Search

KR-102961918-B1 - METHOD AND APPARATUS FOR USING ARTIFICIAL INTELLIGENCE/MACHINE LEARNING MODEL IN WIRELESS COMMUNICATION NETWORK

KR102961918B1KR 102961918 B1KR102961918 B1KR 102961918B1KR-102961918-B1

Abstract

The present embodiments provide a method for a terminal to use an AI/ML model in a wireless communication network, comprising the steps of receiving activation or deactivation instruction information for the AI/ML model, activating or deactivating the AI/ML model based on the instruction information, and transmitting a response regarding the activation or deactivation of the AI/ML model.

Inventors

  • 김선우
  • 정홍석
  • 정민수

Assignees

  • 한양대학교 산학협력단

Dates

Publication Date
20260507
Application Date
20230711
Priority Date
20220712

Claims (20)

  1. In a method for a terminal to use an AI/ML model in a wireless communication network, A step of transmitting capability information of the terminal related to whether the above AI/ML model is supported to a base station; A step of receiving activation or deactivation instruction information for an AI/ML model; A step of activating or deactivating the AI/ML model based on the above instruction information; and The step of transmitting a response regarding the activation or deactivation of the above AI/ML model, wherein The above capability information includes at least one AI/ML function performed at the terminal and at least one AI/ML model ID for each of the at least one AI/ML function, and The above at least one AI/ML function includes a beam prediction function, and A method comprising the above-mentioned instruction information, which instructs switching to another AI/ML model based on the performance of the AI/ML model enabled to perform the beam prediction function.
  2. delete
  3. In Article 1, The above AI/ML model is, A method in which life cycle management is performed according to at least one of feature-based AI/ML model classification or model ID-based AI/ML model classification.
  4. In Paragraph 3, The above activation or deactivation instruction information is, A method received through at least one of upper-layer signaling, MAC CE (MAC Control Element), or downlink control information, in accordance with the above function-based AI/ML model classification.
  5. In Paragraph 3, The above activation or deactivation instruction information is, A method received based on the model ID when following the above model ID-based AI/ML model classification.
  6. In Article 1, The above AI/ML model is, A method classified into UE-side models, Network-side models, and Two-sided models based on the subject of the inference operation through the above AI/ML models.
  7. In Article 1, A method further comprising the step of configuring wireless resources used for transmitting and receiving input data or output data that can be used for the AI/ML model when the AI/ML model is activated.
  8. In Article 1, The above AI/ML model is, A method for determining whether to transmit an AI/ML model based on a pre-configured cooperation level.
  9. In Article 8, A method further comprising the step of receiving a request for training information and transmitting a response according to the request when the transmission of the above AI/ML model is not required.
  10. In Article 8, A method further comprising the step of receiving a request for AI/ML model information and transmitting a response according to the request when the transmission of the above AI/ML model is required.
  11. In a terminal using an AI/ML model in a wireless communication network, Transmitter; Receiver; and It includes a control unit that controls the operation of the transmitting unit and the receiving unit, and The above control unit is, Transmit capability information of the terminal related to whether the above AI/ML model is supported to a base station, receive activation or deactivation instruction information for the AI/ML model, activate or deactivate the AI/ML model based on the instruction information, and transmit a response regarding the activation or deactivation of the AI/ML model, The above capability information includes at least one AI/ML function performed at the terminal and at least one AI/ML model ID for each of the at least one AI/ML function, and The above at least one AI/ML function includes a beam prediction function, and The above instruction information is a terminal that includes information instructing to switch to another AI/ML model based on the performance of the AI/ML model enabled to perform the beam prediction function.
  12. delete
  13. In Article 11, The above AI/ML model is, A terminal in which life cycle management is performed according to at least one of function-based AI/ML model classification or model ID-based AI/ML model classification.
  14. In Article 13, The above activation or deactivation instruction information is, A terminal received through at least one of upper-layer signaling, MAC CE (MAC Control Element), or downlink control information, in accordance with the above function-based AI/ML model classification.
  15. In Article 13, The above activation or deactivation instruction information is, A terminal received based on the model ID, in accordance with the above model ID-based AI/ML model classification.
  16. In Article 11, The above AI/ML model is, A terminal classified into a UE-side model, a Network-side model, and a Two-sided model based on the subject of the inference operation through the above AI/ML model.
  17. In Article 11, The above control unit is, A terminal comprising wireless resources used for transmitting and receiving input data or output data that can be used by the AI/ML model when the above AI/ML model is activated.
  18. In Article 11, The above AI/ML model is, A terminal in which the transmission of an AI/ML model is determined based on a pre-configured cooperation level.
  19. In Article 18, The above control unit is, A terminal that receives a request for training information and transmits a response to the request when the transmission of the above AI/ML model is not required.
  20. In Article 18, The above control unit is, A terminal that receives a request for AI/ML model information and transmits a response in accordance with the request when transmission of the above AI/ML model is required.

Description

Method and apparatus for using artificial intelligence/machine learning model in wireless communication network These embodiments propose a method and apparatus for using an AI/ML (ARTIFICIAL INTELLIGENCE/MACHINE LEARNING) model in a next-generation wireless access network (hereinafter referred to as "NR (New Radio)"). At 3GPP, designs for frame structures, channel coding and modulation, and waveforms and multiple access schemes for NR (New Radio) are currently underway. Compared to LTE, NR is required to be designed to satisfy not only improved data transmission rates but also various QoS requirements for detailed and specific usage scenarios. eMBB (enhancement Mobile BroadBand), mMTC (massive Machine Type Communication), and URLLC (Ultra Reliable and Low Latency Communications) have been defined as representative usage scenarios for NR, and a flexible frame structure design compared to LTE is required to satisfy the requirements of each usage scenario. Since each service requirement (usage scenario) has different demands regarding data rates, latency, reliability, and coverage, there is a need for a method to efficiently multiplex wireless resource units based on different numerologies (e.g., subcarrier spacing, subframe, TTI (Transmission Time Interval), etc.) as a way to efficiently satisfy the requirements of each usage scenario through the frequency bands that constitute an arbitrary NR system. Meanwhile, there is an increasing demand for the introduction of artificial intelligence or machine learning technologies in wireless communication to achieve faster, more accurate, and more efficient communication. Accordingly, specific designs for utilizing AI/ML models in wireless communication networks are becoming necessary. FIG. 1 is a diagram briefly illustrating the structure of an NR wireless communication system to which the present embodiment can be applied. FIG. 2 is a drawing illustrating the frame structure in an NR system to which the present embodiment can be applied. FIG. 3 is a diagram illustrating a resource grid supported by wireless access technology to which the present embodiment can be applied. FIG. 4 is a diagram illustrating the bandwidth part supported by the wireless access technology to which the present embodiment can be applied. FIG. 5 is a diagram illustrating an exemplary synchronization signal block in a wireless access technology to which the present embodiment can be applied. FIG. 6 is a diagram illustrating a random access procedure in a wireless access technology to which the present embodiment can be applied. Figure 7 is a diagram for explaining CORESET. FIG. 8 is a diagram illustrating an example of symbol level alignment in different subcarrier spacing (SCS) to which the present embodiment can be applied. FIG. 9 is a diagram illustrating a conceptual example of a bandwidth part to which the present embodiment can be applied. FIG. 10 is a diagram illustrating the structure of a functional framework for an AI/ML model according to one embodiment. FIG. 11 is a diagram illustrating a procedure for a terminal to use an AI/ML model according to one embodiment. FIG. 12 is a diagram illustrating a procedure for a base station to use an AI/ML model according to one embodiment. FIG. 13 is a diagram showing the configuration of a user terminal according to another embodiment. FIG. 14 is a diagram showing the configuration of a base station according to another embodiment. Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. In assigning reference numerals to the components of each drawing, the same components may have the same reference numeral as much as possible, even if they are shown in different drawings. Furthermore, in describing the embodiments, if it is determined that a detailed description of related known components or functions may obscure the essence of the technical concept, such detailed description may be omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it may include a plural unless otherwise specified. Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are used merely to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by such terms. In describing the positional relationship of components, where it is stated that two or more components are "connected," "combined," or "joined," it should be understood that while the two or more components may be directly "connected," "combined," or "joined," they may also be "connected," "combined," or "joined" with other components "intervened." Here, the other components may be included in one or more of the two or more components that are "c