Search

CN-122029791-A - Control method of AI/ML model in wireless communication system

CN122029791ACN 122029791 ACN122029791 ACN 122029791ACN-122029791-A

Abstract

The present disclosure provides a control method of an artificial intelligence/machine learning (AI/ML) model in a wireless communication system, including acquiring AI/ML model region information by a node in the wireless communication system, the node including at least one of a terminal or a base station, and determining model control of the AI/ML model by the node based on the AI/ML model region information. The present disclosure also provides a wireless communication method for a terminal, including the terminal acquiring AI/ML model area information from a first base station, the AI/ML model area information being used for the terminal to determine model control of an AI/ML model, wherein the terminal determines whether to perform model control of the AI/ML model based on the AI/ML model area information.

Inventors

  • QU MIAO
  • ZHANG YINCHENG
  • CHEN ZHE

Assignees

  • 深圳TCL新技术有限公司

Dates

Publication Date
20260512
Application Date
20230929

Claims (20)

  1. A control method of an artificial intelligence/machine learning AI/ML model in a wireless communication system, comprising: The wireless communication node acquires AI/ML model area information, determines model control of an AI/ML model based on the AI/ML model area information, and is a base station or a terminal.
  2. The method of claim 1, wherein the model control of the AI/ML model comprises at least one of: AI/ML model activation, AI/ML model deactivation, AI/ML model selection, AI/ML model switching, AI/ML model rollback, AI/ML model updating, AI/ML model training, AI/ML model retraining, or AI/ML model fine-tuning.
  3. The method of claim 1, wherein the AI/ML model region information comprises at least one of: The AI/ML model region identification ID, The information of the location of the object is provided, The information of the scene is provided to the user, The wireless communication node capability information is provided to the wireless communication node, And/or AI/ML model information.
  4. The method of claim 3, wherein the location information comprises at least one of: cell information, AI/ML model area identification ID, terminal location information, base station location information, context information, control unit CU ID, data unit DU ID.
  5. The method of claim 3, wherein the scene information comprises at least one of: transmission environment information, speed information, angle spread information, delay spread information, signal to noise ratio, channel received power, and/or interference information.
  6. The method of claim 3, wherein the wireless communication node capability information comprises at least one of: Computing power, storage power, AI/ML model support power, load case, transmission power, AI/ML model support AI/ML usage scenarios and/or AI/ML model support AI/ML features.
  7. The method of claim 3, wherein the AI/ML model information includes at least one of: AI/ML model ID information, and/or AI/ML model meta information.
  8. The method of claim 1, wherein the AI/ML model region information is transmitted by at least one of: A non-access stratum NAS message, a radio resource control RRC message, a medium access control element MAC-CE message, a downlink control information DCI message, an uplink channel, a downlink channel, a system message, an N2 message, and/or an Xn message.
  9. The method of claim 3, wherein determining, by the wireless communication node, model control of an AI/ML model based on the AI/ML model region information comprises at least one of: If the location information of the wireless communication node belongs to the location information indicated in the AI/ML model area information, the wireless communication node does not perform model control of an AI/ML model; If the location information of the wireless communication node does not belong to the location information indicated in the AI/ML model area information, the wireless communication node performs model control of an AI/ML model; If the AI/ML model information of the wireless communication node belongs to the AI/ML model information indicated in the AI/ML model region information, the wireless communication node does not perform model control of the AI/ML model; The wireless communication node performs model control of an AI/ML model if AI/ML model information of the wireless communication node does not belong to AI/ML model information indicated in the AI/ML model region information.
  10. The method of claim 9, wherein the executing model control of an AI/ML model comprises at least one of: AI/ML model activation, AI/ML model deactivation, AI/ML model selection, AI/ML model switching, AI/ML model fallback, AI/ML model updating, AI/ML model training, AI/ML model retraining, or AI/ML model fine tuning, reporting of results of model control of the AI/ML model, and/or response of model control of the AI/ML model.
  11. The method of claim 10, wherein the terminal acquires the AI/ML model region configuration information when the wireless communication node is a terminal, and the terminal performs model control of the AI/ML model in accordance with the AI/ML model region information.
  12. The method of claim 11, wherein the terminal obtaining the AI/ML model region configuration information comprises at least one of: AI/ML model information, an event, an indicator, a terminal ID, and/or location information.
  13. The method of claim 10, wherein when the wireless communication node is a base station, the base station acquires the AI/ML model area configuration information, and the base station performs model control of the AI/ML model in accordance with the AI/ML model area information.
  14. The method of claim 13, wherein the base station obtaining the AI/ML model region configuration information comprises at least one of: AI/ML model information, an event, an indicator, a base station ID, and/or location information.
  15. The method of claim 1, wherein the AI/ML model region information request message and/or response message sent by a first wireless communication node to a second wireless communication node comprises at least one of: The AI/ML model region identification ID, The information of the location of the object is provided, The information of the scene is provided to the user, Wireless communication node capability information, and/or AI/ML model information.
  16. The method of claim 15, wherein the wireless communication node transmits a request message for the AI/ML model region information, including periodic transmission or event triggering.
  17. The method of claim 16, wherein the AI/ML model region information is updated in response to a periodic configuration, wherein the periodic configuration includes a duration, a start time, and/or an end time of the update, in the case of the periodic transmission.
  18. The method of claim 16, wherein the AI/ML model region information is updated in response to an event-triggered configuration, where the manner is event-triggered.
  19. The method according to claim 16, wherein the periodic transmission and/or the event triggered corresponding periodic configuration and/or event triggered configuration is preconfigured, and/or configured, and/or fixed.
  20. The method of claim 15, the AI/ML model region information request message and/or response message is carried by at least one of: A non-access stratum NAS message, a radio resource control RRC message, a medium access control element MAC-CE message, a downlink control information DCI message, an uplink channel, a downlink channel, a system message, an N2 message, and/or an Xn message.

Description

Control method of AI/ML model in wireless communication system Technical Field The present disclosure relates to the field of communication systems, and more particularly, to a control method of an artificial intelligence/machine learning (AI/ML) model and a chip thereof, a computer-readable storage medium and a computer program product for use in a wireless communication system, a wireless communication method and a chip thereof for use in a user equipment (terminal), a computer-readable storage medium and a computer program product, and a wireless communication method and a chip thereof for use in a first base station, a computer-readable storage medium and a computer program product. Background Our society is undergoing a digital revolution, and in the past few years, artificial Intelligence (AI) and Machine Learning (ML) methods are widely used in various industries to promote innovation and increase process efficiency. However, with the dramatic increase in data volume and network complexity in terms of network design, conventional approaches will not provide a fast solution in many cases. Therefore, AI/ML will become an indispensable technology for pushing future wireless communication network performance improvement. In fact, in wireless communication systems using AI/ML over the air interface, the channel may become worse due to user equipment (terminal) mobility, possibly leading to handover. When the terminal moves to a new serving base station (e.g., gNB), the system may use conventional methods or AI/ML-based methods in some use cases. If the AI/ML based approach is employed, model control (e.g., model selection, switching, updating, etc.) of the AI/ML model may need to be performed during the switching process in order to ensure continuity of service. Current wireless communication networks do not have the ability to support such model control. It should be noted that what is described in this section does not constitute or be considered an admission of any prior art. Disclosure of Invention To overcome at least one of the above-described technical problems, the present disclosure provides a control method for an artificial intelligence/machine learning (AI/ML) model in a wireless communication system, which can ensure normal operation of the model control during handover, reduce signaling overhead, and reduce delay in dynamic information reporting. One aspect of the present disclosure provides a control method of an artificial intelligence/machine learning AI/ML model in a wireless communication system, including: The wireless communication node acquires AI/ML model area information, determines model control of an AI/ML model based on the AI/ML model area information, and is a base station or a terminal. In accordance with one or more embodiments of the present disclosure, the model control of the AI/ML model includes at least one of: AI/ML model activation, AI/ML model deactivation, AI/ML model selection, AI/ML model switching, AI/ML model rollback, AI/ML model updating, AI/ML model training, AI/ML model retraining, or AI/ML model fine-tuning. According to one or more embodiments of the present disclosure, the AI/ML model region information includes at least one of: The AI/ML model region identification ID, The information of the location of the object is provided, The information of the scene is provided to the user, The wireless communication node capability information is provided to the wireless communication node, And/or AI/ML model information. According to one or more embodiments of the present disclosure, the location information includes at least one of: cell information, AI/ML model area identification ID, terminal location information, base station location information, context information, control unit CU ID, data unit DU ID. According to one or more embodiments of the present disclosure, the scene information includes at least one of: transmission environment information, speed information, angle spread information, delay spread information, signal to noise ratio, channel received power, and/or interference information. According to one or more embodiments of the present disclosure, the wireless communication node capability information includes at least one of: Computing capabilities, storage capabilities, AI/ML model support capabilities, load conditions, and/or transmission capabilities, AI/ML model support AI/ML usage scenarios and/or AI/ML model support AI/ML features. In detail, in some examples, for example, some specific computing capabilities, some specific storage capabilities, AI/ML models support some specific capabilities, some specific load cases, some specific transmission capabilities, AI/ML models support some specific usage scenarios and/or support some specific features. Wireless network capability node capability information indicating a capability of a wireless network node, such as model operational capability of an AI/ML model supported by the node, hardwar