communication device 700 further includes a communication interface 710 (indicated by a dotted line in FIG. 7 ) for communicating with other devices via a transmission medium, thereby enabling the device in the communication device 700 to communicate with the other device. For example, when the communication device is a second communication device, the other device may be a first communication device, a third communication device, or the like. The processor 720 may utilize the communication interface 710 to send and receive data. For example, the processor 720 may be configured to control the communication interface 710 to receive and / or send signals.

[0373] The communication interface 710 may be a transceiver. In hardware implementation, the transceiver may be used to implement the functions of the transceiver module 602 . The transceiver is integrated into the communication device 700 to form the communication interface 710 .

[0374] It should be pointed out that the communication interface 710 may have a sending function and a receiving function, and may realize the reception and sending of signals; or it may have a sending function but not a receiving function, and be used to realize the sending of signals; or it may have a receiving function but not a sending function, and be used to realize the reception of signals.

[0375] It should be noted that the specific connection medium between the communication interface 710, processor 720, and memory 730 is not limited in the embodiments of the present application. In FIG7 , the memory 730, processor 720, and communication interface 710 are connected via a communication bus 740. The connection methods between other components are merely schematic and not limiting. The communication bus 740 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, FIG7 shows only one thick line, but this does not mean that there is only one communication bus or only one type of communication bus.

[0376] In the embodiments of the present application, the processor 720 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The general-purpose processor may be a microprocessor or any conventional processor. The methods disclosed in conjunction with the embodiments of the present application may be executed by hardware in the processor, or by a combination of hardware and software in the processor.

[0377] In the embodiment of the present application, the memory 730 may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory, such as a random-access memory (RAM). The memory may also be any other medium for carrying or storing program code in the form of instructions or data structures and accessible by a computer; or a circuit or any other device capable of performing a storage function, for storing program instructions and / or data.

[0378] In one example, the communication device 700 can perform the following: receiving first information from a second communication device, the first information is used to indicate the second communication device's receiving capability for the AI ​​model, the first information is used to determine the first AI model to be applied by the second communication device and the transmission method of the first AI model; and, sending the first AI model to the second communication device according to the first information.

[0379] In another example, the communication device 700 can perform the following: sending first information to the first communication device, where the first information is used to indicate the receiving capability of the second communication device for the AI ​​model, and the first information is used to determine the first AI model to be applied by the second communication device and the transmission method of the first AI model; and receiving the first AI model from the first communication device.

[0380] In another example, the communication device 700 can perform the following: receive transmission progress information of the first AI model to be applied by the second communication device; receive first information, where the first information is used to indicate the receiving capability of the second communication device for the AI ​​model; and send information in the first AI model that has not been transmitted to the second communication device based on the first information and the transmission progress information of the first AI model.

[0381] For the specific implementation process, please refer to the aforementioned method embodiments, which will not be repeated here.

[0382] Based on the same concept, please refer to Figure 8, an embodiment of the present application also provides another communication device 800, including: an input and output interface 810 and a logic circuit 820; the input and output interface 810 is used to receive code instructions and transmit them to the logic circuit 820; the logic circuit 820 is used to run the code instructions to execute the method executed by the first communication device, the second communication device, or the third communication device in any of the above embodiments.

[0383] Exemplarily, the communication device 800 may be an access network device or a component in the access network device (e.g., one or more of CU, CU-CP, CU-CP1, or CU-CP2, etc.), or a terminal device or a component in the terminal device, or a core network device or a component in the core network device, or a third-party server or a component in the third-party server. For example, the communication device 800 may implement the functions of the first communication device, the second communication device, or the third communication device in each of the aforementioned embodiments.

[0384] Since the communication device 800 provided in this embodiment can realize the functions of the first communication device, the second communication device, or the third communication device in the aforementioned embodiments, the technical effects that can be obtained can be referred to the aforementioned method embodiments and will not be described in detail here.

[0385] The present application also provides a communication system, which may include one or more of the following: a first communication device, a second communication device, or a third communication device. The first communication device, the second communication device, or the third communication device can all be described in the aforementioned method embodiments and will not be repeated here.

[0386] A computer-readable storage medium is also provided in an embodiment of the present application, including program instructions, which, when executed on a computer, enables the computer to execute the methods or steps of the first communication device, the second communication device, or the third communication device in each of the above embodiments.

[0387] A computer program product is also provided in an embodiment of the present application, including program instructions, which, when executed on a computer, enable the computer to execute the methods or steps of the first communication device, the second communication device, or the third communication device in each of the above embodiments.

[0388] An embodiment of the present application provides a chip system, which includes a processor for implementing the first communication device, the second communication device, or the third communication device in the aforementioned method (for example, executing the corresponding method or step). The chip system can be composed of a chip or can include a chip and other discrete devices.

[0389] Optionally, the chip system further includes a memory for storing program instructions so that the above-mentioned processor reads and executes them to implement the corresponding method.

[0390] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0391] In the embodiments of the present application, "multiple" may refer to two or more. In view of this, in the embodiments of the present application, "multiple" may also be understood as "at least two". "At least one" may be understood as one or more, for example, one, two or more. For example, "including at least one" means including one, two or more. For example, including at least one of A, B and C, then included may be A, B, C, A and B, A and C, B and C, or A, B and C. "And / or" describes the association relationship of associated objects. Specifically, there may be three relationships. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the previous and subsequent associated objects are in an "or" relationship.

[0392] In addition, the terms "system" and "network" in the embodiments of the present application may be used interchangeably, and "according to" and "based on" may be used interchangeably.

[0393] In the embodiments of this application, ordinal numbers such as "first" and "second" are generally used to distinguish different objects and are not used to define the order, timing, priority, or importance of multiple objects. For example, in the embodiments of this application, the first communication device, the second communication device, the third communication device, and the fourth communication device are used to distinguish four communication devices and do not define the priority or importance of these four communication devices.

[0394] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0395] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0396] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0397] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0398] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0399] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the part that essentially contributes to the technical solution of the present application or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0400] The above description is merely a specific embodiment of the present application, but the scope of protection of the embodiments of the present application is not limited thereto. Any person skilled in the art can easily conceive of changes or substitutions within the technical scope disclosed in the embodiments of the present application, and such changes or substitutions should be included in the scope of protection of the embodiments of the present application. Therefore, the scope of protection of the embodiments of the present application should be based on the scope of protection of the claims.

Claims

1. A communication method, applied to a first communication device or a chip in the first communication device, characterized in that: The method comprises: receiving first information from a second communication device, where the first information is used to indicate a receiving capability of the second communication device for an artificial intelligence (AI) model, and the first information is used to determine a first AI model to be applied by the second communication device and a transmission method for the first AI model; The first AI model is sent to the second communication device according to the first information.

2. The method according to claim 1, characterized in that The first information indicates the receiving capability of the second communication device for the AI ​​model through one or more of the following: The second communication device supports the architecture of the received AI model; The second communication device supports a transmission format of the received AI model; an identification of an AI model supported by the second communication device for reception; A first parameter, where the first parameter is a parameter related to a first architecture, where the first architecture is an architecture of an AI model supported and received by the second communication device and known to the first communication device; or A first identifier, wherein the first identifier is used to indicate a second architecture and related parameters applied to the second architecture, where the second architecture belongs to the architecture of the AI ​​model supported by the second communication device for reception.

3. The method according to claim 1 or 2, characterized in that The method further comprises: Send second information to the second communication device, where the second information is used to indicate the transmission capability of the first communication device for the AI ​​model.

4. The method according to claim 3, characterized in that The second information indicates the transmission capability of the first communication device for the AI ​​model through one or more of the following: The first communication device supports the architecture of the transmitted AI model; The first communication device supports a transmission format of the AI ​​model for transmission; an identifier of an AI model that the first communication device supports transmission; a second parameter, where the second parameter is a parameter related to a third architecture, where the third architecture is an architecture of an AI model supported by the first communication device and known to the second communication device; or A second identifier, wherein the second identifier is used to indicate a fourth architecture and related parameters applied to the fourth architecture, and the fourth architecture belongs to the architecture of the AI ​​model supported by the first communication device for transmission.

5. The method according to claim 4, characterized in that The second information is also used to indicate the communication range to which the transmission capability of the first communication device for the AI ​​model is applicable.

6. The method according to any one of claims 1 to 5, characterized in that The sending the first AI model to the second communication device according to the first information includes: receiving third information from the second communication device, where the third information is used to indicate a transmission requirement of the second communication device for the AI ​​model; The first AI model is sent to the second communication device according to the first information and the third information.

7. The method according to any one of claims 1 to 6, characterized in that The sending the first AI model to the second communication device includes: Sending the architecture of the first AI model and a third parameter to the second communication device, where the third parameter is a parameter related to the architecture applied to the first AI model; or Sending an identifier of the architecture of the first AI model and a third parameter to the second communication device, where the third parameter is a relevant parameter applied to the architecture of the first AI model; or, Send fourth information to the second communication device, where the fourth information includes an identifier of the first AI model and / or a third identifier, wherein the third identifier is used to indicate the architecture and third parameters of the first AI model, and the third parameters are relevant parameters applied to the architecture of the first AI model.

8. The method according to any one of claims 1 to 7, characterized in that The sending the first AI model to the second communication device includes: Part of the information of the first AI model is sent to the second communication device through control, and the remaining information of the first AI model except the part of the information is sent to the second communication device through the user.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: Send fifth information to the second communication device, where the fifth information is used to indicate whether the second communication device is allowed to modify the first AI model.

10. The method according to claim 9, characterized in that In the case where the fifth information is used to indicate that the second communication device is allowed to modify the first AI model, the fifth information is further used to indicate the conditions under which the modified AI model needs to be registered and / or the registration method of the modified AI model.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: Send sixth information to the second communication device, where the sixth information is used to instruct the second communication device to record seventh information, where the seventh information is used to indicate that the first AI model has not completed transmission, or the seventh information is transmission progress information of the first AI model.

12. The method according to claim 11, characterized in that The method further comprises: Sending eighth information to the second communication device, the eighth information is used to indicate that the second communication device is allowed to send the seventh information to the third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

13. The method according to claim 11 or 12, characterized in that The seventh information is transmission progress information of the first AI model, and the method further includes: Ninth information is sent to the third communication device, where the ninth information is used to instruct the third communication device to obtain transmission progress information of the first AI model from the second communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

14. The method according to claim 11, characterized in that The method further comprises: Send transmission progress information of the first AI model to a third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the transmission of the first AI model is abnormal.

15. The method according to claim 14, characterized in that The method further comprises: A first request message is received from the third communication device, where the first request message is used to request transmission progress information of the first AI model.

16. The method according to any one of claims 11 to 15, characterized in that The transmission progress information of the first AI model includes one or more of the following: Transmission progress information of the architecture of the first AI model; Transmission progress information of a third parameter, where the third parameter is a parameter related to the architecture applied to the first AI model; or Information used to indicate information that has not been completely transmitted in the first AI model.

17. The method according to any one of claims 11 to 16, characterized in that The method further comprises: The first information and / or third information is sent to a third communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

18. The method according to any one of claims 1 to 12, characterized in that The first AI model transmission is abnormal, and the first communication device re-establishes a connection with the second communication device. The method further includes: Determining the cause of the abnormal transmission of the first AI model; Adjusting a transmission method for information that has not been completely transmitted in the first AI model based on a cause of the transmission abnormality of the first AI model; The untransmitted information in the first AI model is sent to the second communication device according to the adjusted transmission mode.

19. A communication method, applied to a second communication device or a chip in the second communication device, characterized in that: The method comprises: Sending first information to a first communication device, where the first information is used to indicate the second communication device's receiving capability for an artificial intelligence (AI) model, and the first information is used to determine a first AI model to be applied by the second communication device and a transmission method for the first AI model; The first AI model is received from the first communication device.

20. The method according to claim 19, characterized in that The first information indicates the receiving capability of the second communication device for the AI ​​model through one or more of the following: The second communication device supports the architecture of the received AI model; The second communication device supports a transmission format of the received AI model; an identification of an AI model supported by the second communication device for reception; A first parameter, where the first parameter is a parameter related to a first architecture, where the first architecture is an architecture of an AI model supported and received by the second communication device and known to the first communication device; or A first identifier, wherein the first identifier is used to indicate a second architecture and related parameters applied to the second architecture, where the second architecture belongs to the architecture of the AI ​​model supported by the second communication device for reception.

21. The method according to claim 19 or 20, characterized in that The method further comprises: receiving second information from the first communication device, where the second information is used to indicate a transmission capability of the first communication device for the AI ​​model; The first information is determined according to the second information.

22. The method according to claim 21, characterized in that The second information indicates the transmission capability of the first communication device for the AI ​​model through one or more of the following: The first communication device supports the architecture of the transmitted AI model; The first communication device supports a transmission format of the AI ​​model for transmission; an identifier of an AI model that the first communication device supports transmission; a second parameter, where the second parameter is a parameter related to a third architecture, where the third architecture is an architecture of an AI model supported by the first communication device and known to the second communication device; or A second identifier, wherein the second identifier is used to indicate a fourth architecture and related parameters applied to the fourth architecture, and the fourth architecture belongs to the architecture of the AI ​​model supported by the first communication device for transmission.

23. The method according to claim 22, characterized in that The second information is also used to indicate the communication range to which the transmission capability of the first communication device for the AI ​​model is applicable.

24. The method according to any one of claims 19 to 23, characterized in that The method further comprises: Send third information to the first communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model.

25. The method according to any one of claims 19 to 24, characterized in that The receiving the first AI model from the first communication device includes: receiving the architecture of the first AI model and a third parameter from the first communication device, where the third parameter is a parameter related to the architecture applied to the first AI model; or receiving an identifier of the architecture of the first AI model and a third parameter from the first communication device, where the third parameter is a parameter related to the architecture applied to the first AI model; or Receive fourth information from the first communication device, where the fourth information includes an identifier of the first AI model and / or a third identifier, wherein the third identifier is used to indicate the architecture and third parameters of the first AI model, and the third parameters are relevant parameters applied to the architecture of the first AI model.

26. The method according to any one of claims 19 to 25, characterized in that The receiving the first AI model from the first communication device includes: Partial information of the first AI model is received from the first communication device through a control plane, and remaining information other than the partial information of the first AI model is received from the first communication device through a user plane.

27. The method according to any one of claims 19 to 26, characterized in that The method further comprises: Receive fifth information from the first communication device, where the fifth information is used to indicate whether the second communication device is allowed to modify the first AI model.

28. The method according to claim 27, characterized in that In the case where the fifth information is used to indicate that the second communication device is allowed to modify the first AI model, the fifth information is further used to indicate the conditions under which the modified AI model needs to be registered and / or the registration method of the modified AI model.

29. The method according to any one of claims 19 to 28, characterized in that The method further comprises: Receive sixth information from the first communication device, where the sixth information is used to instruct the second communication device to record seventh information, where the seventh information is used to indicate that the first AI model has not completed transmission, or the seventh information is transmission progress information of the first AI model.

30. The method according to claim 29, wherein The method further comprises: Receive eighth information from the first communication device, where the eighth information is used to indicate that the second communication device is allowed to send the seventh information to the third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

31. The method according to claim 29 or 30, characterized in that The method further comprises: The seventh information is sent to the third communication device, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

32. The method according to claim 31, characterized in that The seventh information is transmission progress information of the first AI model, and the method further includes: A second request message is received from the third communication device, where the second request message is used to request transmission progress information of the first AI model.

33. The method according to claim 31 or 32, characterized in that The method further comprises: receiving untransmitted information in the first AI model from the third communication device.

34. The method according to any one of claims 29 to 33, characterized in that The transmission progress information of the first AI model includes one or more of the following: Transmission progress information of the architecture of the first AI model; Transmission progress information of a third parameter, where the third parameter is a parameter related to the architecture applied to the first AI model; or Information used to indicate information that has not been completely transmitted in the first AI model.

35. The method according to any one of claims 29 to 34, characterized in that The method further comprises: The first information and / or third information is sent to a third communication device, where the third information is used to indicate the second communication device's transmission requirement for the AI ​​model, wherein the cell of the third communication device is the cell after the second communication device performs cell switching, or the cell of the third communication device is the cell that provides services to the second communication device after the first AI model transmission is abnormal.

36. A communication device, characterized in that The method comprises a module for executing the method according to any one of claims 1 to 18, or a module for executing the method according to any one of claims 19 to 35.

37. A communication device, characterized in that: The method comprises at least one processor configured to execute the method according to any one of claims 1 to 18 or to execute the method according to any one of claims 19 to 35.

38. A communication system, characterized in that: The method comprises a first communication device and / or a second communication device, wherein the first communication device is used to execute the method according to any one of claims 1 to 18, and the second communication device is used to execute the method according to any one of claims 19 to 35.

39. A computer-readable storage medium, characterized in that A computer program or instructions is stored, wherein the computer program or instructions are used to implement the method according to any one of claims 1 to 18, or to implement the method according to any one of claims 19 to 35.

40. A computer program product, characterized in that The computer program product comprises a computer program, which, when run on a computer, causes the computer to perform the method according to any one of claims 1 to 18 or the method according to any one of claims 19 to 35.

Images