Search

CN-122028094-A - Communication method and device

CN122028094ACN 122028094 ACN122028094 ACN 122028094ACN-122028094-A

Abstract

The application provides a communication method and a communication device, which belong to the field of communication and are suitable for more complex business scenes of an AI/ML model. The method includes the network service consuming entity sending a first message to the network service producing entity requesting the network service producing entity to provide an AI/ML model for completing a service between the network and the terminal, the network service consuming entity receiving a second message from the network service producing entity, the second message including information of the AI/ML model, the AI/ML model including a first AI/ML model and a second AI/ML model, the first AI/ML model being deployed to the network, the first AI/ML model and the second AI/ML model being used to complete the service through interaction in the case the first AI/ML model is deployed to the network, the second AI/ML model being deployed to the terminal.

Inventors

  • GUO TAO

Assignees

  • 华为技术有限公司

Dates

Publication Date
20260512
Application Date
20241112

Claims (20)

  1. 1. A method of communication applied to a network service consumption entity, the method comprising: sending a first message to a network service production entity, the first message for requesting the network service production entity to provide an artificial intelligence AI/machine learning ML model for completing traffic between a network and a terminal; Receiving a second message from the web service production entity, the second message including information of the AI/ML model, the AI/ML model including a first AI/ML model and a second AI/ML model, the first AI/ML model deployed to the network and the second AI/ML model deployed to the terminal, the first AI/ML model and the second AI/ML model configured to complete the service through interaction.
  2. 2. The method of claim 1, wherein the first message comprises first information indicating the service.
  3. 3. The method of claim 2, wherein the first information comprises an identification of the service.
  4. 4. A method according to any one of claims 1-3, wherein the method further comprises: and transmitting information of the second AI/ML model to the terminal in response to the second message.
  5. 5. The method of claim 4, wherein the sending information of the second AI/ML model to the terminal comprises: and in the case that the terminal is a terminal allowing the use of the second AI/ML model, transmitting information of the second AI/ML model to the terminal.
  6. 6. The method according to claim 4 or 5, wherein the second message further comprises a list of terminal identifications, the identification indicated by the list of terminal identifications being identifications of terminals permitted to use the second AI/ML model.
  7. 7. The method of claim 6, wherein the method further comprises: Acquiring the identification of the terminal; and confirming the identification of the terminal in the terminal identification list.
  8. 8. The method of claim 5, wherein the terminal permitted to use the second AI/ML model is any terminal.
  9. 9. The method according to any of claims 1-8, wherein the first message further comprises an identification of the terminal.
  10. 10. The method according to claim 6 or 9, characterized in that the identity of the terminal is any one of a permanent device identifier, a model approval code, or a user permanent identifier.
  11. 11. A method according to any one of claims 1-3, wherein the method further comprises: In response to the second message, information of the first AI/ML model is sent to one or more other entities in the network other than the network service consuming entity.
  12. 12. The method of claim 11, wherein the sending the information of the first AI/ML model to one or more other entities in the network other than the network service consuming entity comprises: and in the case that the other entity is an entity allowing the use of the first AI/ML model, transmitting information of the first AI/ML model to the other entity.
  13. 13. The method according to claim 11 or 12, wherein the second message further comprises an entity identification list indicating an identification of entities allowed to use the first AI/ML model.
  14. 14. The method according to any of claims 10-13, wherein the network service consuming entity is an access and mobility management network element and the other entity is an access network device to which the terminal is accessing.
  15. 15. A method according to any of claims 1-3, wherein the network service consuming entity is an entity in the network, the method further comprising: in response to the second message, the first AI/ML model is deployed locally to the network service consumption entity.
  16. 16. The method of claim 15, wherein the network service consuming entity is an access network device to which the terminal has access.
  17. 17. A communication method applied to a network service production entity, the method comprising: receiving a first message from a network service consumption entity, the first message for requesting the network service production entity to provide an artificial intelligence AI/machine learning ML model for completing traffic between a network and a terminal; And sending a second message to the network service consumption entity, wherein the second message comprises information of the AI/ML model, the AI/ML model comprises a first AI/ML model and a second AI/ML model, and the first AI/ML model and the second AI/ML model are used for completing the service through interaction under the condition that the first AI/ML model is deployed to the network and the second AI/ML model is deployed to the terminal.
  18. 18. The method of claim 17, wherein the first message further comprises first information indicating the service, the method further comprising: And acquiring information of the first AI/ML model and information of the second AI/ML model according to the first information.
  19. 19. The method of claim 17, wherein the sending the second message to the network service consumption entity comprises: And sending a second message to the network service consumption entity according to the fact that the identification of the network service consumption entity corresponds to a service authority identification, wherein the service authority identification is used for indicating an entity which is allowed to request an AI/ML model corresponding to the service.
  20. 20. The method of claim 19, wherein the first message further comprises an identification of the network service consumption entity.

Description

Communication method and device Technical Field The present application relates to the field of communications, and in particular, to a communication method and apparatus. Background Artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) can allow a machine to have human intelligence, such as can allow the machine to employ the software and hardware of a computer to simulate certain human intelligence behavior. To implement artificial intelligence, a machine learning (MACHINE LEARNING, ML) approach may be used to obtain the AI/ML model. The AI/ML model can be used for reasoning, that is, it can be used to derive output data corresponding to a given input data. Therefore, the AI/ML model has rich application scenes in a plurality of industry fields, and the AI/ML model is authorized to be used by model consumers in a network, so that the model consumers can realize functions such as dialogue, writing, code generation, image generation and the like based on the AI/ML model. However, in the present case, how to cope with future more complex AI/ML model application scenarios is a hotspot problem of current research. Disclosure of Invention The embodiment of the application provides a communication method and a communication device, which are used for further expanding the application scene of an AI/ML model. In order to achieve the above purpose, the application adopts the following technical scheme: In a first aspect, a communication method is provided for a network service consumption entity, the method comprising sending a first message to a network service production entity, the first message for requesting the network service production entity to provide an artificial intelligence AI/machine learning ML model for completing a traffic between a network and a terminal, receiving a second message from the network service production entity, the second message comprising information of the AI/ML model, the AI/ML model comprising a first AI/ML model and a second AI/ML model, the first AI/ML model and the second AI/ML model being for completing the traffic by interaction in case the first AI/ML model is deployed to the network and the second AI/ML model is deployed to the terminal. It is known that in some possible AI/ML model service scenarios, where the service needs to be completed by at least two models deployed at different model consumers interacting with each other, the network service consumption entity may send a first message for the service, the first message requesting the network service production entity to provide the AI/ML model for completing the service, and accordingly the network service production entity may send a second message to the network service consumption entity according to the first message, the second message including information of the AI/ML model, where the AI/ML model may refer to the model needed to complete the service, and may include, for example, the first AI/ML model for deployment to the network and the second AI/ML model for deployment to the terminal. Thus, compared to the prior art authorization scenario for a single AI/ML model, the present approach can enable authorization of multiple AI/ML models that are functionally related to each other to accommodate more complex business scenarios. In one possible embodiment, the first message includes first information, where the first information is used to indicate a service. That is, the network service consumption entity can use the service as a granularity request model, deploy different models according to different service demands, and enable the deployment of the models to be more flexible. Optionally, the first information comprises an identification of the service. For example, the identification of the service may be an analysis ID (analytics ID) to indicate the service. The analysis ID can be an existing message structure, if a new service needs to be completed through at least two models deployed to the network and the terminal respectively, the service requirement can be realized by multiplexing the existing cells, the realization complexity is reduced, and the method is more friendly to the standard. A new cell structure may also be defined for the analysis ID to decouple new traffic from existing traffic, enabling more flexibility. In a possible design, the method according to the first aspect further includes sending information of the second AI/ML model to the terminal in response to the second message, so that the second AI/ML model can be deployed to the terminal. Optionally, sending the information of the second AI/ML model to the terminal includes sending the information of the second AI/ML model to the terminal if the terminal is a terminal that allows use of the second AI/ML model. The information of the second AI/ML model is ensured to be sent to the terminal with the use authority, so that the information of the second AI/ML model is prevented from being sent to the terminal without the use authority