Communication method and related apparatus

Abstract

A communication method and a related apparatus. In the method, a first communication apparatus can verify, on the basis of specified input data, whether a terminal device has a capability to execute models corresponding to specific model parameters, and the verification result is indicated by means of third information, so that a recipient of the third information is informed of the verification result. Different model parameters can be used for determining different models (or different model functions), and the requirements of different models (or different model functions) for operating environments (such as, requirements for operating software and hardware environments, computing power required for operation, or data required for operation) may be different. Therefore, in the described solution, the first communication apparatus can verify whether the terminal device has the capability to execute models corresponding to specific model parameters, and the verification result obtained from the verification process can be used as a basis for model deployment, thereby improving model management efficiency.

Description

Communication method and related apparatus

[0001] This application claims priority from the Chinese patent application No. 202410823360.5, filed on June 24, 2024, and entitled "A communication method and related apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and in particular to a communication method and related apparatus. BACKGROUND

[0003] With the development of communication technology, in a communication system, in addition to the traditional communication service, the service performed by the communication device can also include other new services, such as artificial intelligence (AI) service. Generally, the communication system capable of processing the AI service can also be referred to as an AI system.

[0004] At present, the communication device can serve as a participating node of the AI system and provide its own computing power and data. For example, one communication device can perform model processing based on a model deployed by another communication device, i.e., the one communication device can perform one or more model processing (such as model training, model updating, or model fine-tuning, etc.) processes on the model based on local data to obtain another model.

[0005] However, in the above process, how to improve the management efficiency of the model is a technical problem to be solved. SUMMARY

[0006] The present application provides a communication method and related apparatus for improving the management efficiency of the model.

[0007] The first aspect of the present application provides a communication method, which is performed by a first communication device. The first communication device can be a communication device (such as a terminal device or a network device or a device associated with a terminal device, etc.), or the first communication device can be a part of a communication device (such as a circuit or a chip responsible for communication functions (such as a Modem chip, also known as a baseband chip, or a system on chip (SoC) chip containing a modem core or a system in package (SIP) chip, etc.), or the first communication device can also be a logic module or software that can implement all or part of the functions of the communication device. In the method, the first communication device receives first information, which is used to indicate first model parameters; wherein the first model parameters are used to determine a first model; the first communication device receives second information, which is used to indicate input data; wherein the input data and the first model are used to determine output data; the first communication device sends third information, which is used to determine whether the terminal device has the capability to perform model processing of the first model; wherein the third information is determined based on the output data.

[0008] Based on the above scheme, the first communication device can verify whether the terminal device has the capability to perform a model corresponding to a specific model parameter based on the specified input data, and indicate the verification result through the third information, so that the receiver of the third information knows the verification result. Since different model parameters can be used to determine different models (or different model functions), and different models (or different model functions) may have different requirements for the running environment (such as the running software and hardware environment, the required computing power, or the required data, etc.), the first communication device can verify whether the terminal device has the capability to perform a model corresponding to a specific model parameter in the above scheme, and the verification result obtained in the verification process can be used as a basis for model deployment, so as to improve the management efficiency of the model.

[0009] In addition, compared with the offline verification method of the model function (such as the verification method of the radio access network (RAN4)), the first communication device can verify whether the terminal device has the capability to perform a model corresponding to a specific model parameter through online testing in the above scheme, which can reduce the time delay of model function verification and reduce the deployment period of the model, so as to improve the management efficiency of the model.

[0010] In the present application, the model (such as the first model, or the second model mentioned later, etc.) can include an AI model, a neural network model, an AI neural network model, a machine learning model, or an AI processing model, etc.

[0011] In this application, model parameter can refer to a parameter between different neurons in a neural network. For example, the parameter can include weight and / or function, etc.

[0012] For example, a model can process input data to obtain output data, and the processing can include inference or prediction, etc.

[0013] Optionally, the input data can be replaced by other terms, such as model input, input data of the model, or input, etc.

[0014] Optionally, the output data can be replaced by other terms, such as model output, output data of the model, or output, etc.

[0015] It should be understood that the first information is used to indicate the first model parameter, which can be understood as that the first information contains the first model parameter, or the first information contains configuration information / configuration parameters used to generate the first model parameter.

[0016] It should be understood that the second information is used to indicate the input data, which can be understood as that the second information contains the input data, or the second information contains configuration information / configuration parameters used to generate the input data.

[0017] It should be noted that the first information and the second information can be carried in the same message / signaling / information, or the first information and the second information can be carried in different messages / signaling / information.

[0018] It should be noted that the third information is used to determine whether the terminal device has the capability to perform the model processing of the first model, which can be understood as that the third information is used to determine whether the terminal device has the capability to correctly perform the model processing of the first model.

[0019] For example, in the case that the terminal device can obtain output data based on the input data of the first model, it indicates that the terminal device can run the first model, and therefore the third information is used to determine that the terminal device has the capability to perform the model processing of the first model.

[0020] For another example, in the case that the terminal device cannot obtain output data based on the input data of the first model, it indicates that the terminal device cannot run the first model, and therefore the third information is used to determine that the terminal device does not have the capability to perform the model processing of the first model.

[0021] For example, in a case where the terminal device is capable of obtaining output data based on input data of the first model, and a difference between the output data and an expected output corresponding to the input data is less than (or equal to) a threshold, it indicates that the terminal device is capable of running the first model and the model performance obtained by running the first model is higher. Therefore, the third information is used to determine that the terminal device has the capability of performing the model processing of the first model.

[0022] For example, in a case where the terminal device is capable of obtaining output data based on input data of the first model, and a difference between the output data and an expected output corresponding to the input data is greater than (or equal to) a threshold, it indicates that the terminal device is capable of running the first model but the model performance obtained by running the first model is lower. Therefore, the third information is used to determine that the terminal device does not have the capability of performing the model processing of the first model.

[0023] Optionally, the third information is further used to indicate whether one or more terminal devices of a same type (or a same specification, or a similar type, or a similar specification, etc.) as the terminal device are capable of performing the model processing of the first model. In this way, the receiver of the third information can learn the capability of the one or more terminal devices of the same type (or the same specification, or the similar type, or the similar specification, etc.) based on the third information, which can reduce the overhead and latency of capability verification of the terminal devices, and further improve the management efficiency of the model.

[0024] Optionally, one terminal device and another terminal device are of a same type (or a same specification, or a similar type, or a similar specification, etc.), including that software parameters and / or hardware parameters of the one terminal device and the another terminal device are the same or similar.

[0025] For example, the software parameters can include a compilation file version number, or a system version number, etc.

[0026] For example, the hardware parameters can include a chip model, or a device model.

[0027] In a possible implementation of the first aspect, the third information includes at least one of the following:

[0028] first indication information used to indicate the output data;

[0029] second indication information used to indicate whether the terminal device has the capability of performing the model processing of the first model (or used to indicate whether the terminal device has the capability of correctly performing the model processing of the first model);

[0030] third indication information used to indicate a difference between the output data and an expected output corresponding to the input data.

[0031] Based on the above scheme, the third information can include the at least one item, so that the receiver of the third information can determine whether the terminal device has the capability of performing the model processing of the first model based on the at least one item, to improve the flexibility of the scheme implementation.

[0032] In a possible implementation form of the first aspect, the method further includes: receiving, by the first communication device, fourth indication information, the fourth indication information being used for indicating a first compiled file, the first compiled file and the first model parameter being used for determining the first model.

[0033] Based on the above scheme, the first communication device can further receive fourth indication information, so that the first communication device determines the first model based on the compiled file specified by the fourth indication information and the first model parameter specified by the first information, to verify whether the terminal device has the capability of performing the model processing of the model corresponding to the specified compiled file.

[0034] It should be understood that, in the processing of a model by a device, the device needs to perform specific optimization and compilation for different model structures and model parameters, and for the software and hardware environment specific to the chip of the device, to generate a compiled file. The device can perform model inference of the model structure and the corresponding model parameter by using the compiled file. In this document, the process of generating the compiled file after optimization and compilation is uniformly described as compilation. Generally, the compiled file generated for a specific model structure can be used for model inference of different model parameters under the model structure. If the compiled file is generated for a specific model structure and specific model parameters, there may be a certain loss of model performance when the compiled file is used for model inference of the specific model structure and other model parameters.

[0035] In the above scheme, the third information sent by the first communication device can be used to determine whether the terminal device has the capability of performing the model processing of the first model, which can be obtained by a specific compiled file (i.e., the first compiled file) and specific model parameters (i.e., the first model parameter). In other words, the above scheme can verify whether the terminal device has the capability of performing the model corresponding to the specific compiled file and the specific model parameter.

[0036] In a possible implementation form of the first aspect, the method further includes: sending, by the first communication device, fifth indication information, the fifth indication information being used for indicating one or more compiled files, the one or more compiled files including the first compiled file.

[0037] Optionally, the fifth indication information is used for indicating that the terminal device has (or supports, or stores) one or more compiled files.

[0038] Based on the above scheme, the first communication device can further send fifth indication information, so that the receiver (for example, the second communication device) of the fifth indication information can learn that the terminal device has one or more compiled files based on the fifth indication information, so as to specify the first compiled file of the one or more compiled files to the first communication device by the receiver, so that the terminal device can generate / determine / execute the first model based on the compiled file supported by itself.

[0039] In a possible implementation manner of the first aspect, the one or more compiled files correspond to the first model structure; and the method further includes: the first communication device sending sixth indication information, the sixth indication information indicating that the terminal device supports the first model structure.

[0040] Based on the above scheme, the first communication device can further send sixth indication information, so that the receiver (for example, the second communication device) of the sixth indication information can learn the model structure supported by the terminal device based on the sixth indication information, and send the first information indicating the first model parameter to the first communication device based on the supported model structure, so that the terminal device can generate / determine / execute the first model based on the model structure supported by itself.

[0041] In a possible implementation manner of the first aspect, the method is applied to the terminal device (that is, the first communication device can be the terminal device or an internal module of the terminal device), or a device associated with the terminal device (that is, the first communication device can be the device associated with the terminal device or an internal module of the device associated with the terminal device); and the first communication device sending the third information includes: the first communication device sending the third information to the access network device; or, the first communication device sending the third information to the core network device through the access network device.

[0042] Based on the above scheme, the first communication device can be the terminal device or the device associated with the terminal device, and correspondingly, the second communication device providing the second information to the first communication device can be a network device (for example, the access network device or the core network device), so that the first communication device realizes online verification of the capability of the terminal device through the communication process between the first communication device and the network device.

[0043] It should be noted that the terminal device associated device can include a host (or virtual machine, server, etc.) of an over the top (OTT) system, a cloud server, etc. For example, the terminal device associated device can be used to determine the capability of the terminal device. For example, the terminal device associated device can be used to determine whether the terminal device has the capability to execute a model corresponding to a specific model parameter. For another example, the terminal device associated device can be used to determine whether the terminal device has the capability to execute a specific compiled file. For another example, the terminal device associated device can be used to determine whether the terminal device has the capability to execute a specific model.

[0044] In a possible implementation of the first aspect, the method is applied to a core network device (i.e., the first communication apparatus can be a core network device or an internal module of the core network device); and the first communication apparatus sends the third information, including: the first communication apparatus sends the third information to an access network device.

[0045] Based on the above scheme, the first communication apparatus can be a core network device, and accordingly, the second communication apparatus that provides the second information to the first communication apparatus can be an access network device, so that the first communication apparatus realizes online verification of the capability of the terminal device through a communication process with the access network device.

[0046] In a possible implementation of the first aspect, the method further includes: the first communication apparatus receives seventh indication information, the seventh indication information being used to indicate that the terminal device has the capability to execute a model corresponding to the first model parameter.

[0047] Based on the above scheme, after the first communication apparatus sends the third information, the receiver of the third information can determine whether the terminal device has the capability to execute the first model based on the third information. And in the case that the receiver determines that the terminal device has the capability to execute the first model, the receiver can send seventh indication information to the first communication apparatus, so that the first communication apparatus determines that the terminal device has the capability based on the seventh indication information, i.e., the first communication apparatus can explicitly be able to deploy the first model to the terminal device in the future, and explicitly determine that the terminal device has the capability to execute the first model.

[0048] In a possible implementation of the first aspect, the method further includes: the first communication apparatus receives or sends eighth indication information, the eighth indication information being used to indicate whether one or more terminal devices of the same type as the terminal device can execute model processing of the first model.

[0049] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the third information. Moreover, the first communication device can send eighth indication information to other devices (such as an access network device, a core network device, or a terminal device, etc.), so that the receiver of the eighth indication information can determine whether the first model can be deployed to one or more terminal devices of the same type as the terminal device in the future and whether the one or more terminal devices have the capability of executing the first model.

[0050] Alternatively, after the first communication device sends the third information, the receiver of the third information can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the third information. Moreover, the receiver can send eighth indication information to the first communication device, so that the first communication device can determine that the terminal device has the capability based on the eighth indication information, that is, the first communication device can determine whether the first model can be deployed to one or more terminal devices of the same type as the terminal device in the future and whether the one or more terminal devices have the capability of executing the first model.

[0051] The second aspect of the present application provides a communication method, which is executed by a second communication device. The second communication device can be a communication device (such as a terminal device or a network device), or the second communication device can be a part of the communication device (such as a circuit or a chip responsible for communication functions (such as a Modem chip, also known as a baseband chip, or a SoC chip or a system-in-package SIP chip containing a modem core), etc.), or the second communication device can also be a logic module or software that can realize all or part of the functions of the communication device. In the method, the second communication device sends first information, which is used to indicate first model parameters; the first model parameters are used to determine a first model; the second communication device sends second information, which is used to indicate input data; the input data and the first model are used to determine output data (or the input data is used to obtain output data through processing of the first model); the second communication device receives third information, which is used to determine whether a terminal device has the capability of executing model processing of the first model; and the third information is determined based on the output data.

[0052] Based on the above scheme, the second communication apparatus can indicate the first model parameter to the first communication apparatus through the first information, and indicate the input data to the first communication apparatus through the second information, so that the first communication apparatus can verify whether the terminal device has the capability of executing the model corresponding to the specific model parameter based on the specified input data, and indicate the verification result through the third information, so that the second communication apparatus knows the verification result. Since different model parameters can be used to determine different models (or different model functions), and the requirements of different models (or different model functions) for the running environment (such as the running software and hardware environment, the required computing power, or the required data, etc.) may be different. Therefore, in the above scheme, the first communication apparatus can verify whether the terminal device has the capability of executing the model corresponding to the specific model parameter, and the verification result obtained in the verification process can be used as a basis for model deployment, so as to improve the management efficiency of the model.

[0053] In addition, compared with the offline verification mode of the model function (such as the verification mode of the radio access network (RAN4)), in the above scheme, the first communication apparatus can verify whether the terminal device has the capability of executing the model corresponding to the specific model parameter through the online test mode, which can reduce the time delay of the model function verification and reduce the deployment period of the model, so as to improve the management efficiency of the model.

[0054] It should be noted that the first information and the second information can be carried in the same message / signaling / information, or the first information and the second information can be carried in different messages / signaling / information.

[0055] In a possible implementation manner of the second aspect, the third information is further used to indicate whether one or more terminal devices of the terminal device (or the same specification, or the similar type, or the similar specification, etc.) can execute the model processing of the first model. In this way, the receiver of the third information can know the capability of one or more terminal devices of the same type (or the same specification, or the similar type, or the similar specification, etc.) based on the third information, which can reduce the overhead and the time delay of the capability verification of the terminal devices, and further improve the management efficiency of the model.

[0056] In a possible implementation manner of the second aspect, the third information includes at least one of the following:

[0057] The first indication information is used to indicate the output data;

[0058] The second indication information is used to indicate whether the terminal device has the capability of executing the model processing of the first model (or is used to indicate whether the terminal device has the capability of correctly executing the model processing of the first model).

[0059] a third indication information, used for indicating a difference between the output data and an expected output corresponding to the input data.

[0060] Based on the above scheme, the third information can be obtained by including the at least one item, so that the receiver of the third information can determine whether the terminal device has the capability of performing the model processing of the first model based on the at least one item, to improve the flexibility of the scheme implementation.

[0061] In a possible implementation manner of the second aspect, the method further includes: the second communication device sending fourth indication information, the fourth indication information being used for indicating a first compiled file, the first compiled file and the first model parameter being used for determining the first model.

[0062] Based on the above scheme, the second communication device can further send the fourth indication information to the first communication device, so that the first communication device determines the first model based on the compiled file specified by the fourth indication information and the first model parameter specified by the first information, to verify whether the terminal device has the capability of performing the model processing of the specified model corresponding to the compiled file.

[0063] In a possible implementation manner of the second aspect, the method further includes: the second communication device receiving fifth indication information, the fifth indication information being used for indicating one or more compiled files, the one or more compiled files including the first compiled file.

[0064] Based on the above scheme, the second communication device can further receive the fifth indication information from the first communication device, so that the second communication device can learn, based on the fifth indication information, that the terminal device has (or supports, or stores) one or more compiled files, so as to specify, by the second communication device, the first compiled file of the one or more compiled files to the first communication device, so that the terminal device can generate / determine / execute the first model based on the compiled file supported by itself.

[0065] In a possible implementation manner of the second aspect, the model structures corresponding to the one or more compiled files are all the first model structure; the method further includes: the second communication device receiving sixth indication information, the sixth indication information indicating that the terminal device supports the first model structure.

[0066] Based on the above scheme, the second communication device can further receive the sixth indication information from the first communication device, so that the second communication device can learn, based on the sixth indication information, the model structure supported by the terminal device, and send, based on the supported model structure, the first information indicating the first model parameter to the first communication device, so that the terminal device can generate / determine / execute the first model based on the model structure supported by itself.

[0067] In a possible implementation manner of the second aspect, the method is applied to an access network device (i.e., the first communication apparatus can be the access network device or an internal module of the access network device); and the third information is from the terminal device, a device associated with the terminal device, or a core network device.

[0068] Based on the above scheme, the first communication apparatus can be the terminal device or the device associated with the terminal device, and accordingly, the second communication apparatus providing the second information to the first communication apparatus can be a network device (for example, an access network device or a core network device), so that the first communication apparatus implements the online verification of the capability of the terminal device through a communication process between the first communication apparatus and the network device.

[0069] In a possible implementation manner of the second aspect, the method is applied to a core network device; and the third information is from the terminal device or a device associated with the terminal device.

[0070] Based on the above scheme, the first communication apparatus can be the core network device, and accordingly, the second communication apparatus providing the second information to the first communication apparatus can be an access network device, so that the first communication apparatus implements the online verification of the capability of the terminal device through a communication process between the first communication apparatus and the access network device.

[0071] In a possible implementation manner of the second aspect, the method further includes: the second communication apparatus sending seventh indication information, the seventh indication information being used to indicate that the terminal device has the capability of executing the model corresponding to the first model parameter.

[0072] Based on the above scheme, after receiving the third information, the second communication apparatus can determine whether the terminal device has the capability of executing the first model based on the third information. And in a case where the second communication apparatus determines that the terminal device has the capability of executing the first model, the second communication apparatus can send the seventh indication information to the first communication apparatus, so that the first communication apparatus determines that the terminal device has the capability based on the seventh indication information, i.e., the first communication apparatus can explicitly be able to deploy the first model to the terminal device in the future, and explicitly determine that the terminal device has the capability of executing the first model.

[0073] In a possible implementation manner of the second aspect, the method further includes: the second communication apparatus receiving or sending eighth indication information, the eighth indication information being used to indicate whether one or more terminal devices of the same type as the terminal device can execute model processing of the first model.

[0074] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the third information. Moreover, the first communication device can send the eighth indication information to the second communication device, so that the receiver of the second communication device can determine whether the first model can be deployed to one or more terminal devices of the same type as the terminal device in the future and whether the one or more terminal devices have the capability of executing the first model.

[0075] Alternatively, after receiving the third information, the second communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the third information. Moreover, the second communication device can send the eighth indication information to the first communication device, so that the first communication device can determine that the terminal device has the capability based on the eighth indication information, i.e., the first communication device can determine whether the first model can be deployed to one or more terminal devices of the same type as the terminal device in the future and whether the one or more terminal devices have the capability of executing the first model.

[0076] The third aspect of the present application provides a communication method, which is performed by a first communication device. The first communication device can be a communication device (such as a terminal device or a network device), or the first communication device can be a part of the communication device (for example, a circuit or a chip responsible for communication functions (such as a Modem chip, also known as a baseband chip, or a SoC chip or a system-in-package SIP chip containing a modem core), etc.), or the first communication device can also be a logic module or software that can realize all or part of the functions of the communication device. In the method, the first communication device receives fourth information, and the fourth information is used to indicate first model parameters; wherein the first model parameters are used to determine a first model; the first communication device sends fifth information, and the fifth information is used to determine whether a terminal device has the capability of executing model processing of the first model; wherein the terminal device has the capability of executing model processing of a second model, and the fifth information is determined based on the first model and the second model.

[0077] Based on the above scheme, the first communication device verifies whether the terminal device has the capability to execute the model corresponding to the specific model parameter based on the first model generated based on the specified model parameter and the second model that the terminal device has been able to execute model processing, and indicates the verification result through the fifth information, so that the receiver of the fifth information knows the verification result. Since different model parameters can be used to determine different models (or different model functions), and the requirements (such as the running software and hardware environment, the required computing power, or the required data, etc.) of different models (or different model functions) for the running environment can be different. Therefore, in the above scheme, the first communication device can verify whether the terminal device has the capability to execute the model corresponding to the specific model parameter, and the verification result obtained in the verification process can be used as a basis for model deployment, so as to improve the management efficiency of the model.

[0078] In addition, compared with the offline verification mode of the model function (such as the verification mode of the radio access network (RAN4)), in the above scheme, the first communication device can verify whether the terminal device has the capability to execute the model corresponding to the specific model parameter through the online test mode, which can reduce the time delay of the model function verification and reduce the deployment period of the model, so as to improve the management efficiency of the model.

[0079] It should be understood that the fourth information is used to indicate the first model parameter, which can be understood as that the fourth information contains the first model parameter, or the fourth information contains configuration information / configuration parameters used to generate the first model parameter.

[0080] Optionally, the fifth information is also used to indicate whether one or more terminal devices of the same type (or the same specification, or similar type, or similar specification, etc.) as the terminal device can execute the model processing of the first model. In this way, the receiver of the fifth information can know the capability of one or more terminal devices of the same type (or the same specification, or similar type, or similar specification, etc.) based on the fifth information, which can reduce the overhead and time delay of the capability verification of the terminal devices, and further improve the management efficiency of the model.

[0081] In a possible implementation manner of the third aspect, the processing of the first model includes one or more first processes, the processing of the second model includes one or more second processes, and the correlation information of the one or more first processes and the one or more second processes is used to determine the fifth information.

[0082] Optionally, the first process or the second process can include one or more of quantization, pruning, knowledge distillation, or model compression method (or model lightweight method, which can be implemented by lightweight model architecture or compact model design, etc.).

[0083] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of performing the model processing of the first model based on the relevance information between the one or more first processes contained in the first model generated based on the specified model parameters and the one or more second processes contained in the second model that the terminal device has been able to perform model processing.

[0084] Optionally, the fifth information for determining whether the terminal device has the capability of performing the model processing of the first model corresponding to the first model parameter includes: in a case where the relevance indicated by the relevance information is greater than (or equal to) a threshold value, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively small, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device can perform the model processing of the first model.

[0085] And / or, the fifth information for determining whether the terminal device has the capability of performing the model processing of the first model corresponding to the first model parameter includes: in a case where the relevance indicated by the relevance information is less than (or equal to) a threshold value, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively large, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device cannot perform the model processing of the first model.

[0086] In a possible implementation manner of the third aspect, the difference information between the processing performance of the first model on a data set and the processing performance of the second model on the data set is used to determine the fifth information. For example, the data set can include input data of the model, or an input data set of the model, etc.

[0087] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of performing the model processing of the first model based on the processing performance of the first model generated based on the specified model parameters on a data set and the processing performance of the second model that the terminal device has been able to perform model processing on the same data set. Thus, the first communication device can determine whether the terminal device has the capability based on the similarity degree of the processing performance of the two models on the same data set.

[0088] Optionally, the fifth information is used to determine whether the terminal device is capable of performing model processing of the first model corresponding to the first model parameter, including: in a case where the difference indicated by the difference information is less than or equal to a threshold, the first communication apparatus can determine that the difference between the model processing of the first model and the model processing of the second model is relatively small, and for this purpose, the fifth information sent by the first communication apparatus can be used to determine that the terminal device is capable of performing the model processing of the first model.

[0089] Optionally, the fifth information is used to determine whether the terminal device is capable of performing model processing of the first model corresponding to the first model parameter, including: in a case where the difference indicated by the difference information is greater than a threshold, the first communication apparatus can determine that the difference between the model processing of the first model and the model processing of the second model is relatively large, and for this purpose, the fifth information sent by the first communication apparatus can be used to determine that the terminal device is incapable of performing the model processing of the first model.

[0090] In a possible implementation of the third aspect, the fourth information includes the first model parameter; or the fourth information includes the first model parameter and difference information of the second model parameter, wherein the second model parameter is used to determine the second model.

[0091] Based on the above scheme, the fourth information used to indicate the first model parameter can include the above-mentioned multiple ways of implementation, so as to improve the flexibility of the implementation of the scheme.

[0092] In a possible implementation of the third aspect, the method is applied to the terminal device (i.e., the first communication apparatus can be the terminal device or an internal module of the terminal device), or a device associated with the terminal device (i.e., the first communication apparatus can be the device associated with the terminal device or an internal module of the device associated with the terminal device); and the first communication apparatus sends the fifth information, including: the first communication apparatus sends the fifth information to an access network device; or the first communication apparatus sends the fifth information to a core network device through the access network device.

[0093] Based on the above scheme, the first communication apparatus can be the terminal device or the device associated with the terminal device, and correspondingly, the second communication apparatus that provides the fourth information to the first communication apparatus can be a network device (e.g., an access network device or a core network device), so that the first communication apparatus implements online verification of the capability of the terminal device through a communication process between the first communication apparatus and the network device.

[0094] In a possible implementation of the third aspect, the method is applied to a core network device (i.e., the first communication apparatus can be the core network device or an internal module of the core network device); and the first communication apparatus sends the fifth information, including: the first communication apparatus sends the fifth information to an access network device.

[0095] Based on the above scheme, the first communication device can be a core network device, and correspondingly, the second communication device providing the fourth information to the first communication device can be an access network device, so that the first communication device implements online verification of the capability of the terminal device through a communication process between the first communication device and the access network device.

[0096] In a possible implementation form of the third aspect, the method further includes: receiving, by the first communication device, seventh indication information, the seventh indication information being used to indicate that the terminal device has the capability of executing the model corresponding to the first model parameter.

[0097] Based on the above scheme, after the first communication device sends the fifth information, a receiver of the fifth information can determine whether the terminal device has the capability of executing the first model based on the fifth information. And in a case where the receiver determines that the terminal device has the capability of executing the first model, the receiver can send seventh indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the seventh indication information, that is, the first communication device can explicitly enable subsequent deployment of the first model on the terminal device and explicitly determine that the terminal device has the capability of executing the first model.

[0098] In a possible implementation form of the third aspect, the method further includes: receiving or sending, by the first communication device, eighth indication information, the eighth indication information being used to indicate whether one or more terminal devices of the same type as the terminal device can execute model processing of the first model.

[0099] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the fifth information. And the first communication device can send the eighth indication information to other devices (for example, an access network device, a core network device, or a terminal device, etc.), so that a receiver of the eighth indication information explicitly determines whether the first model can be subsequently deployed on one or more terminal devices of the same type as the terminal device and explicitly determines whether the one or more terminal devices have the capability of executing the first model.

[0100] Or, after the first communication device sends the fifth information, a receiver of the fifth information can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the fifth information. And the receiver can send eighth indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the eighth indication information, that is, the first communication device can explicitly determine whether the first model can be subsequently deployed on one or more terminal devices of the same type as the terminal device and explicitly determine whether the one or more terminal devices have the capability of executing the first model.

[0101] The fourth aspect of the present application provides a communication method, which is performed by a second communication device. The second communication device can be a communication device (such as a terminal device or a network device), or the second communication device can be a part of the communication device (for example, a circuit or a chip responsible for communication functions (such as a Modem chip, also known as a baseband chip, or a SoC chip or a system-in-package SIP chip containing a modem core), etc.), or the second communication device can also be a logic module or software that can realize all or part of the functions of the communication device. In the method, the second communication device sends fourth information, which is used to indicate first model parameters; wherein the first model parameters are used to determine a first model; the second communication device receives fifth information, which is used to determine whether the terminal device has the capability to perform model processing of the first model; wherein the terminal device has the capability to perform model processing of a second model, and the fifth information is determined based on the first model and the second model.

[0102] Based on the above scheme, the fourth information sent by the second communication device to the first communication device can indicate the first model parameters, so that the first communication device generates the first model based on the specified first model parameters, and the second model for which the terminal device has already been able to perform model processing, verifies whether the terminal device has the capability to perform the model corresponding to the specific model parameters, and indicates the verification result through the fifth information, so that the second communication device knows the verification result. Since different model parameters can be used to determine different models (or different model functions), and different models (or different model functions) may have different requirements for the running environment (such as the running software and hardware environment, the required computing power, or the required data, etc.), the first communication device can verify whether the terminal device has the capability to perform the model corresponding to the specific model parameters in the above scheme, and the verification result obtained in the verification process can be used as a basis for model deployment, so as to improve the management efficiency of the model.

[0103] In addition, compared with the offline verification method of the model function (for example, the verification method of the radio access network RAN4), in the above scheme, the first communication device can verify whether the terminal device has the capability to perform the model corresponding to the specific model parameters through the online test method, which can reduce the time delay of the model function verification and reduce the deployment period of the model, so as to improve the management efficiency of the model.

[0104] In a possible implementation manner of the fourth aspect, the processing of the first model includes one or more first processes, the processing of the second model includes one or more second processes, and the correlation information of the one or more first processes and the one or more second processes is used to determine the fifth information.

[0105] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of performing the model processing of the first model based on the relevance information between the one or more first processes contained in the first model generated based on the specified model parameters and the one or more second processes contained in the second model that the terminal device has been able to perform model processing.

[0106] Optionally, the fifth information is used to determine whether the terminal device has the capability of performing the model processing of the first model corresponding to the first model parameter, including: in the case where the relevance indicated by the relevance information is greater than (or equal to) a threshold value, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively small, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device can perform the model processing of the first model.

[0107] And / or, the fifth information is used to determine whether the terminal device has the capability of performing the model processing of the first model corresponding to the first model parameter, including: in the case where the relevance indicated by the relevance information is less than (or equal to) a threshold value, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively large, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device cannot perform the model processing of the first model.

[0108] In a possible implementation manner of the fourth aspect, the difference information between the processing performance of the first model on a data set and the processing performance of the second model on the data set is used to determine the fifth information.

[0109] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of performing the model processing of the first model based on the processing performance of the first model generated based on the specified model parameters on a data set and the processing performance of the second model that the terminal device has been able to perform model processing on the same data set. Thus, the first communication device can determine whether the terminal device has the capability based on the similarity degree of the processing performance of the two models on the same data set.

[0110] Optionally, the fifth information is used to determine whether the terminal device can perform the model processing of the first model corresponding to the first model parameter, including: in the case where the difference indicated by the difference information is less than or equal to a threshold value, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively small, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device can perform the model processing of the first model.

[0111] And / or, the fifth information is used to determine whether the terminal device is capable of performing model processing of the first model corresponding to the first model parameter, including: in a case where the difference indicated by the difference information is greater than a threshold, the first communication apparatus can determine that the difference between the model processing of the first model and the model processing of the second model is relatively large, and for this purpose, the fifth information sent by the first communication apparatus can be used to determine that the terminal device is not capable of performing the model processing of the first model.

[0112] In a possible implementation of the fourth aspect, the fourth information includes the first model parameter; or the fourth information includes difference information of the first model parameter and the second model parameter; and the second model parameter is used to determine the second model.

[0113] Based on the above scheme, the fourth information used to indicate the first model parameter can include the above-mentioned multiple ways of implementation, so as to improve the flexibility of the implementation of the scheme.

[0114] In a possible implementation of the fourth aspect, the method is applied to an access network device; and the fifth information is from a terminal device, a device associated with the terminal device, or a core network device.

[0115] Based on the above scheme, the first communication apparatus can be a terminal device or a device associated with the terminal device, and correspondingly, the second communication apparatus that provides the fourth information to the first communication apparatus can be a network device (for example, an access network device or a core network device), so that the first communication apparatus implements online verification of the capability of the terminal device through a communication process between the first communication apparatus and the network device.

[0116] In a possible implementation of the fourth aspect, the method is applied to the core network device; and the fifth information is from a terminal device or a device associated with the terminal device.

[0117] Based on the above scheme, the first communication apparatus can be a core network device, and correspondingly, the second communication apparatus that provides the fourth information to the first communication apparatus can be an access network device, so that the first communication apparatus implements online verification of the capability of the terminal device through a communication process between the first communication apparatus and the access network device.

[0118] In a possible implementation of the fourth aspect, the method further includes: the second communication apparatus sends seventh indication information, and the seventh indication information is used to indicate that the terminal device has the capability of executing a model corresponding to the first model parameter.

[0119] Based on the above scheme, after the second communication device receives the fifth information from the first communication device, the second communication device can determine whether the terminal device has the capability of executing the first model based on the fifth information. Moreover, in a case where the second communication device determines that the terminal device has the capability of executing the first model, the second communication device can send seventh indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the seventh indication information, that is, the first communication device can explicitly know that the first model can be subsequently deployed to the terminal device, and that the terminal device has the capability of executing the first model.

[0120] In a possible implementation manner of the fourth aspect, the method further includes: the second communication device receiving or sending eighth indication information, the eighth indication information being used to indicate whether one or more terminal devices of the same type as the terminal device can execute model processing of the first model.

[0121] Based on the above scheme, the first communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the fifth information. Moreover, the first communication device can send eighth indication information to the second communication device, so that the second communication device explicitly knows whether the first model can be subsequently deployed to one or more terminal devices of the same type as the terminal device, and whether the one or more terminal devices have the capability of executing the first model.

[0122] Or, after the first communication device sends the fifth information to the second communication device, the second communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the fifth information. Moreover, the second communication device can send eighth indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the eighth indication information, that is, the first communication device can explicitly know whether the first model can be subsequently deployed to one or more terminal devices of the same type as the terminal device, and whether the one or more terminal devices have the capability of executing the first model.

[0123] The fifth aspect of the present application provides a communication device, which is a first communication device, the device comprising a transceiver unit and a processing unit; the transceiver unit is configured to receive first information, the first information being used to indicate first model parameters; wherein the first model parameters are used to determine a first model; the transceiver unit is further configured to receive second information, the second information being used to indicate input data; wherein the input data and the first model are used to determine output data; the processing unit is configured to determine third information; the transceiver unit is further configured to send the third information, the third information being used to determine whether a terminal device has the capability of executing model processing of the first model; wherein the third information is determined based on the output data.

[0124] In the fifth aspect of the present application, the constituent modules of the communication device can also be used to perform the steps performed in the various possible implementation manners of the first aspect and achieve the corresponding technical effects, which can be specifically referred to the first aspect and will not be repeated here.

[0125] The sixth aspect of the present application provides a communication device, which is a second communication device, comprising a transceiver unit and a processing unit, the processing unit is configured to determine first information and second information; the transceiver unit is configured to send the first information, the first information is used to indicate first model parameters; the first model parameters are used to determine a first model; the transceiver unit is also configured to send the second information, the second information is used to indicate input data; wherein the input data and the first model are used to determine output data; the transceiver unit is also configured to receive third information, the third information is used to determine whether a terminal device has the capability to perform model processing of the first model; wherein the third information is determined based on the output data.

[0126] In the sixth aspect of the present application, the constituent modules of the communication device can also be used to perform the steps performed in the various possible implementation manners of the second aspect and achieve the corresponding technical effects, which can be specifically referred to the second aspect and will not be repeated here.

[0127] The seventh aspect of the present application provides a communication device, which is a first communication device, comprising a transceiver unit and a processing unit; the transceiver unit is configured to receive fourth information, the fourth information is used to indicate first model parameters; wherein the first model parameters are used to determine a first model; the processing unit is configured to determine fifth information; the transceiver unit is also configured to send the fifth information, the fifth information is used to determine whether a terminal device has the capability to perform model processing of the first model; wherein the terminal device has the capability to perform model processing of a second model, the fifth information is determined based on the first model and the second model.

[0128] In the seventh aspect of the present application, the constituent modules of the communication device can also be used to perform the steps performed in the various possible implementation manners of the third aspect and achieve the corresponding technical effects, which can be specifically referred to the third aspect and will not be repeated here.

[0129] The eighth aspect of the present application provides a communication device, which is a second communication device, comprising a transceiver and a processing unit, the processing unit being configured to determine fourth information; the transceiver being configured to send the fourth information, the fourth information being used to indicate a first model parameter; wherein the first model parameter is used to determine a first model; the transceiver is further configured to receive fifth information, the fifth information being used to determine whether a terminal device has a capability of performing model processing of the first model; wherein the terminal device has a capability of performing model processing of a second model, and the fifth information is determined based on the first model and the second model.

[0130] In the eighth aspect of the present application, the constituent modules of the communication device can also be configured to perform the steps performed in the various possible implementation manners of the fourth aspect and achieve the corresponding technical effects, which can be referred to the fourth aspect for details and will not be described herein.

[0131] The ninth aspect of the present application provides a communication device, comprising at least one processor, the at least one processor being coupled with a memory; the memory being configured to store programs or instructions; the at least one processor being configured to execute the programs or instructions to enable the device to implement the method in any one of the possible implementation manners of any one of the first aspect to the fourth aspect. Optionally, the communication device can comprise the memory.

[0132] The tenth aspect of the present application provides a communication device, comprising at least one logic circuit and an input-output interface; the logic circuit being configured to execute the method as described in any one of the possible implementation manners of any one of the first aspect to the fourth aspect.

[0133] The eleventh aspect of the present application provides a communication system, comprising the first communication device and the second communication device.

[0134] The twelfth aspect of the present application provides a computer readable storage medium, the storage medium being configured to store one or more computer execution instructions, when the computer execution instructions are executed by a processor, the processor executes the method as described in any one of the possible implementation manners of any one of the first aspect to the fourth aspect.

[0135] The thirteenth aspect of the present application provides a computer program product (or computer program), when a computer program in the computer program product is executed by a processor, the processor executes the method as described in any one of the possible implementation manners of any one of the first aspect to the fourth aspect.

[0136] The fourteenth aspect of the present application provides a chip or a chip system, which comprises at least one processor for supporting a communication device to implement the method in any possible implementation manner of any one of the first aspect to the fourth aspect. For example, the chip can be a baseband chip, a modem chip, a system on chip (SoC) chip containing a modem core, a system in package (SIP) chip, or a communication module, etc.

[0137] In a possible design, the chip or the chip system can further comprise a memory for storing necessary program instructions and data of the communication device. The chip system can be composed of a chip, or can comprise a chip and other discrete devices. Optionally, the chip system further comprises an interface circuit for providing program instructions and / or data for the at least one processor.

[0138] The technical effects brought by the fifth aspect to the fourteenth aspect can be referred to the technical effects brought by the first aspect to the fourth aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0139] FIGS. 1a to 1c are schematic diagrams of a communication system provided by the present application;

[0140] FIGS. 1d, 1e and 2a to 2c are schematic diagrams of an AI processing process related to the present application;

[0141] FIGS. 3a and 3b are some interaction schematic diagrams of a communication method provided by the present application;

[0142] FIGS. 4a and 4b are some interaction schematic diagrams of a communication method provided by the present application;

[0143] FIGS. 5a and 5b are some interaction schematic diagrams of a communication method provided by the present application;

[0144] FIGS. 6a and 6b are some interaction schematic diagrams of a communication method provided by the present application;

[0145] FIGS. 7 to 11 are schematic diagrams of a communication device provided by the present application. DETAILED DESCRIPTION

[0146] First, some terms in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0147] (1) Terminal device: can be a wireless terminal device capable of receiving network device scheduling and indication information, the wireless terminal device can be a device that provides voice and / or data connectivity to a user, or a handheld device with wireless connection function, or other processing devices connected to a wireless modem.

[0148] The terminal device can communicate with one or more core networks or the Internet through a radio access network (RAN), and the terminal device can be a mobile terminal device, such as a mobile phone (or called "cellular" phone, mobile phone), computer and data card, for example, can be a portable, pocket-sized, handheld, computer built-in or vehicle-mounted mobile device, which exchanges voice and / or data with the radio access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets (Pads), computers with wireless transceiver functions, etc. The wireless terminal device can also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station (MS), a remote station, an access point (AP), a remote terminal, an access terminal, a user terminal, a user agent, a subscriber station (SS), customer premises equipment (CPE), a terminal, user equipment (UE), a mobile terminal (MT), etc.

[0149] By way of example and not limitation, in embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a smart wearable device or a smart wearable device, etc., which is a general term for devices that can be worn by applying wearable technology to the smart design of daily wear, such as glasses, gloves, watches, clothing, and shoes, etc. The wearable device is a portable device that can be worn directly on the body or integrated into the user's clothes or accessories. The wearable device is not only a hardware device, but also a powerful function realized through software support and data interaction, cloud interaction. The general wearable smart device includes a full function, large size, and can realize complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, etc., and focuses on a certain application function, and needs to cooperate with other devices such as a smart phone, such as various smart wristbands, smart helmets, smart jewelry, etc. for monitoring vital signs.

[0150] The terminal can also be a drone, a robot, a terminal in device-to-device (D2D) communication, a terminal in vehicle to everything (V2X), a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.

[0151] In addition, the terminal device can also be a terminal device in a future communication system or a terminal device in a future evolved public land mobile network (PLMN), etc. For example, in the future network, the form and function of the communication terminal can be further expanded, including but not limited to vehicles, cellular network terminals (with satellite terminal functions), drones, internet of things (IoT) devices.

[0152] In embodiments of the present application, the terminal device described above can also obtain AI services provided by the network device. Optionally, the terminal device can also have AI processing capability.

[0153] (2) Network device: can be a device in a wireless network, for example, the network device can be a RAN node (or device) for accessing a terminal device to a wireless network, which can also be referred to as a base station. At present, some examples of RAN devices are: base station (base station), evolved NodeB (eNodeB), base station gNB (gNodeB) in 5G communication system, transmission reception point (transmission reception point, TRP), evolved Node B (eNB), radio network controller (radio network controller, RNC), Node B (Node B, NB), home base station (for example, home evolved Node B, or home Node B, HNB), baseband unit (baseband unit, BBU), or wireless fidelity (wireless fidelity, Wi-Fi) access point AP, etc. In addition, in a network structure, the network device can include a centralized unit (centralized unit, CU) node, or a distributed unit (distributed unit, DU) node, or a RAN device including a CU node and a DU node.

[0154] Optionally, the RAN node can also be a macro base station, a micro base station or an indoor station, a relay node or a donor node, or a wireless controller in a cloud radio access network (cloud radio access network, CRAN) scenario. The RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in vehicle to everything (vehicle to everything, V2X) technology can be a road side unit (road side unit, RSU).

[0155] In another possible scenario, a terminal is assisted by multiple RAN nodes to implement wireless access, and different RAN nodes respectively implement part of functions of a base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can also be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, included in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0156] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (O-RAN or ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the 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.

[0157] The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer can include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer can include at least one of a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, or a physical (PHY) layer, etc. The user plane protocol layer can include at least one of a service data adaptation protocol (SDAP) layer, a PDCP layer, an RLC layer, a MAC layer, or a physical layer, etc.

[0158] For the correspondence between the network elements in the ORAN system and the protocol layer functions that can be implemented by the network elements, refer to Table 1 below.

[0159] Table 1

[0160] The network device can be another device that provides a wireless communication function for the terminal device. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device. For the convenience of description, the embodiments of the present application do not limit.

[0161] The network device can also include a core network device, which can include, for example, a mobility management entity (MME), a home subscriber server (HSS), a serving gateway (S-GW), a policy and charging rules function (PCRF), a public data network gateway (P-GW) in a fourth generation (4G) network, an access and mobility management function (AMF), a user plane function (UPF), or a session management function (SMF) in a 5G network, and other network elements. In addition, the core network device can also include other core network devices in the 5G network and future networks of the 5G network.

[0162] In the embodiments of the present application, the network device mentioned above can also be an AI-capable network node, which can provide AI services for terminals or other network devices, for example, can be an AI node, a computing power node, an AI-capable RAN node, an AI-capable core network element, etc. of the network side (access network or core network).

[0163] In the embodiments of the present application, the device for implementing the function of the network device can be a network device or a device capable of supporting the network device to implement the function, such as a chip system, which can be installed in the network device. In the technical solutions provided in the embodiments of the present application, the device for implementing the function of the network device is taken as an example to describe the technical solutions provided in the embodiments of the present application.

[0164] (3) Configuration and pre-configuration: In the present application, configuration and pre-configuration will be used at the same time. Among them, configuration refers to that the network device and / or server sends some parameter configuration information or parameter values to the terminal through messages or signaling, so that the terminal determines the communication parameters or resource at the time of transmission according to these values or information. Pre-configuration is similar to configuration, which can be parameter information or parameter values previously negotiated by the network device and / or server with the terminal device, or can be parameter information or parameter values adopted by the base station / network device or terminal device according to the standard protocol, or can be parameter information or parameter values previously stored in the base station and / or server or terminal device. The present application does not limit this.

[0165] Further, these values and parameters can be changed or updated.

[0166] (4) The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "Multiple" means two or more. "And / or" describes the association between the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one (one)" or similar expressions refer to any combination of these items, including any combination of single items (one) or multiple items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. In addition, unless otherwise specified, the ordinal numbers "first", "second", etc. mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, time sequence, priority or importance of the multiple objects.

[0167] (5) In embodiments of the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending information to XX" can be understood as that the destination of the information is XX, which can include direct sending through the air interface, or indirect sending through the air interface by other units or modules. "Receiving information from YY" can be understood as that the source of the information is YY, which can include direct receiving from YY through the air interface, or indirect receiving from YY through the air interface by other units or modules. "Sending" can also be understood as "output" of a chip interface, and "receiving" can also be understood as "input" of a chip interface.

[0168] In other words, sending and receiving can be between devices, such as between network devices and terminal devices, or within devices, such as between components, modules, chips, software modules or hardware modules within a device through a bus, wire or interface.

[0169] It can be understood that the information can be processed as necessary between the source and the destination of the information transmission, such as encoding and modulation, but the destination can understand the valid information from the source. Similar expressions in the present application can be similarly understood and will not be repeated here.

[0170] (6) In embodiments of the present application, "indicating" can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by a certain information (indication information as described below) is referred to as to-be-indicated information. In the implementation process, there are many ways to indicate the to-be-indicated information, for example but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance, for example, the arrangement order of each information can be used to indicate a specific information, thereby reducing the indication overhead to a certain extent. The present application does not limit the specific manner of indication. It can be understood that for the sender of the indication information, the indication information can be used to indicate the to-be-indicated information, and for the receiver of the indication information, the indication information can be used to determine the to-be-indicated information.

[0171] In this application, the same or similar parts between various embodiments can be mutually referred to, unless otherwise specified. In various embodiments in this application, and various methods / designs / implementation manners in each embodiment, the terms and / or descriptions between different embodiments, and between various methods / designs / implementation manners in each embodiment are consistent, and can be mutually referred to, unless otherwise specified and in conflict with logic. The technical features in different embodiments, and in various methods / designs / implementation manners in each embodiment can be combined to form new embodiments, methods, or implementation manners according to their inherent logical relationship. The implementation manners of the present application described below do not constitute a limitation on the protection scope of the present application.

[0172] The present application can be applied to a long term evolution (LTE) system, a new radio (NR) system, or a future communication system. The communication system includes at least one network device and / or at least one terminal device.

[0173] Please refer to FIG. 1a, which is a schematic diagram of a communication system in the present application. In FIG. 1a, one network device and six terminal devices are exemplarily shown, and the six terminal devices are terminal device 1, terminal device 2, terminal device 3, terminal device 4, terminal device 5, and terminal device 6. In the example shown in FIG. 1a, the terminal device 1 is exemplarily taken as a smart tea cup, the terminal device 2 is exemplarily taken as a smart air conditioner, the terminal device 3 is exemplarily taken as a smart fuel dispenser, the terminal device 4 is exemplarily taken as a vehicle, the terminal device 5 is exemplarily taken as a mobile phone, and the terminal device 6 is exemplarily taken as a printer.

[0174] As shown in FIG. 1a, the AI configuration information sending entity can be a network device. The AI configuration information receiving entity can be the terminal device 1 to the terminal device 6. At this time, the network device and the terminal device 1 to the terminal device 6 form a communication system, in which the terminal device 1 to the terminal device 6 can send data to the network device, and the network device needs to receive the data sent by the terminal device 1 to the terminal device 6. At the same time, the network device can send configuration information to the terminal device 1 to the terminal device 6.

[0175] Exemplarily, in FIG. 1a, the terminal device 4 to the terminal device 6 can also form a communication system. Among them, the terminal device 5 acts as a network device, i.e., an AI configuration information sending entity; the terminal device 4 and the terminal device 6 act as terminal devices, i.e., AI configuration information receiving entities. For example, in a vehicle networking system, the terminal device 5 sends AI configuration information to the terminal device 4 and the terminal device 6, and receives the data sent by the terminal device 4 and the terminal device 6; correspondingly, the terminal device 4 and the terminal device 6 receive the AI configuration information sent by the terminal device 5, and send data to the terminal device 5.

[0176] Taking the communication system shown in FIG. 1a as an example, different devices (including network devices, network devices and terminal devices, and / or terminal devices and terminal devices) can perform AI-related services in addition to performing communication-related services.

[0177] As shown in FIG. 1b, taking a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services.

[0178] As shown in FIG. 1c, taking a terminal device including a television and a mobile phone as an example, the television and the mobile phone can also perform communication-related services and AI-related services.

[0179] The technical solutions provided in the present application can be applied to a wireless communication system (for example, the system shown in FIG. 1a, FIG. 1b or FIG. 1c), for example, an AI network element can be introduced in the communication system provided in the present application to implement part or all of the AI-related operations. The AI network element can also be referred to as an AI node, an AI device, an AI entity, an AI module, an AI model, or an AI unit, etc. The AI network element can be built-in in a network element of the communication system. For example, the AI network element can be an AI module built-in in an access network device, a core network device, a cloud server, or an operation, administration and maintenance (OAM), to implement AI-related functions. The OAM can be a core network device network management and / or an access network device network management. Alternatively, the AI network element can also be a network element independently arranged in the communication system. Optionally, the terminal or the chip built-in in the terminal can also include an AI entity for implementing AI-related functions.

[0180] Optionally, in the communication system, the AI application cases can include but are not limited to: channel status information (CSI) feedback enhancement, beam management enhancement, positioning accuracy enhancement, network energy saving, load balancing, and mobility optimization. The following will be described respectively.

[0181] 1. CSI feedback enhancement

[0182] CSI is the channel property of a communication link, and is the channel quality information reported by a terminal device to a network device. The terminal device reports the channel quality information to the network device, so as to select a suitable modulation and coding scheme (MCS) for the terminal device, so that the wireless channel can be adapted to the change. For example, the terminal device performs channel estimation according to the received channel state information-reference signal (CSI-RS), and then feeds back the channel quality information to the network device. The information is used as the input of the model of the network device, so that the network device can implement AI model training. By applying AI to CSI feedback enhancement, the overhead can be reduced, the accuracy can be improved, and prediction can be realized.

[0183] CSI-RS feedback enhancement can include at least one sub-function, such as CSI compression, CSI prediction, and CSI-RS configuration signaling reduction, respectively. The CSI compression can be further divided into CSI compression in at least one of the spatial domain, the time domain, and the frequency domain.

[0184] 2. Beam management enhancement

[0185] BM mainly aims to find the strongest transmit / receive beam pair. Based on AI-based sparse beam prediction, the accuracy can be improved. According to AI training and inference, AI sparse beam prediction on the network side and AI sparse beam prediction on the terminal device side can be divided. Taking AI sparse beam prediction on the terminal device side as an example, the pre-trained AI model on the terminal device side can be delivered by the network side or pre-stored on the terminal device side. In the training phase, the network device scans all possible beams, and then the network reports the transmit beam pattern to the terminal device. When the model training is completed, the network only needs to scan a small part of the beam, and then the terminal device feeds back the inference result to the network. Based on AI-based beam management, beam prediction in the time and / or spatial domain can be realized to reduce the overhead and delay and improve the beam selection accuracy.

[0186] Beam management enhancement can include at least one sub-function, such as beam scanning matrix prediction and optimal beam prediction.

[0187] 3. Positioning enhancement

[0188] In line of sight (LOS) or not line of sight (NLOS) scenarios, AI-based positioning can improve positioning accuracy with a smaller number of TRP antennas. Positioning enhancement can include at least one sub-function, such as: access network device-based positioning enhancement, positioning management function network element-based positioning enhancement, and terminal device-based positioning enhancement.

[0189] 4. Network energy saving

[0190] Network energy saving can be achieved through cell activation / deactivation, load reduction, improved coverage, or other RAN setting adjustments. AI technology can be used to optimize energy saving decisions by utilizing data collected in the RAN network. AI algorithms can predict the energy efficiency and load status of the next period, which can be used to assist in decision-making for cell activation / deactivation to save energy. Based on the predicted load, the system can dynamically configure energy saving strategies to maintain a balance between system performance and energy efficiency, and reduce energy consumption.

[0191] 5. Load balancing

[0192] Load balancing can evenly distribute load among cells and between areas within a cell, or divert some traffic from congested cells, or split users across cells, carriers, or access technologies to improve network performance. AI models can be used to improve load balancing performance, such as inputting various measurements and feedback from terminal devices and network nodes, historical data, etc. into AI models to improve load balancing performance, which can provide a higher quality user experience and improve system capacity.

[0193] 6. Mobility management

[0194] Mobility management is a solution to ensure service continuity during terminal device movement by minimizing dropped calls, radio link failures (RLF), unnecessary handovers, and ping-pong effects. AI can enhance mobility management, such as reducing the probability of unexpected events, predicting terminal device location / mobility / performance, and traffic steering, etc.

[0195] It should be understood that the definitions of the various technical terms described above are only examples. For example, as technology continues to evolve, the scope of the definitions described above can also change, and the embodiments of the present application are not limited.

[0196] For example, an AI function can include multiple AI sub-functions.

[0197] Optionally, AI application cases are also referred to as AI application scenarios or AI functions.

[0198] From the above description of the AI application cases, it can be seen that AI can be widely used in CSI feedback enhancement, beam management, positioning accuracy enhancement, energy saving, mobility enhancement, load balancing, and the like to improve network performance. The AI model can usually be deployed at the network side and / or the terminal device side, and the training of the AI model depends on the collection of training data, which can be derived from the measurement and feedback of the terminal device.

[0199] The artificial intelligence (AI) that can be involved in the present application will be briefly introduced below.

[0200] Artificial intelligence (AI) can enable a machine to have human intelligence, for example, the machine can apply the software and hardware of a computer to simulate certain intelligent behaviors of a human being. In order to realize artificial intelligence, a machine learning method can be used. In the machine learning method, the machine learns (or trains) a model using training data. The model represents the mapping between the input and the output. The learned model can be used for inference (or prediction), i.e., the model can be used to predict the output corresponding to a given input. The output can also be referred to as an inference result (or a prediction result).

[0201] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. The unsupervised learning can also be referred to as non-supervised learning.

[0202] Supervised learning learns the mapping relationship from sample values to sample labels using a machine learning algorithm according to the sample values and sample labels that have been collected, and uses an AI model to express the learned mapping relationship. The process of training a machine learning model is the process of learning such a mapping relationship. In the training process, the sample values are input into the model to obtain the predicted values of the model, and the model parameters are optimized by calculating the error between the predicted values of the model and the sample labels (ideal values). After the mapping relationship is learned, the learned mapping can be used to predict new sample labels. The mapping relationship learned by supervised learning can include linear mapping or nonlinear mapping. According to the type of label, the learned task can be divided into classification tasks and regression tasks.

[0203] Unsupervised learning uses algorithms to discover the internal patterns of samples according to the collected sample values. In unsupervised learning, a class of algorithms uses the sample itself as a supervision signal, i.e., the model learns the mapping relationship from the sample to the sample, which is called self-supervised learning. In the training process, the model parameters are optimized by calculating the error between the predicted values of the model and the sample itself. Self-supervised learning can be used for signal compression and decompression recovery applications, and common algorithms include autoencoders and generative adversarial networks.

[0204] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and a better (e.g., optimal) decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0205] Neural networks (NNs) are a specific model in machine learning techniques. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0206] The idea behind neural networks comes from the neuronal structure of the brain. For example, each neuron performs a weighted summation of its input values ​​and outputs the result through an activation function.

[0207] Figure 1d shows a schematic diagram of a neuron structure. Assume the neuron's input is x = [x0, x1, ..., x...]. n The weights corresponding to each input are w = [w0, w1, ..., w] n ], where n is a positive integer, w i and x i It can be any possible type, such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. i As x i The weights are used to assign weights to x. i Weighting is applied. The bias for the weighted sum of the input values ​​is, for example, b. Activation functions can take many forms. Suppose the activation function of a neuron is: y = f(z) = max(0, z), then the output of that neuron is: For example, if the activation function of a neuron is y = f(z) = z, then the output of that neuron is: where b can be various possible types such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number.

[0208] In addition, a neural network generally includes multiple layers, and each layer can include one or more neurons. By increasing the depth and / or width of the neural network, the expressiveness of the neural network can be improved, providing a more powerful information extraction and abstract modeling capability for complex systems. The depth of a neural network can refer to the number of layers included in the neural network, and the number of neurons included in each layer can be referred to as the width of the layer. In one implementation, a neural network includes an input layer and an output layer. The input layer of the neural network processes received input information through neurons and transmits the processing result to the output layer, and the output layer obtains the output result of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. The input layer of the neural network processes received input information through neurons and transmits the processing result to the intermediate hidden layer, the hidden layer calculates the received processing result to obtain a calculation result, the hidden layer transmits the calculation result to the output layer or the next adjacent hidden layer, and finally the output layer obtains the output result of the neural network. The neural network can include one hidden layer or multiple sequentially connected hidden layers, without limitation.

[0209] The neural network can be, for example, a deep neural network (DNN). According to the construction manner of the network, the DNN can include a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN).

[0210] FIG. 1e is a schematic diagram of an FNN network. The FNN network is characterized in that the neurons of adjacent layers are completely connected two by two. This characteristic makes the FNN usually require a large amount of storage space and lead to high computational complexity.

[0211] The CNN is a neural network specially designed to process data with a similar grid structure. For example, time series data (discrete sampling on the time axis) and image data (two-dimensional discrete sampling) can be considered as data with a similar grid structure. Instead of using all input information at once for operation, the CNN uses a fixed-size window to extract part of the information for convolution operation, which greatly reduces the calculation amount of model parameters. In addition, according to the different types of information extracted by the window (such as people and objects in the same image), each window can use different convolution kernels for operation, which enables the CNN to better extract the features of the input data.

[0212] RNN is a kind of DNN network using feedback time series information. Its input includes new input value at current time and its own output value at previous time. RNN is suitable for obtaining sequence features with correlation in time, and is particularly suitable for speech recognition, channel coding and decoding and other applications.

[0213] In the above model training process of machine learning, a loss function can be defined. The loss function describes the gap or difference between the output value of the model and the ideal target value. The loss function can be embodied in various forms, and the specific form of the loss function is not limited. The model training process can be regarded as the following process: by adjusting part or all of the parameters of the model, the value of the loss function is less than the threshold value or meets the target demand.

[0214] The model can also be referred to as an AI model, a rule or other names. The AI model can be considered as a specific method to realize AI function. The AI model represents the mapping relationship or function between the input and output of the model. The AI function can include one or more of the following: data collection, model training (or model learning), model information publishing, model inference (or model reasoning, reasoning, or prediction, etc.), model monitoring or model verification, or reasoning result publishing, etc. The AI function can also be referred to as AI (related) operation, or AI related function.

[0215] The implementation process of the fully connected neural network will be described below with reference to the accompanying drawings. The fully connected neural network is also called multilayer perceptron (MLP).

[0216] As shown in FIG. 2a, an MLP includes an input layer (left side), an output layer (right side), and multiple hidden layers (middle). Each layer of the MLP includes a plurality of nodes, which are called neurons. The neurons of adjacent two layers are connected to each other.

[0217] Optionally, considering the neurons of adjacent two layers, the output h of the neuron of the next layer is the weighted sum of all the neurons x of the previous layer connected to it and is subjected to an activation function, which can be expressed as: h = f (wx + b).

[0218] where w is a weight matrix, b is a bias vector, and f is an activation function.

[0219] Further optionally, the output of the neural network can be recursively expressed as: y = f n (w n f n-1 (…) + b n ).

[0220] wherein n is the index of the neural network layer, 1<=n<=N, wherein N is the total number of layers of the neural network.

[0221] In other words, the neural network can be understood as a mapping from a set of input data to a set of output data. Usually, the neural network is randomly initialized, and the process of obtaining this mapping from the random w and b using the existing data is called training of the neural network.

[0222] Optionally, the specific manner of training is to evaluate the output result of the neural network by using a loss function.

[0223] As shown in FIG. 2b, the error can be back-propagated, and the neural network parameters (including w and b) can be iteratively optimized by the gradient descent method until the loss function reaches the minimum value, i.e., the "better point (e.g., the optimal point)" in FIG. 2b. It can be understood that the neural network parameters corresponding to the "better point (e.g., the optimal point)" in FIG. 2b can be used as the neural network parameters in the trained AI model information.

[0224] Further optionally, the process of gradient descent can be represented as:

[0225] wherein θ is the parameter to be optimized (including w and b), L is the loss function, η is the learning rate, and controls the step size of gradient descent, represents the derivation operation, represents the derivative of L with respect to θ.

[0226] Further optionally, the process of back-propagation utilizes the chain rule of partial derivative.

[0227] As shown in FIG. 2c, the gradient of the parameters of the previous layer can be recursively calculated from the gradient of the parameters of the next layer, which can be expressed as:

[0228] wherein w ij is the weight of node j connected to node i, and s i is the input weighted sum on node i.

[0229] The technical solution provided in the present application can be applied to a wireless communication system (such as the system shown in FIG. 1a or FIG. 1b), in which the communication nodes generally have signal transceiving capability and computing capability. Taking a network device with computing capability as an example, the computing capability of the network device is mainly to provide computing power support for the signal transceiving capability (such as: to perform sending processing and receiving processing on the signal), so as to realize the communication task of the network device and other communication nodes.

[0230] With the development of communication technology, in a communication system, in addition to the traditional communication service, the service performed by the communication device can also include other new services, such as artificial intelligence (AI) services. Generally, a communication system capable of processing AI services can also be referred to as an AI system.

[0231] At present, a communication device can provide its computing power and data as a participating node of an AI system. For example, one communication device can perform model processing based on a model deployed by another communication device, that is, the one communication device can perform one or more model processing (such as model training, model updating, or model fine-tuning) processes on the model based on local data to obtain another model.

[0232] As an implementation example, taking a terminal device deploying a model as an example. Factors that affect the performance of the model can include:

[0233] Factor 1. Optimization and compilation of a chip manufacturer for a specific model (structure + parameters) for a chip environment.

[0234] Reason: The terminal device is limited in energy consumption and computing power, and needs to optimize and compile the model according to the chip software and hardware environment. The software and hardware environment of different chips is different, and accordingly, the optimization and compilation strategies are also different, which belongs to the implementation behavior of the terminal device.

[0235] Factor 2. Consistency of model training and inference.

[0236] Reason: The model is trained in scenario A and inferred in scenario A, and when scenario A changes, the performance of the model will decrease.

[0237] Based on the above factors, when the network device deploys a model to the terminal device, in order to improve the performance of the model, the network device needs to clearly identify the specific factors that affect the performance of the model, so as to formulate a correct model management strategy. For example, the network device transmits model parameters to the terminal device, and the terminal device uses the model. When the performance decreases, it can be caused by multiple factors. The specific factors need to be identified to formulate a correct model management strategy.

[0238] If the terminal device can execute correctly, the reason can be scenario change, and then the network device can update the model.

[0239] If the terminal device cannot execute correctly, the reason can be the optimization and compilation of the terminal device, which means that the terminal device does not have the ability to correctly execute the model, and then the network device can not use the model for this type of terminal device.

[0240] Currently, whether a terminal device has the capability to execute a certain model is generally obtained through RAN4 testing. In the RAN4 testing process, a tester tests an unshipped terminal device offline in a laboratory, which leads to a large consumption of manpower and material resources, and also leads to a low testing efficiency. In addition, a terminal device is shipped for sale after passing the RAN4 testing. If a new model (for example, new model parameters) is intended to be deployed for a certain terminal device, the new model can only be deployed for unshipped terminal devices and RAN4 testing is performed, while the new model cannot be deployed for terminal devices that have passed the RAN4 testing, which leads to that these terminal devices cannot keep up with the rapid pace of AI technology, and further affects user experience.

[0241] Therefore, how to improve the management efficiency of the model is a technical problem to be solved.

[0242] To solve the above problems, the present application provides a communication method and related apparatus, which will be described in detail below with reference to the accompanying drawings.

[0243] Please refer to FIG. 3a, which is an implementation schematic diagram of a communication method provided by the present application. The method includes the following steps.

[0244] It should be noted that in the following, in the implementation processes of FIG. 3a, FIG. 3b, FIG. 5a, FIG. 5b, etc., the first communication apparatus and other communication apparatuses (for example, the second communication apparatus) are taken as examples of the execution subject of the interaction schematic to illustrate the method, but the present application does not limit the execution subject of the interaction schematic. For example, the communication apparatus can be a communication device (for example, a terminal device or a network device), or a chip, a baseband chip, a modem chip, a system on chip (SoC) chip containing a modem core, a system in package (SIP) chip, a communication module, a chip system, a processor, a logic module or software in the communication device, etc.

[0245] S301. The second communication apparatus sends first information, and correspondingly, the first communication apparatus receives the first information. The first information is used to indicate first model parameters; the first model parameters are used to determine a first model.

[0246] S302. The second communication apparatus sends second information, and correspondingly, the first communication apparatus receives the second information. The second information is used to indicate input data; the input data and the first model are used to determine output data.

[0247] S303. The first communication device sends third information, and the second communication device receives the third information. The third information is used to determine whether the terminal device has the capability to perform model processing of the first model. The third information is determined based on the output data.

[0248] In this application, a model (e.g., the first model, or the second model mentioned later, etc.) can include an AI model, a neural network model, an AI neural network model, a machine learning model, or an AI processing model, etc. For example, the model can be used for CSI feedback enhancement, beam management, positioning accuracy enhancement, energy saving, mobility enhancement, and load balancing, etc. to improve network performance. For another example, the model can be used for other applications, such as transmission and / or enhancement of audio / video, data processing related to large language models, etc.

[0249] In this application, a model parameter can refer to a parameter between different neurons in a neural network. For example, the parameter can include a weight and / or a function, etc.

[0250] For example, a model can process input data to obtain output data, and the processing can include inference or prediction, etc.

[0251] Optionally, the input data can be replaced by other terms, such as model input, input data of the model, or input, etc.

[0252] Optionally, the output data can be replaced by other terms, such as model output, output data of the model, or output, etc.

[0253] It should be understood that the first information is used to indicate the first model parameter, which can be understood as that the first information contains the first model parameter, or the first information contains configuration information / configuration parameters used to generate the first model parameter.

[0254] It should be understood that the second information is used to indicate the input data, which can be understood as that the second information contains the input data, or the second information contains configuration information / configuration parameters used to generate the input data.

[0255] It should be noted that the first information and the second information can be carried in the same message / signaling / information (i.e., the information receiving processes of steps S301 and S302 can be implemented by one receiving process), or the first information and the second information can be carried in different messages / signaling / information (i.e., the information receiving processes of steps S301 and S302 can be implemented by two or more receiving processes), which is not limited here. For example, in the case that the first communication device is a terminal device and the second communication device is a network device, the message / signaling / information can be an RRC message, a MAC layer signaling (such as a medium access control control element (MAC CE)), a physical layer message (such as downlink control information (DCI)), or an application layer message / information, etc.

[0256] It should be noted that the third information is used to determine whether the terminal device has the capability to perform the model processing of the first model, which can be understood as that the third information is used to determine whether the terminal device has the capability to correctly perform the model processing of the first model.

[0257] For example, in the case that the terminal device is able to obtain output data based on input data of the first model, it indicates that the terminal device is able to run the first model, and therefore the third information is used to determine that the terminal device has the capability to perform the model processing of the first model.

[0258] For another example, in the case that the terminal device is unable to obtain output data based on input data of the first model, it indicates that the terminal device is unable to run the first model, and therefore the third information is used to determine that the terminal device does not have the capability to perform the model processing of the first model.

[0259] For another example, in the case that the terminal device is able to obtain output data based on input data of the first model, and the difference between the output data and the expected output corresponding to the input data is less than (or equal to) a threshold, it indicates that the terminal device is able to run the first model and the model performance obtained by running the first model is higher, and therefore the third information is used to determine that the terminal device has the capability to perform the model processing of the first model.

[0260] For another example, in the case that the terminal device is able to obtain output data based on input data of the first model, and the difference between the output data and the expected output corresponding to the input data is greater than (or equal to) a threshold, it indicates that the terminal device is able to run the first model but the model performance obtained by running the first model is lower, and therefore the third information is used to determine that the terminal device does not have the capability to perform the model processing of the first model.

[0261] Optionally, the difference between any two pieces of information (e.g., the difference between the output data and the expected output corresponding to the input data, the difference between the processing performance of a data set mentioned later and the processing performance of the second model on the data set, the difference between the first model parameter and the second model parameter mentioned later, etc.) can be represented by a mathematical calculation result of the two pieces of information. For example, the mathematical calculation result can include one or more of a difference value, a mean square error (MSE), a normalized mean square error (NMSE), or a cosine similarity.

[0262] Optionally, the third information is further used to indicate whether one or more terminal devices of the same type (or the same specification, or a similar type, or a similar specification, etc.) as the terminal device are capable of performing the model processing of the first model. In this way, the receiver of the third information can learn the capability of one or more terminal devices of the same type (or the same specification, or a similar type, or a similar specification, etc.) based on the third information, which can reduce the overhead and latency of capability verification of the terminal devices, and further improve the management efficiency of the model.

[0263] Optionally, one terminal device and another terminal device are of the same type (or the same specification, or a similar type, or a similar specification, etc.), including that the software parameters and / or hardware parameters of the one terminal device and the another terminal device are the same or similar.

[0264] For example, the software parameters can include a compilation file version number or a system version number, etc.

[0265] For another example, the hardware parameters can include a chip model or a device model, etc.

[0266] In a possible implementation, in step S303, the third information includes at least one of the following:

[0267] First indication information used to indicate the output data;

[0268] Second indication information used to indicate whether the terminal device has the capability of performing the model processing of the first model (or used to indicate whether the terminal device has the capability of correctly performing the model processing of the first model);

[0269] Third indication information used to indicate the difference between the output data and the expected output corresponding to the input data.

[0270] Thus, the third information can include the at least one item, so that a receiver of the third information can determine whether the terminal device has the capability of performing the model processing of the first model based on the at least one item, to improve the flexibility of the scheme implementation.

[0271] Based on the scheme shown in FIG. 3a, the first communication device can verify whether the terminal device has the capability of performing the model corresponding to the specific model parameter based on the specified input data, and indicate the verification result through the third information, so that the receiver of the third information knows the verification result. Since different model parameters can be used to determine different models (or different model functions), and the requirements of different models (or different model functions) for the running environment (such as the running software and hardware environment, the required computing power, or the required data, etc.) can be different. Therefore, in the above scheme, the first communication device can verify whether the terminal device has the capability of performing the model corresponding to the specific model parameter, and the verification result obtained in the verification process can be used as a basis for model deployment, to improve the management efficiency of the model.

[0272] In addition, compared with the offline verification mode of the model function (such as the verification mode of the radio access network (RAN4)), in the above scheme, the first communication device can verify whether the terminal device has the capability of performing the model corresponding to the specific model parameter through the online test mode, which can reduce the time delay of the model function verification and reduce the deployment period of the model, to improve the management efficiency of the model.

[0273] In a possible implementation, as shown in FIG. 3b, before step S303, the method further includes:

[0274] Step 3. The second communication device sends fourth indication information, and correspondingly, the first communication device receives the fourth indication information, the fourth indication information being used to indicate the first compiled file, the first compiled file and the first model parameter being used to determine the first model.

[0275] Specifically, the first communication device can also receive the fourth indication information, so that the first communication device determines the first model based on the compiled file specified by the fourth indication information and the first model parameter specified by the first information, to verify whether the terminal device has the capability of performing the model processing of the model corresponding to the specified compiled file.

[0276] It should be understood that in the processing of a model by a device, the device needs to perform specific optimization and compilation for different model structures, model parameters, and chip-specific software and hardware environments of the device to generate a compiled file. The device can use the compiled file to perform model inference of the model structure and corresponding model parameters. In this paper, the process of generating a compiled file after optimization and compilation is described as compilation. Generally, the compiled file generated for a specific model structure can be used for model inference of different model parameters under the model structure. If the compiled file is generated for a specific model structure and specific model parameters, there may be a certain loss of model performance when the compiled file is used for model inference of the specific model structure and other model parameters.

[0277] In the above scheme, the third information sent by the first communication device can be used to determine whether the terminal device has the capability to perform model processing of the first model, which is obtained by the specific compiled file (i.e., the first compiled file) and the specific model parameter (i.e., the first model parameter). In other words, the above scheme can verify whether the terminal device has the capability to perform the model corresponding to the specific compiled file and the specific model parameter.

[0278] In a possible implementation, as shown in FIG. 3b, before step 3, the method further includes:

[0279] Step 2. The first communication device sends fifth indication information, and the second communication device receives the fifth indication information. The fifth indication information is used to indicate one or more compiled files, and the one or more compiled files include the first compiled file.

[0280] Optionally, the fifth indication information is used to indicate that the terminal device has (or supports or stores) one or more compiled files. Specifically, the first communication device can also send the fifth indication information, so that the receiver (for example, the second communication device) of the fifth indication information can know that the terminal device has (or supports or stores) one or more compiled files based on the fifth indication information, so as to specify the first compiled file of the one or more compiled files to the first communication device, so that the terminal device can generate / determine / execute the first model based on the compiled file supported by itself.

[0281] It should be understood that, in the case that the first communication device is a terminal device and the second communication device is a network device, the fifth indication information can be reported through UE capability information, which can frequently change dynamically and reduce the management burden of the network device. Alternatively, in the case that the first communication device is a terminal device and the second communication device is a network device, the fifth indication information can be reported through user equipment assistance information (UE assistance information, UAI). Since different terminal devices can load different versions from the cloud (for example, a cloud server), the UAI reporting mode can reserve the freedom for the implementation of different terminal devices.

[0282] Optionally, the one or more compiled files can be globally unique. In the above process, since the receiving party specifies the first compiled file of the one or more compiled files to the first communication device, it can indicate the compiled file that the terminal device has supported (or has passed the verification), without the need for repeated verification, which can further reduce the overhead and latency.

[0283] Optionally, the one or more compiled files correspond to a first model structure; as shown in FIG. 3b, before step 2, the method further includes:

[0284] Step 1. The first communication device sends sixth indication information, and correspondingly, the second communication device receives the sixth indication information. Wherein, the sixth indication information indicates that the terminal device supports the first model structure. Specifically, the first communication device can also send the sixth indication information, so that the receiver (for example, the second communication device) of the sixth indication information can know the model structure supported by the terminal device based on the sixth indication information, and send first information indicating the first model parameter to the first communication device based on the supported model structure, so that the terminal device can generate / determine / execute the first model based on the model structure supported by itself.

[0285] In a possible implementation, as shown in FIG. 3b, after step S303, the method further includes:

[0286] Step 4. The second communication device sends seventh indication information, and the first communication device receives the seventh indication information. The seventh indication information is used to indicate that the terminal device has the capability of executing the model corresponding to the first model parameter. Specifically, after the first communication device sends the third information, the receiver of the third information can determine whether the terminal device has the capability of executing the first model based on the third information. Moreover, in a case where the receiver determines that the terminal device has the capability of executing the first model, the receiver can send seventh indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the seventh indication information, that is, the first communication device can explicitly know that the terminal device can be subsequently deployed with the first model, and that the terminal device has the capability of executing the first model.

[0287] In a possible implementation, after step S303, the method further includes:

[0288] Step 5. The first communication device sends eighth indication information, and the second communication device receives the eighth indication information. Alternatively, the second communication device sends eighth indication information, and the first communication device receives the eighth indication information. The eighth indication information is used to indicate whether one or more terminal devices of the same type as the terminal device can execute model processing of the first model. Specifically, the first communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the third information. Moreover, the first communication device can send eighth indication information to other devices (for example, an access network device, a core network device, or a terminal device, etc.), so that the receiver of the eighth indication information explicitly knows whether one or more terminal devices of the same type as the terminal device can be subsequently deployed with the first model, and whether the one or more terminal devices have the capability of executing the first model.

[0289] Alternatively, after the first communication device sends the third information, the receiver of the third information can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the third information. Moreover, the receiver can send eighth indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the eighth indication information, that is, the first communication device can explicitly know whether one or more terminal devices of the same type as the terminal device can be subsequently deployed with the first model, and whether the one or more terminal devices have the capability of executing the first model.

[0290] In a possible implementation of the method shown in FIG. 3a, the first communication device can be a terminal device or an internal module of the terminal device, or the first communication device can be a device associated with the terminal device or an internal module of the device associated with the terminal device. Correspondingly, in step S303, the first communication device sends the third information, including: the first communication device sends the third information to the access network device; or the first communication device sends the third information to the core network device through the access network device. Specifically, the first communication device can be a terminal device or a device associated with the terminal device, and correspondingly, the second communication device that provides the second information to the first communication device can be a network device (such as an access network device or a core network device), so that the first communication device realizes online verification of the capability of the terminal device through a communication process between the first communication device and the network device.

[0291] For example, as shown in FIG. 4a, taking the first communication device as a terminal device and the second communication device as an access network device as an example. Wherein, the terminal device and the access network device can interact the first information and the second information (which can be referred to the foregoing description) through steps A1 and A2 shown in FIG. 4a.

[0292] As an implementation example, in FIG. 4a, as the implementation process of mode one, the terminal device can send the third information to the access network device in step A3, that is, the receiving object of the third information can be the access network device, and the third information can be capability information or response information for the first information and / or the second information. In this case, the third information can include at least one of the first indication information, the second indication information, and the third indication information described above, so that the access network device can know whether the terminal device has the capability of performing the model processing of the first model through the third information. Optionally, in FIG. 4a, the access network device can also send the capability information to the core network device in step A4, the capability information is used to indicate whether the terminal device has the capability of performing the model processing of the first model. Thereafter, if the capability information indicates that the terminal device has the capability of performing the model processing of the first model, the core network device can notify one or more terminal devices of the same type as the terminal device of the capability information (which can be referred to the implementation process of the eighth indication information described above), so that the one or more access network devices subsequently perform model deployment (or deployment of model parameters, etc.) on the one or more terminal devices.

[0293] As another implementation example, in FIG. 4a, the terminal device can send the third information to the core network device through the access network device in step A5, i.e., the receiving object of the third information can be the core network device, and the third information can be the capability information. In this case, the third information can include the second indication information described above, so that the core network device can know whether the terminal device has the capability of performing the model processing of the first model through the third information. Similarly, if the third information indicates that the terminal device has the capability of performing the model processing of the first model, the core network device can notify one or more terminal devices of the same type as the terminal device of the capability information (for reference to the implementation process of the eighth indication information described above) so that the one or more access network devices subsequently perform model deployment (or deployment of model parameters, etc.) on the one or more terminal devices.

[0294] Optionally, since the second information is provided by the access network device, the core network device can confirm whether the terminal device has the above-mentioned capability without the expected output corresponding to the output data and the input data of the model, i.e., the third information in step A5 can not include the first indication information and / or the third indication information, so as to reduce the implementation complexity of the core network device.

[0295] Optionally, the second information can be provided by the core network device (or the access network device indicates the second information to the core network device), and the core network device can also confirm whether the terminal device has the above-mentioned capability through the expected output corresponding to the output data and the input data of the model, i.e., the third information in step A5 can include at least one of the first indication information, the second indication information, and the third indication information, so that the core network device can determine whether the terminal device has the above-mentioned capability based on the at least one.

[0296] In another possible implementation of the method shown in FIG. 3a, the first communication device can be the core network device or an internal module of the core network device. Accordingly, in step S303, the first communication device sends the third information, including: the first communication device sends the third information to the access network device. Specifically, the first communication device can be the core network device, and the second communication device providing the second information to the first communication device can be the access network device, so that the first communication device implements online verification of the capability of the terminal device through the communication process between the first communication device and the access network device.

[0297] For example, as shown in FIG. 4b, the first communication device can be a core network device, and the second communication device can be an access network device. The core network device and the access network device can interact with each other through steps B1, B2 and B3 shown in FIG. 4b to exchange the first information, the second information and the third information (which can be referred to the description above). Optionally, in FIG. 4b, after the access network device determines whether the terminal device has the capability of performing the model processing of the first model through the third information, if the third information indicates that the terminal device has the capability of performing the model processing of the first model, the access network device can notify the core network device of the information, so that the core network device further notifies one or more terminal devices of the same type as the terminal device of the capability information, so as to facilitate the one or more access network devices to perform model deployment (or deployment of model parameters, etc.) on the one or more terminal devices.

[0298] Referring to FIG. 5a, an implementation of a communication method provided by the present application is shown. The method includes the following steps.

[0299] S501. The second communication device sends fourth information, and the first communication device receives the fourth information. The fourth information is used to indicate first model parameters. The first model parameters are used to determine a first model.

[0300] S502. The first communication device sends fifth information, and the second communication device receives the fifth information. The fifth information is used to determine whether a terminal device has the capability of performing model processing of the first model. The terminal device has the capability of performing model processing of a second model. The fifth information is determined based on the first model and the second model.

[0301] Based on the scheme shown in FIG. 5a, the first communication device verifies whether the terminal device has the capability of performing the model corresponding to the specific model parameters based on the first model generated based on the specified model parameters and the second model that the terminal device has already been able to perform model processing, and indicates the verification result through the fifth information, so that the receiver of the fifth information knows the verification result. Since different model parameters can be used to determine different models (or different model functions), and different models (or different model functions) can have different requirements for the running environment (such as the running software and hardware environment, the required computing power, or the required data, etc.), the first communication device can verify whether the terminal device has the capability of performing the model corresponding to the specific model parameters in the above scheme. The verification result obtained in the verification process can be used as a basis for model deployment, so as to improve the management efficiency of the model.

[0302] In addition, compared with an offline verification manner of the model function (for example, a verification manner of a radio access network 4 (RAN4)), in the foregoing scheme, the first communication apparatus can verify whether the terminal device has the capability of performing the model corresponding to the specific model parameter through an online test manner, can reduce the latency of model function verification, and reduce the deployment period of the model, so as to improve the management efficiency of the model.

[0303] For example, the fifth information can include the second indication information described above, that is, the fifth information can be used to indicate whether the terminal device has the capability of performing the model processing of the first model, or the fifth information can be used to indicate whether the terminal device has the capability of correctly performing the model processing of the first model.

[0304] Optionally, the fifth information is also used to indicate whether one or more terminal devices of the same type (or the same specification, or a similar type, or a similar specification, etc.) as the terminal device can perform the model processing of the first model. In this way, the receiver of the fifth information can learn the capability of the one or more terminal devices of the same type (or the same specification, or a similar type, or a similar specification, etc.) based on the fifth information, can reduce the overhead and latency of capability verification of the terminal devices, and further improve the management efficiency of the model.

[0305] It should be noted that the fifth information is determined based on the first model and the second model, and the determination process can be implemented in various ways, which will be described below in conjunction with some examples.

[0306] In an implementation example one, the processing of the first model includes one or more first processes, the processing of the second model includes one or more second processes, and the correlation information of the one or more first processes and the one or more second processes is used to determine the fifth information.

[0307] Optionally, the first process or the second process can include one or more of quantization, pruning, knowledge distillation, or a model compression method (or a model lightweight method, which can be implemented through a lightweight model architecture or a compact model design, etc.). In other words, the first communication apparatus can determine whether the terminal device has the capability of performing the model processing of the first model based on the correlation information between the one or more first processes included in the first model generated based on the specified model parameter and the one or more second processes included in the second model that the terminal device has already been able to perform the model processing. Thus, the first communication apparatus can determine whether the terminal device has the capability based on the similarity of the model processing included in the two models.

[0308] Optionally, the fifth information is used to determine whether the terminal device has the capability to perform the model processing of the first model corresponding to the first model parameter, including: in a case where the correlation indicated by the correlation information is greater than (or equal to) a threshold, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively small, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device can perform the model processing of the first model.

[0309] And / or, the fifth information is used to determine whether the terminal device has the capability to perform the model processing of the first model corresponding to the first model parameter, including: in a case where the correlation indicated by the correlation information is less than (or equal to) a threshold, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively large, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device cannot perform the model processing of the first model.

[0310] In implementation example II, the difference information between the processing performance of the first model on a data set and the processing performance of the second model on the data set is used to determine the fifth information.

[0311] In implementation example II, the first communication device can determine whether the terminal device has the capability to perform the model processing of the first model based on the processing performance of the first model generated based on the specified model parameter on a data set and the processing performance of the second model on the same data set on which the terminal device has been able to perform the model processing. Thus, the first communication device can determine whether the terminal device has the capability based on the similarity of the processing performance of the two models on the same data set.

[0312] Optionally, the fifth information is used to determine whether the terminal device can perform the model processing of the first model corresponding to the first model parameter, including: in a case where the difference indicated by the difference information is less than or equal to a threshold, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively small, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device can perform the model processing of the first model.

[0313] And / or, the fifth information is used to determine whether the terminal device can perform the model processing of the first model corresponding to the first model parameter, including: in a case where the difference indicated by the difference information is greater than a threshold, the first communication device can determine that the difference between the model processing of the first model and the model processing of the second model is relatively large, and for this purpose, the fifth information sent by the first communication device can be used to determine that the terminal device cannot perform the model processing of the first model.

[0314] In a possible implementation, the fourth information includes the first model parameter; or, the fourth information includes difference information of the first model parameter and the second model parameter; wherein the second model parameter is used to determine the second model. Specifically, the fourth information used to indicate the first model parameter can include the above-mentioned multiple manners, so as to improve the flexibility of the implementation of the scheme.

[0315] In a possible implementation, as shown in FIG. 5b, after step S502, the method further includes:

[0316] Step 6. The second communication device sends seventh indication information, and correspondingly, the first communication device receives the seventh indication information. The seventh indication information is used to indicate that the terminal device has the capability of executing the model corresponding to the first model parameter. Specifically, after the first communication device sends the fifth information, the receiver of the fifth information can determine whether the terminal device has the capability of executing the first model based on the fifth information. And in the case that the receiver determines that the terminal device has the capability of executing the first model, the receiver can send the seventh indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the seventh indication information, that is, the first communication device can explicitly deploy the first model to the terminal device in the future, and explicitly that the terminal device has the capability of executing the first model.

[0317] In a possible implementation, as shown in FIG. 5b, after step S502, the method further includes:

[0318] Step 7. The first communication device sends eighth indication information, and correspondingly, the second communication device receives the eighth indication information. Or, the second communication device sends the eighth indication information, and correspondingly, the first communication device receives the eighth indication information. The eighth indication information is used to indicate whether one or more terminal devices of the same type as the terminal device can execute the model processing of the first model. Specifically, the first communication device can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the fifth information. And the first communication device can send the eighth indication information to other devices (for example, an access network device, a core network device, or a terminal device, etc.), so that the receiver of the eighth indication information explicitly whether to deploy the first model to one or more terminal devices of the same type as the terminal device in the future, and explicitly whether the one or more terminal devices have the capability of executing the first model.

[0319] Or, after the first communication device sends the fifth information, the receiver of the fifth information can determine whether the terminal device has the capability of executing the model corresponding to the first model parameter based on the fifth information. And the receiver can send eighth indication information to the first communication device, so that the first communication device determines that the terminal device has the capability based on the eighth indication information, that is, the first communication device can determine whether the first model can be deployed to one or more terminal devices of the same type as the terminal device and whether the one or more terminal devices have the capability of executing the first model.

[0320] In a possible implementation, the first communication device can be a terminal device or an internal module of the terminal device, or the first communication device can be a device associated with the terminal device or an internal module of the device associated with the terminal device. Correspondingly, in step S502, the first communication device sends the fifth information, including: the first communication device sends the fifth information to the access network device; or the first communication device sends the fifth information to the core network device through the access network device. Specifically, the first communication device can be a terminal device or a device associated with the terminal device, and correspondingly, the second communication device that provides the fourth information to the first communication device can be a network device (such as an access network device or a core network device), so that the first communication device realizes online verification of the capability of the terminal device through a communication process between the first communication device and the network device.

[0321] For example, as shown in FIG. 6a, taking the first communication device as a terminal device and the second communication device as an access network device as an example. Wherein, the terminal device and the access network device can interact the fourth information and the fifth information (which can be referred to the foregoing description) through steps C1 and C2 shown in FIG. 6a.

[0322] As an implementation example, in FIG. 6a, as an implementation process of mode A, the terminal device can send the fifth information to the access network device in step C2, that is, the receiver of the fifth information can be the access network device, and the fifth information can be capability information or response information for the fourth information. In this case, the access network device can know whether the terminal device has the capability of executing model processing of the first model through the fifth information. Optionally, in FIG. 6a, the access network device can also send capability information to the core network device in step C3, the capability information is used to indicate whether the terminal device has the capability of executing model processing of the first model. Thereafter, if the capability information indicates that the terminal device has the capability of executing model processing of the first model, the core network device can notify one or more access network devices of the capability information of one or more terminal devices of the same type as the terminal device (which can be referred to the implementation process of the eighth indication information in the foregoing description), so as to facilitate the one or more access network devices to deploy the model (or deploy the model parameter, etc.) to the one or more terminal devices in the future.

[0323] As an implementation example, in FIG. 6a, the terminal device can send the fifth information through the access network device in step C4, i.e., the receiving object of the fifth information can be the access network device, and the fifth information can be the capability information. In this case, the access network device can learn whether the terminal device has the capability of performing the model processing of the first model through the fifth information. Optionally, in FIG. 6a, if the fifth information indicates that the terminal device has the capability of performing the model processing of the first model, the core network device can notify one or more access network devices of the capability information of one or more terminal devices of the same type as the terminal device (for reference to the implementation process of the eighth indication information described above), so as to facilitate the model deployment (or the deployment of model parameters, etc.) of the one or more terminal devices by the one or more access network devices subsequently.

[0324] In a possible implementation, the first communication device can be a core network device or an internal module of the core network device. Correspondingly, in step S502, the first communication device sends the fifth information, including: the first communication device sends the fifth information to the access network device. Specifically, the first communication device can be a core network device, and correspondingly, the second communication device providing the fourth information to the first communication device can be an access network device, so that the first communication device implements online verification of the capability of the terminal device through the communication process between the first communication device and the access network device.

[0325] For example, as shown in FIG. 6b, taking the first communication device as a core network device and the second communication device as an access network device as an example. Wherein, the core network device and the access network device can interact the fourth information and the fifth information through steps D1 and D2 shown in FIG. 6b (for reference to the description above). Optionally, in FIG. 6b, after the access network device determines whether the terminal device has the capability of performing the model processing of the first model through the fifth information, if the fifth information indicates that the terminal device has the capability of performing the model processing of the first model, the access network device can notify the core network device of the information, so that the core network device further notifies one or more access network devices of the capability information of one or more terminal devices of the same type as the terminal device, so as to facilitate the model deployment (or the deployment of model parameters, etc.) of the one or more terminal devices by the one or more access network devices subsequently.

[0326] Please refer to FIG. 7, the embodiment of the present application provides a communication device 700, which can realize the functions of the first communication device or the second communication device in the above-mentioned method embodiment, and thus can realize the beneficial effects possessed by the above-mentioned method embodiment. In the embodiment of the present application, the communication device 700 can be the first communication device (or the second communication device), or an integrated circuit or element etc. inside the first communication device (or the second communication device), such as a chip.

[0327] It should be noted that the transceiver unit 702 can include at least one sending unit and at least one receiving unit, respectively used for performing sending and receiving.

[0328] In a possible implementation, when the device 700 is used for executing the method performed by the first communication device in the above-mentioned method embodiment shown in FIG. 3a, the device 700 includes at least one processing unit 701 and at least one transceiver unit 702; the transceiver unit 702 is used for receiving first information, the first information being used for indicating first model parameters; wherein the first model parameters are used for determining a first model; the transceiver unit is also used for receiving second information, the second information being used for indicating input data; wherein the input data and the first model are used for determining output data; the processing unit 701 is used for determining third information; the transceiver unit 702 is also used for sending the third information, the third information being used for determining whether a terminal device has the capability of performing model processing of the first model; wherein the third information is determined based on the output data.

[0329] In a possible implementation, when the device 700 is used for executing the method performed by the second communication device in the above-mentioned method embodiment shown in FIG. 3a, the device 700 includes at least one processing unit 701 and at least one transceiver unit 702; the processing unit 701 is used for determining first information and second information; the transceiver unit 702 is used for sending the first information, the first information being used for indicating first model parameters; the first model parameters are used for determining a first model; the transceiver unit 702 is also used for sending the second information, the second information being used for indicating input data; wherein the input data and the first model are used for determining output data; the transceiver unit 702 is also used for receiving third information, the third information being used for determining whether a terminal device has the capability of performing model processing of the first model; wherein the third information is determined based on the output data.

[0330] In a possible implementation, when the apparatus 700 is configured to perform the method performed by the first communication device in the embodiment of the method shown in FIG. 6a, the apparatus 700 includes at least one processing unit 701 and at least one transceiver 702; the transceiver 702 is configured to receive fourth information, the fourth information being used to indicate a first model parameter; the first model parameter is used to determine a first model; the processing unit 701 is configured to determine fifth information; the transceiver 702 is further configured to send the fifth information, the fifth information being used to determine whether a terminal device has a capability of performing model processing of the first model; the terminal device has a capability of performing model processing of a second model, and the fifth information is determined based on the first model and the second model.

[0331] In a possible implementation, when the apparatus 700 is configured to perform the method performed by the second communication device in the embodiment of the method shown in FIG. 6a, the apparatus 700 includes at least one processing unit 701 and at least one transceiver 702; the processing unit 701 is configured to determine fourth information; the transceiver 702 is configured to send the fourth information, the fourth information being used to indicate a first model parameter; the first model parameter is used to determine a first model; the transceiver 702 is further configured to receive fifth information, the fifth information being used to determine whether a terminal device has a capability of performing model processing of the first model; the terminal device has a capability of performing model processing of a second model, and the fifth information is determined based on the first model and the second model.

[0332] It should be noted that the information execution process and the like of the units of the communication apparatus 700 are described in the foregoing method embodiments of the present application, and will not be described here.

[0333] FIG. 8 is another schematic structural diagram of a communication apparatus 800 provided in the present application, the communication apparatus 800 includes at least one logic circuit 801 and at least one input / output interface 802. The communication apparatus 800 can be a chip or an integrated circuit.

[0334] The transceiver 702 shown in FIG. 7 can be a communication interface, which can be the input / output interface 802 in FIG. 8. The input / output interface 802 can include an input interface and an output interface. Alternatively, the communication interface can be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0335] Optionally, the input / output interface 802 is used to receive first information, which indicates first model parameters; wherein the first model parameters are used to determine the first model; the input / output interface 802 is also used to receive second information, which indicates input data; wherein the input data and the first model are used to determine output data; the logic circuit 801 is used to determine third information; the input / output interface 802 is also used to send third information, which determines whether the terminal device has the capability to perform model processing of the first model; wherein the third information is determined based on the output data.

[0336] Optionally, the logic circuit 801 is used to determine first information and second information; the input / output interface 802 is used to send the first information, which indicates first model parameters; the first model parameters are used to determine the first model; the input / output interface 802 is also used to send the second information, which indicates input data; wherein the input data and the first model are used to determine output data; the input / output interface 802 is also used to receive third information, which determines whether the terminal device has the capability to perform model processing of the first model; wherein the third information is determined based on the output data.

[0337] Optionally, the input / output interface 802 is used to receive fourth information, which is used to indicate the first model parameters; wherein the first model parameters are used to determine the first model; the logic circuit 801 is used to determine fifth information; the input / output interface 802 is also used to send the fifth information, which is used to determine whether the terminal device has the ability to perform model processing of the first model; wherein the terminal device has the ability to perform model processing of the second model, and the fifth information is determined based on the first model and the second model.

[0338] Optionally, the logic circuit 801 is used to determine the fourth information; the input / output interface 802 is used to send the fourth information, which is used to indicate the first model parameters; wherein the first model parameters are used to determine the first model; the input / output interface 802 is also used to receive the fifth information, which is used to determine whether the terminal device has the ability to perform model processing of the first model; wherein the terminal device has the ability to perform model processing of the second model, and the fifth information is determined based on the first model and the second model.

[0339] The logic circuit 801 and the input / output interface 802 can also perform other steps performed by the first or second communication device in any embodiment and achieve corresponding beneficial effects, which will not be elaborated here.

[0340] In one possible implementation, the processing unit 701 shown in FIG7 can be the logic circuit 801 in FIG8.

[0341] Optionally, the logic circuit 801 can be a processing device, the functions of which can be partially or entirely implemented in software.

[0342] Optionally, the processing apparatus may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform the corresponding processing and / or steps in any of the method embodiments.

[0343] Optionally, the processing device may consist of only a processor. A memory for storing computer programs is located outside the processing device, and the processor is connected to the memory via circuitry / wires to read and execute the computer programs stored in the memory. The memory and processor may be integrated together or physically independent of each other.

[0344] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), central processing units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0345] Please refer to Figure 9, which shows the communication device 900 involved in the above embodiments provided in the embodiments of this application. Specifically, the communication device 900 can be the communication device as a terminal device in the above embodiments. The communication device shown in Figure 9 is implemented through a terminal device (or a component in the terminal device).

[0346] The present invention provides a possible logical structure diagram of the communication device 900, which may include, but is not limited to, at least one processor 901 and at least one communication port 902.

[0347] In Figure 7, the transceiver unit 702 can be a communication interface, which can be the communication port 902 in Figure 9. The communication port 902 can include an input interface and an output interface. Alternatively, the communication port 902 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0348] Further optionally, the device may also include at least one of a memory 903 and a bus 904. In the embodiments of this application, the at least one processor 901 is used to control the operation of the communication device 900.

[0349] Furthermore, the processor 901 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, etc. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0350] It should be noted that the communication device 900 shown in Figure 9 can be used to implement the steps implemented by the terminal device in the aforementioned method embodiments and to achieve the corresponding technical effects of the terminal device. The specific implementation of the communication device shown in Figure 9 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0351] Please refer to Figure 10, which is a schematic diagram of the structure of the communication device 1000 involved in the above embodiments provided in the embodiments of this application. The communication device 1000 can specifically be a communication device as a network device in the above embodiments. The communication device shown in Figure 10 is implemented through a network device (or a component in a network device). The structure of the communication device can refer to the structure shown in Figure 10.

[0352] The communication device 1000 includes at least one processor 1011 and at least one network interface 1014. Optionally, the communication device further includes at least one memory 1012, at least one transceiver 1013, and one or more antennas 1015. The processor 1011, memory 1012, transceiver 1013, and network interface 1014 are connected, for example, via a bus. In this embodiment, the connection may include various interfaces, transmission lines, or buses, etc., and this embodiment is not limited thereto. The antenna 1015 is connected to the transceiver 1013. The network interface 1014 enables the communication device to communicate with other communication devices through a communication link. For example, the network interface 1014 may include a network interface between the communication device and core network equipment, such as an S1 interface; the network interface may also include a network interface between the communication device and other communication devices (e.g., other network devices or core network equipment), such as an X2 or Xn interface.

[0353] In this context, the transceiver unit 702 shown in Figure 7 can be a communication interface, which can be the network interface 1014 in Figure 10. The network interface 1014 can include an input interface and an output interface. Alternatively, the network interface 1014 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0354] The processor 1011 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process data from these programs, for example, to support the actions described in the embodiments of the communication device. The communication device may include a baseband processor and a central processing unit (CPU). The baseband processor is primarily used to process communication protocols and communication data, while the CPU is primarily used to control the entire terminal device, execute software programs, and process data from these programs. The processor 1011 in Figure 10 can integrate the functions of both a baseband processor and a CPU. Those skilled in the art will understand that the baseband processor and CPU can also be independent processors interconnected via technologies such as buses. Those skilled in the art will understand that a terminal device can include multiple baseband processors to adapt to different network standards, and multiple CPUs to enhance its processing capabilities. Various components of the terminal device can be connected via various buses. The baseband processor can also be described as a baseband processing circuit or a baseband processing chip. The CPU can also be described as a central processing circuit or a central processing chip. The function of processing communication protocols and communication data can be built into the processor or stored in memory as a software program, which is then executed by the processor to implement the baseband processing function.

[0355] The memory is primarily used to store software programs and data. The memory 1012 can exist independently or be connected to the processor 1011. Optionally, the memory 1012 can be integrated with the processor 1011, for example, integrated within a single chip. The memory 1012 can store program code that executes the technical solutions of the embodiments of this application, and its execution is controlled by the processor 1011. The various types of computer program code being executed can also be considered as drivers for the processor 1011.

[0356] Figure 10 shows only one memory and one processor. In actual terminal devices, there may be multiple processors and multiple memories. Memory can also be called storage medium or storage device, etc. Memory can be a storage element on the same chip as the processor, i.e., an on-chip storage element, or it can be a separate storage element; this application does not limit this.

[0357] Transceiver 1013 can be used to support the reception or transmission of radio frequency (RF) signals between a communication device and a terminal. Transceiver 1013 can be connected to antenna 1015. Transceiver 1013 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1015 can receive RF signals. The receiver Rx of transceiver 1013 is used to receive the RF signals from the antennas, convert the RF signals into digital baseband signals or digital intermediate frequency (IF) signals, and provide the digital baseband signals or IF signals to processor 1011 so that processor 1011 can perform further processing on the digital baseband signals or IF signals, such as demodulation and decoding. In addition, the transmitter Tx in transceiver 1013 is also used to receive modulated digital baseband signals or IF signals from processor 1011, convert the modulated digital baseband signals or IF signals into RF signals, and transmit the RF signals through one or more antennas 1015. Specifically, the receiver Rx can selectively perform one or more stages of downmixing and analog-to-digital conversion on the radio frequency signal to obtain a digital baseband signal or a digital intermediate frequency (IF) signal. The order of these downmixing and IF conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of upmixing and digital-to-analog conversion on the modulated digital baseband signal or digital IF signal to obtain a radio frequency signal. The order of these upmixing and IF conversion processes is also adjustable. The digital baseband signal and the digital IF signal can be collectively referred to as digital signals.

[0358] The transceiver 1013 can also be called a transceiver unit, transceiver, transceiver device, etc. Optionally, the device in the transceiver unit that performs the receiving function can be regarded as the receiving unit, and the device in the transceiver unit that performs the transmitting function can be regarded as the transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit can also be called a receiver, input port, receiving circuit, etc., and the transmitting unit can be called a transmitter, transmitter, or transmitting circuit, etc.

[0359] It should be noted that the communication device 1000 shown in Figure 10 can be used to implement the steps implemented by the network device in the aforementioned method embodiments and to achieve the corresponding technical effects of the network device. The specific implementation of the communication device 1000 shown in Figure 10 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0360] Please refer to Figure 11, which is a schematic diagram of the structure of the communication device involved in the above embodiments provided in the embodiments of this application.

[0361] It is understood that the communication device 110 includes, for example, modules, units, elements, circuits, or interfaces, which are appropriately configured together to execute the technical solutions provided in this application. The communication device 110 may be the terminal device or network device described above, or a component (e.g., a chip) within these devices, used to implement the methods described in the following method embodiments. The communication device 110 includes one or more processors 111. The processor 111 may be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (e.g., a RAN node, terminal, or chip), execute software programs, and process data from the software programs.

[0362] Optionally, in one design, the processor 111 may include a program 113 (sometimes also referred to as code or instructions) that can be executed on the processor 111 to cause the communication device 110 to perform the methods described in the embodiments below. In yet another possible design, the communication device 110 includes circuitry (not shown in FIG11).

[0363] Optionally, the communication device 110 may include one or more memories 112 storing a program 114 (sometimes referred to as code or instructions), which can be run on the processor 111 to cause the communication device 110 to perform the methods described in the above method embodiments.

[0364] Optionally, the processor 111 and / or memory 112 may include AI modules 117 and 118, which are used to implement AI-related functions. The AI ​​modules can be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a radio intelligence control (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0365] Optionally, the processor 111 and / or memory 112 may also store data. The processor and memory may be configured separately or integrated together.

[0366] Optionally, the communication device 110 may further include a transceiver 115 and / or an antenna 116. The processor 111, sometimes referred to as a processing unit, controls the communication device (e.g., a RAN node or terminal). The transceiver 115, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, is used to realize the transmission and reception functions of the communication device through the antenna 116.

[0367] In this context, the processing unit 701 shown in Figure 7 can be a processor 111. The transceiver unit 702 shown in Figure 7 can be a communication interface, which can be the transceiver 115 in Figure 11. The transceiver 115 can include an input interface and an output interface. Alternatively, the transceiver 115 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0368] This application also provides a computer-readable storage medium for storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor performs the method described in the possible implementations of the first or second communication device in the foregoing embodiments.

[0369] This application also provides a computer program product (or computer program) that, when executed by a processor, executes the method described above for the possible implementation of the first or second communication device.

[0370] This application also provides a chip system including at least one processor for supporting a communication device in implementing the functions involved in the possible implementations of the communication device described above. Optionally, the chip system further includes an interface circuit that provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory for storing the program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices, wherein the communication device may specifically be the first communication device or the second communication device in the aforementioned method embodiments.

[0371] This application also provides a communication system, the network system architecture of which includes a first communication device and a second communication device in any of the above embodiments.

[0372] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0373] The units described as separate components may or may not be physically separate. 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0374] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A communication method, characterized in that, include: Receive first information, the first information being used to indicate first model parameters; wherein, the first model parameters are used to determine the first model; Receive second information, which is used to indicate input data; wherein, the input data and the first model are used to determine output data; Send a third piece of information, which is used to determine whether the terminal device has the ability to perform model processing of the first model; wherein the third piece of information is determined based on the output data.

2. The method according to claim 1, characterized in that, The third information includes at least one of the following: The first indication information is used to indicate the output data; The second indication information is used to indicate whether the terminal device has the ability to perform model processing of the first model; The third indication information is used to indicate the difference between the output data and the expected output corresponding to the input data.

3. The method according to claim 1 or 2, characterized in that, The method further includes: A fourth instruction is received, which is used to instruct a first compiled file, and the first compiled file and the first model parameters are used to determine the first model.

4. The method according to claim 3, characterized in that, The method further includes: Send a fifth instruction message, which is used to instruct one or more compiled files, including the first compiled file.

5. The method according to claim 4, characterized in that, The model structure corresponding to the one or more compiled files is the first model structure; the method further includes: A sixth instruction message is sent, which instructs the terminal device to support the first model structure.

6. A communication method, characterized in that, include: Send a first message, the first message being used to indicate a first model parameter; wherein, the first model parameter is used to determine the first model; Send a second message, which is used to indicate input data; wherein the input data and the first model are used to determine the output data; Receive third information, the third information being used to determine whether the terminal device has the capability to perform model processing of the first model; wherein, the third information is determined based on the output data.

7. The method according to claim 6, characterized in that, The third information includes at least one of the following: The first indication information is used to indicate the output data; The second indication information is used to indicate whether the terminal device has the ability to perform model processing of the first model; The third indication information is used to indicate the difference between the output data and the expected output corresponding to the input data.

8. The method according to claim 6 or 7, characterized in that, The method further includes: Send a fourth instruction message, which is used to instruct the first compilation file, and the first compilation file and the first model parameters are used to determine the first model.

9. The method according to claim 8, characterized in that, The method further includes: Receive a fifth instruction message, the fifth instruction message being used to indicate one or more compiled files, the one or more compiled files including the first compiled file.

10. The method according to claim 9, characterized in that, The model structure corresponding to the one or more compiled files is the first model structure; the method further includes: The sixth instruction information is received, which indicates that the terminal device supports the first model structure.

11. A communication method, characterized in that, include: Receive fourth information, the fourth information being used to indicate first model parameters; wherein, the first model parameters are used to determine the first model; A fifth message is sent, which is used to determine whether the terminal device has the ability to perform model processing of the first model; wherein the terminal device has the ability to perform model processing of the second model, and the fifth message is determined based on the first model and the second model.

12. The method according to claim 11, characterized in that, The processing of the first model includes one or more first processes, and the processing of the second model includes one or more second processes. The correlation information between the one or more first processes and the one or more second processes is used to determine the fifth information.

13. The method according to claim 12, characterized in that, The first or second processing includes at least one of the following: quantization, pruning, knowledge distillation, or model compression methods.

14. The method according to claim 11, characterized in that, The difference between the processing performance of the first model on a dataset and the processing performance of the second model on the same dataset is used to determine the fifth information.

15. The method according to any one of claims 11 to 14, characterized in that, The fourth information includes the first model parameters; or, The fourth information includes the difference information between the first model parameters and the second model parameters; wherein, the second model parameters are used to determine the second model.

16. A communication method, characterized in that, include: Send a fourth message, the fourth message being used to indicate the first model parameters; wherein, the first model parameters are used to determine the first model; The fifth information is received, which is used to determine whether the terminal device has the ability to perform model processing of the first model; wherein the terminal device has the ability to perform model processing of the second model, and the fifth information is determined based on the first model and the second model.

17. The method according to claim 16, characterized in that, The processing of the first model includes one or more first processes, and the processing of the second model includes one or more second processes. The correlation information between the one or more first processes and the one or more second processes is used to determine the fifth information.

18. The method according to claim 17, characterized in that, The first or second processing includes at least one of the following: quantization, pruning, knowledge distillation, or model compression methods.

19. The method according to claim 16, characterized in that, The difference between the processing performance of the first model on a dataset and the processing performance of the second model on the same dataset is used to determine the fifth information.

20. The method according to any one of claims 16 to 19, characterized in that, The fourth information includes the first model parameters; or, The fourth information includes the difference information between the first model parameters and the second model parameters; wherein, the second model parameters are used to determine the second model.

21. A communication device, characterized in that, It includes at least one processor; the at least one processor is coupled to at least one memory; the at least one processor is used to perform the method as described in any one of claims 1 to 20.

22. A chip or chip system, characterized in that, It includes at least one processor, said at least one processor being used to implement the method as claimed in any one of claims 1 to 20.

23. A readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method as described in any one of claims 1 to 20.

24. A computer program product, characterized in that, It includes a computer program or instructions that, when executed by a communication device, implement the method as described in any one of claims 1 to 20.

Images