Communication method, apparatus, medium, and computer program product

Abstract

The present application discloses a communication method, an apparatus, a medium, and a computer program product. In the method, a first communication apparatus sends first information, wherein the first information is used for indicating a target model, the first information comprises first sub-information and second sub-information, the first sub-information is used for indicating an input parameter type of the target model, and the second sub-information is used for indicating an output parameter type of the target model; and the first communication apparatus receives second information, wherein the second information is used for indicating a model parameter of the target model. On the basis of the solution, the first communication apparatus may notify, by means of the first information, the second communication apparatus of the type of the target model that needs to be obtained, so that the second communication apparatus can determine a model training requirement of the first communication apparatus, and train, on the basis of the type of the target model, the target model required by the first communication apparatus, thereby meeting training requirements of the first communication apparatus for various models such as a custom model.

Description

A communication method, apparatus, medium, and computer program product

[0001] This application claims priority to Chinese Patent Application No. 202510241301.1, filed with the State Intellectual Property Office of China on February 28, 2025, entitled "A Communication Method, Apparatus, Medium and Computer Program Product", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, specifically to a communication method, device, medium, and computer program product. Background Technology

[0003] With the rapid development of deep learning technology, more and more communication devices need to rely on models to analyze and process data. In the field of communication, due to limitations in cost and size, terminal devices often have limited computing power, making it difficult to meet the needs of services such as model training. On the other hand, network devices can provide increasingly powerful computing capabilities. Therefore, when terminal devices require model training, network devices can assist in the model training process and then transmit the trained model to the terminal devices.

[0004] However, current network devices can typically only help terminal devices train fixed types of models, which means they cannot meet the training needs of terminal devices for models other than fixed types. Summary of the Invention

[0005] This application provides a communication method, device, medium, and computer program product, with the aim of improving the flexibility of model training.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] The first aspect of this application provides a communication method that can be applied to a first communication device. For example, the first communication device may be a communication equipment (such as a terminal device), or it may be a component of a communication equipment (such as a processor, circuit, chip, or chip system responsible for communication functions), or it may be a logic module or software capable of implementing all or part of the functions of the communication equipment. The following description uses a first communication device as an example. In this method, the first communication device sends first information, which indicates a target model. The first information includes first sub-information and second sub-information. The first sub-information indicates the input parameter type of the target model, and the second sub-information indicates the output parameter type of the target model. The first communication device receives second information, which indicates the model parameters of the target model.

[0008] Based on the above scheme, the first communication device can inform the second communication device of the type of the target model to be acquired through the first information. Specifically, the first and second sub-informations in the first information can be used to inform the second communication device of the input parameter type and output parameter type of the target model to be acquired. This allows the second communication device to clearly understand the model training requirements of the first communication device and train the target model required by the first communication device based on the type of the target model. This enables the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training requirements of the first communication device for various models, including custom models.

[0009] In one possible implementation of the first aspect, the first sub-information includes a list of input parameter types of the target model, and the second sub-information includes a list of output parameter types of the target model.

[0010] Based on the above scheme, the first information sent by the first communication device may specifically include a list of input parameter types of the target model, enabling the second communication device to determine one or more input parameter types of the target model to be trained based on the first sub-information. Similarly, the second sub-information sent by the first communication device may specifically include a list of output parameter types of the target model, enabling the second communication device to determine one or more output parameter types of the target model to be trained based on the second sub-information. This allows the second communication device to determine the specific type of the target model based on the input and output parameter types, and train the target model required by the first communication device based on the specific type of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0011] In one possible implementation of the first aspect, the first information is carried in the training data of the target model.

[0012] Based on the above scheme, the first information sent by the first communication device to indicate the target model can be carried in the training data of the target model. That is, the first communication device can send the training data of the target model carrying the first information so that the second communication device can extract or parse the first information from the training data of the target model. This allows the second communication device to clarify the model training requirements of the first communication device based on the first information and train the target model required by the first communication device based on the type of the target model. This enables the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training requirements of the first communication device for various models, including custom models.

[0013] In one possible implementation of the first aspect, sending the first information includes: sending a first message, the first message including the first information, the first message being used to request the acquisition of the target model.

[0014] Based on the above scheme, the first communication device can send first information based on a first message used to request the acquisition of the target model. That is, the first message can carry the first information, meaning the first information can be sent simultaneously with the first message, further saving transmission resources. Furthermore, the second communication device can acquire the first information upon receiving the first message, thereby enabling the second communication device to clarify the model training requirements of the first communication device based on the first information, and train the target model required by the first communication device based on the type of the target model. This allows the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thus satisfying the first communication device's training needs for various models, including custom models.

[0015] In one possible implementation of the first aspect, the first message includes training data of the target model, or the method further includes sending a second message for sending training data of the target model.

[0016] Based on the above scheme, the first communication device can also send the training data required for training the target model based on the first message, or it can also send the training data of the target model based on the second message, so that the second communication device can obtain the training data of the target model based on the first message or the second message, and train the target model required by the first communication device based on the training data of the target model, thereby completing the training of various models entrusted by the first communication device, including custom models, and thus meeting the training needs of the first communication device for various models such as custom models.

[0017] In one possible implementation of the first aspect, sending the first information includes: sending a first message for requesting the acquisition of the target model; and sending a second message for sending the training data of the target model, the second message including the first information.

[0018] Based on the above scheme, the first communication device can first send a first message to request the acquisition of the target model to inform the second communication device that the target model needs to be trained. Then, based on the second message, the first information and the training data of the target model can be sent to the second communication device. This allows the second communication device to understand the model training requirements of the first communication device based on the first information, and to train the target model required by the first communication device based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training requirements of the first communication device for various models, including custom models.

[0019] In one possible implementation of the first aspect, the difference between the sending time of the first message and the sending time of the second message is less than a first threshold.

[0020] Based on the above scheme, the first communication device can send the first message and the second message sequentially, and the difference between the sending time of the first message and the second message can be less than the first threshold. That is, the interval between the sending time of the first message and the second message can be within a certain range, so that the second communication device can determine the association between the first message and the second message. In other words, it can determine that the training data of the target model carried in the second message is used to train the target model requested by the first message, thereby completing the training of multiple models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for multiple models, including custom models.

[0021] In one possible implementation of the first aspect, the first message includes first identification information, and the second message includes the first identification information.

[0022] Based on the above scheme, the first communication device can send a first message and a second message sequentially, and both the first message and the second message can carry the first identification information, that is, the first message and the second message can carry the same identification information, so that the second communication device can determine the association between the first message and the second message, that is, determine that the training data of the target model carried in the second message is used to train the target model requested by the first message, thereby completing the training of multiple models entrusted by the first communication device, including custom models, and thus meeting the training needs of the first communication device for multiple models such as custom models.

[0023] In one possible implementation of the first aspect, the training data of the target model includes a first information element and a second information element, wherein the first information element includes input data in the training data and the second information element includes output data in the training data.

[0024] Based on the above scheme, the training data of the target model sent by the first communication device can be composed of a first information element and a second information element. The first information element can include the input data in the training data, and the second information element can include the output data in the training data. That is, the input data and output data in the training data can be sent to the second communication device through two different information elements, so that the second communication device can better extract the first information from the training data of the target model, or can better distinguish the input data or output data in the training data, so as to train the target model required by the first communication device based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, and thus meet the training needs of the first communication device for various models, including custom models.

[0025] In one possible implementation of the first aspect, the training data of the target model includes multiple information elements, which include one or more input data and one or more output data of the training data.

[0026] Based on the above scheme, the training data of the target model sent by the first communication device can be composed of multiple information elements, each of which can carry one or more input data and one or more output data of the training data. That is, one or more complete data, including both input and output data, can be carried in the same information element for transmission. This allows the second communication device to better extract the first information from the training data of the target model, or to better identify the complete data in the training data. This enables the first communication device to train the target model required by the first communication device based on the training data of the target model, thereby completing the training of various models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for various models, including custom models.

[0027] In one possible implementation of the first aspect, the method further includes: receiving a third message, the third message being used to indicate that the first message has been received.

[0028] Based on the above scheme, if the first communication device sends a first message to the second communication device requesting the acquisition of the target model, and the second communication device needs a certain amount of time to train the target model, there may be a situation where the first communication device does not receive a reply from the second communication device after sending the first message. In this case, the first communication device may mistakenly believe that the first message was not successfully sent and may retransmit the first message, resulting in wasted resources. Therefore, after sending the first message, the first communication device can receive a third message from the second communication device to indicate that the first message has been received, thereby avoiding the first communication device mistakenly believing that the first message was not successfully sent and retransmitting the message, further saving transmission resources.

[0029] In one possible implementation of the first aspect, the third message includes at least one of the expected acquisition time of the target model or the identification information of the target model.

[0030] Based on the above scheme, the third message received by the first communication device may also carry the expected acquisition time of the target model and / or the identification information of the target model, so that the first communication device can also determine how long it will take to acquire the target model based on the third message, and / or determine the expected acquisition time and the specific association between the third message and the target model based on the identification information of the target model carried in the third message.

[0031] In one possible implementation of the first aspect, receiving the second information includes receiving a fourth message, the fourth message including the second information and the identification information of the target model.

[0032] Based on the above scheme, the first communication device can obtain the second information for indicating the model parameters of the target model and the identification information of the target model based on the fourth message. That is, after the second communication device trains the target model, it can send the second information for indicating the model parameters of the target model and the identification information of the target model to the first communication device based on the fourth message. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0033] In one possible implementation of the first aspect, if the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

[0034] Based on the above scheme, if the target model requested by the first communication device is used to replace the existing first model in the first communication device, the fourth message used to transmit the second information may also carry the identification information of the first model, so that the first communication device can determine that the target model is used to replace the existing first model in the first communication device, and can replace the first model with the obtained target model.

[0035] In one possible implementation of the first aspect, the method further includes: sending a fifth message, the fifth message being used to request the transmission of model parameters of the target model.

[0036] Based on the above scheme, after sending a first message to request the acquisition of the target model, the first communication device can send a fifth message to the second communication device after a certain period of time, such as when the target model training is estimated to be completed, to request the second communication device to transmit the model parameters of the target model to the first communication device, thereby meeting the training needs of the first communication device for various models such as custom models.

[0037] A second aspect of this application provides a communication method applied to a second communication device. For example, the second communication device may be a communication equipment (such as a network device), or it may be a component of the communication equipment (e.g., a processor, circuit, chip, or chip system responsible for communication functions). Alternatively, the second communication device may be a logic module or software capable of implementing all or part of the communication equipment's functions. The following description uses a second communication device as an example. In this method, the second communication device receives first information indicating a target model. The first information includes first sub-information and second sub-information. The first sub-information indicates the input parameter type of the target model, and the second sub-information indicates the output parameter type of the target model. The second communication device then sends second information indicating the model parameters of the target model.

[0038] Based on the above scheme, the first communication device can inform the second communication device of the type of the target model to be acquired through the first information. Specifically, the first and second sub-information in the first information can be used to inform the second communication device of the input parameter type and output parameter type of the target model to be acquired. This allows the second communication device to clarify the model training requirements of the first communication device based on the first information and train the target model required by the first communication device based on the type of the target model. Finally, the second information used to indicate the target model is sent to the first communication device, thereby enabling the training of various models, including custom models, entrusted by the first communication device, and thus meeting the training requirements of the first communication device for various models, including custom models.

[0039] In one possible implementation of the second aspect, the first sub-information includes a list of input parameter types of the target model, and the second sub-information includes a list of output parameter types of the target model.

[0040] In one possible implementation of the second aspect, the first information is carried in the training data of the target model.

[0041] In one possible implementation of the second aspect, receiving the first information includes: receiving a first message, the first message including the first information, the first message being used to request the acquisition of the target model.

[0042] In one possible implementation of the second aspect, the first message includes training data of the target model; or, the method further includes receiving a second message, the second message being used to send the training data of the target model.

[0043] In one possible implementation of the second aspect, receiving the first information includes: receiving a first message, the first message being used to request the acquisition of the target model; and receiving a second message, the second message being used to send training data of the target model, the second message including the first information.

[0044] In one possible implementation of the second aspect, the difference between the sending time of the first message and the sending time of the second message is less than a first threshold.

[0045] In one possible implementation of the second aspect, the first message includes first identification information, and the second message includes the first identification information.

[0046] In one possible implementation of the second aspect, the training data of the target model includes a first information element and a second information element, wherein the first information element includes input data in the training data and the second information element includes output data in the training data.

[0047] In one possible implementation of the second aspect, the training data of the target model includes multiple information elements, the information elements including one or more input data and one or more output data in the training data.

[0048] In one possible implementation of the second aspect, the method further includes: sending a third message, the third message being used to indicate that the first message has been received.

[0049] In one possible implementation of the second aspect, the third message includes at least one of the expected acquisition time of the target model or the identification information of the target model.

[0050] In one possible implementation of the second aspect, sending the second information includes sending a fourth message, the fourth message including the second information and the identification information of the target model.

[0051] In one possible implementation of the second aspect, if the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

[0052] In one possible implementation of the second aspect, the method further includes:

[0053] Receive a fifth message, which is used to request the transmission of the model parameters of the target model.

[0054] A third aspect of this application provides a communication method that can be applied to a first communication device. For example, the first communication device may be a communication equipment (such as a terminal device), or it may be a component of a communication equipment (such as a processor, circuit, chip, or chip system responsible for communication functions), or it may be a logic module or software capable of implementing all or part of the functions of the communication equipment. The following description uses a first communication device as an example. In this method, the first communication device sends a first message requesting the acquisition of a target model; receives a third message indicating that the first message has been received; and receives a fourth message including second information indicating the model parameters of the target model.

[0055] Based on the above implementation scheme, after the first communication device sends a first message to the second communication device requesting the acquisition of the target model, the second communication device needs a certain amount of time to train the target model. There may be a situation where the first communication device does not receive a response from the second communication device after sending the first message. In this case, the first communication device may mistakenly believe that the first message was not successfully sent and may retransmit the first message, resulting in wasted resources. Therefore, after sending the first message requesting the acquisition of the target model, the first communication device can receive a third message from the second communication device indicating that the first message has been received, and finally receive the second information indicating the model parameters of the target model based on the fourth message. This avoids the first communication device mistakenly believing that the first message was not successfully sent and retransmitting the message, further saving transmission resources.

[0056] In one possible implementation of the third aspect, the third message includes at least one of the expected acquisition time of the target model or the identification information of the target model.

[0057] Based on the above implementation scheme, the third message received by the first communication device may also carry the expected acquisition time of the target model and / or the identification information of the target model, so that the first communication device can also determine how long it will take to acquire the target model based on the third message, and / or determine the expected acquisition time and the specific association between the third message and the target model based on the identification information of the target model carried in the third message.

[0058] In one possible implementation of the third aspect, the fourth message also includes identification information of the target model.

[0059] Based on the above implementation scheme, the fourth message received by the first communication device may also carry the identification information of the target model, so that the first communication device can determine that the second information carried in the fourth message and the fourth message itself are associated with the target model.

[0060] In one possible implementation of the third aspect, if the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

[0061] Based on the above implementation scheme, if the target model requested by the first communication device is used to replace the existing first model in the first communication device, the fourth message used to transmit the second information may also carry the identification information of the first model, so that the first communication device can determine that the target model is used to replace the existing first model in the first communication device, and can replace the first model with the obtained target model.

[0062] In one possible implementation of the third aspect, the method further includes: sending a fifth message, the fifth message being used to request the transmission of model parameters of the target model.

[0063] Based on the above implementation scheme, after sending a first message to request the acquisition of the target model, the first communication device can send a fifth message to the second communication device after a certain period of time, such as when the target model training is estimated to be completed, to request the second communication device to transmit the model parameters of the target model to the first communication device, thereby meeting the training needs of the first communication device for various models such as custom models.

[0064] In one possible implementation of the third aspect, the first message includes first information for indicating a target model, the first information including first sub-information and second sub-information, the first sub-information for indicating the input parameter type of the target model, and the second sub-information for indicating the output parameter type of the target model.

[0065] Based on the above scheme, the first communication device can send first information based on a first message used to request the acquisition of the target model. That is, the first message can carry the first information, meaning the first information can be sent simultaneously with the first message, further saving transmission resources. Furthermore, the second communication device can acquire the first information upon receiving the first message, thereby enabling the second communication device to clarify the model training requirements of the first communication device based on the first information, and train the target model required by the first communication device based on the type of the target model. This allows the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thus satisfying the first communication device's training needs for various models, including custom models.

[0066] In one possible implementation of the third aspect, the first sub-information includes a list of input parameter types of the target model, and the second sub-information includes a list of output parameter types of the target model.

[0067] Based on the above scheme, the first information sent by the first communication device may specifically include a list of input parameter types of the target model, enabling the second communication device to determine one or more input parameter types of the target model to be trained based on the first sub-information. Similarly, the second sub-information sent by the first communication device may specifically include a list of output parameter types of the target model, enabling the second communication device to determine one or more output parameter types of the target model to be trained based on the second sub-information. This allows the second communication device to determine the specific type of the target model based on the input and output parameter types, and train the target model required by the first communication device based on the specific type of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0068] In one possible implementation of the third aspect, the first information is carried in the training data of the target model.

[0069] Based on the above scheme, the first information sent by the first communication device to indicate the target model can be carried in the training data of the target model. That is, the first communication device can send the training data of the target model carrying the first information so that the second communication device can extract or parse the first information from the training data of the target model. This allows the second communication device to clarify the model training requirements of the first communication device based on the first information and train the target model required by the first communication device based on the type of the target model. This enables the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training requirements of the first communication device for various models, including custom models.

[0070] In one possible implementation of the third aspect, the first message includes the training data of the target model, or the method further includes sending a second message for sending the training data of the target model.

[0071] The first communication device can also send training data required for training the target model based on the first message, or it can send training data of the target model based on the second message, so that the second communication device can obtain the training data of the target model based on the first message or the second message, and train the target model required by the first communication device based on the training data of the target model, thereby completing the training of various models entrusted by the first communication device, including custom models, and thus meeting the training needs of the first communication device for various models such as custom models.

[0072] In one possible implementation of the third aspect, the method further includes: sending a second message, the second message being used to send training data of the target model, the second message including the first information.

[0073] Based on the above scheme, the first communication device can first send a first message to request the acquisition of the target model to inform the second communication device that the target model needs to be trained. Then, based on the second message, the first information and the training data of the target model can be sent to the second communication device. This allows the second communication device to understand the model training requirements of the first communication device based on the first information, and to train the target model required by the first communication device based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training requirements of the first communication device for various models, including custom models.

[0074] In one possible implementation of the third aspect, the difference between the sending time of the first message and the sending time of the second message is less than a first threshold.

[0075] Based on the above scheme, the first communication device can send the first message and the second message sequentially, and the difference between the sending time of the first message and the second message can be less than a first threshold. The interval between the sending time of the first message and the second message can be within a certain range, so that the second communication device can determine the association between the first message and the second message. That is, it can determine that the training data of the target model carried in the second message is used to train the target model requested by the first message, thereby completing the training of multiple models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for multiple models, including custom models.

[0076] In one possible implementation of the third aspect, the first message includes first identification information, and the second message includes the first identification information.

[0077] Based on the above scheme, the first communication device can send a first message and a second message sequentially, and both the first message and the second message can carry the first identification information, that is, the first message and the second message can carry the same identification information, so that the second communication device can determine the association between the first message and the second message, that is, determine that the training data of the target model carried in the second message is used to train the target model requested by the first message, thereby completing the training of multiple models entrusted by the first communication device, including custom models, and thus meeting the training needs of the first communication device for multiple models such as custom models.

[0078] In one possible implementation of the third aspect, the training data of the target model includes a first information element and a second information element, wherein the first information element includes the input data in the training data and the second information element includes the output data in the training data.

[0079] Based on the above scheme, the training data of the target model sent by the first communication device can be composed of a first information element and a second information element. The first information element can carry the input data in the training data, and the second information element can carry the output data in the training data. That is, the input data and output data in the training data can be sent to the second communication device through two different information elements, so that the second communication device can better extract the first information from the training data of the target model, or can better distinguish the input data or output data in the training data, so as to train the target model required by the first communication device based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, and thus meet the training needs of the first communication device for various models, including custom models.

[0080] In one possible implementation of the third aspect, the training data of the target model includes multiple information elements, which include one or more input data and one or more output data of the training data.

[0081] Based on the above scheme, the training data of the target model sent by the first communication device can be composed of multiple information elements, each of which can carry one or more input data and one or more output data of the training data. That is, one or more complete data, including both input and output data, can be carried in the same information element for transmission. This allows the second communication device to better extract the first information from the training data of the target model, or to better identify the complete data in the training data. This enables the first communication device to train the target model required by the first communication device based on the training data of the target model, thereby completing the training of various models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for various models, including custom models.

[0082] A fourth aspect of this application provides a communication method applied to a second communication device. For example, the second communication device may be a communication equipment (such as a network device), or it may be a component of the communication equipment (e.g., a processor, circuit, chip, or chip system responsible for communication functions). Alternatively, the second communication device may be a logic module or software capable of implementing all or part of the communication equipment's functions. The following description uses a second communication device as an example. In this method, the second communication device receives a first message requesting the acquisition of a target model; sends a third message indicating that the first message has been received; and sends a fourth message including the second information indicating the model parameters of the target model.

[0083] Based on the above scheme, after the first communication device sends a first message to the second communication device requesting the acquisition of the target model, the second communication device needs a certain amount of time to train the target model. There may be a situation where the first communication device does not receive a response from the second communication device after sending the first message. In this case, the first communication device may mistakenly believe that the first message was not successfully sent and may retransmit the first message, resulting in wasted resources. Therefore, after receiving the first message requesting the acquisition of the target model, the second communication device can send a third message indicating that the first message has been received, and finally, based on the fourth message, send the second information indicating the model parameters of the target model to the first communication device. This avoids the first communication device mistakenly believing that the first message was not successfully sent and retransmitting the message, further saving transmission resources.

[0084] In one possible implementation of the fourth aspect, the third message includes at least one of the expected acquisition time of the target model or the identification information of the target model.

[0085] In one possible implementation of the fourth aspect, the fourth message also includes identification information of the target model.

[0086] In one possible implementation of the fourth aspect, if the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

[0087] In one possible implementation of the fourth aspect, the method further includes: receiving a fifth message, the fifth message being used to request the transmission of model parameters of the target model.

[0088] In one possible implementation of the fourth aspect, the first message includes the first information, the first information includes a first sub-information and a second sub-information, the first sub-information is used to indicate the input parameter type of the target model, and the second sub-information is used to indicate the output parameter type of the target model.

[0089] In one possible implementation of the fourth aspect, the first sub-information includes a list of input parameter types of the target model, and the second sub-information includes a list of output parameter types of the target model.

[0090] In one possible implementation of the fourth aspect, the first information is carried in the training data of the target model.

[0091] In one possible implementation of the fourth aspect, the first message includes the training data of the target model, or the method further includes:

[0092] Receive a second message, which is used to send the training data of the target model.

[0093] In one possible implementation of the fourth aspect, the method further includes:

[0094] Receive the second message, which is used to send the training data of the target model. The second message includes the first information.

[0095] In one possible implementation of the fourth aspect, the difference between the sending time of the first message and the sending time of the second message is less than a first threshold.

[0096] In one possible implementation of the fourth aspect, the first message includes first identification information, and the second message includes first identification information.

[0097] In one possible implementation of the fourth aspect, the training data of the target model includes a first information element and a second information element, wherein the first information element includes the input data in the training data and the second information element includes the output data in the training data.

[0098] In one possible implementation of the fourth aspect, the training data of the target model includes multiple information elements, which include one or more input data and one or more output data in the training data.

[0099] A fifth aspect of this application provides a communication device that performs the functions described in the first or third aspect above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the first or third aspect. These modules, units, or means can be implemented in software, hardware, or a combination of both. For instance, the device includes a processing unit and a transceiver unit.

[0100] In the fifth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the first or third aspect and achieve the corresponding technical effects. For details, please refer to the first or third aspect, which will not be repeated here.

[0101] A sixth aspect of this application provides a communication device that performs the functions described in the second or fourth aspect above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the second or fourth aspect. These modules, units, or means can be implemented in software, hardware, or a combination of both. For instance, the device includes a processing unit and a transceiver unit.

[0102] In the sixth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the second or fourth aspect and achieve the corresponding technical effects. For details, please refer to the second or fourth aspect, which will not be repeated here.

[0103] A seventh aspect of this application provides a communication device including at least one processor for executing computer programs or instructions to enable the device to implement any one of the first to fourth aspects and any possible implementation thereof.

[0104] Optionally, the at least one processor is coupled to a memory for storing computer programs or instructions.

[0105] Optionally, the communication device includes the memory. Optionally, the memory is integrated with at least one processor.

[0106] The eighth aspect of this application provides a communication device including at least one logic circuit and an input / output interface; the logic circuit is used to perform a method as described in any one of the possible implementations of the first to fourth aspects.

[0107] In one possible implementation, the communication device is a chip or chip system.

[0108] The ninth aspect of this application provides a communication system, which includes the first communication device and the second communication device described above.

[0109] The tenth aspect of this application provides a computer-readable storage medium for storing one or more computer-executable instructions, which, when executed by a processor, perform a method as described in any possible implementation of any of the first to fourth aspects above.

[0110] The eleventh aspect of this application provides a computer program product (or computer program) in which, when the computer program in the computer program product is executed by the processor, the processor executes any possible implementation of any of the first to fourth aspects described above.

[0111] The twelfth aspect of this application provides a chip or chip system including at least one processor for supporting a communication device to implement any possible implementation of any of the first to fourth aspects described above. For example, the chip may be a baseband chip, a modem chip, a system-on-a-chip (SoC) chip containing a modem core, a system-in-package (SIP) chip, or a communication module, etc.

[0112] In one possible design, the chip or chip system may further include a memory for storing 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. Optionally, the chip system may also include interface circuitry that provides program instructions and / or data to the at least one processor.

[0113] The technical effects of any of the design methods in aspects four through twelfth can be found in the technical effects of the different design methods in aspects one through four above, and will not be repeated here. Attached Figure Description

[0114] Figure 1 is a schematic diagram of the architecture of the mobile communication system used in the embodiments of this application;

[0115] Figure 2 is a schematic diagram of the process of a terminal device entrusting a network device to train a model, as provided in an embodiment of this application.

[0116] Figures 3 and 4 are schematic diagrams of the communication method provided in this application;

[0117] Figures 5 to 8 are some schematic diagrams of the communication device provided in this application. Detailed Implementation

[0118] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0119] To facilitate understanding of the technical solutions of this application, several technical terms involved in the embodiments of this application will be introduced below.

[0120] (1) Terminal device: can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0121] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (or "cellular" phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the RAN. Examples include personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile station (MS), remote station, access point (AP), remote terminal, access terminal, user terminal, user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), drone, etc. Terminal equipment can also be wearable devices and next-generation communication systems, such as terminal equipment in 5G communication systems or terminal equipment in future public land mobile networks (PLMNs).

[0122] (2) Network equipment (or network element): This can be equipment in a wireless network. For example, network equipment can be a RAN node (or device) that connects terminal devices to the wireless network, and can also be called a base station. Currently, some examples of RAN equipment include: base station, evolved NodeB (eNodeB), gNB (gNodeB) in 5G communication systems, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point (AP), etc. In addition, in a network structure, network equipment can include centralized unit (CU) nodes, distributed unit (DU) nodes, or RAN equipment including CU nodes and DU nodes.

[0123] Optionally, RAN nodes can also be macro base stations, micro base stations, indoor stations, relay nodes, donor nodes, or radio controllers in cloud radio access network (CRAN) scenarios. RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, the access network equipment in V2X technology can be a roadside unit (RSU).

[0124] In this embodiment, network equipment can be deployed on satellites or on the ground. For example, a base station can be deployed entirely on a satellite, or only some of its functions can be deployed on a satellite. For instance, the radio frequency unit (RU) of a base station can be deployed on a satellite, while other parts can be deployed on the ground. Another example is that the RU and DU of a base station can be deployed on a satellite, while the CU can be deployed on the ground. Similarly, core network equipment can also be deployed on satellites. For example, some core network user plane elements can be deployed on satellites to support direct interaction between terminals via satellite, eliminating the need for ground-based communication. Some core network control plane elements can also be deployed on satellites. For example, deploying mobility management and session management elements on satellites can support emergency disaster relief services in situations where there is no terrestrial network.

[0125] For example, network devices may be deployed on non-terrestrial platforms, including but not limited to low-Earth orbit satellites, medium-Earth orbit satellites, high-Earth orbit satellites, high-altitude platforms, drones, and other high-altitude platforms.

[0126] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0127] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open access network (open RAN, O-RAN, or ORAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0128] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, medium access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0129] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0130] Table 1

[0131] Network devices can be other devices that provide wireless communication functions for terminal devices. The embodiments of this application do not limit the specific technology or form of the network device. For ease of description, the embodiments of this application are not limited.

[0132] Network equipment may also include core network equipment, such as the Mobility Management Entity (MME), Home Subscriber Server (HSS), Serving Gateway (S-GW), Policy and Charging Rules Function (PCRF), and Public Data Network Gateway (PDN Gateway, P-GW) in 4th generation (4G) networks; and AMF, User Plane Function (UPF), or Session Management Function (SMF) in 5G networks. Furthermore, this core network equipment may also include other core network equipment in 5G networks and next-generation networks of 5G networks.

[0133] In this application embodiment, the device for implementing the function of the network device can be the network device itself, or it can be a device capable of supporting the network device in implementing that function, such as a chip system, which can be installed in the network device. In the technical solutions provided in this application embodiment, the example of a network device being used to implement the function of the network device is used to describe the technical solutions provided in this application embodiment.

[0134] (3) Configuration and Pre-configuration: In this application, both configuration and pre-configuration are used. Configuration refers to the network device sending configuration information or parameter values ​​of some parameters to the terminal device through messages or signaling, so that the terminal device can determine the communication parameters or resources during transmission based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​that the network device and the terminal device have negotiated in advance, or it can be parameter information or parameter values ​​that the network device or the terminal device uses as specified by the standard protocol, or it can be parameter information or parameter values ​​that are pre-stored in the network device or the terminal device. This application does not limit this.

[0135] Furthermore, these values ​​and parameters can be changed or updated.

[0136] (4) The terms "system" and "network" in the embodiments of this application can be used interchangeably. "At least one" means one or more, and "more" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, sequence, priority or importance of multiple objects.

[0137] (5) In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include sending directly through the air interface or sending indirectly through the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include receiving directly from YY through the air interface or receiving indirectly from YY through the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0138] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0139] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0140] (6) In the embodiments of this application, "instruction" may include direct instruction and indirect instruction, as well as explicit instruction and implicit instruction. The information indicated by a certain piece of information (as described below, the instruction information) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is an association between the other information and the information to be instructed; or it can only indicate a part of the information to be instructed, while the other parts of the information to be instructed are known or pre-agreed upon. For example, the instruction can be implemented by using a pre-agreed (e.g., protocol predefined) arrangement order of various information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction. It is understood that for the sender of the instruction information, the instruction information can be used to indicate the information to be instructed, and for the receiver of the instruction information, the instruction information can be used to determine the information to be instructed.

[0141] (7) Model training refers to the process of training a machine learning or deep learning model using a specific dataset and algorithm. The main purpose of this process is to enable the model to learn from the input data and extract useful features so that it can accurately predict or classify unseen data. Model training typically includes key steps such as data preparation, model selection, model configuration, training process, model validation, model testing, and model deployment.

[0142] Figure 1 is a schematic diagram of the architecture of a communication system 1000 provided in an embodiment of this application. As shown in Figure 1, the communication system 1000 includes a radio access network (RAN) 100, wherein the RAN 100 includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110), and may also include at least one terminal (120a-120j in Figure 1, collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). The terminal 120 is wirelessly connected to the RAN node 110. Terminals and RAN nodes can be interconnected via wired or wireless means. The communication system 1000 may also include a core network 200. The RAN node 110 is connected to the core network 200 via wireless or wired means. The core network equipment in core network 200 and the RAN node 110 in RAN 100 can be independent and different physical devices, or they can be the same physical device that integrates the logical functions of the core network equipment and the logical functions of the RAN node. Communication system 1000 may also include Internet 300.

[0143] RAN100 can be an evolved universal terrestrial radio access (E-UTRA) system, a new radio (NR) system, a 6th generation (6G) radio access system, or a future radio access system as defined in the 3rd generation partnership project (3GPP), or it can be a WiFi system. RAN100 can also include two or more of the above-mentioned different radio access systems. RAN100 can also be an open RAN (O-RAN).

[0144] RAN nodes, also known as radio access network devices, RAN entities, or access nodes, are used to help terminals access communication systems wirelessly. In one application scenario, an RAN node can be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next-generation NodeB (gNB) in a 5G mobile communication system, a next-generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. RAN nodes can be macro base stations (as shown in Figure 1, 110a), micro base stations or indoor stations (as shown in Figure 1, 110b), relay nodes, or donor nodes.

[0145] In another application scenario, multiple RAN nodes can collaborate to help terminals achieve wireless access, with different RAN nodes implementing different functions of the base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), or a radio unit (RU). Here, the CU performs the functions of the base station's Radio Resource Control (RRC) and Packet Data Convergence Protocol (PDCP), and can also perform the functions of the Service Data Adaptation Protocol (SDAP). The DU performs the functions of the base station's Radio Link Control (RANC) and Medium Access Control (MAC) layers, and can also perform some or all of the physical layer functions. For specific descriptions of these protocol layers, refer to the relevant 3GPP technical specifications. The RU can be used to implement radio frequency signal transmission and reception. The CU and DU can be two independent RAN nodes or integrated into the same RAN node, such as within a baseband unit (BBU). The RU can be included in radio frequency equipment, such as in a remote radio unit (RRU) or an active antenna unit (AAU). The CU can be further divided into two types of RAN nodes: CU-control plane and CU-user plane.

[0146] In different systems, RAN nodes may have different names. For example, in an O-RAN system, a CU can be called an open CU (O-CU), a DU can be called an open DU (O-DU), and an RU can be called an open RU (O-RU). The RAN nodes in the embodiments of this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules. For example, a RAN node can be a server loaded with the corresponding software modules. The embodiments of this application do not limit the specific technology or device form used in the RAN nodes. For ease of description, a base station is used as an example of a RAN node in the following description.

[0147] A terminal is a device with wireless transceiver capabilities, capable of sending signals to or receiving signals from a base station. Terminals can also be called terminal equipment, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, airplanes, ships, robots, robotic arms, smart home devices, etc. The embodiments of this application do not limit the specific technology or device form used in the terminal.

[0148] Base stations and terminals can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the base stations and terminals.

[0149] The roles of base stations and terminals can be relative. For example, the helicopter or drone 120i in Figure 1 can be configured as a mobile base station. For terminals 120j that access the wireless access network 100 through 120i, terminal 120i is a base station; however, for base station 110a, 120i is a terminal, meaning that 110a and 120i communicate via a wireless air interface protocol. Of course, 110a and 120i can also communicate via a base station-to-base station interface protocol. In this case, relative to 110a, 120i is also a base station. Therefore, both base stations and terminals can be collectively referred to as communication devices. 110a and 110b in Figure 1 can be called communication devices with base station functions, and 120a-120j in Figure 1 can be called communication devices with terminal functions.

[0150] Communication between base stations and terminals, between base stations, and between terminals can be conducted using licensed spectrum, unlicensed spectrum, or both simultaneously. Communication can be conducted using spectrum below 6 GHz, spectrum above 6 GHz, or both simultaneously. The embodiments of this application do not limit the spectrum resources used for wireless communication.

[0151] In the embodiments of this application, the functions of the base station can be executed by modules (such as chips) within the base station, or by a control subsystem that includes base station functions. This control subsystem, including base station functions, can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. Similarly, the functions of the terminal can be executed by modules (such as chips or modems) within the terminal, or by a device that includes terminal functions.

[0152] In this application, the base station sends downlink signals or downlink information to the terminal, with the downlink information carried on the downlink channel; the terminal sends uplink signals or uplink information to the base station, with the uplink information carried on the uplink channel. To communicate with the base station, the terminal needs to establish a radio connection on a cell controlled by the base station. The cell with which the terminal has established a radio connection is called the terminal's serving cell. When the terminal communicates with this serving cell, it is also susceptible to interference from signals from neighboring cells.

[0153] With the rapid development of deep learning technology, more and more communication devices need to rely on models to analyze and process data. In the communications field, due to limitations in cost and size, terminal devices often have limited computing power, making it difficult to meet the needs of services such as model training. On the other hand, network devices can provide increasingly powerful computing capabilities. Therefore, when a terminal device needs model training, the network device can assist in the model training process and then transmit the trained model back to the terminal device. Referring to Figure 2, the terminal device can send its acquired training data to the network device, leveraging the network device's computing power to train its own artificial intelligence (AI) model. After training the AI ​​model, the network device can return the AI ​​model to the terminal device.

[0154] However, current network devices typically only allow terminal devices to train a limited number of models. That is, the network device pre-informs the terminal device about the types of models that can be trained, and the terminal device then selects the type of model it wants to train from these available options and informs the network device of this selection. This prevents terminal devices from delegating the training of custom models to the network device, thus failing to meet the terminal device's training needs for various models, including custom models.

[0155] To address the aforementioned problems, this application provides a communication method, apparatus, medium, and computer program product, which will be described in detail below with reference to the accompanying drawings.

[0156] Please refer to Figure 3, which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0157] It should be noted that, in Figure 3 and related implementation examples below, the method is illustrated using a first communication device and other communication devices (such as a second communication device) as the execution subjects of this interaction illustration. However, this application does not limit the execution subjects of this interaction illustration. For example, the first communication device can be a terminal device or a network device, or a chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, chip system, processor, logic module, or software in the terminal device or network device. Exemplarily, the first communication device can be a terminal device, and the second communication device can be a network device.

[0158] As an example, network equipment can be a base station or an access network device.

[0159] As another example, the second communication device can be an ORAN device (including at least one of O-CU, O-DU, or O-RU). For instance, the second communication device may include an O-RU that can transmit information or messages via a wireless link, enabling the first communication device to receive such information or messages. Alternatively, the second communication device may include an O-CU and / or an O-DU, and transmit information or messages via the O-RU, enabling the first communication device to receive such information or messages.

[0160] S301. The first communication device sends first information, and correspondingly, the second communication device receives the first information.

[0161] The first information is used to indicate the target model. The first information includes a first sub-information and a second sub-information. The first sub-information is used to indicate the input parameter type of the target model, and the second sub-information is used to indicate the output parameter type of the target model.

[0162] In this embodiment, the first communication device can first determine the target model to be acquired and the training data required to train the target model. After determining the target model, the first communication device can send first information indicating the target model to inform the second communication device of the type of the target model to be acquired. This allows the second communication device to understand the model training requirements of the first communication device and train the target model required by the first communication device based on the type of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby satisfying the first communication device's training requirements for various models, including custom models. Specifically, the first sub-information in the first information can inform the second communication device of the input parameter type of the target model, and the second sub-information can inform the second communication device of the output parameter type of the target model to be acquired. This ensures that the input parameter type of the model trained by the second communication device is the same as that indicated by the first sub-information, and the output parameter type of the model trained by the second communication device is the same as that indicated by the second sub-information. In other words, the model trained by the second communication device is the target model required by the first communication device. It should be noted that the target model can be the model required by the first communication device, which is trained by the second communication device based on the training data of the target model and the original model. The first sub-information can indicate the input parameter types of one or more target models, and the second sub-information can also indicate the input parameter types of one or more target models.

[0163] It is understood that the training data used to train the target model can be acquired by the first communication device and sent to the second communication device, or the second communication device can pre-store the training data of the target model. When the second communication device stores the training data of the target model, the first communication device may not need to send the training data of the target model to the second communication device, or it may send the training data of the target model to the second communication device again. This application embodiment does not limit this. For example, the training data of the target model can be as shown in Table 2, which can include not only the data content itself, but also the data type. For example, it can include not only data content such as 8:00, 8:30, West Gate of Institute A, South Gate of Institute A, chat, voice, 20KB and 50KB, but also data types such as time, location, business and data volume.

[0164] Table 2

[0165] The training data for the target model can also be as shown in Table 3, which only includes the data content itself.

[0166] Table 3

[0167] It is understandable that different training data can train different models, and the same training data can also train different models. For example, the training data shown in Table 2 can train the following three models:

[0168] Model 1: Input parameters include time, location, and business; output parameters include data volume.

[0169] Model 2: Input parameters include time, business, and data volume; output parameters include location.

[0170] Model 3: Input parameters include time, location, and data volume, while output parameters include business operations.

[0171] Furthermore, the training data described in Table 2 can be used to train various different models based on different business needs, and this application embodiment does not limit them.

[0172] In one possible implementation of this application embodiment, the first sub-information includes a list of input parameter types of the target model, and the second sub-information includes a list of output parameter types of the target model. In this application embodiment, the first sub-information included in the first information sent by the first communication device may specifically include a list of input parameter types of the target model, enabling the second communication device to determine one or more input parameter types of the target model to be trained based on the first sub-information. Similarly, the second sub-information included in the first information sent by the first communication device may specifically include a list of output parameter types of the target model, enabling the second communication device to determine one or more output parameter types of the target model to be trained based on the second sub-information. This allows the second communication device to determine the specific type of the target model based on the input and output parameter types, and to train the target model required by the first communication device based on the specific type of the target model. This enables the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0173] It should be noted that the target model's input parameter type list may include one or more input parameter types, and the target model's output parameter type list may include one or more output parameter types. For example, if the target model's input parameter type list includes three input parameter types: time, location, and business, then the target model's input parameter type list can be represented as input(time, location, business); if the target model's output parameter type list includes one input parameter type: data volume, then the target model's output parameter type list can be represented as output(data volume).

[0174] In one possible implementation of this application embodiment, the first information is carried in the training data of the target model. In this application embodiment, the first information sent by the first communication device to indicate the target model can be carried in the training data of the target model. That is, the first communication device can send the training data of the target model carrying the first information, so that the second communication device can extract or parse the first information from the training data of the target model. This allows the second communication device to clarify the model training requirements of the first communication device based on the first information, and train the target model required by the first communication device based on the type of the target model. This enables the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby satisfying the training requirements of the first communication device for various models, including custom models.

[0175] It is understandable that when the first information is carried in the training data of the target model, the second communication device can analyze the received training data, determine the parameter types included in the training data, and further determine the input parameter types and output parameter types included in the parameter types based on the composition structure or arrangement order of the training data. That is, the first information can be extracted or parsed from the training data of the target model.

[0176] For example, if the training data of the target model is as shown in Table 2 above, after receiving the training data, the second communication device can directly extract the parameter types included in the training data, including time, location, service, and data volume. Furthermore, since the order of the data corresponding to time, location, and service precedes the order of the data corresponding to data volume, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0177] If the training data of the target model is as shown in Table 2 above, and the first three columns of data in Table 2 constitute the first information element, and the fourth column of data in Table 2 constitutes the second information element, where the first information element is marked as the input parameter and the second information element is marked as the output parameter, then after receiving the training data, the second communication device can directly extract the parameter types included in the training data, including time, location, service, and data volume. Furthermore, since the data corresponding to time, location, and service constitute the first information element carrying the input parameters, and the data volume constitutes the first information element carrying the input parameters, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0178] If the training data of the target model is as shown in Table 3 above, after receiving the training data, the second communication device can determine the parameter types included in the training data, including time, location, service, and data volume, by parsing or classifying the training data. Furthermore, since the order of the data corresponding to time, location, and service precedes the order of the data corresponding to data volume, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0179] If the training data of the target model is as shown in Table 3 above, and the first three columns of data in Table 3 constitute the first information element, and the fourth column of data in Table 3 constitutes the second information element, where the first information element is labeled as the input parameter and the second information element is labeled as the output parameter, then after receiving the training data, the second communication device can determine the parameter types included in the training data, including time, location, service, and data volume, by parsing or classifying the training data. Furthermore, since the data corresponding to time, location, and service constitute the first information element carrying the input parameters, and the data volume constitutes the first information element carrying the input parameters, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0180] In one possible implementation of this application embodiment, the training data of the target model includes a first information element and a second information element. The first information element includes input data in the training data, and the second information element includes output data in the training data.

[0181] In this embodiment, the training data of the target model sent by the first communication device can be composed of a first information element and a second information element. The first information element may include input data in the training data, and the second information element may include output data in the training data. That is, the input data and output data in the training data can be sent to the second communication device through two different information elements, so that the second communication device can better extract the first information from the training data of the target model, or can better distinguish the input data or output data in the training data, so as to train the target model required by the first communication device based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, and thus meet the training needs of the first communication device for various models, including custom models.

[0182] In the field of communications, an information element (IE) is a basic unit used to describe the structure and content of information. An information element can represent a single piece of information, a group of information, or even a complex information structure. Information elements can be used to describe various types of information, such as information type, message content, transmission rate, and signal strength.

[0183] For example, if the training data of the target model is as shown in Table 2, and the first three columns in Table 2 are input data and the fourth column is output data, then the first information element of the training data may include the data in the first three columns of Table 2, and the second information element may include the data in the fourth column of Table 2.

[0184] In one possible implementation of this application embodiment, the training data of the target model includes multiple information elements, and the information elements include one or more input data and one or more output data of the training data.

[0185] In this embodiment, the training data of the target model sent by the first communication device can be composed of multiple information elements, each of which can carry one or more input data and one or more output data of the training data. That is, one or more complete data, including both input and output data, can be carried in the same information element for transmission. This allows the second communication device to better extract the first information from the training data of the target model, or to better identify the complete data in the training data. This enables the first communication device to train the target model required by the first communication device based on the training data of the target model, thereby completing the training of various models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for various models, including custom models.

[0186] For example, if the training data of the target model is as shown in Table 3, and the training data of the target model includes three information elements, then the first information element may include the data in the first row of Table 3, the second information element may include the data in the second row of Table 3, and the third information element may include the data in the third row of Table 3.

[0187] In one possible implementation of this application embodiment, step 301, whereby the first communication device sends first information and the corresponding second communication device receives the first information, includes:

[0188] A1. The first communication device sends a first message, and correspondingly, the second communication device receives the first message.

[0189] The first message includes the first information, which is used to request the target model.

[0190] In this embodiment, the first communication device can send first information based on a first message requesting the acquisition of a target model. That is, the first message can carry the first information, meaning the first information can be sent simultaneously with the first message, further saving transmission resources. Furthermore, the second communication device can acquire the first information upon receiving the first message, thereby enabling the second communication device to clearly define the model training requirements of the first communication device based on the first information, and to train the target model required by the first communication device based on the type of the target model. This allows the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thus satisfying the first communication device's training needs for various models, including custom models.

[0191] It is understood that the first message can be used to request the acquisition of the target model, to request the second communication device to train the target model, or to request the second communication device to train the target model based on the training data of the target model. For example, the first message can specifically be a model acquisition request or a model training request; this embodiment of the application does not limit this. The first message may also carry third and / or fourth information, where the third information can be used to indicate the algorithm used when training the target model, and the fourth information can be used to indicate the accuracy of the target model, etc., thereby enabling the second communication device to more clearly understand the model training requirements of the first communication device, accurately train the target model required by the first communication device, and thus complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0192] It should be noted that when the first message carries the first information, the training data required for training the target model can be sent from the first communication device to the second communication device, and the second communication device can also pre-store the training data of the target model. When the training data of the target model is sent from the first communication device to the second communication device, the first communication device can send the training data of the target model to the second communication device based on the first message, or it can send the training data of the target model to the second communication device based on other messages.

[0193] In one possible implementation of this application embodiment, the first message includes training data of the target model, or the method further includes:

[0194] A2. The first communication device sends a second message, and correspondingly, the second communication device receives the second message.

[0195] The second message is used to send the training data for the target model.

[0196] In this embodiment, the first communication device can also send training data required for training the target model based on the first message, meaning the first message can directly carry training data for training the target model. Alternatively, the first communication device can also send training data for the target model based on the second message, enabling the second communication device to obtain the training data of the target model based on the first or second message, and train the target model required by the first communication device based on the training data of the target model. This allows the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0197] In one possible implementation of this application embodiment, step 301, whereby the first communication device sends first information and the corresponding second communication device receives the first information, includes:

[0198] B1. The first communication device sends a first message, and correspondingly, the second communication device receives the first message.

[0199] The first message is used to request the target model.

[0200] B2. The first communication device sends a second message, and correspondingly, the second communication device receives the second message.

[0201] The second message is used to send the training data of the target model, and the second message includes the first message.

[0202] In this embodiment, the first communication device can first send a first message requesting the acquisition of a target model to inform the second communication device that the target model needs to be trained. Then, based on the second message, the first message and the training data of the target model can be sent to the second communication device. That is, the first message requesting the acquisition of the target model and the second message sending the training data can be sent sequentially. This allows the second communication device to first understand the need for model training based on the first message, then understand the specific model training needs of the first communication device based on the second message, i.e., to train the target model, and then acquire the training data required for training the target model based on the second message. Finally, the target model required by the first communication device is trained based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby satisfying the training needs of the first communication device for various models, including custom models.

[0203] In one possible implementation of this application embodiment, the difference between the sending time of the first message and the sending time of the second message is less than a first threshold. In this application embodiment, the first communication device can send the first message and the second message sequentially, and the difference between the sending times of the first message and the second message can be less than the first threshold. That is, the interval between the sending times of the first message and the second message can be within a certain range, so that the second communication device can determine the association between the first message and the second message. This means it can determine that the training data of the target model carried in the second message is used to train the target model requested by the first message, thereby enabling the training of multiple models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for various models, including custom models. It should be noted that the specific value of the first threshold can be set according to actual conditions, and this application embodiment does not limit this.

[0204] In one possible implementation of this application embodiment, the first message includes first identification information, and the second message includes first identification information. In this application embodiment, the first communication device can send the first message and the second message sequentially, and both the first message and the second message can carry the first identification information; that is, the first message and the second message can carry the same identification information. This allows the second communication device to determine the association between the first message and the second message, and thus determine that the training data of the target model carried in the second message is used to train the target model requested by the first message. This enables the first communication device to complete the training of multiple models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models. It should be noted that the first identification information can be an identity number (ID), a random value, or a serial number, etc., and is not limited in this application embodiment.

[0205] In one possible implementation of the first aspect, the method further includes:

[0206] C1. The second communication device sends a third message, and correspondingly, the first communication device receives the third message.

[0207] The third message is used to indicate that the first message has been received.

[0208] In this embodiment, if the first communication device sends a first message to the second communication device requesting to obtain a target model, and the second communication device needs a certain amount of time to train the target model, there may be a situation where the first communication device does not receive a reply from the second communication device after sending the first message. In this case, the first communication device may mistakenly believe that the first message was not successfully sent and may retransmit the first message, resulting in wasted resources. Therefore, after sending the first message, the first communication device can receive a third message from the second communication device indicating that the first message has been received. That is, after receiving the first message, the second communication device can send a third message to the first communication device to indicate that the first message has been received, thereby avoiding the first communication device mistakenly believing that the first message was not successfully sent and retransmitting the message, further saving transmission resources.

[0209] It is understood that the third message can be used to indicate that the first message has been received, to indicate that the target model is being trained, or to indicate that the second communication device has agreed to compute and provide feedback on the target model. For example, the third message can specifically be a response to a model acquisition request or a response to a model training request; this embodiment of the application does not limit the specific details.

[0210] In one possible implementation of this application embodiment, the third message includes at least one of the expected acquisition time of the target model or the identification information of the target model. In this application embodiment, the third message received by the first communication device may also carry the expected acquisition time of the target model and / or the identification information of the target model, enabling the first communication device to determine, based on the third message, how long it is expected to take to acquire the target model, and / or to determine, based on the identification information of the target model carried in the third message, the expected acquisition time and whether the third message is specifically associated with the target model. It should be noted that the expected acquisition time of the target model may be the remaining training time of the target model predicted by the second communication device based on the training progress of the target model. The identification information of the target model may be information assigned to the target model by the second communication device to uniquely identify the target model.

[0211] S302. The second communication device sends the second information, and correspondingly, the first communication device receives the second information.

[0212] The second piece of information is used to indicate the model parameters of the target model.

[0213] In this embodiment, after receiving the first information, the second communication device can determine its model training requirements based on the first information, that is, determine the type of model to be trained, and identify the target model. The second communication device can also acquire the training data required for training the target model and determine the original model or training algorithm. Based on the determined model type, training data, and original model or training algorithm, the second communication device can perform model training to obtain the target model. Finally, the second communication device can send the model parameters of the trained target model, i.e., the second information indicating the model parameters of the target model, to the first communication device. This allows the first communication device, upon receiving the second information, to construct the target model based on the model parameters, thereby enabling it to train various models, including custom models, as requested by the first communication device, thus meeting its training requirements for custom models and other types of models. For example, the first communication device can adjust the parameters of the original model used to train the target model based on the model parameters of the target model to obtain the target model.

[0214] In one possible implementation of this application embodiment, step 302 involves the second communication device sending second information, and correspondingly, the first communication device receiving the second information, including:

[0215] D1. The second communication device sends the fourth message, and correspondingly, the first communication device receives the fourth message.

[0216] The fourth message includes the second information and the identification information of the target model.

[0217] In this embodiment of the application, the first communication device can obtain the second information for indicating the model parameters of the target model and the identification information of the target model based on the fourth message. That is, after the second communication device trains the target model, it can send the second information for indicating the model parameters of the target model and the identification information of the target model to the first communication device based on the fourth message, so that the first communication device can construct the target model based on the second information, thereby completing the training of various models entrusted by the first communication device, including custom models, and thus meeting the training needs of the first communication device for various models such as custom models.

[0218] In one possible implementation of this application embodiment, if the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

[0219] In this embodiment, the first communication device may have one or more models in use, each model may correspond to an identification information, and different models may have different functions. After these models have been used for a period of time, their accuracy may gradually decrease due to various reasons, requiring adjustment and updates. If the target model requested by the first communication device is used to replace the existing first model in the first communication device, the fourth message used to transmit the second information may also carry the identification information of the first model, so that the first communication device can determine that the target model is used to replace the existing first model in the first communication device, and can replace the first model with the obtained target model.

[0220] It should be noted that different models may have different functions, meaning each model can have a corresponding function identifier, or function ID. When a model is assigned a corresponding function ID, the model's identification information can include the function ID and model ID. In other words, the target model's identification information can include the target model's corresponding function ID and model ID, and the first model's identification information can also include the first model's corresponding function ID and model ID.

[0221] In one possible implementation of this application embodiment, the method further includes:

[0222] E1. The first communication device sends the fifth message, and correspondingly, the second communication device receives the fifth message.

[0223] The fifth message is used to request the transmission of the model parameters of the target model.

[0224] In this embodiment, after sending a first message requesting the acquisition of the target model, the first communication device can, after a certain period of time, such as when the target model training is estimated to be complete, send a fifth message to the second communication device to request the second communication device to transmit the model parameters of the target model to the first communication device. This satisfies the training needs of the first communication device for various models, such as custom models. It is understood that after sending the first message, the first communication device can not only passively wait for the model parameters of the target model from the second communication device, but also actively request the network to send the model parameters of the target model by sending the fifth message. The fifth message may carry the identification information of the target model.

[0225] As illustrated by the examples in the foregoing embodiments, the first communication device can inform the second communication device of the type of the target model to be acquired through the first information. Specifically, the first and second sub-informations in the first information can respectively inform the second communication device of the input parameter type and the output parameter type of the target model to be acquired. This allows the second communication device to clearly understand the model training requirements of the first communication device and train the target model required by the first communication device based on the type of the target model. In this way, the first communication device can complete the training of various models, including custom models, entrusted by the first communication device, thereby satisfying the training requirements of the first communication device for various models, including custom models.

[0226] Please refer to Figure 4, which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0227] It should be noted that, in Figure 4 and related implementation examples below, the method is illustrated using a first communication device and other communication devices (such as a second communication device) as the execution subjects of this interaction illustration. However, this application does not limit the execution subjects of this interaction illustration. For example, the first communication device can be a terminal device or a network device, or a chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, chip system, processor, logic module, or software in the terminal device or network device. Exemplarily, the first communication device can be a terminal device, and the second communication device can be a network device.

[0228] As an example, network equipment can be a base station or an access network device.

[0229] As another example, the second communication device can be an ORAN device (including at least one of O-CU, O-DU, or O-RU). For instance, the second communication device may include an O-RU that can transmit information or messages via a wireless link, enabling the first communication device to receive such information or messages. Alternatively, the second communication device may include an O-CU and / or an O-DU, and transmit information or messages via the O-RU, enabling the first communication device to receive such information or messages.

[0230] S401. The first communication device sends a first message, and correspondingly, the second communication device receives the first message.

[0231] The first message is used to request the target model.

[0232] In this embodiment, the first communication device can first determine the target model to be acquired and determine the training data of the target model required to train it. After determining the target model, the first communication device can send a first message to the second communication device to request the acquisition of the target model.

[0233] It is understood that the first message can be used to request the acquisition of the target model, to request the second communication device to train the target model, or to request the second communication device to train the target model based on the training data of the target model. For example, the first message can specifically be a model acquisition request or a model training request; this embodiment of the application does not limit this. The first message may also carry third and / or fourth information, where the third information can be used to indicate the algorithm used when training the target model, and the fourth information can be used to indicate the accuracy of the target model, etc., thereby enabling the second communication device to more clearly understand the model training requirements of the first communication device, accurately train the target model required by the first communication device, and thus complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0234] In one possible implementation of this application embodiment, the first message includes first information, which is used to indicate a target model. The first information includes first sub-information and second sub-information. The first sub-information is used to indicate the input parameter type of the target model, and the second sub-information is used to indicate the output parameter type of the target model.

[0235] In this embodiment, after determining the target model, the first communication device can send first information indicating the target model to inform the second communication device of the type of the target model to be acquired. This allows the second communication device to understand the model training requirements of the first communication device and train the target model required by the first communication device based on the type of the target model. This enables the first communication device to train various models, including custom models, as requested by the first communication device, thus satisfying its training needs for custom models and other types of models. Specifically, the first sub-information in the first information can inform the second communication device of the input parameter type of the target model, and the second sub-information can inform the second communication device of the output parameter type of the target model to be acquired. This ensures that the input parameter type of the model trained by the second communication device is the same as that indicated by the first sub-information, and the output parameter type of the model trained by the second communication device is the same as that indicated by the second sub-information. Therefore, the model trained by the second communication device is the target model required by the first communication device. It should be noted that the target model can be the model required by the first communication device, trained by the second communication device based on the training data of the target model and the original model. The first sub-information can indicate the input parameter type of one or more target models, and the second sub-information can also indicate the input parameter type of one or more target models.

[0236] It should be noted that when the first message carries the first information, the training data required for training the target model can be sent from the first communication device to the second communication device, and the second communication device can also pre-store the training data of the target model. When the training data of the target model is sent from the first communication device to the second communication device, the first communication device can send the training data of the target model to the second communication device based on the first message, or it can send the training data of the target model to the second communication device based on other messages.

[0237] It is understood that the training data used to train the target model can be acquired by the first communication device and sent to the second communication device, or the second communication device can pre-store the training data of the target model. When the second communication device stores the training data of the target model, the first communication device may not need to send the training data of the target model to the second communication device, or it may send the training data of the target model to the second communication device again. This application embodiment does not limit this. For example, the training data of the target model can be as shown in Table 2, which can include not only the data content itself, but also the data type. For example, it can include not only data content such as 8:00, 8:30, West Gate of Institute A, South Gate of Institute A, chat, voice, 20KB and 50KB, but also data types such as time, location, business and data volume. The training data of the target model can also be as shown in Table 3, which only includes the data content itself.

[0238] It is understandable that different training data can train different models, and the same training data can also train different models. For example, the training data shown in Table 2 can train the following three models:

[0239] Model 1: Input parameters include time, location, and business; output parameters include data volume.

[0240] Model 2: Input parameters include time, business, and data volume; output parameters include location.

[0241] Model 3: Input parameters include time, location, and data volume, while output parameters include business operations.

[0242] Furthermore, the training data described in Table 2 can be used to train various different models based on different business needs, and this application embodiment does not limit them.

[0243] In one possible implementation of this application embodiment, the first sub-information includes a list of input parameter types of the target model, and the second sub-information includes a list of output parameter types of the target model. In this application embodiment, the first sub-information included in the first information sent by the first communication device may specifically include a list of input parameter types of the target model, enabling the second communication device to determine one or more input parameter types of the target model to be trained based on the first sub-information. Similarly, the second sub-information included in the first information sent by the first communication device may specifically include a list of output parameter types of the target model, enabling the second communication device to determine one or more output parameter types of the target model to be trained based on the second sub-information. This allows the second communication device to determine the specific type of the target model based on the input and output parameter types, and to train the target model required by the first communication device based on the specific type of the target model. This enables the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0244] It should be noted that the target model's input parameter type list may include one or more input parameter types, and the target model's output parameter type list may include one or more output parameter types. For example, if the target model's input parameter type list includes three input parameter types: time, location, and business, then the target model's input parameter type list can be represented as input(time, location, business); if the target model's output parameter type list includes one input parameter type: data volume, then the target model's output parameter type list can be represented as output(data volume).

[0245] In one possible implementation of this application embodiment, the first information is carried in the training data of the target model. In this application embodiment, the first information sent by the first communication device to indicate the target model can be carried in the training data of the target model. That is, the first communication device can send the training data of the target model carrying the first information, so that the second communication device can extract or parse the first information from the training data of the target model. This allows the second communication device to clarify the model training requirements of the first communication device based on the first information, and train the target model required by the first communication device based on the type of the target model. This enables the second communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby satisfying the training requirements of the first communication device for various models, including custom models.

[0246] It is understandable that when the first information is carried in the training data of the target model, the second communication device can analyze the received training data, determine the parameter types included in the training data, and further determine the input parameter types and output parameter types included in the parameter types based on the composition structure or arrangement order of the training data. That is, the first information can be extracted or parsed from the training data of the target model.

[0247] For example, if the training data of the target model is as shown in Table 2 above, after receiving the training data, the second communication device can directly extract the parameter types included in the training data, including time, location, service, and data volume. Furthermore, since the order of the data corresponding to time, location, and service precedes the order of the data corresponding to data volume, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0248] If the training data of the target model is as shown in Table 2 above, and the first three columns of data in Table 2 constitute the first information element, and the fourth column of data in Table 2 constitutes the second information element, where the first information element is marked as the input parameter and the second information element is marked as the output parameter, then after receiving the training data, the second communication device can directly extract the parameter types included in the training data, including time, location, service, and data volume. Furthermore, since the data corresponding to time, location, and service constitute the first information element carrying the input parameters, and the data volume constitutes the first information element carrying the input parameters, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0249] If the training data of the target model is as shown in Table 3 above, after receiving the training data, the second communication device can determine the parameter types included in the training data, including time, location, service, and data volume, by parsing or classifying the training data. Furthermore, since the order of the data corresponding to time, location, and service precedes the order of the data corresponding to data volume, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0250] If the training data of the target model is as shown in Table 3 above, and the first three columns of data in Table 3 constitute the first information element, and the fourth column of data in Table 3 constitutes the second information element, where the first information element is labeled as the input parameter and the second information element is labeled as the output parameter, then after receiving the training data, the second communication device can determine the parameter types included in the training data, including time, location, service, and data volume, by parsing or classifying the training data. Furthermore, since the data corresponding to time, location, and service constitute the first information element carrying the input parameters, and the data volume constitutes the first information element carrying the input parameters, it can be determined that the input parameter types of the target model include time, location, and service, and the output parameter type of the target model includes data volume.

[0251] In one possible implementation of this application embodiment, the training data of the target model includes a first information element and a second information element. The first information element includes input data in the training data, and the second information element includes output data in the training data.

[0252] In this embodiment, the training data of the target model sent by the first communication device can be composed of a first information element and a second information element. The first information element may include input data in the training data, and the second information element may include output data in the training data. That is, the input data and output data in the training data can be sent to the second communication device through two different information elements, so that the second communication device can better extract the first information from the training data of the target model, or can better distinguish the input data or output data in the training data, so as to train the target model required by the first communication device based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, and thus meet the training needs of the first communication device for various models, including custom models.

[0253] Information elements are the basic units used in the field of communication to describe the structure and content of information. An information element can represent a single piece of information, a group of information, or even a complex information structure. Information elements can be used to describe various types of information, such as information type, message content, transmission rate, and signal strength.

[0254] For example, if the training data of the target model is as shown in Table 2, and the first three columns in Table 2 are input data and the fourth column is output data, then the first information element of the training data may include the data in the first three columns of Table 2, and the second information element may include the data in the fourth column of Table 2.

[0255] In one possible implementation of this application embodiment, the training data of the target model includes multiple information elements, and the information elements include one or more input data and one or more output data of the training data.

[0256] In this embodiment, the training data of the target model sent by the first communication device can be composed of multiple information elements, each of which can carry one or more input data and one or more output data of the training data. That is, one or more complete data, including both input and output data, can be carried in the same information element for transmission. This allows the second communication device to better extract the first information from the training data of the target model, or to better identify the complete data in the training data. This enables the first communication device to train the target model required by the first communication device based on the training data of the target model, thereby completing the training of various models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for various models, including custom models.

[0257] For example, if the training data of the target model is as shown in Table 3, and the training data of the target model includes three information elements, then the first information element may include the data in the first row of Table 3, the second information element may include the data in the second row of Table 3, and the third information element may include the data in the third row of Table 3.

[0258] In one possible implementation of this application embodiment, the first message includes training data of the target model, or the method further includes:

[0259] F1. The first communication device sends a second message, and correspondingly, the second communication device receives the second message.

[0260] The second message is used to send the training data for the target model.

[0261] In this embodiment, the first communication device can also send training data required for training the target model based on the first message, meaning the first message can directly carry training data for training the target model. Alternatively, the first communication device can also send training data for the target model based on the second message, enabling the second communication device to obtain the training data of the target model based on the first or second message, and train the target model required by the first communication device based on the training data of the target model. This allows the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models.

[0262] In one possible implementation of this application embodiment, step 301, whereby the first communication device sends first information and the corresponding second communication device receives the first information, includes:

[0263] G1. The first communication device sends a first message, and correspondingly, the second communication device receives the first message.

[0264] The first message is used to request the target model.

[0265] G2. The first communication device sends a second message, and correspondingly, the second communication device receives the second message.

[0266] The second message is used to send the training data of the target model, and the second message includes the first message.

[0267] In this embodiment, the first communication device can first send a first message requesting the acquisition of a target model to inform the second communication device that the target model needs to be trained. Then, based on the second message, the first message and the training data of the target model can be sent to the second communication device. That is, the first message requesting the acquisition of the target model and the second message sending the training data can be sent sequentially. This allows the second communication device to first understand the need for model training based on the first message, then understand the specific model training needs of the first communication device based on the second message, i.e., to train the target model, and then acquire the training data required for training the target model based on the second message. Finally, the target model required by the first communication device is trained based on the training data of the target model. This enables the first communication device to complete the training of various models, including custom models, entrusted by the first communication device, thereby satisfying the training needs of the first communication device for various models, including custom models.

[0268] In one possible implementation of this application embodiment, the difference between the sending time of the first message and the sending time of the second message is less than a first threshold. In this application embodiment, the first communication device can send the first message and the second message sequentially, and the difference between the sending times of the first message and the second message can be less than the first threshold. That is, the interval between the sending times of the first message and the second message can be within a certain range, so that the second communication device can determine the association between the first message and the second message. This means it can determine that the training data of the target model carried in the second message is used to train the target model requested by the first message, thereby enabling the training of multiple models, including custom models, entrusted by the first communication device, and thus meeting the training needs of the first communication device for various models, including custom models. It should be noted that the specific value of the first threshold can be set according to actual conditions, and this application embodiment does not limit this.

[0269] In one possible implementation of this application embodiment, the first message includes first identification information, and the second message includes first identification information. In this application embodiment, the first communication device can send the first message and the second message sequentially, and both the first message and the second message can carry the first identification information; that is, the first message and the second message can carry the same identification information. This allows the second communication device to determine the association between the first message and the second message, i.e., to determine that the training data of the target model carried in the second message is used to train the target model requested by the first message. This enables the first communication device to complete the training of multiple models, including custom models, entrusted by the first communication device, thereby meeting the training needs of the first communication device for various models, including custom models. It should be noted that the first identification information can be an identity identification number, a random value, or a serial number, etc., and is not limited in this application embodiment.

[0270] S402. The second communication device sends a third message, and correspondingly, the first communication device receives the third message.

[0271] The third message is used to indicate that the first message has been received.

[0272] In this embodiment, if the first communication device sends a first message to the second communication device requesting to obtain a target model, and the second communication device needs a certain amount of time to train the target model, there may be a situation where the first communication device does not receive a reply from the second communication device after sending the first message. In this case, the first communication device may mistakenly believe that the first message was not successfully sent and may retransmit the first message, resulting in wasted resources. Therefore, after sending the first message, the first communication device can receive a third message from the second communication device indicating that the first message has been received. That is, after receiving the first message, the second communication device can send a third message to the first communication device to indicate that the first message has been received, thereby avoiding the first communication device mistakenly believing that the first message was not successfully sent and retransmitting the message, further saving transmission resources.

[0273] It is understood that the third message can be used to indicate that the first message has been received, to indicate that the target model is being trained, or to indicate that the second communication device has agreed to compute and provide feedback on the target model. For example, the third message can specifically be a response to a model acquisition request or a response to a model training request; this embodiment of the application does not limit the specific details.

[0274] In one possible implementation of this application embodiment, the third message includes at least one of the expected acquisition time of the target model or the identification information of the target model. In this application embodiment, the third message received by the first communication device may also carry the expected acquisition time of the target model and / or the identification information of the target model, enabling the first communication device to determine, based on the third message, how long it is expected to take to acquire the target model, and / or to determine, based on the identification information of the target model carried in the third message, the expected acquisition time and whether the third message is specifically associated with the target model. It should be noted that the expected acquisition time of the target model may be the remaining training time of the target model predicted by the second communication device based on the training progress of the target model. The identification information of the target model may be information assigned to the target model by the second communication device to uniquely identify the target model.

[0275] S403. The second communication device sends a fourth message, and correspondingly, the first communication device receives the fourth message.

[0276] The fourth message includes the second information, which is used to indicate the model parameters of the target model.

[0277] In this embodiment, after receiving the first information, the second communication device can determine its model training requirements based on the first information, that is, determine the type of model to be trained, and identify the target model. The second communication device can also obtain the training data required for training the target model and determine the original model or training algorithm. Based on the determined model type, training data, and original model or training algorithm, the second communication device can train the model to obtain the target model. Finally, the second communication device can send the trained target model's parameters (i.e., second information indicating the target model's parameters) to the first communication device via a fourth message. This allows the first communication device, upon receiving the second information, to construct the target model based on its parameters, thereby enabling it to train various models, including custom models, as requested by the first communication device, thus meeting its training requirements for custom models and other types of models. For example, the first communication device can adjust the parameters of the original model used to train the target model based on the target model's parameters to obtain the target model.

[0278] In one possible implementation of this application embodiment, the fourth message further includes identification information of the target model. In this application embodiment, the fourth message received by the first communication device may also carry identification information of the target model, so that the first communication device can determine that the second information carried in the fourth message and the fourth message itself are associated with the target model.

[0279] In one possible implementation of this application embodiment, if the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

[0280] In this embodiment, the first communication device may have one or more models in use, each model may correspond to an identification information, and different models may have different functions. After these models have been used for a period of time, their accuracy may gradually decrease due to various reasons, requiring adjustment and updates. If the target model requested by the first communication device is used to replace the existing first model in the first communication device, the fourth message used to transmit the second information may also carry the identification information of the first model, so that the first communication device can determine that the target model is used to replace the existing first model in the first communication device, and can replace the first model with the obtained target model.

[0281] It should be noted that different models may have different functions, meaning each model can have a corresponding function identifier, or function ID. When a model is assigned a corresponding function ID, the model's identification information can include the function ID and model ID. In other words, the target model's identification information can include the target model's corresponding function ID and model ID, and the first model's identification information can also include the first model's corresponding function ID and model ID.

[0282] In one possible implementation of this application embodiment, the method further includes:

[0283] S404. The first communication device sends the fifth message, and correspondingly, the second communication device receives the fifth message.

[0284] The fifth message is used to request the transmission of the model parameters of the target model.

[0285] In this embodiment, after sending a first message requesting the acquisition of the target model, the first communication device can, after a certain period of time, such as when the target model training is estimated to be complete, send a fifth message to the second communication device to request the second communication device to transmit the model parameters of the target model to the first communication device. This satisfies the training needs of the first communication device for various models, such as custom models. It is understood that after sending the first message, the first communication device can not only passively wait for the model parameters of the target model from the second communication device, but also actively request the network to send the model parameters of the target model by sending the fifth message. The fifth message may carry the identification information of the target model.

[0286] As illustrated by the foregoing embodiments, after the first communication device sends a first message to the second communication device requesting to obtain the target model, the second communication device needs a certain amount of time to train the target model. There may be a situation where the first communication device does not receive a response from the second communication device after sending the first message. In this case, the first communication device may mistakenly believe that the first message was not successfully sent and may retransmit the first message, resulting in wasted resources. Therefore, after sending the first message requesting to obtain the target model, the first communication device can receive a third message from the second communication device indicating that the first message has been received, and finally receive second information indicating the model parameters of the target model based on a fourth message. This avoids the first communication device mistakenly believing that the first message was not successfully sent and retransmitting the message, further saving transmission resources.

[0287] Referring to Figure 5, this application embodiment provides a communication device 500. This communication device 500 can implement the functions of the second or first communication device in the above method embodiments, and therefore also achieves the beneficial effects of the above method embodiments. In this application embodiment, the communication device 500 can be the first communication device (or the second communication device), or it can be an integrated circuit or component, such as a chip, inside the first communication device (or the second communication device). The communication device 500 may include a processing unit 501 and a transceiver unit 502.

[0288] It should be noted that the transceiver unit 502 may include a transmitting unit and a receiving unit, which are used to perform transmitting and receiving respectively.

[0289] In one possible implementation, when the device 500 is used to execute the method performed by the first communication device in the foregoing embodiments; the transceiver unit 502 is used to send first information, which is used to indicate a target model, the first information including first sub-information and second sub-information, the first sub-information being used to indicate the input parameter type of the target model, and the second sub-information being used to indicate the output parameter type of the target model; and to receive second information, which is used to indicate the model parameters of the target model.

[0290] In one possible implementation, when the device 500 is used to execute the method performed by the second communication device in the foregoing embodiments, the transceiver unit 502 is used to receive first information, which is used to indicate a target model. The first information includes first sub-information and second sub-information. The first sub-information is used to indicate the input parameter type of the target model, and the second sub-information is used to indicate the output parameter type of the target model. The transceiver unit 502 is used to send second information, which is used to indicate the model parameters of the target model.

[0291] In one possible implementation, when the device 500 is used to execute the method performed by the first communication device in the foregoing embodiments; the transceiver unit 502 is used to send a first message, the first message being used to request the acquisition of a target model; receive a third message, the third message being used to indicate that the first message has been received; and receive a fourth message, the fourth message including second information, the second information being used to indicate the model parameters of the target model.

[0292] In one possible implementation, when the device 500 is used to execute the method performed by the second communication device in the foregoing embodiments, the transceiver unit 502 is used to receive a first message, which is used to request the acquisition of a target model; send a third message, which is used to indicate that the first message has been received; and send a fourth message, which includes the second information, which is used to indicate the model parameters of the target model.

[0293] It should be noted that the information execution process of the unit of the above-mentioned communication device 500 can be specifically described in the method embodiment shown above in this application, and will not be repeated here.

[0294] Please refer to Figure 6, which is another schematic structural diagram of the communication device 600 provided in this application. The communication device 600 includes a logic circuit 601 and an input / output interface 602. The communication device 600 can be a chip or an integrated circuit.

[0295] In Figure 5, the transceiver unit 502 can be a communication interface, which can be the input / output interface 602 in Figure 6, and the input / output interface 602 can include an input interface and an output interface. Alternatively, the communication interface can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0296] Optionally, the input / output interface 602 is used to send first information, which is used to indicate a target model. The first information includes first sub-information and second sub-information. The first sub-information is used to indicate the input parameter type of the target model, and the second sub-information is used to indicate the output parameter type of the target model. It also receives second information, which is used to indicate the model parameters of the target model.

[0297] Optionally, the input / output interface 602 is used to receive first information, which is used to indicate a target model. The first information includes first sub-information and second sub-information. The first sub-information is used to indicate the input parameter type of the target model, and the second sub-information is used to indicate the output parameter type of the target model. The second information is used to indicate the model parameters of the target model.

[0298] Optionally, the input / output interface 602 is used to send a first message, which is used to request the acquisition of the target model; receive a third message, which is used to indicate that the first message has been received; and receive a fourth message, which includes second information, which is used to indicate the model parameters of the target model.

[0299] Optionally, the input / output interface 602 is used to receive a first message, which is used to request the acquisition of a target model; send a third message, which is used to indicate that the first message has been received; and send a fourth message, which includes the second information, which is used to indicate the model parameters of the target model.

[0300] The logic circuit 601 and the input / output interface 602 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.

[0301] In one possible implementation, the processing unit 501 shown in FIG5 can be the logic circuit 601 in FIG6.

[0302] Optionally, the logic circuit 601 can be a processing device, the functions of which can be partially or entirely implemented in software.

[0303] 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.

[0304] 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.

[0305] 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.

[0306] Please refer to Figure 7, which shows the communication device 700 involved in the above embodiments provided in the embodiments of this application. Specifically, the communication device 700 can be the communication device as a terminal device in the above embodiments. The communication device shown in Figure 7 is implemented through a terminal device (or a component in the terminal device).

[0307] The present invention provides a possible logical structure diagram of the communication device 700, which may include, but is not limited to, at least one processor 701 and a communication port 702.

[0308] In Figure 5, the transceiver unit 502 can be a communication interface, which can be the communication port 702 in Figure 7. The communication port 702 can include an input interface and an output interface. Alternatively, the communication port 702 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0309] Further optionally, the device may also include at least one of a memory 703 and a bus 704. In the embodiments of this application, the at least one processor 701 is used to control the operation of the communication device 700.

[0310] Furthermore, the processor 701 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.

[0311] It should be noted that the communication device 700 shown in Figure 7 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 7 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0312] Please refer to Figure 8, which is a schematic diagram of the structure of the communication device 800 involved in the above embodiments provided in the embodiments of this application. Specifically, the communication device 800 can be a communication device as a network device in the above embodiments. The communication device shown in Figure 8 is implemented through a network device (or a component in a network device). The structure of the communication device can be referred to the structure shown in Figure 9.

[0313] The communication device 800 includes at least one processor 811 and at least one network interface 814. Optionally, the communication device further includes at least one memory 812, at least one transceiver 813, and one or more antennas 815. The processor 811, memory 812, transceiver 813, and network interface 814 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 815 is connected to the transceiver 813. The network interface 814 enables the communication device to communicate with other communication devices through a communication link. For example, the network interface 814 may include a network interface between the communication device and core network equipment, such as an S1 interface, or 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.

[0314] In Figure 5, the transceiver unit 502 can be a communication interface, which can be the network interface 814 in Figure 8. The network interface 814 can include an input interface and an output interface. Alternatively, the network interface 814 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0315] The processor 811 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 811 in Figure 8 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 may include multiple baseband processors to adapt to different network standards, and multiple CPUs to enhance its processing capabilities. The 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.

[0316] The memory is primarily used to store software programs and data. The memory 812 can exist independently or be connected to the processor 811. Optionally, the memory 812 can be integrated with the processor 811, for example, integrated into a single chip. The memory 812 can store program code that executes the technical solutions of the embodiments of this application, and its execution is controlled by the processor 811. The various types of computer program code being executed can also be considered as drivers for the processor 811.

[0317] Figure 8 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.

[0318] Transceiver 813 can be used to support the reception or transmission of radio frequency (RF) signals between a communication device and a terminal. Transceiver 813 can be connected to antenna 815. Transceiver 813 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 815 can receive RF signals. The receiver Rx of transceiver 813 receives the RF signals from the antennas, converts the RF signals into digital baseband signals or digital intermediate frequency (IF) signals, and provides the digital baseband signals or IF signals to processor 811 so that processor 811 can perform further processing on the digital baseband signals or IF signals, such as demodulation and decoding. Furthermore, the transmitter Tx in transceiver 813 is also used to receive modulated digital baseband signals or IF signals from processor 811, convert the modulated digital baseband signals or IF signals into RF signals, and transmit the RF signals through one or more antennas 815. 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.

[0319] The transceiver 813 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.

[0320] It should be noted that the communication device 800 shown in Figure 8 can be used to implement the steps implemented by the network device in the aforementioned method embodiments and achieve the corresponding technical effects of the network device. The specific implementation of the communication device 800 shown in Figure 8 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0321] 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.

[0322] 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.

[0323] 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.

[0324] This application also provides a communication system, which includes a first communication device and a second communication device in any of the above embodiments.

[0325] 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.

[0326] 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.

[0327] 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, The method includes: Send first information, which is used to indicate the target model. The first information includes first sub-information and second sub-information. The first sub-information is used to indicate the input parameter type of the target model, and the second sub-information is used to indicate the output parameter type of the target model. Receive second information, which is used to indicate the model parameters of the target model.

2. The method according to claim 1, characterized in that, The first sub-information includes a list of input parameter types for the target model, and the second sub-information includes a list of output parameter types for the target model.

3. The method according to claim 1, characterized in that, The first information is contained in the training data of the target model.

4. The method according to any one of claims 1 to 3, characterized in that, The sending of the first information includes: Send a first message, which includes the first information, and the first message is used to request the acquisition of the target model.

5. The method according to claim 4, characterized in that, The first message includes the training data of the target model, or the method further includes: Send a second message, which is used to send the training data of the target model.

6. The method according to any one of claims 1 to 3, characterized in that, The sending of the first information includes: Send a first message, which is used to request the acquisition of the target model; Send a second message, which is used to send the training data of the target model, and the second message includes the first information.

7. The method according to claim 6, characterized in that, The difference between the sending time of the first message and the sending time of the second message is less than a first threshold.

8. The method according to claim 6, characterized in that, The first message includes first identification information, and the second message includes the first identification information.

9. The method according to claim 5 or 6, characterized in that, The training data of the target model includes a first information element and a second information element. The first information element includes the input data in the training data, and the second information element includes the output data in the training data.

10. The method according to claim 5 or 6, characterized in that, The training data of the target model includes multiple information elements, which include one or more input data and one or more output data of the training data.

11. A communication method, characterized in that, The method includes: Receive first information, the first information being used to indicate a target model, the first information including first sub-information and second sub-information, the first sub-information being used to indicate the input parameter type of the target model, and the second sub-information being used to indicate the output parameter type of the target model; Send a second message, which indicates the model parameters of the target model.

12. The method according to claim 11, characterized in that, The first sub-information includes a list of input parameter types for the target model, and the second sub-information includes a list of output parameter types for the target model.

13. The method according to claim 11, characterized in that, The first information is contained in the training data of the target model.

14. The method according to claims 11 to 13, characterized in that, The receiving of the first information includes: Receive a first message, the first message including the first information, the first message being used to request the acquisition of the target model.

15. The method according to claim 14, characterized in that, The first message includes the training data of the target model, or the method further includes: Receive a second message, which is used to send the training data of the target model.

16. The method according to claims 11 to 13, characterized in that, The receiving of the first information includes: Receive a first message, which is used to request the acquisition of the target model; A second message is received, which is used to send the training data of the target model, and the second message includes the first information.

17. The method according to claim 16, characterized in that, The difference between the sending time of the first message and the sending time of the second message is less than a first threshold.

18. The method according to claim 16, characterized in that, The first message includes first identification information, and the second message includes the first identification information.

19. The method according to claim 15 or 16, characterized in that, The training data of the target model includes a first information element and a second information element. The first information element includes the input data in the training data, and the second information element includes the output data in the training data.

20. The method according to claim 15 or 16, characterized in that, The training data of the target model includes multiple information elements, which include one or more input data and one or more output data in the training data.

21. A communication method, characterized in that, The method includes: Send a first message, which is used to request the target model; Receive a third message, the third message being used to indicate that the first message has been received; A fourth message is received, the fourth message including second information, the second information being used to indicate the model parameters of the target model.

22. The method according to claim 21, characterized in that, The third message includes at least one of the expected acquisition time of the target model or the identification information of the target model.

23. The method according to claim 21, characterized in that, The fourth message also includes the identification information of the target model.

24. The method according to claim 23, characterized in that, If the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

25. The method according to any one of claims 21 to 24, characterized in that, The method further includes: Send a fifth message, which is used to request the transmission of the model parameters of the target model.

26. A communication method, characterized in that, The method includes: Receive a first message, which is used to request the target model; Send a third message, the third message being used to indicate that the first message has been received; A fourth message is sent, the fourth message including second information, the second information being used to indicate the model parameters of the target model.

27. The method according to claim 26, characterized in that, The third message includes at least one of the expected acquisition time of the target model or the identification information of the target model.

28. The method according to claim 26, characterized in that, The fourth message also includes the identification information of the target model.

29. The method according to claim 26, characterized in that, If the target model is used to replace the first model, the fourth message also includes the identification information of the first model.

30. The method according to any one of claims 26 to 29, characterized in that, The method further includes: Receive a fifth message, which is used to request the transmission of the model parameters of the target model.

31. A communication device, characterized in that, Includes a module for performing the method as described in any one of claims 1 to 30.

32. 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 30.

33. A computer program product, characterized in that, It includes a computer program or instructions that, when executed by a computer, implement the method as described in any one of claims 1 to 30.

Images