WO2024065772A1

WO2024065772A1 - Wireless communication method and user equipment

Info

Publication number: WO2024065772A1
Application number: PCT/CN2022/123508
Authority: WO
Inventors: Miao Qu
Original assignee: Shenzhen TCL New Technology Co Ltd
Current assignee: Shenzhen TCL New Technology Co Ltd
Priority date: 2022-09-30
Filing date: 2022-09-30
Publication date: 2024-04-04
Anticipated expiration: 2025-03-30
Also published as: CN119999160A

Abstract

A wireless communication method executable in a user equipment (UE) includes: sending a first message to a first base station (BS), wherein the first message is used for requesting an artificial intelligence or machine learning (AI/ML) model selection; and receiving a second message from the first BS, wherein the second message is used for informing the UE of a result in response to the first message.

Description

WIRELESS COMMUNICATION METHOD AND USER EQUIPMENT

Technical Field

The present disclosure relates to the field of communication systems, and more particularly, to a wireless communication method and a user equipment (UE) .

Background Art

Our society is undergoing a digitization revolution. In the last few years, artificial intelligence (AI) and machine learning (ML) methods are widely used in various industries to advance innovation and increase process efficiency. However, for the network design, with the dramatic increase of both the extraordinary amount of data and network complexity, conventional approaches will not be able to provide swift solutions in many cases. Hence, AI/ML will be an indispensable technology to improve the performance for future wireless communication networks.

In order to support for integrating AI/ML into the design of cellular network, the network data analytics function (NWDAF) was introduced in Release (Rel. 15) and has been enhanced in Rel. 16 and Rel. 17 in Service and System Aspects Working Group 2 (SA2) , which insights are mainly applied to 5G core (5GC) networks to enhance their functionality. Meanwhile, optimized data collection and storage have been specified, together with training and ML model retrieval. In Nov 2019, 3GPP SA1 TR22.874 has studied the use cases and the potential performance requirements for 5G system (5GS) support of AI/ML model distribution and transfer. For Radio Access Network (RAN) perspective, a study item about AI/ML enabled RAN in RAN3 Rel. 17 has been approved. This study TR37.817 was to explore the wireless Big Data acquisitions and applications for network automation and intelligence, including the definition of use case, and the process and information interaction required by different uses cases. Then, for investigating the potential benefits of AI/ML algorithms for air interface, a new study item was supported in Rel. 18 at 3GPP RAN plenary meetings, which is leaded by RAN1. In this study, it will explore the 3GPP framework for AI/ML for air interface corresponding to each target use case regarding aspects such as performance, complexity, and potential specification impact.

Since a trained AI/ML model may not always work over the air interface for the dynamic variations of the wireless channel, it is important to characterize the life cycle management (LCM) of AI/ML model. An AI/ML model selection After the detailed discussion of many companies, in the last RAN1 #110 meeting, an agreement clearly states that an AI/ML model selection the LCM is a necessary part in the LCM.

As mentioned above, the AI/ML model selection is a necessary step for activating an AI/ML model over air interface. In addition, it is helpful for the AI/ML models to work effectively in the wireless communication system by selecting the suitable AI/ML models.

Technical Problem

In the prior art, a procedure of an AI/ML model selection and assistance information of the AI/ML model selection have not been introduced clearly.

Technical Solution

An object of the present disclosure is to propose a wireless communication method and a user equipment.

A first aspect of the present disclosure provides a wireless communication method executable in a user equipment (UE) , including: sending a first message to a first base station (BS) , wherein the first message is used for requesting an artificial intelligence or machine learning (AI/ML) model selection; and receiving a second message from the first BS, wherein the second message is used for informing the UE of a result in response to the first message.

A second aspect of the present disclosure provides a wireless communication method executable in a user equipment (UE) , including: receiving a first message from a first base station (BS) , wherein the first message is used for inquiring whether the UE initiates an artificial intelligence or machine learning (AI/ML) model selection or comprises at least one new AI/ML model; and sending a second message to the first BS, wherein the second message is used for informing the first BS of a result in response to the first message.

A third aspect of the present disclosure provides a wireless communication method executable in a user equipment (UE) , including: receiving, in response to a first message from a first base station (BS) to a server and a second message from the server to the first BS, a third message, wherein the first message is used for requesting whether at least one new AI/ML model exists, the second message comprises the at least one new AI/ML model, and the third message is used for inquiring whether the UE initiates an AI/ML model selection or comprises at least one new AI/ML model; and sending a fourth message to the first BS, wherein the fourth message is used for informing the first BS of a result in response to the third message.

A fourth aspect of the present disclosure provides a user equipment, including: a memory, a transceiver, and a processor coupled to the memory and the transceiver, wherein the processor is configured to execute any one of the above-mentioned methods.

The disclosed method may be implemented in a chip. The chip may include a processor, configured to call and run a computer program stored in a memory, to cause a device in which the chip is installed to execute the disclosed method.

The disclosed method may be programmed as computer executable instructions stored in non-transitory computer readable medium. The non-transitory computer readable medium, when loaded to a computer, directs a processor of the computer to execute the disclosed method.

The non-transitory computer readable medium may include at least one from a group consisting of: a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a Read Only Memory, a Programmable Read Only Memory, an Erasable Programmable Read Only Memory, EPROM, an Electrically Erasable Programmable Read Only Memory and a Flash memory.

The disclosed method may be programmed as computer program product that causes a computer to execute the disclosed method.

The disclosed method may be programmed as computer program that causes a computer to execute the disclosed method.

Advantageous Effects

The present disclosure can solve the problem of how to execute an AI/ML model selection between or among nodes. The present disclosure provides two methods to initiate the AI/ML model selection. One method is initiated by a UE, and the other method is initiated by a BS.

Description of Drawings

In order to more clearly illustrate the embodiments of the present disclosure or related art, the following figures will be described in the embodiments are briefly introduced. It is obvious that the drawings are merely some embodiments of the present disclosure, a person having ordinary skill in this field can obtain other figures according to these figures without paying the premise.

FIG. 1 is a schematic diagram showing a telecommunication system.

FIG. 2 is a schematic diagram showing a wireless communication method executable in a user equipment (UE) according to an embodiment of the present disclosure.

FIG. 3 is a schematic diagram showing a wireless communication method according to an embodiment of the present disclosure. The wireless communication method in FIG. 3 illustrates a detailed process of selecting at least one AI/ML model.

FIG. 4 is a schematic diagram showing a wireless communication method according to another embodiment of the present disclosure.

FIG. 5 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 6 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 7 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 8 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 9 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 10 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 11 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 12 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 13 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 14 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 15 is a schematic diagram showing a wireless communication method executable in a user equipment (UE) according to another embodiment of the present disclosure.

FIG. 16 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 17 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 18 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 19 is a schematic diagram showing a wireless communication method executable in a user equipment (UE) according to yet another embodiment of the present disclosure.

FIG. 20 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 21 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure.

FIG. 22 is a block diagram of a system for wireless communication according to an embodiment of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS

Embodiments of the present disclosure are described in detail with the technical matters, structural features, achieved objects, and effects with reference to the accompanying drawings as follows. Specifically, the terminologies in the embodiments of the present disclosure are merely for describing the purpose of the certain embodiment, but not to limit the present disclosure.

With reference to FIG. 1, a telecommunication system including a group 100a of a plurality of UEs, a base station (BS) 200a, and a network entity device 300 executes the disclosed method according to an embodiment of the present disclosure. The group 100a of a plurality of UEs may include a UE 10a, a UE 10b, and other UEs. FIG. 1 is shown for illustrative not limiting, and the system may include more UEs, BSs, and CN entities. Connections between devices and device components are shown as lines and arrows in the figure. Connections between devices may be realized by wireless connections. Connections between device components may be realized by wirelines, buses, traces, cables or optical fabrics. The UE 10a may include a processor 11a, a memory 12a, and a transceiver 13a. The UE 10b may include a processor 11b, a memory 12b, and a transceiver 13b. The base station 200a may include a baseband unit (BBU) 204a. The base band unit 204a may include a processor 201a, a memory 202a, and a transceiver 203a. The network entity device 300 may include a processor 301, a memory 302, and a transceiver 303. Each of the

processors

11a, 11b, 201a, and 301 may be configured to implement proposed functions, procedures and/or methods described in the description. Layers of radio interface protocol may be implemented in the

processors

11a, 11b, 201a, and 301. Each of the

memories

12a, 12b, 202a, and 302 operatively stores a variety of programs and information to operate a connected processor. Each of the

transceivers

13a, 13b, 203a, and 303 is operatively coupled with a connected processor, transmits and/or receives radio signals or wireline signals. The UE 10a may be in communication with the UE 10b through a sidelink. The base station 200a may be an eNB, a gNB, or one of other types of radio nodes.

Each of the

processors

11a, 11b, 201a, and 301 may include a central processing unit (CPU) , an application-specific integrated circuits (ASICs) , other chipsets, logic circuits and/or data processing devices. Each of the

memories

12a, 12b, 202a, and 302 may include a read-only memory (ROM) , a random access memory (RAM) , a flash memory, a memory card, a storage medium and/or other storage devices. Each of the

transceivers

13a, 13b, 203a, and 303 may include baseband circuitry and radio frequency (RF) circuitry to process radio frequency signals. When the embodiments are implemented in software, the techniques described herein can be implemented with modules, units, procedures, functions, entities and so on, that perform the functions described herein. The modules can be stored in a memory and executed by the processors. The memory can be implemented within a processor or external to the processor, in which those can be communicatively coupled to the processor via various means are known in the art.

The network entity device 300 may be a node in a CN. CN may include LTE CN or 5G core (5GC) which includes user plane function (UPF) , session management function (SMF) , mobility management function (AMF) , unified data management (UDM) , policy control function (PCF) , control plane (CP) /user plane (UP) separation (CUPS) , authentication server (AUSF) , network slice selection function (NSSF) , and network exposure function (NEF) .

The present disclosure aims to solve the problem that a procedure of an artificial intelligence or machine learning (AI/ML) model selection and assistance information of the AI/ML model selection have not been introduced clearly in the prior art. It is noted that the AI/ML model selection refers to select an AI model or an ML model.

In an AI/ML model over an air interface, a trained AI/ML model by a model training function is used for a model inference function, and then the model inference function using the trained AI/ML model to produce a set of outputs based on a set of inputs. As discussion in the before meetings, the model inference function and the model training function can be located in the same side or the different sides, whatever in one-sided AI/ML model or two-sided AI/ML model. Hence, due to the locations of the model inference function and the model training function in different use cases, the process of the AI/ML model selection may be different.

When the model inference function and the model training function are located in the same side, a node (e.g., gNB, network (NW) , or UE) knows the trained AI/ML model, and the nodes also knows its own requirement. Hence, the AI/ML model selection is up to the node implementation. However, the signaling and assistance information about data collection for model training, and/or model interface and others, are not included in the procedure of the AI/ML model selection.

When the model inference function and the model training function are located in different sides, two nodes do not know information about at least one AI/ML model. Moreover, a model transfer occurs in this case. Hence, in order to process the AI/ML model selection between or among nodes, the AI/ML model selection can be initiated by two methods. One method is initiated by a UE, and the other method is initiated by a BS.

Please refer to FIG. 2. FIG. 2 is a schematic diagram showing a wireless communication method executable in a user equipment (UE) according to an embodiment of the present disclosure. In the present embodiment, a model training function is deployed in a BS, and a model inference function is used within a UE. Furthermore, an AI/ML model selection is initiated by a UE.

In operation S200, a first message is sent to a first BS, wherein the first message is used for requesting an artificial intelligence or machine learning (AI/ML) model selection.

After receiving the first message, the first BS is noted that the UE has a requirement for enabling the AI/ML model selection and wants to select at least one AI/ML model for use in some cases.

In operation S202, a second message is received from the first BS, wherein the second message is used for informing the UE of a result in response to the first message.

After receiving the first message, the first BS sends the second message to the UE to inform the UE whether to agree the request of the AI/ML model selection.

According to the embodiment in FIG. 2, there are several methods for performing an AI/ML model selection. Please refer to FIG. 3. FIG. 3 is a schematic diagram showing a wireless communication method according to an embodiment of the present disclosure. The wireless communication method in FIG. 3 illustrates a detailed process of selecting at least one AI/ML model.

In operation S300, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

After receiving the first message, the first BS is noted that the UE has a requirement for enabling the AI/ML model selection and wants to select at least one AI/ML model for use in some cases. The first message includes at least one of the following information: an identification (ID) of the UE, a request cause, and a capability of the UE for supporting an AI/ML model transfer, delivery, or download. The ID of the UE is used for identifying the UE. The request cause is used for indicating a reason for initiating the AI/ML model selection. The capability of the UE for supporting an AI/ML model transfer, delivery, or download is used for indicating that the UE has the capability for supporting the AI/ML model transfer, delivery, or download from the first BS to the UE.

In operation S302, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

After receiving the first message, the first BS sends the second message to the UE to inform the UE whether to agree the request of the AI/ML model selection in operation S300. For example, the second message can include an information element (IE) for indicating that the request of the AI/ML model selection in operation S300 is accepted or rejected. Alternatively, the second message can be used for informing the UE that the first BS agrees the request of the AI/ML model selection in operation S300. That is, when the UE receives the second message, the UE can continue to send related information for the AI/ML Model selection.

Alternatively, the second message can be further used for configuring at least one of the following information for the UE: a storage capability of the UE, a valid storage capability of the UE, at least one type of at least one AI/ML model required by the UE, an amount of the at least one AI/ML model required by the UE, complexity of the at least one AI/ML model required by the UE, at least one generalization of the at least one AI/ML model required by the UE, at least one key performance indicator (KPI) of the at least one AI/ML model required by the UE, and at least one transfer format of the at least one AI/ML model required by the UE.

The storage capability of the UE means the storage capability of UE for storing the at least one AI/ML models. According to complexity of different AI/ML models, the different AI/ML models can occupy different storage of the UE.

The valid storage capability of the UE means the valid storage of the UE at the current time.

The at least one type of the at least one AI/ML model required by the UE means which kind of AI/ML models that the UE requires.

The amount of the at least one AI/ML model required by the UE means that a number of the at least one AI/ML model that the UE requires. In detail, the UE can require more than one AI/ML model within a same family of models or within different families of models.

The complexity of the at least one AI/ML model required by the UE can be, but is not limited to, floating point operations (FLPOs) or a size of parameters.

The at least one generalization of the at least one AI/ML model required by the UE means that a capability of the at least one AI/ML model can be worked in different use cases.

The at least one KPI of the at least one AI/ML model required by the UE can be, but is not limited to, latency, rate, precision, power consumption, reliability and so on.

The at least one transfer format of the at least one AI/ML model required by the UE means the at least one transfer format of the at least one AI/ML model supported by the UE.

In operation, S304, a third message is sent to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection.

After sending the second message, the first BS receives the third message from the UE. In detail, the third message is used for indicating the condition of selecting the at least one the AI/ML model. Only an AI/ML model or models which meet the condition of the AI/ML model selection can serve as a candidate AI/ML model or candidate models.

In an embodiment, the third message is used for indicating the condition of the AI/ML model selection according to the at least one information configured by the second message in operation S302. That is, the UE selects the condition of the AI/ML model selection from the information configured by the first BS in operation S302 and sends the condition of the AI/ML model selection to the first BS via the third message.

In another embodiment, the third message is used for indicating the condition of the AI/ML model selection according to at least one requirement of the UE. That is, the UE selects the condition of the AI/ML model selection according to the at least one requirement of the UE. The UE can select the condition of the AI/ML model selection from the information in operation S302.

In operation S306, at least one candidate AI/ML model is selected according to the third message by the first BS, and at least one AI/ML model is selected from the at least one candidate AI/ML model.

After receiving the third message, the first BS can determine the at least one candidate AI/ML model according to the third message (including the condition of the AI/ML model selection) . Then, the at least one AI/ML model is selected from the at least one candidate AI/ML model, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S308, the at least one AI/ML model selected according to the third message by the first BS is sent from the first BS to the UE.

The UE receives the at least one AI/ML model selected according to the third message by the first BS and can activate the at least one AI/ML model.

Please refer to FIG. 4. FIG. 4 is a schematic diagram showing a wireless communication method according to another embodiment of the present disclosure. The wireless communication method in FIG. 4 illustrates another detailed process of selecting at least one AI/ML model.

In operation S400, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S402, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

In operation, S404, a third message is sent from the UE to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection.

Detailed descriptions of operations S400-S404 can refer to related descriptions of operations S300-S304 and are not repeated herein.

In operation S406, at least one candidate AI/ML model is selected according to the third message by the first BS, and the at least one candidate AI/ML model is transferred to the UE by the first BS.

After receiving the third message, the first BS can determine the at least one candidate AI/ML model according to the third message (including the condition of the AI/ML model selection) . Then, the first BS transfers the at least one candidate AI/ML model to the UE.

In operation S408, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

The UE receives the at least one candidate AI/ML model and selects the at least one AI/ML model from the at least one candidate AI/ML model and can activate the at least one AI/ML model.

Please refer to FIG. 5. FIG. 5 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 5 illustrates a detailed process of selecting at least one AI/ML model.

In operation S500, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S502, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

In operation, S504, a third message is sent from the UE to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection.

Detailed descriptions of operations S500-S504 can refer to related descriptions of operations S300-S304 and are not repeated herein.

In operation S506, a fourth message is sent from the first BS to at least one second BS, wherein the fourth message is used for searching the at least second BS.

In the present embodiment, at least one of the first message and the third message includes information of at least one second BS paired with the UE. Information of an ID of the at least one second BS can be obtained by the UE, a network, and so on. Furthermore, the fourth message can further include the condition of the AI/ML model selection in operation S504.

In an embodiment of the present disclosure, the wireless communication method includes operations S508a-S512a.

In operation S508a, a fifth message is sent from the at least one second BS to the first BS, and at least one candidate AI/ML model selected by the at least one second BS is transferred to the first BS, wherein the fifth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S510a, at least one AI/ML model is selected from the at least one candidate AI/ML model by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S512a, the at least one AI/ML model selected according to the third message by the first BS is sent from the first BS to the UE.

In another embodiment of the present disclosure, the wireless communication method includes operations S508b-S512b.

In operation S508b, a fifth message is sent from the at least one second BS to the UE, wherein the fifth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S510b, at least one AI/ML model is selected from at least one candidate AI/ML model by the at least one second BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S512b, the at least one AI/ML model selected according to the third message by the at least one second BS is sent from the at least one second BS to the UE.

Please refer to FIG. 6. FIG. 6 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 6 illustrates a detailed process of selecting at least one AI/ML model.

In operation S600, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S602, a second message is received from the first BS, wherein the second message is used for informing the UE of a result in response to the first message.

In operation, S604, a third message is sent from the UE to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection.

Detailed descriptions of operations S600-S604 can refer to related descriptions of operations S300-S304 and are not repeated herein.

In operation S606, a fourth message is sent from the first BS to at least one second BS, wherein the fourth message is used for searching the at least second BS.

In the present embodiment, at least one of the first message and the third message includes information of at least one second BS paired with the UE. Information of an ID of the at least one second BS can be obtained by the UE, a network, and so on. Furthermore, the fourth message can further include the condition of the AI/ML model selection in operation S604.

In an embodiment of the present disclosure, the wireless communication method includes operations S608a-S612a.

In operation S608a, a fifth message is sent from the at least one second BS to the first BS, and at least one candidate AI/ML model selected by the at least one second BS is transferred to the first BS, wherein the fifth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S610a, the at least one candidate AI/ML model is transferred to the UE by the first BS.

In operation S612a, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In another embodiment of the present disclosure, the wireless communication method includes operations S608b-S562b.

In operation S608b, a fifth message is sent to from the at least one second BS to the UE, wherein the fifth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S610b, at least one candidate AI/ML model is transferred to the UE by the at least one second BS.

In operation S612b, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

Please refer to FIG. 7. FIG. 7 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 7 illustrates a detailed process of selecting at least one AI/ML model.

In operation S700, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S702, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

In operation, S704, a third message is sent from the UE to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection.

Detailed descriptions of operations S700-S704 can refer to related descriptions of operations S300-S304 and are not repeated herein.

In operation S706, a fourth message is sent from the first BS to a server, wherein the fourth message is used for sending the condition of the AI/ML model selection to the server.

In operation S708, at least one AI/ML model is selected from at least one candidate AI/ML model according to the third message by the server.

In operation S710, the at least one AI/ML model is transferred to the first BS by the at least one second BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S712, the at least one AI/ML model is transferred to the UE by the first BS.

Please refer to FIG. 8. FIG. 8 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 8 illustrates a detailed process of selecting at least one AI/ML model.

In operation S800, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S802, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

In operation, S804, a third message is sent from the UE to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection.

Detailed descriptions of operations S800-S804 can refer to related descriptions of operations S300-S304 and are not repeated herein.

In operation S806, a fourth message is sent from the first BS to a server, wherein the fourth message is used for sending the condition of the AI/ML model selection to the server.

In operation S808, at least one candidate AI/ML model is transferred to the first BS by the server.

In operation S810, the at least one candidate AI/ML model is transferred to the UE by the first BS.

In operation S812, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

Please refer to FIG. 9. FIG. 9 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 9 illustrates a detailed process of selecting at least one AI/ML model.

In operation S900, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In the present embodiment, the first message is further used for indicating a condition of the AI/ML model selection and includes at least one of the following information: an identification (ID) of the UE, a request cause for indicating a reason for initiating the AI/ML model selection, a capability of the UE for supporting an AI/ML model transfer, delivery, or download, a storage capability of the UE, a valid storage capability of the UE, at least one type of at least one AI/ML model required by the UE, an amount of the at least one AI/ML model required by the UE, complexity of the at least one AI/ML model required by the UE, at least one generalization of the at least one AI/ML model required by the UE, at least one key performance indicator (KPI) of the at least one AI/ML model required by the UE, and at least one transfer format of the at least one AI/ML model required by the UE.

The above-mentioned information can refer to the related descriptions of the embodiment in FIG. 3.

In operation S902, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

After receiving the first message, the first BS sends the second message to the UE to inform the UE whether to agree the request of the AI/ML model selection in operation S900. For example, the second message can include an information element (IE) for indicating that the request of the AI/ML model selection in operation S900 is accepted or rejected. Alternatively, the second message can be used for informing the UE that the first BS agrees the request of the AI/ML model selection in operation S900.

In operation, S904, at least one AI/ML model is selected according to the first message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S906, the at least one AI/ML model is transferred to the UE by the first BS.

Please refer to FIG. 10. FIG. 10 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 10 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1000, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S1002, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

Detailed descriptions of operations S1000-S1002 can refer to related descriptions of operations S900-S904 and are not repeated herein.

In operation, S1004, at least one candidate AI/ML model is transferred to the UE by the first BS.

In operation S1006, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

Please refer to FIG. 11. FIG. 11 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 11 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1100, a first message is sent from UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In the present embodiment, the first message is further used for indicating a condition of the AI/ML model selection and includes at least one of the following information: an identification (ID) of the UE, a request cause for indicating a reason for initiating the AI/ML model selection, a capability of the UE for supporting an AI/ML model transfer, delivery, or download, a storage capability of the UE, a valid storage capability of the UE, at least one type of at least one AI/ML model required by the UE, an amount of the at least one AI/ML model required by the UE, complexity of the at least one AI/ML model required by the UE, at least one generalization of the at least one AI/ML model required by the UE, at least one key performance indicator (KPI) of the at least one AI/ML model required by the UE, and at least one transfer format of the at least one AI/ML model required by the UE. Furthermore, the first message further includes information of at least one second BS paired with the UE.

In operation S1102, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

After receiving the first message, the first BS sends the second message to the UE to inform the UE whether to agree the request of the AI/ML model selection in operation S500. For example, the second message can include an information element (IE) for indicating that the request of the AI/ML model selection in operation S1000 is accepted or rejected. Alternatively, the second message can be used for informing the UE that the first BS agrees the request of the AI/ML model selection in operation S1000. That is, when the UE receives the second message, the UE can continue to send related information for the AI/ML Model selection.

In operation S1104, a third message is sent from the first BS to the at least one second BS, wherein the third message is used for searching the at least second BS and includes the condition of the AI/ML model selection.

In an embodiment of the present disclosure, the wireless communication method includes operations S1106a-S1110a.

In operation S1106a, a fourth message is sent from the at least one second BS to the first BS, and at least one candidate AI/ML model is transferred to the first BS by the at least one second BS, wherein the fourth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S1108a, at least one AI/ML model is selected from the at least one candidate AI/ML model by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S1110a, the at least one AI/ML model is sent from the first BS to the UE.

In another embodiment of the present disclosure, the wireless communication method includes operations S1106b-S1110b.

In operation S1106b, a fourth message is sent from the at least one second BS to the UE, wherein the fourth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S1108a, at least one AI/ML model is selected from at least one candidate AI/ML model by the at least one second BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S1110ab, the at least one AI/ML model is transferred from the at least one second BS to the UE.

Please refer to FIG. 12. FIG. 12 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 12 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1200, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S1202, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

In operation S1204, a third message is sent from the first BS to the at least one second BS, wherein the third message is used for searching the at least second BS and includes the condition of the AI/ML model selection.

Detailed descriptions of operations S1200-S1204 can refer to related descriptions of operations S1100-S1104 and are not repeated herein.

In an embodiment of the present disclosure, the wireless communication method includes operations S1206a-S1210a.

In operation S1206a, a fourth message is sent from the at least one second BS to the first BS, and at least one candidate AI/ML model is transferred to the first BS by the at least one second BS, wherein the fourth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S1208a, the at least one candidate AI/ML model is transferred to the UE from the first BS.

In operation S1210a, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In another embodiment of the present disclosure, the wireless communication method includes operations S1206b-S1210b.

In operation S1206b, a fourth message is sent from the at least one second BS to the UE, wherein the fourth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.

In operation S1208a, at least one candidate AI/ML model is transferred to the UE from the at least one second BS.

In operation S1210b, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

Please refer to FIG. 13. FIG. 13 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 13 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1300, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S1302, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

After receiving the first message, the first BS sends the second message to the UE to inform the UE whether to agree the request of the AI/ML model selection in operation S1300. For example, the second message can include an information element (IE) for indicating that the request of the AI/ML model selection in operation S1300 is accepted or rejected. Alternatively, the second message can be used for informing the UE that the first BS agrees the request of the AI/ML model selection in operation S1300. That is, when the UE receives the second message, the UE can continue to send related information for the AI/ML Model selection.

In operation S1304, a third message is sent from the first BS to a server, wherein the third message is used for sending the condition of the AI/ML model selection to the server.

In operation S1306, at least one AI/ML model is selected according to the third message by the server, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S1308, the at least one AI/ML model is transferred to the first BS by the at least one second BS.

In operation S1310, the at least one AI/ML model is transferred to the UE by the first BS.

Please refer to FIG. 14. FIG. 14 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 14 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1400, a first message is sent from a UE to a first BS, wherein the first message is used for requesting an AI/ML model selection.

In operation S1402, a second message is sent from the first BS to the UE, wherein the second message is used for informing the UE of a result in response to the first message.

In operation S1404, a third message is sent from the first BS to a server, wherein the third message is used for sending the condition of the AI/ML model selection to the server.

Detailed descriptions of operations S1400-S1404 can refer to related descriptions of operations S1300-S1304 and are not repeated herein.

In operation S1406, at least one candidate AI/ML model is transferred to the first BS by the server.

In operation S1408, the at least one candidate AI/ML model is transferred to the UE by the first BS.

In operation S1410, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

Please refer to FIG. 15. FIG. 15 is a schematic diagram showing a wireless communication method executable in a user equipment (UE) according to another embodiment of the present disclosure. In the present embodiment, a model training function is deployed in a BS, and a model inference function is used within a UE. Furthermore, an AI/ML model selection is initiated by a first BS.

In operation S1500, a first message is received from a first BS, wherein the first message is used for inquiring whether the UE initiates an AI/ML model selection or includes at least one new AI/ML model.

In the present embodiment, the first message includes at least one of the following information: an identification (ID) of the UE, a request cause for indicating a reason for initiating the AI/ML model selection, a capability of the UE for supporting an AI/ML model transfer, delivery, or download, a storage capability of the UE, a valid storage capability of the UE, at least one type of at least one AI/ML model required by the UE, an amount of the at least one AI/ML model required by the UE, complexity of the at least one AI/ML model required by the UE, at least one generalization of the at least one AI/ML model required by the UE, at least one key performance indicator (KPI) of the at least one AI/ML model required by the UE, and at least one transfer format of the at least one AI/ML model required by the UE.

In an embodiment of the present disclosure, in response to the first message used for inquiring whether the UE initiates the AI/ML model selection or in response to the first message including the at least one new AI/ML model, the first message is received from the first BS when at least one AI/ML model stored in the first BS is changed.

In another embodiment of the present disclosure, in response to the first message used for inquiring whether the UE initiates the AI/ML model selection or in response to the first message including the at least one new AI/ML model, the first message is received from the first BS periodically. That is, the first BS periodically sends the first message to the UE.

In operation S1502, a second message is sent to the first BS, wherein the second message is used for informing the first BS of a result in response to the first message.

Please refer to FIG. 16. FIG. 16 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 16 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1600, a first message is sent from a first BS to a UE, wherein the first message is used for inquiring whether the UE initiates an AI/ML model selection or informing the UE that the first BS includes at least one new AI/ML model.

In operation S1602, a second message is sent from the UE to the first BS, wherein the second message is used for informing the first BS of a result in response to the first message.

After receiving the first message, the UE sends the second message to the first BS to inform the UE whether to agree the request in operation S1600. For example, the second message can include an information element (IE) for indicating that the request in operation S1600 is accepted or rejected. Alternatively, the second message can be used for informing the firs BS that the UE agrees the request in operation S1600. Furthermore, the second message is further used for indicating a condition of the AI/ML model selection

In operation S1604, at least one AI/ML model is selected according to the second message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S1606, the at least one AI/ML model is transferred to the UE by the first BS.

Please refer to FIG. 17. FIG. 17 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 17 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1700, a first message is sent from a first BS to a UE, wherein the first message is used for inquiring whether the UE initiates an AI/ML model selection or informing the UE that the first BS includes at least one new AI/ML model.

In operation S1702, a second message is sent from the UE to the first BS, wherein the second message is used for informing the first BS of a result in response to the first message.

Detailed descriptions of operations S1700-S1702 can refer to related descriptions of operations S1600-S1602 and are not repeated herein.

In operation S1704, at least one candidate AI/ML model is transferred to the UE by the first BS.

In operation S1706, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

Please refer to FIG. 18. FIG. 18 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 18 illustrates a detailed process of selecting at least one AI/ML model.

In operation S1800, at least one new AI/ML model is sent from a first BS to a UE.

The at least one new AI/ML model refers to an AI/ML model which is newly stored in the first BS and is not known (or used) by the UE before.

In operation S1802, at least one AI/ML model is selected from the at least one new AI/ML model by the UE.

In operation S1804, a second message is sent from the UE to the first BS, wherein the second message is used for indicating that the UE rejects the at least one new AI/ML model. Accordingly, a currently used AI/ML model continues work.

Please refer to FIG. 19. FIG. 19 is a schematic diagram showing a wireless communication method executable in a user equipment (UE) according to yet another embodiment of the present disclosure. In the present embodiment, a model training function is deployed in a BS, and a model inference function is used within a UE. Furthermore, an AI/ML model selection is initiated by a first BS.

In operation S1900, in response to a first message from a first BS to a server and a second message from the server to the first BS, a third message is received, wherein the first message is used for requesting whether at least one new AI/ML model exists, the second message comprises the at least one new AI/ML model, and the third message is used for inquiring whether the UE initiates an AI/ML model selection or comprises at least one new AI/ML model.

In operation S1902, a fourth message is sent to the first BS, wherein the fourth message is used for informing the first BS of a result in response to the third message.

Please refer to FIG. 20. FIG. 20 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 20 illustrates a detailed process of selecting at least one AI/ML model.

In operation S2000, a first message is sent from a first BS to a server, wherein the first message is used for requesting whether at least one new AI/ML model exists.

In operation S2002, a second message is sent from the server to the first BS, wherein the second message comprises the at least one new AI/ML model.

In operation S2004, a third message is sent from the first BS to a UE, wherein the third message is used for inquiring whether the UE initiates an AI/ML model selection or comprises at least one new AI/ML model.

In operation S2006, a fourth message is sent from the UE to the first BS, wherein the fourth message is used for informing the first BS of a result in response to the third message.

Furthermore, the fourth message is further used for indicating a condition of the AI/ML model selection

In operation S2008, at least one AI/ML model is selected according to the fourth message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

In operation S2010, the at least one AI/ML model is transferred to the UE by the first BS.

Please refer to FIG. 21. FIG. 21 is a schematic diagram showing a wireless communication method according to yet another embodiment of the present disclosure. The wireless communication method in FIG. 21 illustrates a detailed process of selecting at least one AI/ML model.

In operation S2100, a first message is sent from a first BS to a server, wherein the first message is used for requesting whether at least one new AI/ML model exists.

In operation S2102, a second message is sent from the server to the first BS, wherein the second message comprises the at least one new AI/ML model.

In operation S2104, a third message is sent from the first BS to a UE, wherein the third message is used for inquiring whether the UE initiates an AI/ML model selection or comprises at least one new AI/ML model.

In operation S2106, a fourth message is sent from the UE to the first BS, wherein the fourth message is used for informing the first BS of a result in response to the third message.

Detailed descriptions of operations S2100-S2106 can refer to related descriptions of operations S2000-S2006 and are not repeated herein.

In operation S2108, at least one candidate AI/ML model is transferred to the UE by the first BS.

In operation S2110, at least one AI/ML model is selected from the at least one candidate AI/ML model by the UE, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.

It should be noted that the first BS or the at least one second BS can refer to, but is not limited to, a gNB or a network (NW) .

The above-mentioned AI/ML model selection can be triggered by the following scenarios. When a node decides to use an AI/ML model in some use cases in a wireless communication. Alternatively, when some new requirements of a node appear, the node can select another AI/ML model/model. Alternatively, when a scenario has be changed, a node can select another AI/ML model.

For the process of the AI/ML model selection, a post processing should also be considered. This function can be located in the same side as a model training function, such as a gNB, a NW, or a server.

When AI/ML models are identified as candidate AI/ML models, a node can initiate the post processing for the candidate AI/ML models before a model transfer. In an example, the complexity of the AI/ML models can be reduced. In another example, the accuracy of the AI/ML models can be increased.

Information of the AI/ML model selection can be configured or provided. When a node which receives information, an AI/ML model might not meet all requirements or might only meet all the requirements strictly. A rule for the AI/ML model selection can include setting up priorities of requirements and/or setting up group priorities of requirements.

In an example, each of the requirements can be marked with a priority. For example, the type of an AI/ML model is priority 1, the complexity of an AI/ML model is priority 2, the latency of an AI/ML model is 3, and the generalization of an AI/ML is 4. When all the requirements are met, an AI/ML model or models can be regard as the most suitable AI/ML model or models, which have the highest probability to be transferred.

In another example, each of the requirements can be marked with a priority. For example, the type of an AI/ML model is priority 1, the complexity of an AI/ML model is priority 2, the latency of an AI/ML model is 3, and the generalization of an AI/ML is 4. When several requirements are met, an AI/ML model or models can be regard as the suitable AI/ML model or models, which have probability to be transferred.

In another example, each of the requirements can be marked with a priority. For example, the type of an AI/ML model is priority 1, the complexity of an AI/ML model is priority 2, the latency of an AI/ML model is 3, and the generalization of an AI/ML is 4. When an AI/ML model or models in a priority group meet several requirements, the priority group has probability to be transferred. In summary, it is necessary to index or configure priorities of requirements.

The messages mentioned above can be higher layer messages and/or physical messages, such as radio resource control (RRC) messages, MAC CE, control protocol data unit (PDU) , downlink control information (DCI) , data PDU, or non-access stratum (NAS) . The messages can be sent by unicast, broadcast, or groupcast.

Furthermore, the messages mentioned above can be out of 3GPP. Alternatively, the messages mentioned above can be Xn messages.

Furthermore, the present disclosure further provides a user equipment, a chip, a non-transitory computer-readable storage medium, a non-transitory machine-readable storage medium, a computer program product, and a computer program to execute or cause a computer to perform the above-mentioned methods.

Please refer to FIG. 22. FIG. 22 is a block diagram of a system 700 for wireless communication according to an embodiment of the present disclosure. Embodiments described herein may be implemented into the system using any suitably configured hardware and/or software. FIG. 8 illustrates the system 700 including a radio frequency (RF) circuitry 710, a baseband circuitry 720, a processing unit 730, a memory/storage 740, a display 750, a camera 760, a sensor 770, and an input/output (I/O) interface 780, coupled with each other as illustrated.

The processing unit 730 may include a circuitry, such as, but not limited to, one or more single-core or multi-core processors. The processors may include any combinations of general-purpose processors and dedicated processors, such as graphics processors and application processors. The processors may be coupled with the memory/storage and configured to execute instructions stored in the memory/storage to enable various applications and/or operating systems running on the system. The RF circuitry 710, baseband circuitry 720, processing unit 730, memory/storage 740, display 750, camera 760, sensor 770, and I/O interface 780 are well-known elements in the system 700 such as, but not limited to, a laptop computing device, a tablet computing device, a netbook, an ultrabook, a smartphone, etc. In addition, the instructions as a software product can be stored in a readable storage medium in a computer. The software product in the computer is stored in a storage medium, including a plurality of commands for a computational device (such as a personal computer, a server, or a network device) to run all or some of the steps disclosed by the embodiments of the present disclosure. The storage medium includes a USB disk, a mobile hard disk, a read-only memory (ROM) , a random access memory (RAM) , a floppy disk, or other kinds of media capable of storing program codes.

The embodiment of the present disclosure is a combination of techniques/processes that can be adopted in 3GPP specification to create an end product.

While the present disclosure has been described in connection with what is considered the most practical and preferred embodiments, it is understood that the present disclosure is not limited to the disclosed embodiments but is intended to cover various arrangements made without departing from the scope of the broadest interpretation of the appended claims.

Claims

A wireless communication method, executable in a user equipment (UE) , the wireless communication method comprising:

sending a first message to a first base station (BS) , wherein the first message is used for requesting an artificial intelligence or machine learning (AI/ML) model selection; and

receiving a second message from the first BS, wherein the second message is used for informing the UE of a result in response to the first message.
The wireless communication method of claim 1, wherein the first message comprises at least one of the following information:

an identification (ID) of the UE;

a request cause for indicating a reason for initiating the AI/ML model selection; and

a capability of the UE for supporting an AI/ML model transfer, delivery, or download.
The wireless communication method of claim 1, wherein the second message is further used for configuring at least one of the following information for the UE:

a storage capability of the UE;

a valid storage capability of the UE;

at least one type of at least one AI/ML model required by the UE;

an amount of the at least one AI/ML model required by the UE;

complexity of the at least one AI/ML model required by the UE;

at least one generalization of the at least one AI/ML model required by the UE;

at least one key performance indicator (KPI) of the at least one AI/ML model required by the UE; and

at least one transfer format of the at least one AI/ML model required by the UE.
The wireless communication method of claim 3, further comprising:

sending a third message to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection according to the at least one information configured by the second message.
The wireless communication method of claim 3, further comprising:

sending a third message to the first BS, wherein the third message is used for indicating a condition of the AI/ML model selection according to at least one requirement of the UE.
The wireless communication method of claim 4 or 5, further comprising:

receiving the at least one AI/ML model selected according to the third message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
The wireless communication method of claim 4 or 5, further comprising:

receiving at least one candidate AI/ML model transferred from the first BS, wherein the at least one candidate AI/ML model meets the condition of the AI/ML model selection; and

selecting the at least one AI/ML model from the at least one candidate AI/ML model.
The wireless communication method of claim 4 or 5, wherein at least one of the first message and the third message comprises information of at least one second BS paired with the UE, and the wireless communication method further comprises:

receiving, in response to a fourth message sent from the first BS to the at least one second BS and a fifth message sent from the at least one second BS to the first BS, the at least one AI/ML model selected according to the third message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, the fourth message is used for searching the at least second BS, and the fifth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.
The wireless communication method of claim 4 or 5, wherein at least one of the first message and the third message comprises information of at least one second BS paired with the UE, and the wireless communication method further comprises:

receiving, in response to a fourth message sent from the first BS to the at least one second BS and a fifth message sent from the at least one second BS to the UE, the at least one AI/ML model selected according to the third message by the at least one second BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, the fourth message is used for searching the at least second BS, and the fifth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.
The wireless communication method of claim 4 or 5, wherein at least one of the first message and the third message comprises information of at least one second BS paired with the UE, and the wireless communication method further comprises:

receiving, in response to a fourth message sent from the first BS to the at least one second BS and a fifth message sent from the at least one second BS to the UE, at least one candidate AI/ML model transferred from the at least one second BS, wherein the fourth message is used for searching the at least second BS, and the fifth message is used for indicating that the at least one second BS agrees with the AI/ML model selection; and

selecting the at least one AI/ML model from the at least one candidate AI/ML model, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
The wireless communication method of claim 4 or 5, further comprising:

receiving, in response to a fourth message sent from the first BS to a server, the at least one AI/ML model selected according to the third message by the server, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, and the fourth message is used for sending the condition of the AI/ML model selection to the server.
The wireless communication method of claim 4 or 5, further comprising:

receiving, in response to a fourth message sent from the first BS to a server, at least one candidate AI/ML model transferred from the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, and the fourth message is used for sending the condition of the AI/ML model selection to the server.
The wireless communication method of claim 1, wherein the first message is further used for indicating a condition of the AI/ML model selection and comprises at least one of the following information:

an identification (ID) of the UE;

a request cause for indicating a reason for initiating the AI/ML model selection;

a capability of the UE for supporting an AI/ML model transfer, delivery, or download;

a storage capability of the UE;

a valid storage capability of the UE;

at least one type of at least one AI/ML model required by the UE;

an amount of the at least one AI/ML model required by the UE;

complexity of the at least one AI/ML model required by the UE;

at least one generalization of the at least one AI/ML model required by the UE;

at least one key performance indicator (KPI) of the at least one AI/ML model required by the UE; and

at least one transfer format of the at least one AI/ML model required by the UE.
The wireless communication method of claim 13, further comprising:

receiving the at least one AI/ML model selected according to the first message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
The wireless communication method of claim 13, further comprising:

receiving at least one candidate AI/ML model transferred from the first BS, wherein the at least one candidate AI/ML model meets the condition of the AI/ML model selection; and

selecting the at least one AI/ML model from the at least one candidate AI/ML model, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
The wireless communication method of claim 13, wherein the first message further comprises information of at least one second BS paired with the UE, and the wireless communication method further comprises:

receiving, in response to a third message sent from the first BS to the at least one second BS and a fourth message sent from the at least one second BS to the first BS, the at least one AI/ML model selected according to the first message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, the third message is used for searching the at least second BS, and the fourth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.
The wireless communication method of claim 13, wherein the first message comprises information of at least one second BS paired with the UE, and the wireless communication method further comprises:

receiving, in response to a third message sent from the first BS to the at least one second BS and a fourth message sent from the at least one second BS to the UE, the at least one AI/ML model selected according to the first message by the at least one second BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, the third message is used for searching the at least second BS, and the fourth message is used for indicating that the at least one second BS agrees with the AI/ML model selection.
The wireless communication method of claim 13, wherein the first message comprises information of at least one second BS paired with the UE, and the wireless communication method further comprises:

receiving, in response to a third message sent from the first BS to the at least one second BS and a fourth message sent from the at least one second BS to the UE, at least one candidate AI/ML model transferred from the at least one second BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, the third message is used for searching the at least second BS, and the fourth message is used for indicating that the at least one second BS agrees with the AI/ML model selection; and

selecting the at least one AI/ML model from the at least one candidate AI/ML model.
The wireless communication method of claim 13, further comprising:

receiving, in response to a third message sent from the first BS to a server, the at least one AI/ML model selected according to the third message by the server, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, and the third message is used for sending the condition of the AI/ML model selection to the server.
The wireless communication method of claim 13, further comprising:

receiving, in response to a third message sent from the first BS to a server BS, at least one candidate AI/ML model transferred from the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection, and the third message is used for sending the AI/ML model selection to the server; and

selecting the at least one AI/ML model from the at least one candidate AI/ML model.
A wireless communication method, executable in a user equipment (UE) , the wireless communication method comprising:

receiving a first message from a first base station (BS) , wherein the first message is used for inquiring whether the UE initiates an artificial intelligence or machine learning (AI/ML) model selection or comprises at least one new AI/ML model; and

sending a second message to the first BS, wherein the second message is used for informing the first BS of a result in response to the first message.
The wireless communication method of claim 21, wherein in response to the first message used for inquiring whether the UE initiates the AI/ML model selection or in response to the first message comprising the first BS comprises the at least one new AI/ML model, the first message is received from the first BS when at least one AI/ML model stored in the first BS is changed.
The wireless communication method of claim 21, wherein in response to the first message used for inquiring whether the UE initiates the AI/ML model selection or in response to the first message used for informing the UE that the first BS comprises the at least one new AI/ML model, the first message is received from the first BS periodically.
The wireless communication method of claim 21, wherein the first message comprises at least one of the following information:

an identification (ID) of the UE;

a request cause for indicating a reason for initiating the AI/ML model selection;

a capability of the UE for supporting an AI/ML model transfer, delivery, or download;

a storage capability of the UE;

a valid storage capability of the UE;

at least one type of at least one AI/ML model required by the UE;

an amount of the at least one AI/ML model required by the UE;

complexity of the at least one AI/ML model required by the UE;

at least one generalization of the at least one AI/ML model required by the UE;

at least one key performance indicator (KPI) of the at least one AI/ML model required by the UE; and

at least one transfer format of the at least one AI/ML model required by the UE.
The wireless communication method of claim 24, wherein the second message is further used for indicating a condition of the AI/ML model selection, and the wireless communication method further comprises:

receiving the at least one AI/ML model selected according to the second message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
The wireless communication method of claim 21, wherein the second message is further used for indicating a condition of the AI/ML model selection, and the wireless communication method further comprises:

receiving at least one candidate AI/ML model transferred from the first BS, wherein the at least one candidate AI/ML model meets the condition of the AI/ML model selection; and

selecting the at least one AI/ML model from the at least one candidate AI/ML model, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
The wireless communication method of claim 21, wherein in response to the first message comprising the at least one new AI/ML model, the method further comprises:

selecting at least one AI/ML model from the at least one new AI/ML model.
A wireless communication method, executable in a user equipment (UE) , the wireless communication method comprising:

receiving, in response to a first message from a first base station (BS) to a server and a second message from the server to the first BS, a third message, wherein the first message is used for requesting whether at least one new AI/ML model exists, the second message comprises the at least one new AI/ML model, and the third message is used for inquiring whether the UE initiates an AI/ML model selection or comprises at least one new AI/ML model; and

sending a fourth message to the first BS, wherein the fourth message is used for informing the first BS of a result in response to the third message.
The wireless communication method of claim 28, wherein the fourth message is further used for indicating a condition of the AI/ML model selection, and the wireless communication method further comprises:

receiving the at least one AI/ML model selected according to the fourth message by the first BS, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
The wireless communication method of claim 28, wherein the fourth message is further used for indicating a condition of the AI/ML model selection, and the wireless communication method further comprises:

receiving at least one candidate AI/ML model transferred from the first BS; and

selecting the at least one AI/ML model from the at least one candidate AI/ML model, wherein the at least one AI/ML model meets the condition of the AI/ML model selection.
A user equipment, comprising:

a memory;

a transceiver; and

a processor coupled to the memory and the transceiver;

wherein the processor is configured to execute any one of the wireless communication methods of claims 1 to 30.
A chip, comprising:

a processor, configured to call and run a computer program stored in a memory, to cause a device in which the chip is installed to execute any one of the wireless communication methods of claims 1 to 30.
A non-transitory computer-readable storage medium, in which a computer program is stored, wherein the computer program causes a computer to execute any one of the wireless communication methods of claims 1 to 30.
A non-transitory machine-readable storage medium having stored thereon instructions that, when executed by a computer, cause the computer to perform any one of the wireless communication methods of claims 1 to 30.
A computer program product, comprising a computer program, wherein the computer program causes a computer to execute any one of the wireless communication methods of claims 1 to 30.
A computer program, wherein the computer program causes a computer to execute any one of the wireless communication methods of claims 1 to 30.