Wireless communication method and wireless communication device for monitoring ai / ML model / function

Abstract

Provided in the embodiments of the present application are a wireless communication method and wireless communication device for monitoring an artificial intelligence / machine learning (AI / ML) model / function. The wireless communication method is executed by a user equipment (UE), and comprises: receiving a plurality of monitoring time windows configured by a network-side device, and before monitoring an AI / ML model / function during a first monitoring time window among the plurality of monitoring time windows, receiving first signaling sent by the network-side device, wherein the plurality of monitoring time windows have periodicity, and the first signaling is used for indicating whether to execute, during the first monitoring time window, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented on the basis of the AI / ML model.

Description

Wireless communication method and wireless communication device for monitoring AI / ML models / functions Technical Field

[0001] The embodiments of the present application relate to the field of mobile communication technologies, and more particularly to a wireless communication method and wireless communication device for monitoring artificial intelligence / machine learning (AI / ML) models / functions. Background Art

[0002] In existing technologies, artificial intelligence / machine learning (AI / ML) is a system that can replace human labor through computational learning. AI / ML can be used to solve various problems, such as natural human language processing, computing, and graphics processing. In recent years, AI / ML has been applied in the communications field. However, monitoring the application of AI / ML models / functions in the wireless communications field remains an unresolved issue. Therefore, it is necessary to propose a wireless communication method and wireless communication device for monitoring AI / ML models / functions to improve the existing technology and other issues.

[0003] Summary of the Invention

[0004] Embodiments of the present application provide a wireless communication method and wireless communication device for monitoring artificial intelligence / machine learning (AI / ML) models / functions.

[0005] An embodiment of the present application provides a wireless communication method for monitoring AI / ML models / functions, which is executed on user equipment (UE), wherein the wireless communication method includes: receiving multiple monitoring time windows configured by a network-side device, wherein the multiple monitoring time windows are periodic; and before monitoring the AI / ML model / function during a first monitoring time window of the multiple monitoring time windows, receiving first signaling sent by the network-side device, wherein the first signaling is used to indicate whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the first monitoring time window.

[0006] With the above technical solution, the first signaling is used to indicate whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model during the first monitoring time window. In this way, unnecessary monitoring can be avoided, reducing the UE's processing complexity, power consumption, and reporting overhead.

[0007] An embodiment of the present application provides a wireless communication method for monitoring AI / ML models / functions, which is executed on a UE, wherein the wireless communication method includes: determining whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model based on a first condition and / or a second condition, wherein the first condition is that a monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is lower than, higher than or equal to a defined threshold, or an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model occurs, and the first condition and the second condition are related.

[0008] Through the above technical solution, based on the first condition and / or the second condition, it is determined whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model. This can avoid unnecessary monitoring and reduce the processing complexity, power consumption, and reporting overhead of the UE.

[0009] An embodiment of the present application provides a wireless communication method for monitoring AI / ML models / functions, which is executed on a UE, wherein the wireless communication method includes: receiving multiple first monitoring time windows and at least one second monitoring time window configured by a network-side device, wherein the multiple first monitoring time windows are periodic; and based on the behavior of the UE during the at least one second window, determining whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

[0010] Through the above technical solution, based on the UE's behavior during the at least one second window, a decision is made as to whether to perform monitoring of at least one AI / ML model under the same function, or monitoring of a function implemented based on an AI / ML model, during the multiple first monitoring time windows. This avoids unnecessary monitoring and reduces UE processing complexity, power consumption, and reporting overhead.

[0011] An embodiment of the present application provides a wireless communication method for monitoring AI / ML models / functions, which is executed on a network-side device. The wireless communication method includes: configuring multiple monitoring time windows, wherein the multiple monitoring time windows are periodic; and before monitoring the AI / ML model / function during a first monitoring time window of the multiple monitoring time windows, determining whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the first monitoring time window.

[0012] With the above technical solution, before monitoring an AI / ML model / function during the first of the multiple monitoring time windows, the network-side device determines whether to monitor at least one AI / ML model under the same function, or a function implemented based on an AI / ML model, during the first monitoring time window. This avoids unnecessary monitoring and reduces processing complexity, power consumption, and overhead for the network-side device.

[0013] An embodiment of the present application provides a wireless communication method for monitoring AI / ML models / functions, which is executed on a network-side device, wherein the wireless communication method includes: determining whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model based on a first condition and / or a second condition, wherein the first condition is that a monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is lower than, higher than, or equal to a defined threshold, or an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model occurs, and the first condition and the second condition are related.

[0014] Through the above technical solution, based on the first condition and / or the second condition, a decision is made as to whether to monitor at least one AI / ML model under the same function or a function implemented by an AI / ML model. This avoids unnecessary monitoring and reduces processing complexity, power consumption, and overhead of network-side devices.

[0015] An embodiment of the present application provides a wireless communication method for monitoring AI / ML models / functions, which is executed on a network-side device. The wireless communication method includes: configuring multiple first monitoring time windows and at least one second monitoring time window, wherein the multiple first monitoring time windows are periodic; and based on the behavior of the network-side device during the at least one second window, determining whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

[0016] Through the above technical solution, based on the behavior of the network-side device during the at least one second window, a decision is made as to whether to monitor at least one AI / ML model under the same function, or a function implemented by the AI / ML model, during the multiple first monitoring time windows. This avoids unnecessary monitoring and reduces processing complexity, power consumption, and overhead of the network-side device.

[0017] A wireless communication device provided in an embodiment of the present application includes: a processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the above-mentioned wireless communication method.

[0018] The user equipment provided in the embodiment of the present application includes a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the above-mentioned wireless communication method.

[0019] The base station provided in the embodiment of the present application includes a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the above-mentioned wireless communication method.

[0020] The network element provided in the embodiment of the present application includes a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to perform the above-mentioned wireless communication method.

[0021] The chip provided in the embodiment of the present application is used to implement the above-mentioned wireless communication method.

[0022] Specifically, the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned wireless communication method.

[0023] The computer-readable storage medium provided in an embodiment of the present application is used to store a computer program, which enables a computer to execute the above-mentioned wireless communication method.

[0024] The computer program product provided in the embodiments of the present application includes computer program instructions, which enable a computer to execute the above-mentioned wireless communication method.

[0025] The computer program provided in the embodiment of the present application, when executed on a computer, enables the computer to execute the above-mentioned method for wireless communication.

[0026] In the above technical solution, the UE / network-side device determines whether to monitor at least one AI / ML model under the same function or a function implemented based on an AI / ML model during the first monitoring time window. This avoids unnecessary monitoring and reduces processing complexity, power consumption, and overhead of the UE / network-side device. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0028] FIG1 is a schematic diagram of a wireless communication system architecture provided in an embodiment of the present application;

[0029] FIG2A is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0030] FIG2B is a schematic flow chart of a wireless communication method according to an embodiment of the present application;

[0031] FIG2C is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0032] FIG2D is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0033] FIG3A is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0034] FIG3B is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0035] FIG3C is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0036] FIG3D is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0037] FIG3E is a schematic flow chart of a wireless communication method according to an embodiment of the present application;

[0038] FIG3F is a schematic flow chart of a wireless communication method according to an embodiment of the present application;

[0039] FIG4A is a schematic diagram of a flow chart of a wireless communication method provided in an embodiment of the present application;

[0040] FIG4B is a schematic flow chart of a wireless communication method according to an embodiment of the present application;

[0041] FIG5 is a schematic structural diagram of a wireless communication device provided in an embodiment of the present application;

[0042] FIG6 is a schematic structural diagram of a chip according to an embodiment of the present application;

[0043] FIG7 is a schematic block diagram of a wireless communication system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0045] The technical solutions of the embodiments of the present application can be applied to various wireless communication systems, such as: Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, 5G communication system or future wireless communication systems, etc.

[0046] Exemplarily, a wireless communication system 100 used in an embodiment of the present application is shown in FIG1 . The wireless communication system 100 may include a network-side device 110, which may be a device that communicates with a user equipment 120 (User Equipment, UE). The network-side device 110 may provide communication coverage for a specific geographical area and may communicate with user equipment located within the coverage area. Optionally, the network-side device 110 may be a base station or a location management function (LMF) for providing positioning services. Optionally, the base station may be an evolved Node B (eNB or eNodeB) in an LTE system, or the base station may be a mobile switching center, a relay station, an access point, an in-vehicle device, a wearable device, a hub, a switch, a bridge, a router, a network-side device in a 5G network, or a base station in a future communication system, etc.

[0047] The wireless communication system 100 also includes at least one user device 120 located within the coverage area of ​​the network-side device 110. As used herein, "user device" includes, but is not limited to, a device configured to receive / send communication signals via a wired connection, such as a Public Switched Telephone Network (PSTN), a Digital Subscriber Line (DSL), a digital cable, a direct cable connection; and / or another data connection / network; and / or via a wireless interface, such as a cellular network, a Wireless Local Area Network (WLAN), a digital television network such as a DVB-H network, a satellite network, an AM-FM broadcast transmitter; and / or another user device; and / or an Internet of Things (IoT) device. A user device configured to communicate via a wireless interface may be referred to as a "wireless communication user device 120," a "wireless user device 120," or a "mobile user device 120." Examples of mobile user equipment 120 include, but are not limited to, satellite or cellular telephones; Personal Communications System (PCS) user equipment 120, which may combine a cellular radio telephone with data processing, fax, and data communication capabilities; a PDA, which may include a radiotelephone, a pager, Internet / Intranet access, a web browser, a notepad, a calendar, and / or a Global Positioning System (GPS) receiver; and conventional laptop and / or palmtop receivers or other electronic devices that include a radiotelephone transceiver. User equipment may be referred to as access user equipment 120, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, a remote user device, a mobile device, a wireless communication device, or a user agent. The access user device 120 can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a user device in a 5G network, or a user device in a future evolved PLMN, etc.

[0048] Some embodiments of this application mainly use AI / ML to solve various problems in communication systems. In order to better enable at least one AI / ML model under the same function or a function implemented based on the AI / ML model to work better, how to monitor the AI / ML model / function so that the AI / ML model / function can work better. Some embodiments of this application mainly involve the setting of trigger conditions for AI / ML model / function monitoring, the design of triggering processes, and the control of terminal processing complexity, reducing terminal reporting overhead, ensuring system performance stability, etc.

[0049] In some embodiments of the present application, the user device 120 decides whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the first monitoring time window. In this way, unnecessary monitoring can be avoided, and the processing complexity, power consumption, and overhead of the user device 120 can be reduced. In some embodiments of the present application, the network side device 110 decides whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the first monitoring time window. In this way, unnecessary monitoring can be avoided, and the processing complexity, power consumption, and overhead of the network side device 110 can be reduced.

[0050] Optionally, the user equipments 120 may perform device-to-device (D2D) communication with each other.

[0051] Optionally, the 5G communication system or 5G network may also be referred to as a New Radio (NR) system or NR network.

[0052] The wireless communication system 100 also includes a network 130. Network 130 may be an IP mobile communication network operated by a mobile communication operator. For example, network 130 may be a core network used by a mobile communication operator that operates and manages the wireless communication system 100, or a core network used by a virtual mobile communication operator such as an MVNO (Mobile Virtual Network Operator).

[0053] The network 130 can be connected to the network side device 110 as a relay device for transmitting user data. The user device 120 sends and receives user data via the network 130. It should be noted that the communication of user data is not limited to IP communication, and non-IP communication may also be used.

[0054] Figure 1 exemplarily shows a network-side device 110, two user devices 120 and a network 130. Optionally, the wireless communication system 100 may include multiple network-side devices and each network-side device may include other numbers of user devices within its coverage area, which is not limited in this embodiment of the present application.

[0055] Optionally, the wireless communication system 100 may further include other network entities such as a network controller, a mobility management entity, and a network element, which is not limited in this embodiment of the present application. For example, the network 130 may include other network entities such as a network controller, a mobility management entity, and a network element, which is not limited in this embodiment of the present application.

[0056] It should be understood that in the embodiments of the present application, a device having wireless communication capabilities in a network / system may be referred to as a wireless communication device. Taking the wireless communication system 100 shown in Figure 1 as an example, the wireless communication device may include a network-side device 110 having communication capabilities, a user device 120, and a network 130. The network-side device 110 and the user device 120 may be the specific devices described above and will not be described in detail here. The wireless communication device may also include other devices (network 130) in the wireless communication system 100. For example, the network 130 may include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.

[0057] It should be understood that the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects before and after are in an "or" relationship. In some embodiments, the term "configuration" may refer to "pre-configuration" and "network configuration". The terms "definition" or "pre-definition" in the embodiments of the present application may be implemented by pre-storing corresponding codes, tables or other methods of indicating relevant information in devices (for example, including UE and network devices). This application does not limit the specific implementation methods. For example, "definition" or "pre-definition" may refer to those defined in the protocol. It should also be understood that the "protocol" in the present invention may refer to a standard protocol in the field of communications, for example, it may include the Long Term Evolution (LTE) protocol, the New Radio (NR) protocol, and related protocols used in future communication systems. This application is not limited to this.

[0058] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions related to the embodiments of the present application are described below.

[0059] First embodiment:

[0060] Figure 2A is a flow chart of a method for wireless communication provided in an embodiment of the present application. As shown in Figure 2A, the method for wireless communication is executed on a user equipment (UE) and includes at least one of the following operations: Operation 201A: Receive multiple monitoring time windows configured by a network-side device. The multiple monitoring time windows are periodic. Operation 202A: Before monitoring the AI / ML model / function during the first monitoring time window of the multiple monitoring time windows, receive a first signaling sent by the network-side device. The first signaling is used to indicate whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model during the first monitoring time window.

[0061] FIG2B is a flow chart of a wireless communication method provided in an embodiment of the present application. As shown in FIG2B , the wireless communication method is executed on a network-side device and includes at least one of the following operations: Operation 201B: Configuring multiple monitoring time windows. The multiple monitoring time windows are periodic. Operation 202B: Before monitoring an AI / ML model / function during a first monitoring time window of the multiple monitoring time windows, determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model during the first monitoring time window.

[0062] In some embodiments, monitoring an AI / ML model / function refers to monitoring at least one AI / ML model under the same function or monitoring a function implemented based on an AI / ML model. The first monitoring time window refers to one monitoring time window, at least one monitoring time window, a portion of the monitoring time windows, or all of the monitoring time windows.

[0063] Specifically, in some embodiments, the UE is, for example, the user equipment 120 shown in FIG. 1 . The network-side device is, for example, the network-side device 110 shown in FIG. 1 . The network-side device 110 is, for example, a base station or a LMF. For example, in some embodiments of the present application, as shown in FIG. 2C , for monitoring at least one AI / ML model under the same function on the user equipment 120 side, or monitoring a function implemented based on an AI / ML model, the network-side device 110 configures multiple periodic monitoring time windows for the user equipment 120. Before starting monitoring during each monitoring time window, the network-side device 110 indicates via first signaling whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model during the next monitoring time window. In some embodiments, the next monitoring time window refers to the monitoring time window after the user equipment 120 receives the first signaling. That is, in this embodiment, only after the user equipment 120 receives the first signaling sent by the network-side device 110 will it decide whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model based on the instruction of the first signaling.

[0064] Because conventional technology only uses periodic monitoring, unnecessary monitoring is caused, thereby increasing the processing complexity of the user equipment 120 / network device 110. In particular, for the user equipment 120, reporting the monitoring results will further increase the overhead of air interface signaling.

[0065] In some embodiments of the present application, the monitoring of AI / ML models / functions is performed in a periodic manner. However, in order to avoid unnecessary monitoring and reduce the processing complexity, power consumption, reporting overhead, etc. of the user equipment 120, before each monitoring cycle window, signaling is used to indicate whether the next time window is started / triggered, and at least one AI / ML model under the same function or a function implemented based on the AI / ML model is monitored.

[0066] In some embodiments of the present application, the first signaling includes Media Access Control (MAC) control element (CE) signaling or downlink control information (DCI). In some embodiments of the present application, the UE also receives a second signaling sent by the network side device, and the second signaling is used to indicate or update the period and window length of the multiple monitoring time windows. In some embodiments of the present application, the second signaling includes Radio Resource Control (RRC) signaling, MAC CE signaling, or DCI. The present application is not limited to this. In some embodiments, the first signaling may also be RRC signaling.

[0067] Specifically, in some embodiments, multiple periodic monitoring time windows can be configured through MAC CE signaling or DCI. The period and window length of multiple periodic monitoring time windows can be configured through RRC signaling. The network side device 110 can indicate through MAC CE signaling or DCI configuration whether the next monitoring time window is to monitor at least one AI / ML model under the same function or monitor a function implemented based on the AI / ML model. The next monitoring time window refers to, for example, the monitoring time window after the user equipment 120 receives the MAC CE signaling or DCI.

[0068] In some embodiments of the present application, if the first signaling is not received before monitoring the AI / ML model / function during the first monitoring time window, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is not performed during the first monitoring time window; or monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is performed; or the behavior during the previous monitoring time window of the first monitoring time window is repeated during the first monitoring time window.

[0069] In some embodiments of the present application, if the first signaling is received during the first monitoring time window, the first signaling is used to indicate whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the first monitoring time window or the next monitoring time window of the first monitoring time window.

[0070] Specifically, in some embodiments, as shown in FIG2C , the network-side device 110 sends MAC CE signaling, DCI, or RRC signaling before the monitoring time window to indicate whether to monitor at least one AI / ML model under the same function or monitor a function implemented based on the AI / ML model during the next monitoring time window. For example, the network-side device 110 indicates through 1 bit in the DCI whether to monitor at least one AI / ML model under the same function or monitor a function implemented based on the AI / ML model during the next monitoring time window. 0 indicates monitoring, 1 indicates not monitoring, and the meanings of the two can be reversed, that is, 1 indicates monitoring, and 0 indicates not monitoring.

[0071] Specifically, in some embodiments, the network side device 110 indicates to the user device 120 through the first value '1' of the DCI that during the next monitoring time window, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model shall not be performed. The network side device 110 indicates to the user device 120 through the second value '0' of the DCI that during the next monitoring time window, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model shall be performed.

[0072] Specifically, in some embodiments, the network side device 110 indicates to the user device 120 through the first value '1' of the DCI that during the next monitoring time window, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is performed, and the network side device 110 indicates to the user device 120 through the second value '0' of the DCI that during the next monitoring time window, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is not performed.

[0073] Specifically, in some embodiments, if no signaling information indicating whether to monitor is received before a certain monitoring time window, it is assumed that the monitoring time window does not perform / performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, or the current monitoring time window repeats the behavior during the previous monitoring time window. In some embodiments, if MAC CE signaling or DCI is received within a certain monitoring time window, the MAC CE signaling or DCI is applicable to monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the current monitoring time window or during the next monitoring time window.

[0074] In some embodiments of the present application, when the first signaling indicates activation of monitoring of the AI / ML model / function during the first monitoring time window, the UE performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the next monitoring time window and the monitoring time window after the next monitoring time window, until the first signaling indicates deactivation of monitoring of the AI / ML model / function.

[0075] In some embodiments of the present application, when the first signaling indicates deactivation of monitoring of the AI / ML model / function during the first monitoring time window, the UE immediately stops or stops performing monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the next monitoring time window.

[0076] Specifically, in some embodiments, as shown in FIG2D , the network-side device 110 may activate or deactivate the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model through the first signaling (e.g., MAC CE signaling, DCI, or RRC signaling). That is, after the user equipment 120 receives the activation indication of the MAC CE signaling, DCI, or RRC signaling, it starts to monitor the at least one AI / ML model under the same function or the function implemented based on the AI / ML model during the next monitoring time window, and monitors the at least one AI / ML model under the same function or the function implemented based on the AI / ML model during subsequent monitoring time windows until the user equipment 120 receives the deactivation indication of the MAC CE signaling, DCI, or RRC signaling. If the user equipment 120 receives a deactivation indication of MAC CE signaling, DCI, or RRC signaling, the user equipment 120 immediately stops or starts to stop during the next time window and stops performing the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model during the next monitoring time window.

[0077] Specifically, in some embodiments, if an activation or deactivation indication of MAC CE signaling, DCI, or RRC signaling is received within a certain monitoring time window, the user equipment 120 activates or deactivates the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model from the monitoring time window, or the user equipment 120 activates or deactivates the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model from the next monitoring time window. As shown in Figure 2D, if the user equipment 120 receives an activation or deactivation indication of MAC CE signaling, DCI, or RRC signaling before the nth periodic monitoring time window, the user equipment 120 activates or deactivates the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model during the nth monitoring time window.

[0078] Specifically, in some embodiments, for the above-mentioned method in which the network side device 110 configures a periodic monitoring time window for the user device 120, the monitoring of the AI / ML model / function on the user device 120 side can be effective immediately after the period and monitoring window length are configured, including the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model. Then, the network side device 110 sends an activation or deactivation indication through MAC CE signaling, DCI, or RRC signaling, so that the user device 120 activates or deactivates the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model.

[0079] In some embodiments of the present application, the wireless communication method further includes the UE sending a request message to the network side device to monitor the AI / ML model / function.

[0080] Specifically, in some embodiments, considering that the AI / ML model / function is located on the user device 120 side, the user device 120 may have a better understanding of environmental changes, the environment in which the user device 120 is located, changes in the status of the AI / ML model / function, etc. Therefore, the user device 120 can send a request message to the network device 110 to monitor the AI / ML model / function, requesting that the network device 110 allocate time-frequency domain resources for reporting monitoring results to the user device 120. Based on the request of the user device 120, the network device 110 configures parameters such as the period of the monitoring time window, the monitoring window length, and the time-frequency domain resources for reporting monitoring results for the user device 120. In some embodiments, the network device 110 can also configure the period and length of the monitoring time window for the user device 120. In some embodiments, whether to enable / start / trigger monitoring of the AI / ML model / function in each specific monitoring time window can also be determined by the user device 120. If the reporting amount changes during the monitoring process of the user equipment 120, the user equipment 120 notifies / sends a request message to the network side device 110, requesting the network side device 110 to configure reporting resources.

[0081] In some embodiments of the present application, the multiple monitoring time windows have multiple candidate periods and window lengths. In some embodiments of the present application, the multiple candidate periods and window lengths of the multiple monitoring time windows are configured by a network-side device.

[0082] Specifically, in some embodiments, for the above-mentioned periodic monitoring time window, the period of the monitoring time window has multiple candidate periods and window lengths, and the network side device 110 can configure different monitoring time window periods and window lengths for the user device 120 based on factors such as model type (model ID or model group ID), generalization, stability, system performance changes, changes in the external environment, etc. For example, the period and window length of the monitoring time window can be time slot level (how many time slots), frame level (how many time frames), second level (how many seconds), minute level (how many minutes), hour level (how many hours), day level (how many days), week level (how many weeks), month level (how many months), year level (how many years), etc. The period of the configured monitoring time window is related to factors such as the generalization, stability, and changes in the external environment of the AI / ML model / function. When the network side device 110 detects changes in system performance, AI / ML model / function, or external environment, the network side device 110 can update the period of the monitoring time window currently configured for the user equipment 120, the window length of the monitoring window and other parameters by reconfiguring / reissuing MAC CE signaling, DCI, or RRC signaling, so that the configuration of the period of the monitoring time window and the window length of the monitoring window is more suitable for the currently activated or working AI / ML model / function.

[0083] In some embodiments of the present application, the network-side device 110 is further configured to decide whether to activate or deactivate monitoring of the AI / ML model / function. In some embodiments of the present application, when the network-side device 110 decides to activate monitoring of the AI / ML model / function during the first monitoring time window, the network-side device 110 performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the next monitoring time window of the first monitoring time window and the monitoring time window after the next monitoring time window, until the network-side device 110 decides to deactivate monitoring of the AI / ML model / function. In some embodiments of the present application, when the network-side device 110 decides to deactivate monitoring of the AI / ML model / function during the first monitoring time window, the network-side device 110 immediately stops or stops performing monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the next monitoring time window.

[0084] Specifically, in some embodiments, for the AI / ML model / function on the network side, a periodic monitoring method can also be adopted. The monitoring period and window length can be agreed upon through standards, or it can be completely an implementation behavior on the network side. That is, the period and window length of the monitoring time window are defined or configured. In some embodiments, whether to start / start / trigger the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model in each monitoring time window can also be determined by the network side device 110, or based on the request of the user device 120. In some embodiments, the network side device 110 can determine which event in the lifecycle management (LCM) the network side device 110 triggers / starts based on the monitoring results of at least one AI / ML model under the same function or a function implemented based on the AI / ML model. LCM events include, for example, activation, deactivation, selection, switching, fallback and other operations of the AI / ML model / function.

[0085] In some embodiments of the present application, the monitoring of the AI / ML model / function is the monitoring of the currently activated or working AI / ML model / function, or the monitoring of all or part of the AI / ML models under the same function.

[0086] Specifically, in some embodiments, it should be noted that the monitoring of AI / ML models / functions herein may refer to the monitoring of currently activated or working AI / ML models / functions, or may refer to the monitoring of all or part of the AI / ML models under the same function, wherein if some AI / ML models are not currently in an activated or working state, in order to monitor them, they need to be activated and then monitored, or the activation of the AI / ML models to be monitored can be completed through monitoring message configuration. For example, the monitoring of activated or working AI / ML models / functions can be real-time, but the decision on LCM events of AI / ML models / functions may require monitoring of multiple AI / ML models under the same function, and these multiple AI / ML models may include those that are already activated or working, as well as those that are inactivated or not in working state.

[0087] Therefore, the monitoring of AI / ML models / functions here may refer to the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on an AI / ML model, including those that have been activated or are working, and may also include those that are inactivated or not in working state. For AI / ML models / functions that are inactivated or not in working state, they need to be activated or put into working state before monitoring. The activation or working state here means that the AI / ML model / function can perform normal reasoning output. AI / ML model / function refers to, for example, at least one AI / ML model under the same function or a function implemented based on an AI / ML model. AI / ML model refers to, for example, at least one AI / ML model under the same function. AI / ML function refers to, for example, a function implemented based on an AI / ML model.

[0088] Second embodiment:

[0089] Specifically, in some embodiments, if the network device 110 determines that it is necessary to monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model, the network device 110 will issue an instruction to deactivate / start / trigger / instruct the user equipment 120 to monitor the at least one AI / ML model under the same function or a function implemented based on the AI / ML model for the AI / ML model / function on the user equipment 120 or the AI / ML model / function on the user equipment 120 in the dual-side AI / ML model / function. The instruction may be issued using MAC CE signaling, DCI, or RRC signaling. The user equipment 120 starts monitoring the at least one AI / ML model under the same function or a function implemented based on the AI / ML model during the next or current monitoring time window according to the instruction issued by the network device 110. The user equipment 120 may monitor a single AI / ML model / function, multiple AI / ML models / functions simultaneously, or at least one AI / ML model supported by the same function. For example, the two sides refer to the network side device 110 and the user equipment 120.

[0090] It is understood that monitoring AI / ML models / functions can refer to monitoring at least one AI / ML model under the same function or monitoring a function implemented based on an AI / ML model, including those that are already activated or working, and those that are inactivated or not working. Inactivated or not working AI / ML models / functions must first be activated or put into working state before monitoring. Activation or working state here means that the AI / ML model / function can perform normal inference output.

[0091] In some embodiments of the present application, performing the monitoring of at least one AI / ML model under the same function, or monitoring a function implemented based on the AI / ML model further includes: constraining the monitoring of at least one AI / ML model under the same function, or monitoring a function implemented based on the AI / ML model. In some embodiments, the constraints include that the outputs of the monitored AI / ML model / function and the activated AI / ML model / function are based on the reference signal measurement results of the same or multiple adjacent time slots. In some embodiments, the inputs of the monitored AI / ML model / function and the activated AI / ML model / function are based on the reference signal measurement results of the same or multiple adjacent time slots.

[0092] Specifically, in some embodiments, the monitoring process may also require constraining the behavior of the monitored AI / ML model / function, including measurement and reporting behavior, such as constraining the output of the monitored AI / ML model / function and the activated AI / ML model / function to be based on the same reference signal measurement result, or the activated AI / ML model / function and the monitoring AI / ML model / function to be based on the reference signal measurement results of multiple adjacent time slots, but the interval in the measurement signal time domain is not greater than the defined value, such as the input of the activated AI / ML model / function and the monitoring AI / ML model / function is based on the reference signal measurement results of the same or multiple adjacent time slots. Specifically, in this embodiment, the monitored AI / ML model / function refers to all monitored AI / ML models / functions minus the AI / ML model / function currently working in the activated state.

[0093] To ensure fairness in monitoring AI / ML models / functions, some constraints need to be added when monitoring multiple AI / ML models / functions. For example, the input of the AI / ML model / function needs to be based on the measurement results of the same time slot or multiple adjacent time slots. The reporting of the AI / ML model / function monitoring results also needs to meet certain constraints and can be based on the same time slot or multiple adjacent time slots, or within a certain time window.

[0094] Specifically, in some embodiments, the sending of the reference signal for the activated AI / ML model / function may be periodic, semi-continuous, or non-periodic, and the relationship between the reference signal for the monitoring AI / ML model / function and the reference signal for the activated AI / ML model / function may be one or more of the following: the sending of the reference signal for the activated AI / ML model / function is periodic, and the sending of the reference signal for the monitoring AI / ML model / function is semi-continuous or non-periodic; the sending of the reference signal for the activated AI / ML model / function is semi-continuous, and the sending of the reference signal for the monitoring AI / ML model / function is semi-continuous or non-periodic; the sending of the reference signal for the activated AI / ML model / function is non-periodic, and the sending of the reference signal for the monitoring AI / ML model / function is also non-periodic.

[0095] In some embodiments of the present application, if the output result reporting of the activated AI / ML model / function is periodic, the output result reporting of the monitored AI / ML model / function is semi-continuous or non-periodic. In some embodiments of the present application, the period of reporting the output result of the monitored AI / ML model / function and the period of reporting the output result of the activated AI / ML model / function satisfy an integer multiple relationship. Specifically, in this embodiment, the monitored AI / ML model / function refers to all monitored AI / ML models / functions minus the AI / ML model / function currently working in the activated state. In some embodiments of the present application, the starting / earliest reporting moment / time slot of the output result of the monitored AI / ML model / function coincides with a reporting moment / time slot of the periodic reporting of the output result of the activated AI / ML model / function.

[0096] In some embodiments of the present application, if the output result reporting of the activated AI / ML model / function is semi-continuous, the output result reporting of the monitored AI / ML model / function is semi-continuous or aperiodic. In this embodiment, the monitored AI / ML model / function refers to all monitored AI / ML models / functions excluding the AI / ML model / function currently working in the activated state. Specifically, in this embodiment, the monitored AI / ML model / function refers to all monitored AI / ML models / functions (e.g., the first AI / ML model / function, the second AI / ML model / function, and the third AI / ML model / function) excluding the activated AI / ML model / function (e.g., the first AI / ML model / function). That is, if the output result reporting of the activated AI / ML model / function (e.g., the first AI / ML model / function) is semi-continuous, the output result reporting of the monitored AI / ML model / function (e.g., the first AI / ML model / function and the second AI / ML model / function) is semi-continuous or aperiodic.

[0097] In some embodiments of the present application, if the output result reporting of the activated AI / ML model / function is aperiodic, the output result reporting of the monitored AI / ML model / function is aperiodic.

[0098] Specifically, in some embodiments, the reporting of the output results of the activated AI / ML model / function may also take various forms, such as periodic, aperiodic, and semi-continuous. If the output results of the activated AI / ML model / function and the monitoring AI / ML model / function are reported independently, the reporting of the output results of the activated AI / ML model / function and the monitoring AI / ML model / function must also meet certain constraints. For example, it can be one or more of the following:

[0099] If the output result reporting of the currently activated AI / ML model / function is periodic, then the output result reporting of other AI / ML models / functions monitored during the AI / ML model / function monitoring period may be semi-continuous or non-periodic, and the reporting period of the monitored AI / ML model / function or the AI / ML model / function output result is an integer multiple of the reporting period of the activated AI / ML model / function output result, or the reporting period of the activated AI / ML model / function output result is an integer multiple of the reporting period of the monitored AI / ML model / function output result. In some embodiments, the starting / earliest reporting time / time slot for monitoring the AI / ML model / function or the AI / ML model / function output result coincides with a reporting time / time slot for the periodic reporting of the output result of the activated AI / ML model / function; or there is no constraint on the period for semi-continuous reporting of the monitoring AI / ML model / function output result. When the output result reporting of the monitoring AI / ML model / function is non-periodic, the reporting time / time slot of the output result of the monitoring AI / ML model / function coincides with a reporting time / time slot of the periodic reporting of the output result of the activated AI / ML model / function, or the interval is less than the defined value, for example, the two are at the same or adjacent time / time slot, or there is no constraint.

[0100] If the output result reporting of the currently active AI / ML model / function is semi-continuous, the output result reporting of other AI / ML models / functions monitored during the monitoring period of the AI / ML model / function can be semi-continuous or aperiodic. The reporting period for the output result of the monitored AI / ML model / function is an integer multiple of the output result reporting period of the activated AI / ML model / function, or the reporting period of the output result of the activated AI / ML model / function is an integer multiple of the output result reporting period of the monitored AI / ML model / function, and the starting / earliest reporting time / time slot of the output result of the monitored AI / ML model / function coincides with a reporting time / time slot of the periodic reporting of the output result of the activated AI / ML model / function. Alternatively, there is no restriction on the period for semi-continuous reporting of the output result of the monitored AI / ML model / function. When the output result reporting of the monitoring AI / ML model / function is non-periodic, the reporting time / time slot of the output result of the monitoring AI / ML model / function coincides with a reporting time / time slot of the periodic reporting of the output result of the activated AI / ML model / function, or the interval is less than the defined value, for example, the two are at the same or adjacent time / time slot, or there is no constraint.

[0101] If the output result reporting of the currently active AI / ML model / function is non-periodic, then the output result reporting of other AI / ML models / functions monitored during the monitoring period of the AI / ML model / function can be non-periodic, and the reporting time / time slot of the output result of the monitored AI / ML model / function coincides with the reporting time / time slot of the output result of the activated AI / ML model / function, or the interval is less than the defined value, for example, the two are at the same or adjacent time / time slot, or there is no constraint.

[0102] It is understandable that the activated AI / ML model / function may refer to at least one AI / ML model under the same function that is in an activated state or in a working state. The activation or working state here means that the AI / ML model / function (at least one AI / ML model under the same function) can perform normal reasoning output. It is understandable that the correspondence between the activated AI / ML model / function and the monitored AI / ML model / function may be that the monitored AI / ML model / function refers to all monitored AI / ML models / functions minus the AI / ML model / function currently working in the activated state.

[0103] It can be understood that the input results of the activated AI / ML model / function and the monitoring AI / ML model / function can be obtained by directly measuring the reference signal, or can be the result of pre-processing the reference signal measurement result. The pre-processing here refers to a series of processing / transformation / conversion based on the measurement result of the reference signal, and there is no restriction on the specific processing / transformation / conversion method. The output results of the above-mentioned activated AI / ML model / function and the monitoring AI / ML model / function can be the direct output of the AI / ML model / function, or can be the result of post-processing after the output of the AI / ML model / function. The post-processing here refers to a series of processing / transformation / conversion based on the inferred results of the AI / ML model / function, and there is no restriction on the specific processing / transformation / conversion method. There is no restriction on the functions corresponding to the above-mentioned AI / ML model / function, nor is there any restriction on the reported amount.

[0104] It is understandable that the above constraints on the input, measurement behavior, output, and reporting behavior of the activated AI / ML model / function and the monitored AI / ML model / function can be independent or parallel. The achievement of the above constraints requires standard regulations, or is achieved through the configuration of the network-side device 110, or is achieved through a combination of the two. For example, if the output result reporting period of the activated AI / ML model / function and the monitoring AI / ML model / function is the same, the network-side device 110 will configure the same period for them when configuring the output result reporting of the activated AI / ML model / function and the monitoring AI / ML model / function.

[0105] In some embodiments of the present application, the solution of the second embodiment may be implemented in conjunction with the solution of the first embodiment, or may be implemented independently of the solution of the first embodiment.

[0106] Third embodiment:

[0107] In some embodiments of the present application, the UE reports the output results of multiple AI / ML models under the same monitored function independently or jointly, and when the output results of the multiple AI / ML models are multiple channel state information CSIs, the reporting of the multiple CSIs satisfies a priority order relationship. In some embodiments of the present application, the priority order relationship means that the reporting of the CSI corresponding to the output result of the currently activated or working AI / ML model has the highest priority.

[0108] Specifically, in some embodiments, if the activation AI / ML model / function and the monitoring AI / ML model / function are reported in a joint reporting manner, the reporting amounts of multiple AI / ML models / functions can be multiplexed and merged to reduce the reporting overhead. For example, for beam management, for the AI / ML model / function on the user equipment 120 side, the user equipment 120 may need to report the Channel State Information-Reference Signal Resource Indicator (CRI) / Synchronization Signal Block Resource indicator (SSBRI) of the predicted beam and the corresponding Reference Signal Received Power (RSRP) information, or CRI / SSBRI and the corresponding Signal to Interference plus Noise Ratio (SINR) information.

[0109] In order to reduce the reporting overhead of the user device 120, the output results of multiple AI / ML models can be jointly reported. The quantification of the reported amount can be based on the median or a maximum value. At the same time, in order to control the complexity of the processing of the user device 120, some constraints can be added to the number of AI / ML models monitored simultaneously by the user device 120, or the number can be controlled by reporting the capabilities of the user device 120; in order to ensure the stability of the system performance, the priority of the reporting amount of multiple AI / ML models can be constrained to ensure that the output of the currently working AI / ML model is reported first, thereby ensuring the stability of the system performance.

[0110] Regarding the reporting of the above information, this embodiment discusses several scenarios:

[0111] The user equipment 120 reports the CRI / SSBRI and RSRP corresponding to a single or multiple beams, or the CRI / SSBRI and SINR information corresponding to multiple AI / ML models under the same function under monitoring:

[0112] Method 1: Select the CRI / SSBRI corresponding to the RSRP or SINR with the largest amplitude among all AI / ML models that need to be reported as a reference, and quantize it using a certain bit width, such as 7 bits. The RSRP or SINR of the remaining other AI / ML models are reported in the form of a difference from the maximum RSRP or SINR, and the differential value is quantized using 4 bits or more or less bits, such as 3 bits or 5 bits. This method helps to reduce the feedback overhead of the user equipment 120.

[0113] Method 2: Independent reporting: Each AI / ML model reports independently. The RSRP or SINR information of each AI / ML model is quantized using a certain bit width, for example, 7 bits. To reduce overhead, fewer bits can be used for quantization. This method quantizes each AI / ML model / function independently, using the same standard, and can effectively compare the differences between AI / ML models / functions.

[0114] Method three: Take the RSRP / SINR value of the activated AI / ML model / function as the baseline or select the median of multiple RSRP / SINR values ​​as the baseline, and differentiate the multiple AI / ML models under the same function monitored by other monitoring and the activated AI / ML model / function by default. Add 1 bit to indicate the upward difference or downward difference, and the differential value can be quantized using 1 bit, 2 bits, 3 bits, 4 bits, 5 bits, or 6 bits. This method can reduce the reporting overhead of the user equipment 120 to a certain extent, and can improve the accuracy of the feedback RSRP / SINR to a certain extent.

[0115] Regarding the reporting of Channel State Information (CSI) prediction, the user equipment 120 reports CSI for multiple AI / ML models under the same function under monitoring, which can be specifically divided into the following methods:

[0116] Method 1: Multiple AI / ML models under different AI / ML models / functions use independent reporting. When the CSI corresponding to multiple AI / ML models conflicts, the CSI corresponding to the initial AI / ML model under the currently active AI / ML model / function has the highest reporting priority. Prioritizing the reporting of the CSI corresponding to the active AI / ML model / function can help maintain stable system performance. In some embodiments, the initial AI / ML model refers to the AI / ML model that is initially activated when the function takes effect.

[0117] Method 2: Different AI / ML models or multiple AI / ML models under AI / ML functions adopt a joint reporting method.

[0118] Specifically, in some embodiments, the content carried by the first and second parts of the information in the CSI can be multiplexed in a multi-TRP joint reporting manner, but for the reporting of the content in the second part of the CSI, the reporting priority of the CSI corresponding to the initial AI / ML model under the currently activated AI / ML model / function can be made the highest; the priority reporting of the CSI corresponding to the activated AI / ML model / function can help maintain the stability of system performance. CSI can be the output result of an AI / ML model / function based on AI / ML CSI prediction / compression, or it can be the output result of an AI / ML model / function based on AI / ML beam management. In some embodiments, the initial AI / ML model refers to the AI / ML model that is initially activated when the function takes effect.

[0119] In some embodiments of the present application, the solution of the third embodiment may be implemented in conjunction with the solution of the first embodiment and / or the second embodiment, or may be implemented independently of the solution of the first embodiment and / or the second embodiment.

[0120] Fourth embodiment:

[0121] In some embodiments of the present application, the number of AI / ML models under the same function that the UE monitors simultaneously is used as a capability item of the UE. In some embodiments of the present application, based on the number of AI / ML models under the same function that the UE monitors simultaneously as a capability item of the UE, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is performed. In some embodiments of the present application, if the total number of monitored AI / ML models / functions exceeds the number of AI / ML models / functions monitored simultaneously by the UE, the UE monitors different AI / ML models / functions in batches based on the configured monitoring time window, and the number of AI / ML models / functions monitored each time is the same or different. In some embodiments of the present application, the window length of the minimum effective monitoring time window of a single AI / ML model / function or the window length of the effective monitoring time window is configured or defined.

[0122] In some embodiments of the present application, the number of AI / ML models under the same function that the network-side device monitors simultaneously is used as a capability item of the network-side device. In some embodiments of the present application, based on the number of AI / ML models under the same function that the network-side device monitors simultaneously as a capability item of the network-side device, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is performed. In some embodiments of the present application, if the total number of monitored AI / ML models / functions exceeds the number of AI / ML models / functions that the network-side device monitors simultaneously, the network-side device monitors different AI / ML models / functions in batches based on the configured monitoring time window, and the number of AI / ML models / functions monitored each time is the same or different.

[0123] Specifically, in some embodiments, for the monitoring of AI / ML models / functions, whether based on a periodic monitoring time window or based on event triggering, both of the above methods require the configuration of a monitoring time window for the AI / ML model / function. However, if at least one AI / ML model under the same function or a function implemented based on the AI / ML model is monitored simultaneously during the monitoring time window, the processing power, memory, load, and air interface signaling overhead of the user equipment 120 are very high. To this end, this embodiment provides the following multiple solutions to solve the problem of limited user equipment 120 and / or air interface capabilities during the AI / ML model / function monitoring process:

[0124] Solution 1: Considering the processing power limitations of user device 120, the number of AI / ML models for the same function that user device 120 can simultaneously monitor is defined as a capability of user device 120. User device 120 reports the maximum number of AI / ML models for the same function that it can simultaneously monitor or the number of models to be monitored to network device 110. For example, simultaneous monitoring of one or two AI / ML models for the same function by user device 120 is a basic capability of user device 120, while simultaneous monitoring of more than one or two AI / ML models for the same function is an optional capability of user device 120. Furthermore, based on the capabilities reported by user device 120, network device 110, taking into account uplink time-frequency domain resource constraints, can instruct user device 120 to monitor the number of AI / ML models for the same function that it can simultaneously monitor. The number of AI / ML models for the same function that network device 110 instructs user device 120 to monitor simultaneously cannot exceed the maximum number of AI / ML models for the same function that it can simultaneously monitor or the number of models to be monitored reported by user device 120.

[0125] Solution 2: Considering the processing power limitations of user device 120 and the effectiveness of AI / ML model / function monitoring, the standard stipulates or the network device 110 instructs the user device 120 on the length of the time window for AI / ML model / function monitoring. Furthermore, based on the capability item for simultaneously monitoring the number of AI / ML models under the same function reported by the user device 120, or based on the capability item for simultaneously monitoring the number of AI / ML models under the same function reported by the user device 120, the network device 110 instructs the user device 120 on the number of AI / ML models under the same function to monitor simultaneously, and the user device 120 monitors the AI / ML models under the same function. If the total number of AI / ML models under the same function to be monitored exceeds the number of AI / ML models under the same function that the user device 120 can simultaneously monitor, the user device 120 may continuously monitor different AI / ML models under the same function based on the configured or agreed monitoring time window, and the number of AI / ML models under the same function monitored each time may be the same or different. Assuming that the total number of AI / ML models under the same function that need to be monitored is 5, and the number of AI / ML models under the same function that the user device 120 monitors simultaneously at a single time is 3, the user device 120 needs to complete the monitoring of the AI / ML models under the same function in two times. For example, the user device 120 monitors 3 AI / ML models under the same function for the first time. After the first monitoring time window is reached, the user device 120 uses the same monitoring time window to monitor the other 2 AI / ML models under the same function. It should be noted here that when the user device 120 monitors multiple AI / ML models under the same function in multiple times according to capability constraints, the window lengths of the multiple monitoring time windows can be different. It depends on the configuration of the network side device 110. The network side device 110 or the user device 120 can also group multiple AI / ML models under the same function, and the window lengths of the monitoring windows corresponding to the AI / ML models in the same group are the same. In addition, the standard may also specify multiple time windows, which the network-side device 110 configures to the user equipment 120 through RRC signaling. Then, when the network-side device 110 instructs the user equipment 120 to monitor the AI / ML model under the same function, it instructs the user equipment 120 through DCI or MAC CE signaling to use one or several monitoring time windows to monitor the AI / ML model under the same function.

[0126] Solution three: Taking into account the effectiveness of AI / ML model / function monitoring, on the basis of the agreed monitoring time window or the monitoring time window configured by the network side device 110, the minimum effective monitoring time window length or the effective monitoring time window length of the user device 120 for a single AI / ML model / function can also be limited by agreement or the configuration of the network side device 110. The user device 120 completes the monitoring of the AI / ML model / function based on the agreed monitoring time window length or the monitoring time window length configured by the network side device 110, as well as the minimum effective monitoring time window length or the effective monitoring time window length for a single AI / ML model / function.

[0127] Conventional technology uses event-triggered monitoring, where monitoring is triggered based on a single result or performance, potentially leading to false triggers and unnecessary monitoring. However, triggering based on statistical results requires continuous monitoring of the output results or performance, requiring long-term memory allocation and increasing processing complexity for user device 120 / network device 110. Furthermore, event-triggered monitoring relies heavily on the criteria for measuring the event. Setting a low threshold for the event metric can degrade system performance, while setting a high threshold for the metric can lead to unnecessary monitoring.

[0128] In some embodiments of the present application, for event-triggered monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model, a short-term event + long-term event joint decision-making mechanism is adopted to avoid mismonitoring of the AI / ML model and leave a certain amount of operating space for processing on the network side or the terminal side. At the same time, this mechanism can also be used for decision-making of LCM events. In some embodiments of the present application, an event and periodic method is used to determine when to monitor at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model. On the one hand, it ensures that the system performance will not continue to deteriorate; on the other hand, it avoids the performance deterioration of the AI / ML model / or function due to sudden changes in the channel or the external environment or other emergencies; at the same time, the above method can reduce the power consumption of the system to a certain extent while ensuring performance.

[0129] In some embodiments of the present application, the solution of the fourth embodiment may be implemented in conjunction with the solutions of the first embodiment, the second embodiment, and / or the third embodiment, or may be implemented independently of the solutions of the first embodiment, the second embodiment, and / or the third embodiment.

[0130] Fifth embodiment:

[0131] UE side: In some embodiments of the present application, the wireless communication method further includes triggering a fallback operation of the AI / ML model / function and notifying the network-side device of the fallback operation. In some embodiments of the present application, the event / condition triggering the fallback operation of the AI / ML model / function includes the failure of the AI / ML model / function to load, or the inability to implement the corresponding function based on the current AI / ML model / function, or the detection of an instantaneous difference or statistical information of the difference between the output result of the model and the true / approximate true label exceeding a predefined threshold, or the monitoring of system performance exceeding a defined threshold, thereby triggering the fallback operation of the AI / ML model / function. In some embodiments of the present application, if the monitoring of at least one AI / ML model under the same function, or the monitoring of a function implemented based on the AI / ML model, results in the fallback operation, and the monitoring of the AI / ML model / function and the lifecycle management (LCM) decision of the AI / ML model / function after monitoring are not made on the same side, then the first signaling is further used to instruct the UE to perform the fallback operation, or the UE notifies the network-side device to perform the fallback operation.

[0132] Network-side device: In some embodiments of the present application, the wireless communication method further includes triggering a rollback operation of the AI / ML model / function and notifying the user equipment (UE) of the rollback operation. In some embodiments of the present application, the event / condition triggering the rollback operation of the AI / ML model / function includes the failure of the AI / ML model / function to load, the inability to implement the corresponding function based on the current AI / ML model / function, the detection of an instantaneous difference or statistical information of the difference between the output result of the model and the true / approximate true label exceeding a predefined threshold, or the monitoring of system performance degradation exceeding a defined threshold, thereby triggering the rollback operation of the AI / ML model / function. In some embodiments of the present application, if the result of performing the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is the rollback operation, and the decision of the lifecycle management (LCM) of the AI / ML model / function after the monitoring is not made on the same side, the network-side device performs the rollback operation, or the network-side device notifies the UE to perform the rollback operation.

[0133] Specifically, in some embodiments, when triggering AI / ML model / function monitoring, the selection of the triggering moment is crucial. If the system performance is better than the performance of the traditional signal processing method when the AI / ML model / function monitoring is triggered, it may result in waste of network-side device 110 and / or user equipment 120 capabilities and waste of air interface resources. If the system performance is worse than the performance of the traditional signal processing method when the AI / ML model / function monitoring is triggered, the system performance cannot be guaranteed. In view of this, this embodiment believes that the following solution can be used to ensure the performance of the system:

[0134] Solution 1: The network-side device 110 and / or the user device 120 have the ability or authority to control the system to fallback to the traditional signal processing method, and the fallback operation may not depend on the monitoring results of the AI / ML model / function; for example, if the AI / ML model / function fails to load or if the system performance is significantly degraded, the network-side device 110 and / or the user device 120 can trigger the AI / ML model / function fallback operation and notify the other end of the fallback operation. For example, if the network-side device 110 detects that the system's performance has significantly degraded, the network-side device 110 can directly instruct the user device 120 through signaling to perform a fallback operation on the AI / ML model / function. For example, when the AI / ML model / function of the user device 120 fails to work properly, the user device 120 can directly fall back from the state of the AI / ML model / function to the traditional signal processing method and notify the network-side device 110 through signaling, so that the network-side device 110 can adopt corresponding processing. For example, for a dual-end AI / ML model / function, after receiving the notification signaling from the user device 120, the network-side device 110 also falls back from the state of the AI / ML model / function to the traditional signal processing method. A significant performance degradation, for example, refers to a performance degradation exceeding a defined threshold.

[0135] Solution 2: Considering that the performance of AI / ML models / functions is affected by generalization, when the external environment or channel conditions change, if the generalization of the AI / ML model / function is poor, the system performance may be significantly affected. Monitoring of the AI / ML model / function is usually triggered only when the system performance is unstable or drops below a certain threshold. Therefore, it is difficult to guarantee the system performance during the monitoring process. To address the above issues, this solution proposes that during the monitoring of the AI / ML model / function, the network device 110 and / or the user device 120 directly fall back to the traditional signal processing method. If the result after the AI / ML model / function completes the monitoring is a fallback, and the decision on the monitoring of the AI / ML model / function and the life cycle management (LCM) of the AI / ML model / function after monitoring is not made on the same side, the network device 110 sends a signaling to notify the user device 120 to roll back the AI / ML model / function, or the user device 120 sends a signaling to notify the network device 110 to roll back the AI / ML model / function. If the result after the AI / ML model / function is monitored is to maintain the AI / ML model / function before monitoring in an activated state, the network side device 110 sends a signaling to notify the user device 120 to activate the AI / ML model / function, or the user device 120 sends a signaling to notify the network side device 110 to activate the AI / ML model / function; if the result after the AI / ML model / function is monitored is to switch to another AI / ML model under the same function, the network side device 110 sends a signaling to notify the user device 120 to switch the AI / ML model, or the user device 120 sends a signaling to notify the network side device 110 to switch the AI / ML model. The indication of the event in the LCM corresponding to the above-mentioned AI / ML model / function can be indicated in the form of a bitmap, or it can be indicated by bits (bits) are used for indication, where the value of X is the type of event for which the network side device 110 or the user device 120 makes a decision after the AI / ML model / function is monitored.

[0136] In some embodiments of the present application, the network device 110 or the user device 120 may instruct monitoring of a certain AI / ML model. In some embodiments of the present application, the monitoring may be real-time monitoring, that is, the system monitors the AI / ML model in real time and determines the corresponding LCM event based on the real-time monitoring results.

[0137] In some embodiments of the present application, the scheme of the fifth embodiment may be implemented in conjunction with the schemes of the first embodiment, the second embodiment, the third embodiment and / or the fourth embodiment, or may be implemented independently of the schemes of the first embodiment, the second embodiment, the third embodiment and / or the fourth embodiment.

[0138] Sixth embodiment:

[0139] In some embodiments of the present application, the number of AI / ML models loaded by a single function of the network side device and / or the UE is configured or defined. In some embodiments of the present application, the number of AI / ML models loaded by a single function of the UE is reported as a capability item of the UE. In some embodiments of the present application, for a certain function, there is an initial AI / ML model, that is, the AI / ML model that is activated by default when the function takes effect. For the AI / ML model on the UE side, the AI / ML model can be indicated to the UE by the network side device, or it can be determined when the model is loaded, or it can be constrained by the standard, for example, it can be the AI / ML model with the smallest / largest AI / ML model ID, or it can be the AI / ML model loaded first. As for the AI / ML model on the network side, it can be determined by the network side device itself, or it can be a standard agreement, for example, it can be the AI / ML model with the smallest / largest AI / ML model ID; and for the AI / ML model on both sides, it can be determined by the network side or the UE side and informed to the other side, or it can be a standard agreement, for example, it can be the AI / ML model with the smallest / largest AI / ML model ID, or it can be the AI / ML model loaded first. In some embodiments of the present application, the AI / ML model that has been loaded under a function is upgraded or updated. If the AI / ML model is deployed on the UE side and downloaded from the network side device, the UE receives the parameters / architecture information for the AI / ML model upgrade or update sent by the network side device, and the UE also receives the upgraded or updated AI / ML model indicated by the network side device. In some embodiments of the present application, the number of AI / ML models loaded by a single function of the network side device is reported as a capability item of the network side device. In some embodiments of the present application, an AI / ML model that has been loaded under a function is upgraded or updated. If the AI / ML model is deployed on the UE side and is downloaded from the network side device, the network side device sends parameter / architecture information of the AI / ML model upgrade or update to the UE, and the network side device also indicates the upgraded or updated AI / ML model to the UE.

[0140] Specifically, in some embodiments, considering that loading too many AI / ML models / functions on the network device 110 and / or the user device 120 consumes a large amount of memory, and that loading a large number of AI / ML models / functions imposes a certain burden on subsequent monitoring of the AI / ML models / functions and air interface signaling interactions, this embodiment considers restricting the number of AI / ML models that can be loaded by a single function on the network device 110 and / or the user device 120. The number of AI / ML models that can be downloaded by a single function on the user device 120 is reported as a capability item of the user device 120, or the standard directly restricts the number of AI / ML models that can be loaded by the network device 110 and / or the user device 120 for a single function. For loaded AI / ML models, the network device 110 or the user device 120 can upgrade or update the AI / ML model, or delete the AI / ML model, but the user device 120 or the network device 110 needs to be informed. For example, if the number of AI / ML models loaded by the network device 110 and / or the user device 120 under a certain function has reached the constraint of the maximum number of supported AI / ML models, if the network device 110 and / or the user device 120 needs to load a new AI / ML model for the function, if the AI / ML model is deployed on the user device 120 side and is downloaded from the network device 110 side, the network device 110 side needs to instruct the user device 120 to delete one of the AI / ML models and send the newly added AI / ML model to the user device 120.

[0141] Specifically, in some embodiments, the AI / ML model to be deleted can be indicated via a bitmap, with each bit corresponding to a specific AI / ML model. If the AI / ML model is deployed on the network device 110 and uploaded from the user device 120, the user device 120 needs to send a request to the network device 110, requesting that the network device 110 delete the specific AI / ML model and allocate resources for uploading the AI / ML model to the user device 120. The AI / ML model to be deleted can also be indicated via a bitmap, with each bit corresponding to a specific AI / ML model. For dual-sided AI / ML models, if the AI / ML model is sent from the network device 110 to the user device 120, the network device 110 needs to instruct the user device 120 to delete one of the AI / ML models and send the newly added AI / ML model to the user device 120. The AI / ML model to be deleted can be indicated via a bitmap, with each bit corresponding to a specific AI / ML model. If an AI / ML model is uploaded from user device 120 to network device 110, user device 120 needs to send a request to network device 110 to delete the AI / ML model and allocate the resources used to upload the AI / ML model to user device 120. The AI / ML model to be deleted can also be indicated using a bitmap, with each bit corresponding to an AI / ML model.

[0142] Furthermore, in the case where the network device 110 and / or user device 120 load multiple AI / ML models for a certain function, if an AI / ML model already loaded for a certain function needs to be upgraded or updated, if the AI / ML model is deployed on the user device 120 and downloaded from the network device 110, the network device 110, in addition to sending the parameters / architecture information for the AI / ML model upgrade or update, needs to indicate to the user device 120 which of the multiple AI / ML models is being upgraded or updated. This specific indication can be provided via a bitmap, with each bit corresponding to a specific AI / ML model. If the AI / ML model is deployed on the network device 110 and uploaded from the user device 120, the user device 120 needs to send an AI / ML model upgrade or update request to the network device 110, notifying the network device 110 of which AI / ML model needs to be upgraded or updated. This AI / ML model indication can be provided via a bitmap, with each bit corresponding to a specific AI / ML model. After receiving the request from user device 120, network device 110 sends a response message to user device 120, which is used to configure the parameters / architecture information for the AI / ML model upgrade or update. For dual-side AI / ML models, the process is the same as that for single-side AI / ML models.

[0143] In some embodiments of the present application, the scheme of the sixth embodiment may be implemented in conjunction with the scheme of the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, and / or the fifth embodiment, or may be implemented independently of the scheme of the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, and / or the fifth embodiment.

[0144] Seventh embodiment:

[0145] FIG3A is a flow chart of a method for wireless communication provided in an embodiment of the present application. As shown in FIG3A , the method for wireless communication is executed on a user equipment (UE) and includes at least one of the following operations: Operation 301A: Based on a first condition and / or a second condition, the UE decides whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model. The first condition is that a monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model is lower than, higher than, or equal to a defined threshold, or an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model occurs, and the first condition is related to the second condition.

[0146] FIG3B is a flow chart of a wireless communication method provided in an embodiment of the present application. As shown in FIG3B , the wireless communication method is executed on a network-side device and includes at least one of the following operations: Operation 301B: Based on the first condition and / or the second condition, the network-side device determines whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model. The first condition is that the monitoring quantity related to the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is lower than, higher than or equal to a defined threshold or the occurrence of an event related to the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model, and the first condition is related to the second condition.

[0147] In some embodiments of the present application, the window length for performing monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is defined, or configured by a network-side device, or controlled by the UE. In some embodiments of the present application, an event-triggered approach is adopted to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, and the event-triggered approach is to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model based on the first condition and / or the second condition.

[0148] Specifically, in some embodiments, considering that the performance of AI / ML models / functions is related to their generalization, in order to ensure that the AI / ML models / functions can work properly in the network, it is necessary to monitor the performance of the AI / ML models / functions and determine certain events in the LCM based on the performance monitoring. Monitoring the AI / ML models / functions will increase the processing complexity of the network or user equipment 120. Furthermore, in particular, for the AI / ML models / functions on the user equipment 120 side, some monitoring results may need to be reported, resulting in high reporting overhead and other issues. If the decision-making process for an LCM event only requires monitoring of the currently activated / normally operating AI / ML models / functions, the impact on the processing complexity, power consumption, and reporting overhead of the network device 110 or user device 120 is relatively controllable. However, the decision-making process for some LCM events may require monitoring multiple AI / ML models / functions simultaneously. These multiple AI / ML models / functions may be activated or operating, or they may be non-activated or non-operating AI / ML models / functions. These non-activated or non-operating AI / ML models / functions need to be activated before monitoring. This increases the processing complexity and power consumption of the network device 110 or user device 120, and may also increase the reporting overhead of the user device 120. Therefore, the network device 110 and / or user device 120 needs to determine when to start / activate simultaneous monitoring of multiple AI / ML models / functions based on the monitoring results of the currently operating AI / ML models / functions.

[0149] Specifically, in some embodiments, for AI / ML models / functions on the user device 120 side, at least one AI / ML model under the same function or a function implemented based on the AI / ML model can be monitored in an event-triggered manner. The monitoring window length can be determined using standard constraints, can be configured by the network-side device 110, or can be unconstrained. The specific monitoring duration is controlled by the user device 120. The triggering / starting / starting of the simultaneous monitoring of at least one AI / ML model under the same function or a function implemented based on the AI / ML model can be determined based on one or more conditions. For example, the monitoring of the AI / ML model / function is triggered / started / started when the first condition and / or the second condition are met.

[0150] Specifically, in some embodiments, for AI / ML models / functions on the network side, an event triggering method can be used to determine whether to monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model simultaneously. The monitoring window length can be determined by a standard constraint method or the window length can be unconstrained. The specific monitoring duration is controlled by the network side device 110. The triggering / starting / starting of the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model can be determined based on one or more conditions. For example, the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is triggered / started / started when the first condition and / or the second condition are met.

[0151] Conventional technology uses event-triggered monitoring, where monitoring is triggered based on a single result or performance, potentially leading to false triggers and unnecessary monitoring. However, triggering based on statistical results requires continuous monitoring of the output results or performance, requiring long-term memory allocation and increasing processing complexity for user device 120 / network device 110. Furthermore, event-triggered monitoring relies heavily on the criteria for measuring the event. Setting a low threshold for the event metric can degrade system performance, while setting a high threshold for the metric can lead to unnecessary monitoring.

[0152] In some embodiments of the present application, for event-triggered monitoring of at least one AI / ML model under the same function, or monitoring of a function implemented based on an AI / ML model, a short-term event + long-term event joint decision-making mechanism is adopted to avoid mis-monitoring of the AI / ML model and leave a certain amount of operating space for processing on the network side or the terminal side. At the same time, this short-term event + long-term event joint decision-making mechanism can also be used for LCM event decision-making. In some embodiments, based on the first condition and / or the second condition, the decision on whether to perform monitoring of at least one AI / ML model under the same function, or monitoring of a function implemented based on an AI / ML model, can also be used to trigger / start an LCM event. LCM events include, for example, activation, deactivation, selection, switching, and fallback of AI / ML models / functions. In some embodiments of the present application, an event and periodic approach is used to determine when to monitor at least one AI / ML model under the same function, or monitoring of a function implemented based on an AI / ML model. This ensures that system performance does not continue to deteriorate, while also preventing performance degradation of the AI / ML model / function due to sudden changes in the channel or external environment, or other unexpected conditions. Furthermore, while ensuring performance, the above approach can also reduce system power consumption to a certain extent.

[0153] In some embodiments of the present application, whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is determined according to the instruction of the network side device, and the instruction of the network side device is based on the first condition and / or the second condition to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model.

[0154] Specifically, in some embodiments, for the AI / ML model / function on the user equipment 120 side, at least one AI / ML model under the same function or a function implemented based on the AI / ML model can be monitored according to the instruction of the network side device 110. The monitoring window length can be determined in a standard constraint manner, or can be configured by the network side device 110, or the window length can be unconstrained, and the specific monitoring duration is controlled by the user equipment 120. The network side device 110 determines whether to instruct the user equipment 120 to simultaneously monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model based on one or more conditions. For example, the network side device 110 determines whether to instruct the user equipment 120 to simultaneously monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model based on the first condition and / or the second condition.

[0155] Specifically, in some embodiments, for AI / ML models / functions on the network side, the triggering / starting / starting of simultaneous monitoring of at least one AI / ML model under the same function or a function implemented based on an AI / ML model can be based on a request sent by the user device 120. If the user device 120 meets the first condition and / or the second condition, the user device 120 sends a request to the network side device 110, requesting the network side device 110 to monitor at least one AI / ML model under the same function or a function implemented based on an AI / ML model. The window length monitored by the network side device 110 can be determined by standard constraints, or the window length can be unconstrained, and the specific monitoring duration is controlled by the network.

[0156] In some embodiments of the present application, whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is determined based on the request information and the indication information in response to the request information, wherein the UE decides whether to send the request information to the network side device based on the first condition and / or the second condition.

[0157] Specifically, in some embodiments, for the AI / ML model / function on the user device 120 side, the user device 120 may first initiate a request message to the network side device 110 for simultaneously monitoring at least one AI / ML model under the same function or a function implemented based on the AI / ML model. The network side device 110 issues an instruction message based on the request of the user device 120, instructing the user device 120 to simultaneously monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model. When the user device 120 side initiates the request is determined based on one or more conditions. For example, if the first condition and / or the second condition are met, the user device 120 sends a request to the network side device 110 to simultaneously monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model. The request information of the user device 120 may also include specific trigger / start / start time information, and may also include corresponding information about the AI / ML model / function that needs to be started / triggered / started to be monitored. The network side device 110 decides to simultaneously monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model based on the request of the user device 120. At the same time, the network side device 110 may also instruct the user device 120 to monitor which AI / ML models / functions, and may also indicate the time information of triggering / starting / starting monitoring, as well as monitoring duration information, etc.

[0158] In some embodiments of the present application, for a two-sided AI / ML model, the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is performed by the UE or the UE requests the network-side device to perform. In some embodiments of the present application, for a two-sided AI / ML model, the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is performed by the network-side device or the network-side device requests the UE to perform.

[0159] Specifically, in some embodiments, for the AI / ML models on both the network side and the user device 120 side, the triggering / starting / starting of the simultaneous monitoring of at least one AI / ML model under the same function may be initiated by one side and then instructed or requested to the other side, or it may be based on the request of one side, and then the other side initiates and instructs the other side to trigger / start / start the simultaneous monitoring of at least one AI / ML model under the same function. For example, the user device 120 first requests the network side to trigger / start / start the simultaneous monitoring of at least one AI / ML model under the same function, and the request information may also include specific triggering / starting / starting time information, and may also include information about the corresponding AI / ML model to be monitored. The network side decides to simultaneously monitor at least one AI / ML model under the same function based on the request of the user device 120. At the same time, the network side may also instruct the user device 120 which AI / ML models to monitor, and may also indicate the time information of triggering / starting / starting the monitoring, as well as the monitoring duration information, etc. For a dual-sided AI / ML model, if the network side triggers / starts / begins simultaneous monitoring of at least one AI / ML model under the same function directly based on a request from the user device 120, the network side may also send an indication message to the user device 120, indicating to the user device 120 that the project has been started.

[0160] Furthermore, for AI / ML models on the network side, if the user device 120 requests to monitor at least one AI / ML model under the same function or a function implemented based on an AI / ML model, the specific AI / ML models to be monitored may be determined by the user device 120's request, or the network may independently decide which AI / ML models to monitor. For AI / ML models on the user device 120 side, if the network device 110 instructs the user device 120 to monitor at least one AI / ML model under the same function or a function implemented based on an AI / ML model, the network device 110 may also instruct the user device 120 to monitor the specific AI / ML models, or the user device 120 may independently decide which AI / ML models to monitor.

[0161] In some embodiments of the present application, the occurrence of an event related to the monitoring of at least one AI / ML model under the execution of the same function or the monitoring of a function implemented based on the AI / ML model refers to whether the monitored quantity matches the reference value or the error is within a defined range. In some embodiments of the present application, the second condition is that the first condition persists for a period of time, or the second condition is how many times the first condition occurs consecutively within a period of time, or the total number of times the first condition occurs within a period of time is greater than, less than, or equal to the defined threshold, or the probability distribution of the occurrence of the first condition within a period of time is greater than, less than, or equal to the defined threshold.

[0162] Specifically, in some embodiments, the determination of the first condition and / or the second condition can be based on the monitoring results of the currently activated AI / ML model / function or the working AI / ML model / function. The above-mentioned first condition can be at least one of the following forms: a certain quantity X is lower than / higher than / equal to a defined threshold Y; or it can be the occurrence of a certain event, such as whether a certain variable (monitored quantity) matches the actual measurement value (reference value), or the error is within a defined range.

[0163] The second condition can be that the first condition persists for a period of time, such as multiple time slots or frames; it can also be how many times the first condition appears consecutively; it can also be how many times the first condition appears consecutively within a period of time (consecutive multiple time slots or frames); it can also be that the total number of times the first condition appears within a period of time is greater than / less than / equal to a defined threshold; it can also be that the probability distribution of the first condition appearing within a period of time is greater than / less than / equal to a defined threshold.

[0164] Note that the duration mentioned in the second condition above, or the specific duration within a period of time thereafter, can be a standard agreement on the network device 110 side, or an internal implementation behavior of the network device 110; and the conditions on the user device 120 side can also be a standard agreement, or a configuration of the network device 110, or an internal implementation of the user device 120 itself; for example, the duration of the second condition can be in the form of a time window, and the window length can be configured by the network side or agreed upon by the standard. Furthermore, for different use cases supported by AI / ML, a certain quantity X may be different, and the corresponding threshold value Y may also be different.

[0165] For example, for AI / ML-based beam management, the quantity X can be the Reference Signal Received Power (RSRP) or Signal to Interference plus Noise Ratio (SINR), the system throughput or target block error rate (BLER), the angular difference between the predicted beam and the optimal beam, or the RSRP / SINR difference between the predicted beam and the actual beam. For the case of simultaneously predicting multiple beams at a certain moment, it can be the degree of match between the predicted beams and the actual measured beams, for example, the match between the predicted four beams and the actual four beams is less than 50%, or the difference between the RSRP / SINR values ​​of the predicted beams and the actual measured beams is greater than / less than / equal to a defined value, and the proportion of the predicted beams to the total number of beams is greater than / less than / equal to a defined value. If the first condition is based on whether a certain event occurs, then for beam prediction, it can be whether the predicted beam is / is not the actual optimal beam, or the deviation between the predicted beam and the optimal beam is greater than / less than / equal to a defined value.

[0166] For channel state information (CSI) prediction, a certain quantity X can be an SINR value, a channel quality indicator (CQI) value, the system throughput, the BLER value, the modulation and coding scheme (MCS) value, or the correlation between the predicted CSI and the measured CSI. The CSI here can be the channel, the channel eigenvector, or the eigenvector after SVD decomposition of the channel eigenvector. The specific form of CSI is not limited here and can be any form of channel state information. The correlation here can be represented by a value between 0 and 1, where 0 indicates no correlation at all and 1 indicates the best correlation between the two.

[0167] For CSI compression, the quantity X can be a Signal to Interference plus Noise Ratio (SINR) value, a CQI value, a system throughput, a BLER value, an MCS value, or the correlation between the non-zero coefficients in the eigenvector / precoding matrix indicator (PMI) after singular value decomposition (SVD) of the decompressed channel / eigenvector / precoding matrix and the non-zero coefficients in the eigenvector / PMI after SVD decomposition of the pre-compression channel / eigenvector / precoding matrix. It can also be the correlation between the measured CSI information sampling results and the CSI sampling results recovered after quantization. The correlation here can be represented by a value between 0 and 1, where 0 indicates no correlation at all and 1 indicates the best correlation between the two.

[0168] For positioning, a certain quantity X can be downlink reference signal time difference (DL-RSTD), uplink RSTD (UL-RSTD), time of arrival (TOA), time difference of arrival (TDOA), timing time difference, round trip time (RTT), or reference signal received power (RSRP), reference signal received quality (RSRQ), power delay profile (PDP), channel impulse response (CIR), channel frequency response (CFR), etc.

[0169] For positioning, the quantity X can also be the difference between the positioning result of the AI / ML model / function and the ground truth label or the approximate ground truth label, or the difference between some intermediate positioning quantities and the ground truth label or the approximate ground truth label. These intermediate positioning quantities can be downlink reference signal time difference (DL-RSTD), uplink RSTD (UL-RSTD), time of arrival (TOA), time difference of arrival (TDOA), timing time difference, round trip time (RTT), or reference signal received power (RSRP), reference signal received quality (RSRQ), power delay profile (PDP), channel impulse response (CIR), channel frequency response (CFR), etc.

[0170] If the first condition is based on whether a certain event occurs, then for positioning, the difference between the positioning result and the true label (ground truth label) or the approximate true label can be greater than / less than / equal to the defined threshold value, or some differences between some intermediate results of positioning and the true label or the approximate true label can be greater than / less than / equal to the defined threshold value. These intermediate results of positioning can be downlink reference signal time difference (DL-RSTD), uplink RSTD (UL-RSTD), time of arrival (TOA), time difference of arrival (TDOA), timing time difference, round trip time (RTT), or reference signal received power (RSRP), reference signal received quality (RSRQ), power delay profile (PDP), channel impulse response (CIR), channel frequency response (CFR), etc. Furthermore, regarding whether an event has occurred, since positioning involves the coordination of multiple network-side devices 110 / transmission reception points (TRPs) and may involve the outputs of multiple AI / ML models / functions, an event may be considered to have occurred if the outputs of multiple AI / ML models / functions do not meet certain conditions. For example, the ranges defined by the TOA / TDOA / RSTD measurements of multiple network-side devices 110 / TRPs do not intersect, making positioning impossible. Alternatively, the ranges defined by the angle of departure (AoD) / angle of arrival (AoA) determined based on the RSRP / RSRQ / PDP / CIR / CFR obtained by multiple network-side devices 110 / TRPs do not intersect, making positioning impossible. Alternatively, positioning cannot be completed based on at least one of the aforementioned measurements. In this embodiment, AoA can be used to represent AoA in the azimuth plane and / or the elevation plane. The AoA in the azimuth plane can be referred to as azimuth / horizontal AoA. The AoA in the elevation plane can be referred to as elevation / zenith AoA. AoD may be used herein to encompass AoD in the azimuth plane and / or the elevation plane.The AoD in the azimuth plane may be referred to as azimuth / horizontal AoD, and the AoD in the elevation plane may be referred to as elevation / zenith AoD.

[0171] It should be noted that there is no necessary binding relationship between the first condition, the duration of monitoring the currently operating AI / ML model / function after the first condition is met, and the second condition. These conditions may be configured as separate configurations or standard agreements, or may be combined configurations or standard agreements. For example, the standard may stipulate only one first condition, and upon meeting the first condition, the network device 110 or user device 120 initiates / triggers / requests / continues continuous monitoring of the activated AI / ML model / function or the currently operating AI / ML model / function. Based on the monitoring results, the network device 110 or user device 120 determines whether to initiate / trigger / request simultaneous monitoring of at least one AI / ML model under the same function or a function implemented based on the AI / ML model. The process by which the network device 110 or user device 120 makes this decision, as well as the duration of continuous monitoring of the activated AI / ML model / function or the currently operating AI / ML model / function after the first condition is met, may be internally implemented by the network device 110 or user device 120. For another example, the standard only stipulates the first condition and the duration of continuous monitoring of the activated AI / ML model / function or the currently working AI / ML model / function after the first condition is met. After the first condition is met, the network-side device 110 or the user device 120 starts / triggering / requesting / continues to monitor the activated AI / ML model / function or the currently working AI / ML model / function for a certain period of time, and then based on the monitoring results, the network-side device 110 or the user device 120 decides whether to start / trigger / request simultaneous monitoring of at least one AI / ML model under the same function or a function implemented based on the AI / ML model. The process of the network-side device 110 or the user device 120 making the decision can be based on the internal implementation of the network-side device 110 or the user device 120.

[0172] It should be noted that the activated AI / ML model / function or the currently working AI / ML model / function mentioned above can be one or more, and the triggering / starting / starting of simultaneous monitoring of at least one AI / ML model under the same function or a function implemented based on the AI / ML model can refer to at least one AI / ML model under the same function or a function implemented based on the AI / ML model in addition to the currently activated AI / ML model / function or the currently working AI / ML model / function.

[0173] Specifically, in some embodiments, for different use cases, the beam management for monitoring of AI / ML models / functions mainly includes the following aspects: For the AI / ML model / function on the user device 120 side, the user device 120 monitors the performance indicators, and the user device 120 decides whether to activate, deactivate, select, switch, fallback, etc. the AI / ML model / function, where fallback refers to falling back to the traditional signal processing method. For the AI / ML model / function on the user device 120 side, the network side monitors the performance indicators, and the network side decides whether to activate, deactivate, select, switch, fallback, etc. the AI / ML model / function. For the AI / ML model / function on the user device 120 side, the user device 120 monitors the performance indicators, and the network side decides whether to activate, deactivate, select, switch, fallback, etc. the AI / ML model / function.

[0174] Positioning mainly includes the following aspects:

[0175] The acquisition of monitoring indicators for the AI / ML model / function on the user equipment 120 side can be the user equipment 120, the model on the network side can be the gNB, and the AI / ML model / function on the LMF side can be the LMF.

[0176] When using dual-sided AI / ML models / functions for CSI compression, the following aspects are mainly involved:

[0177] The network side performs performance monitoring and decides whether to activate / deactivate / update / switching the AI / ML model / function. The user equipment 120 side performs performance monitoring and decides whether to activate / deactivate / update / switching the AI / ML model / function.

[0178] Specifically, in some embodiments, with respect to location monitoring based on AI / ML models, at least the following potential data needs to be further investigated as a possibility for calculating monitoring indicators: If monitoring is performed based on model output: for example, for direct AI / ML positioning, the estimated user device location corresponding to the model output; for assisted AI / ML positioning, the estimated intermediate parameters corresponding to the model output; for direct and assisted AI / ML positioning, the ground truth labels corresponding to the model inference output. If monitoring is performed based on model input: for example, measurement data corresponding to the model inference input. Note that other types of model monitoring potential data are not excluded. Note that one or more types of potential data can be combined for monitoring.

[0179] Specifically, in some embodiments, if a certain type of data is necessary to calculate a monitoring indicator, the following issues need to be studied: How entities are used to provide data of a given type to calculate the monitoring indicator; For each case, the entity (or entities) reporting its use is required to provide the given type of data to calculate the monitoring indicator. Potential signaling for providing data of a given type to calculate the relevant monitoring indicator. Potential auxiliary signaling and procedures for facilitating entities to provide data for calculating the monitoring indicator. Potential user equipment and network interactions. For example, model monitoring decision instructions between user equipment and the network.

[0180] In some embodiments of the present application, the scheme of the seventh embodiment may be implemented in conjunction with the schemes of the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, and / or the sixth embodiment, or may be implemented independently of the schemes of the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, and / or the sixth embodiment.

[0181] Eighth embodiment:

[0182] In some embodiments of the present application, the wireless communication method further includes, based on the first condition and / or the second condition, deciding a lifecycle management LCM event. In some embodiments of the present application, if the first condition and / or the second condition are met, the UE performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model to obtain a monitoring result, and decides an LCM event based on the monitoring result. In some embodiments of the present application, the decision on the LCM event is also determined based on a third condition, and the third condition is a defined threshold value, and the defined threshold value determines the type of the LCM event. In some embodiments of the present application, the LCM event decision mechanism can be specified by the network side device or the UE to monitor a certain AI / ML model.

[0183] The first and second conditions mentioned in the seventh embodiment can not only be used to determine whether to start / trigger / begin monitoring of at least one AI / ML model under the same function or a function implemented based on the AI / ML model, but can also serve as a basis for LCM event decisions. For example, after the first condition is met, the network-side device 110 or the user device 120 starts / triggers / requests / continues to continuously monitor the activated AI / ML model / function or the currently operating AI / ML model / function, or after monitoring for a period of time, determines an LCM event for the AI / ML model / function based on the monitoring results. The corresponding LCM event can be a fallback to a traditional processing method, a switching of at least one AI / ML model under the same function or a function implemented based on the AI / ML model, the activation of at least one AI / ML model under the same function or a function implemented based on the AI / ML model, the deactivation of at least one AI / ML model under the same function or a function implemented based on the AI / ML model, the selection of at least one AI / ML model under the same function or a function implemented based on the AI / ML model, or the upgrade of at least one AI / ML model under the same function or a function implemented based on the AI / ML model. In this regard, if it is an AI / ML model / function on the network side, the user device 120 may request the network side device 110 to implement the corresponding LCM event, for example, to activate / deactivate / select / switch / upgrade one or more AI / ML models / functions, or to fall back to the traditional processing method. If it is an AI / ML model / function on the user device 120 side, the network side device 110 may instruct the user device 120 to implement the corresponding LCM event, including activating / deactivating / selecting / switching / upgrading one or more AI / ML models / functions, or to fall back to the traditional processing method. For bilateral AI / ML models / functions or multiple AI / ML models / functions or a group of AI / ML models / functions (which can be the same AI / ML model / function or different AI / ML models / functions) collaboratively positioned by multiple network side devices 110 / TRPs in positioning, the decision of the LCM event applies to multiple AI / ML models / functions or a group of AI / ML models / functions under multiple network side devices 110 / TRPs at the same time.

[0184] Furthermore, in some embodiments of the present application, for the AI / ML model / function on the network side, the network side device 110 may decide to monitor one or more AI / ML models / functions based on the switching request of the user device 120, or based on its own (network side device 110) decision, and thereby determine whether to switch to a certain AI / ML model / function to work based on the monitoring results. As for the AI / ML model / function of the user device 120, the user device 120 may decide to monitor one or more AI / ML models / functions based on the switching instruction of the network side device 110, or based on its own (network side device 110) decision, and thereby determine whether to switch to a certain AI / ML model / function to work based on the monitoring results. In addition, the acquisition of the first condition and the second condition mentioned in the seventh embodiment can also be considered as the result of monitoring the AI / ML model / function. In some embodiments of the present application, the monitoring of AI / ML models / functions can be considered to be real-time, that is, any detection of performance indicators of the AI / ML model / function in the working state can be understood as monitoring of the AI / ML model / function. LCM events can also be decided based on the real-time monitoring results of the AI / ML model / function. The decision-making process of LCM events is as described in some of the above embodiments.

[0185] Similarly, for LCM event decisions, there's no necessary constraint between the first condition, the duration of monitoring the currently active AI / ML model / function after the first condition is met, and the second condition. These conditions can be configured or standardized separately or in combination. Note that the first and second conditions here represent the same meaning in the different AI / ML use cases and in the seventh embodiment. It should be noted that the first condition and the second condition may correspond to multiple threshold values, and different threshold values ​​correspond to different LCM events. For example, the first condition corresponds to two thresholds, threshold 1 and threshold 2. If the first condition is less than / equal to threshold 1, the corresponding LCM event is a fallback operation. Specifically, it can be the RSRP or SINR for beam management mentioned in the seventh embodiment that is less than threshold 1; if the first condition is greater than threshold 1 and less than / equal to threshold 2, the corresponding LCM event is the switching / selection / upgrade / activation / deactivation of the AI / ML model / function, etc.; if the first condition is greater than threshold 2, the current state is maintained; at the same time, if the first condition is greater than threshold 1 and less than / equal to threshold 2, it can also be the start / trigger / start of monitoring at least one AI / ML model under the same function or a function implemented based on the AI / ML model, including the currently activated or working AI / ML model / function, and some or all of the AI / ML models / functions that are not activated or in working state. Note that for unactivated Activated or inactive AI / ML models / functions need to be activated before monitoring. If the first condition is greater than threshold 2, the current state is maintained. It should be noted that the relationship between the first condition and thresholds 1 and 2, as well as the corresponding related operations, may also be different for different monitoring quantities. For example, if the first condition is greater than / equal to threshold 2, the corresponding LCM event is a rollback operation. If the first condition is less than threshold 2 and greater than / equal to threshold 1, the corresponding LCM event is switching / selecting / upgrading / activating / deactivating the AI / ML model / function, or starting / triggering / starting monitoring of at least one AI / ML model under the same function or a function implemented based on the AI / ML model. If the first condition is less than threshold 1, the current state is maintained. Furthermore, threshold 1 can also be greater than / equal to threshold 2, and the corresponding conditions and executed operations will also change accordingly. There are no specific constraints here. The above-mentioned LCM event can be based on the judgment of the first condition threshold, and the same applies to the second condition.

[0186] Furthermore, after the first and / or second conditions are met, the network device 110 or the user device 120 monitors at least one AI / ML model under the same function or a function implemented based on the AI / ML model, and decides on possible LCM events based on the monitoring results. The monitoring duration can be controlled by a time window. The window length of the time window can be agreed upon by the standard or determined by the network device 110 or the user device 120. For the AI / ML model / function on the user device 120 side, it can be configured by the network side or configured by the network side based on the user device 120 request. For the AI / ML model / function on the network side, it can be requested by the user device 120 or constrained by the standard. For the AI / ML model / function on both sides, it can be determined by one side and then notified to the other side, or it can be agreed upon by the standard. For the collaborative implementation of a function involving multiple AI / ML models / functions, the window lengths of the monitoring time windows of the multiple AI / ML models / functions need to be the same, or they can be different.

[0187] After monitoring at least one AI / ML model under the same function or a function implemented based on an AI / ML model, the decision on the LCM event can be determined based on condition 3. Condition 3 can be a threshold value Y, which mainly determines the type of LCM event. For example, when monitoring at least one AI / ML model under the same function or a function implemented based on an AI / ML model, a certain quantity X corresponding to the monitored AI / ML model / function is continuously monitored. After a period of monitoring, if the monitoring result of the quantity X corresponding to the AI / ML model / function is greater than / less than / equal to a threshold Y, and there are multiple such AI / ML models, the network device 110 or the user device 120 will select one or more AI / ML models from these AI / ML models for normal operation of the functionality. The specific selection of the one or more AI / ML models can be implemented by the network device 110 or the user device 120. The network device 110 or the user device 120 can also directly select an AI / ML model with a larger / smaller / equal difference from the threshold value as the AI / ML model for normal operation of the functionality, and the other AI / ML models need to be deactivated. It is important to note that for a given AI / ML model / function, if multiple AI / ML models / functions have the same input and output, the network device 110 or user device 120 may not be aware of the selected AI / ML model. Alternatively, at least one AI / ML model within the same function, or a function implemented based on an AI / ML model, may be divided into multiple groups. The specific grouping criteria may be based on the same input, output, or both. In this case, if the LCM event decision results in a selection or switch between AI / ML models / functions within the group, the peer may not need to be aware of the decision. Otherwise, the peer must be informed via relevant signaling of the selected / switched AI / ML model(s) within the function, or the selected / switched AI / ML model(s) within the group. LCM events include activation / deactivation / switching / selection / upgrade / rollback.

[0188] Of course, the network device 110 or user device 120 may also select multiple or multiple groups of AI / ML models to support the normal operation of the functionality. Furthermore, for those AI / ML models whose performance falls below a threshold, the network device 110 or user device 120 will deactivate these AI / ML models. Furthermore, if the monitoring results of the quantity X corresponding to all AI / ML models do not meet the threshold, which can be greater than, less than, or equal to the threshold, the functionality will need to fall back to traditional signal processing methods.

[0189] The monitored quantity X mentioned in this embodiment may be different for different use cases. For details, please refer to the different monitoring quantities listed in the seventh embodiment, which can be roughly divided into several categories. It can be a specific quantity RSRP / RSRQ / SINR, or it can be the difference or correlation between different quantities, or based on the statistical results of the above quantities, such as the difference or correlation between the predicted value and the measured value or the true label / approximate true label, or based on the statistical results of the above quantities, it can also be the probability distribution or CDF statistical result of a certain quantity.

[0190] Regarding the first condition and the second condition mentioned in the seventh embodiment, in addition to the threshold value mentioned in the seventh embodiment, the first condition and the second condition can be a compound condition. For example, the first condition or the second condition can be lower than / higher than / equal to the defined threshold and last for a period of time; or the first condition or the second condition can be lower than / higher than / equal to the defined threshold and appear consecutively for a plurality of times; or a certain event can occur and appear consecutively for a certain number of times or appear a certain number of times over a period of time thereafter.

[0191] It should be noted that there is no necessary constraint relationship between the first condition and the second condition. They can be used as separate configurations or standard agreements, or as combined configurations or standard agreements.

[0192] Figure 3C is a flowchart of a wireless communication method provided in an embodiment of the present application. As shown in Figure 3C , in some embodiments of the present application, the wireless communication method includes at least one of the following steps: Step 1: Network device 110 issues relevant configuration information for monitoring an AI / ML model / function. Step 2: Network device 110 determines whether a first condition is met. Step 3: Network device 110 determines whether a second condition is met. Step 4: Network device 110 instructs user device 120 to monitor the AI / ML model / function and issues relevant configuration information. Step 5: User device 120 monitors the AI / ML model / function. Step 6: User device 120 reports the monitoring results. Step 7: Network device 110 determines the behavior in the LCM of the AI / ML model / function. Step 8: Network device 110 instructs user device 120 to execute the operation in the LCM executed by the AI / ML model / function. In some embodiments of the present application, the steps of the method described in Figure 3C may be implemented in any suitable order, or simultaneously, as appropriate.

[0193] FIG3D is a flow chart illustrating a wireless communication method provided in an embodiment of the present application. As shown in FIG3D , in some embodiments of the present application, the wireless communication method includes at least one of the following steps: Step 1: The network device 110 issues relevant configuration information for monitoring an AI / ML model / function. Step 2: The network device 110 determines whether a first condition is met. Step 3: The network device 110 instructs the user device 120 to perform preprocessing before monitoring the AI / ML model / function. Step 4: The user device 120 determines whether a second condition is met. Step 5: The user device 120 requests monitoring of the AI / ML model / function. Step 6: The network device 110 instructs the user device 120 to monitor the AI / ML model / function and issues relevant configuration information. Step 7: The user device 120 performs monitoring of the AI / ML model / function. Step 8: The user device 120 reports the monitoring results. Step 9: The network device 110 determines the behavior in the LCM of the AI / ML model / function. Step 10: The network device 110 instructs the user device 120 to execute the operations in the LCM executed by the AI / ML model / function. In some embodiments of the present application, the steps of the method described in FIG3D can be implemented in any suitable order or simultaneously where appropriate.

[0194] FIG3E is a flow chart of a wireless communication method provided in an embodiment of the present application. As shown in FIG3E , in some embodiments of the present application, the wireless communication method includes at least one of the following steps: Step 1: The network device 110 issues configuration information related to monitoring an AI / ML model / function. Step 2: The user device 120 determines whether a first condition is met. Step 3: The user device 120 instructs the network device 110 to perform preprocessing before monitoring the AI / ML model / function. Step 4: The network device 110 determines whether a second condition is met. Step 5: The network device 110 instructs the user device 120 to monitor the AI / ML model / function and issues relevant configuration information. Step 6: The user device 120 monitors the AI / ML model / function. Step 7: The user device 120 reports the monitoring results. Step 8: The network device 110 determines the behavior in the LCM of the AI / ML model / function. Step 9: The network device 110 instructs the user device 120 to execute the operation in the LCM of the AI / ML model / function. In some embodiments of the present application, the steps of the method described in FIG. 3E may be implemented in any suitable order, or simultaneously, where appropriate.

[0195] Figure 3F is a flowchart of a wireless communication method provided in an embodiment of the present application. As shown in Figure 3F , in some embodiments of the present application, the wireless communication method includes at least one of the following steps: Step 1: Network device 110 issues relevant configuration information for monitoring an AI / ML model / function. Step 2: User device 120 determines whether a first condition is met. Step 3: User device 120 determines whether a second condition is met. Step 4: User device 120 requests monitoring of the AI / ML model / function. Step 5: Network device 110 instructs user device 120 to monitor the AI / ML model / function and issues relevant configuration information. Step 6: User device 120 monitors the AI / ML model / function. Step 7: User device 120 reports the monitoring results. Step 8: Network device 110 determines the behavior in the LCM of the AI / ML model / function. Step 9: Network device 110 instructs user device 120 to execute the operation in the LCM executed by the AI / ML model / function. In some embodiments of the present application, the steps of the method described in Figure 3F may be implemented in any suitable order, or simultaneously, as appropriate.

[0196] In some embodiments of the present application, the scheme of the eighth embodiment may be implemented in conjunction with the schemes of the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, the sixth embodiment, and / or the seventh embodiment, or may be implemented independently of the schemes of the first embodiment, the second embodiment, the third embodiment, the fourth embodiment, the fifth embodiment, the sixth embodiment, and / or the seventh embodiment.

[0197] Ninth embodiment:

[0198] Figure 4A is a flow chart of a method for wireless communication provided in an embodiment of the present application. As shown in Figure 4A, the method for wireless communication is executed on a user equipment (UE) and includes at least one of the following operations: Operation 401A: Receive multiple first monitoring time windows and at least one second monitoring time window configured by a network-side device. The multiple monitoring time windows are periodic. Operation 402A: Based on the behavior of the UE during the at least one second window, determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

[0199] FIG4B is a flow chart of a wireless communication method provided in an embodiment of the present application. As shown in FIG4B , the wireless communication method is executed on a network-side device and includes at least one of the following operations: Operation 401B: Configuring multiple first monitoring time windows and at least one second monitoring time window. The multiple monitoring time windows are periodic. Operation 402B: Based on the behavior of the network-side device during the at least one second window, determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model during the multiple first monitoring time windows.

[0200] In some embodiments of the present application, a decision is made as to whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows based on a first condition and / or a second condition, wherein the first condition is whether a monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is lower than, higher than, or equal to a defined threshold, or an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model occurs, and the first condition and the second condition are related. In some embodiments of the present application, the occurrence of an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model refers to whether the monitoring quantity matches a reference value or the error is within a defined range. In some embodiments of the present application, the second condition is whether the first condition persists for a period of time, or the second condition is how many times the first condition occurs consecutively within a period of time, or the total number of times the first condition occurs within a period of time is greater than, less than, or equal to the defined threshold, or the probability distribution of the occurrence of the first condition within a period of time is greater than, less than, or equal to the defined threshold.

[0201] In some embodiments of the present application, the at least one second monitoring time window includes an event-triggered monitoring time window and an event-triggered pre-monitoring time window. In some embodiments of the present application, the at least one second monitoring time window includes a period-based pre-monitoring time window, and the behavior of the UE during the at least one second window refers to monitoring the system performance, the reasoning accuracy or indicators of the currently activated AI / ML model / function in the pre-monitoring time window of the period to obtain a monitoring result. If the monitoring result meets the defined threshold, it is decided to perform the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows. In some embodiments of the present application, if the monitoring result does not meet the defined threshold, it is decided not to perform the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

[0202] Conventional technology uses event-triggered monitoring, where monitoring is triggered based on a single result or performance, potentially leading to false triggers and unnecessary monitoring. However, triggering based on statistical results requires continuous monitoring of the output results or performance, requiring long-term memory allocation and increasing processing complexity for user device 120 / network device 110. Furthermore, event-triggered monitoring relies heavily on the criteria for measuring the event. Setting a low threshold for the event metric can degrade system performance, while setting a high threshold for the metric can lead to unnecessary monitoring.

[0203] In some embodiments of the present application, for event-triggered monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model, a short-term event + long-term event joint decision-making mechanism is adopted to avoid mismonitoring of the AI / ML model and leave a certain amount of operating space for processing on the network side or the terminal side. At the same time, this mechanism can also be used for decision-making of LCM events. In some embodiments of the present application, an event and periodic method is used to determine when to monitor at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model. On the one hand, it ensures that the system performance will not continue to deteriorate; on the other hand, it avoids the performance deterioration of the AI / ML model / or function due to sudden changes in the channel or the external environment or other emergencies; at the same time, the above method can reduce the power consumption of the system to a certain extent while ensuring performance.

[0204] Specifically, in some embodiments, the periodic plus event triggering method can be further divided into the following schemes:

[0205] Solution 1: The network-side device 110 or the user device 120 is configured with a periodic monitoring time window and a period-based pre-monitoring time window. The network-side device 110 monitors the system performance / the inference accuracy of the currently activated AI / ML model / function or some indicators within the pre-monitoring time window. If the monitoring of these indicators does not meet a certain threshold, the monitoring will not be started in the next monitoring time window. This method can continuously monitor the performance of the AI / ML model / function periodically to ensure that the system performance does not continue to deteriorate. On the other hand, it avoids the increase in the processing complexity of the user device 120 caused by monitoring the AI / ML model / function when the AI / ML model / function is working relatively stably, and the possible waste of uplink resources caused by reporting the monitoring results, while reducing the power consumption of the system to a certain extent.

[0206] Solution 2: The network-side device 110 configures a periodic monitoring time window for the user device 120. At the same time, the network-side device 110 may also set a monitoring time window based on event-triggered monitoring in the manner shown in the seventh embodiment. At the same time, the standard may also stipulate the first and second conditions in the seventh embodiment, as well as an event-based pre-monitoring time window, that is, after the first condition is met, how long to monitor to see whether the monitoring result meets the second condition. If the first and second conditions are met at the same time or one of them is met, the user device 120 starts / begins to monitor the AI / ML model / function. It should be noted that there is no necessary constraint relationship between the above-mentioned first condition, the event-based pre-monitoring time window, and the second condition. They can be used as separate configurations or standard agreements, or they can be combined configurations or standard agreements. Furthermore, if the user device 120 reaches / encounters a periodic monitoring time window, the user device 120 starts / begins to monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model, wherein the multiple AI / ML models may be AI / ML models that are currently activated or working, or AI / ML models that are not currently activated or working. These AI / ML models that are not currently activated or working need to be activated before monitoring. In addition, for the method of configuring a periodic monitoring time window, as pointed out in the first embodiment, whether to start / start monitoring at least one AI / ML model under the same function or a function implemented based on the AI / ML model in each periodic monitoring time window can be determined based on the network side indication or by the user device 120 itself; for the AI / ML model on the network side, it can also be based on the network side's self-determination or the user device 120's request. This approach can periodically monitor the performance of AI / ML models / functions to ensure that system performance does not continue to deteriorate. It also avoids performance degradation of AI / ML models / functions due to sudden changes in the channel or external environment, or other emergencies. While ensuring performance, the above approach can also reduce system power consumption to a certain extent.

[0207] Solution three: The network side device 110 configures a periodic monitoring time window for the user device 120, and may also configure a period-based pre-monitoring time window. At the same time, the network side device 110 may also set an event-triggered monitoring time window in the manner shown in the seventh embodiment. At the same time, the standard may also stipulate the first and second conditions in the seventh embodiment, as well as a pre-monitoring time window for event triggering. If the first condition and the second condition are met at the same time or one of them is met, or within a periodic pre-monitoring time window, the system performance / inference accuracy of the currently activated AI / ML model or at least one indicator is monitored. If the monitoring of these indicators exceeds / is lower than the defined threshold value or the first condition and the second condition of the seventh embodiment are met, then in the next periodic monitoring time window, the user device 120 or the network device 110 starts / begins monitoring at least one AI / ML model under the same function or a function implemented based on the AI / ML model, or the network device 110 instructs the user device 120 to start / start monitoring at least one AI / ML model under the same function or a function implemented based on the AI / ML model, or the user device 120 requests the network device 110 to start / start monitoring at least one AI / ML model under the same function or a function implemented based on the AI / ML model, where the multiple AI / ML models can be AI / ML models that are currently activated or working, or can be AI / ML models that are not currently activated or working. These AI / ML models that are not currently activated or working need to be activated before monitoring. It should be noted that there is no necessary constraint relationship between the above-mentioned first condition, pre-monitoring time window, and second condition. They can be used as separate configurations or standard agreements, or they can be combined configurations or standard agreements. The periodic pre-monitoring time window may not be necessary. Whether each periodic monitoring time window starts / starts to monitor at least one AI / ML model under the same function or a function implemented based on the AI / ML model can be determined by the AI / ML model on the user device 120 side according to the network side indication, or it can be decided by the user device 120 itself; for the AI / ML model on the network side, it can also be based on the network side's self-determination or the user device 120's request. This method can periodically monitor the performance of the AI / ML model / function continuously to ensure that the system performance does not continue to deteriorate; on the other hand, it also avoids the performance deterioration of the AI / ML model / function due to channel mutations or external environment mutations or other emergencies; it also avoids the increase in the processing complexity of the user equipment 120 caused by monitoring the AI / ML model / function when the AI / ML model / function is working relatively stably, and the possible waste of uplink resources caused by reporting the monitoring results; at the same time, the above method can reduce the power consumption of the system to a certain extent while ensuring performance.

[0208] Note that the above-mentioned periodic monitoring time window, the pre-monitoring time window and threshold value based on periodic triggering / starting, and any one of the first condition, the second condition, the pre-monitoring time window and threshold value based on event triggering / starting can be configured through at least one of RRC, MAC CE, DCI, and standard constraints.

[0209] For the monitoring of AI / ML models / functions, if the triggering method of period plus event is adopted, there may be a situation where the monitoring time window triggered by the event and the monitoring time window triggered by the period may overlap. If the two overlap, the time window with the earlier start time will be used, and the monitoring of the AI / ML model / function will be processed based on that time window. It should be noted that if the monitoring time window of the period is earlier and the AI / ML model / function is not monitored in the current period monitoring time window, the event-based monitoring of the AI / ML model / function will be processed. Furthermore, if event-based monitoring of the AI / ML model / function occurs between the two period monitoring time windows, the time window of the next period monitoring can be skipped / ignored and the AI / ML model / function will not be monitored.

[0210] In some embodiments of the present application, the scheme of the ninth embodiment may be implemented in conjunction with the schemes of the first, second, third, fourth, and fifth embodiments, and the sixth, seventh, and / or eighth embodiments, or may be implemented independently of the schemes of the first, second, third, fourth, and fifth embodiments, and the sixth, seventh, and / or eighth embodiments.

[0211] Figure 5 is a schematic structural diagram of a wireless communication device 700 provided in an embodiment of the present application. The wireless communication device can be a user equipment, a base station, or a network element. The wireless communication device 700 shown in Figure 5 includes a processor 710, which can call and execute a computer program from a memory to implement the method in the embodiment of the present application.

[0212] Optionally, as shown in FIG6 , the wireless communication device 700 may further include a memory 720. The processor 710 may call and execute a computer program from the memory 720 to implement the method in the embodiment of the present application. The memory 720 may be a separate device independent of the processor 710 or may be integrated into the processor 710.

[0213] Optionally, as shown in FIG5 , the wireless communication device 700 may further include a transceiver 730. The processor 710 may control the transceiver 730 to communicate with other devices. Specifically, the transceiver 730 may send information or data to other devices or receive information or data sent by other devices. The transceiver 730 may include a transmitter and a receiver. The transceiver 730 may further include one or more antennas.

[0214] Optionally, the wireless communication device 700 may specifically be the network side device 110 of the embodiment of the present application, and the wireless communication device 700 may implement the corresponding processes implemented by the network side device 110 in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0215] Optionally, the wireless communication device 700 may specifically be a user equipment of an embodiment of the present application, and the wireless communication device 700 may implement the corresponding processes implemented by the user equipment in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0216] Optionally, the wireless communication device 700 may specifically be a network element in an embodiment of the present application, and the wireless communication device 700 may implement the corresponding processes implemented by the network element in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0217] Figure 6 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 800 shown in Figure 6 includes a processor 810, which can call and run a computer program from a memory to implement the method according to the embodiment of the present application.

[0218] Optionally, as shown in FIG6 , the chip 800 may further include a memory 820. The processor 810 may call and execute computer programs from the memory 820 to implement the methods in the embodiments of the present application. The memory 820 may be a separate device independent of the processor 810 or may be integrated into the processor 810.

[0219] Optionally, the chip 800 may further include an input interface 830. The processor 910 may control the input interface 830 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0220] Optionally, the chip 800 may further include an output interface 840. The processor 810 may control the output interface 840 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0221] Optionally, the chip can be applied to the network side device 110 in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the network side device 110 in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0222] Optionally, the chip can be applied to the user equipment in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the user equipment in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0223] Optionally, the chip can be applied to the network element in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the mobile network element in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0224] Figure 7 is a schematic block diagram of a wireless communication system 100 provided in an embodiment of the present application. As shown in Figure 7, the communication system 100 includes a user device 120 and a network device 110. The user device 120 can be used to implement the corresponding functions implemented by the user device 120 in the above method, and the network device 110 can be used to implement the corresponding functions implemented by the network device 110 in the above method. For the sake of brevity, these functions are not further described here.

[0225] It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment may be completed by hardware integrated logic circuits in the processor or software instructions.

[0226] It is understood that the memory in the embodiments of the present application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. The embodiments of the present application also provide a computer-readable storage medium for storing a computer program.

[0227] Optionally, the computer-readable storage medium may be applied to the network-side device in the embodiments of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the network-side device in the various methods of the embodiments of the present application. For the sake of brevity, no further description is given here. Optionally, the computer-readable storage medium may be applied to the user equipment in the embodiments of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the user equipment in the various methods of the embodiments of the present application. For the sake of brevity, no further description is given here.

[0228] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0229] Optionally, the computer program product may be applied to the network-side device in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the network-side device in the various methods of the embodiments of the present application. For the sake of brevity, no further description is given here. Optionally, the computer program product may be applied to the user equipment in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the user equipment in the various methods of the embodiments of the present application. For the sake of brevity, no further description is given here.

[0230] The embodiment of the present application also provides a computer program.

[0231] Optionally, the computer program may be applied to the network-side device in the embodiments of the present application. When the computer program is run on a computer, the computer executes the corresponding processes implemented by the network-side device in the various methods of the embodiments of the present application. For the sake of brevity, no further details are given here. Optionally, the computer program may be applied to the user equipment in the embodiments of the present application. When the computer program is run on a computer, the computer executes the corresponding processes implemented by the user equipment in the various methods of the embodiments of the present application. For the sake of brevity, no further details are given here.

[0232] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0233] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method for monitoring artificial intelligence / machine learning AI / ML models / functions, executed on a user equipment (UE), wherein: The wireless communication method comprises: receiving a plurality of monitoring time windows configured by a network-side device, wherein the plurality of monitoring time windows are periodic; and Before monitoring the AI / ML model / function during the first monitoring time window of the multiple monitoring time windows, a first signaling sent by the network side device is received, where the first signaling is used to indicate whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the first monitoring time window.

2. The method according to claim 1, wherein The first signaling includes media access control MAC control element CE signaling or downlink control information DCI.

3. The method according to claim 1 or 2, wherein: If the first signaling is not received before monitoring the AI / ML model / function during the first monitoring time window, the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is not performed during the first monitoring time window; or the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is performed; or the behavior during the previous monitoring time window of the first monitoring time window is repeated during the first monitoring time window.

4. The method according to any one of claims 1 to 3, wherein If the first signaling is received during the first monitoring time window, the first signaling is used to indicate whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the first monitoring time window or the next monitoring time window of the first monitoring time window.

5. The method according to any one of claims 1 to 4, wherein The first signaling is also used to indicate activation or deactivation of monitoring of the AI / ML model / function.

6. The method according to claim 5, wherein: When the first signaling indicates activation of monitoring of the AI / ML model / function during the first monitoring time window, the UE performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the next monitoring time window and the monitoring time window after the next monitoring time window, until the first signaling indicates deactivation of monitoring of the AI / ML model / function.

7. The method according to claim 5, wherein: When the first signaling indicates deactivation of monitoring of the AI / ML model / function during the first monitoring time window, the UE immediately stops or stops performing monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the next monitoring time window.

8. The method according to any one of claims 1 to 7, wherein The UE further receives second signaling sent by the network side device, where the second signaling is used to indicate or update the periods and window lengths of the multiple monitoring time windows.

9. The method according to claim 8, wherein The second signaling includes radio resource control RRC signaling, MAC CE signaling, or DCI.

10. The method according to any one of claims 1 to 9, wherein The wireless communication method also includes the UE sending a request message to the network side device to monitor the AI / ML model / function.

11. The method according to any one of claims 1 to 10, wherein The multiple monitoring time windows have multiple candidate periods and window lengths.

12. The method according to claim 11, wherein The multiple candidate periods and window lengths of the multiple monitoring time windows are configured by a network-side device.

13. The method according to any one of claims 1 to 12, wherein The monitoring of the AI / ML model / function is the monitoring of the currently activated or working AI / ML model / function, or the monitoring of all or part of the AI / ML models under the same function.

14. The method according to any one of claims 1 to 13, wherein The monitoring of at least one AI / ML model executing the same function, or the monitoring of a function implemented based on the AI / ML model, further includes: constraining the monitoring of at least one AI / ML model executing the same function, or the monitoring of a function implemented based on the AI / ML model.

15. The method according to claim 14, wherein The constraints include that the outputs of the monitored AI / ML model / function and the activated AI / ML model / function are based on the reference signal measurement results of the same or multiple adjacent time slots.

16. The method according to claim 15, wherein Inputs of the monitored AI / ML model / function and the activated AI / ML model / function are based on reference signal measurement results of the same or multiple adjacent time slots.

17. The method according to claim 15, wherein: If the output result reporting of the activated AI / ML model / function is periodic, the output result reporting of the monitored AI / ML model / function is semi-continuous or aperiodic.

18. The method according to claim 15, wherein The period for reporting the output results of the monitored AI / ML model / function and the period for reporting the output results of the activated AI / ML model / function satisfy an integer multiple relationship.

19. The method according to claim 15, wherein The starting / earliest reporting time / time slot of the output result of the monitored AI / ML model / function coincides with a reporting time / time slot for periodic reporting of the output result of the activated AI / ML model / function.

20. The method according to claim 15, wherein If the output result reporting of the activated AI / ML model / function is semi-continuous, the output result reporting of the monitored AI / ML model / function is semi-continuous or aperiodic.

21. The method according to claim 15, wherein If the output result reporting of the activated AI / ML model / function is aperiodic, the output result reporting of the monitored AI / ML model / function is aperiodic.

22. The method according to any one of claims 1 to 21, wherein The UE reports the output results of multiple AI / ML models under the same monitored function independently or jointly, and when the output results of the multiple AI / ML models are multiple channel state information CSIs, the reporting of the multiple CSIs satisfies the priority order relationship.

23. The method according to claim 22, wherein The priority order relationship means that the CSI corresponding to the output result of the currently activated or working AI / ML model has the highest priority for reporting.

24. The method according to any one of claims 1 to 23, wherein The number of AI / ML models under the same function that the UE simultaneously monitors is used as the capability item of the UE.

25. The method according to any one of claims 1 to 24, wherein Based on the number of AI / ML models under the same function simultaneously monitored by the UE as the capability item of the UE, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is performed.

26. The method according to claim 25, wherein If the total number of monitored AI / ML models / functions exceeds the number of AI / ML models / functions simultaneously monitored by the UE, the UE monitors different AI / ML models / functions in batches during the configured monitoring time window, with the same or different number of AI / ML models / functions monitored each time.

27. The method according to any one of claims 1 to 26, wherein The minimum effective monitoring time window length or the effective monitoring time window length of a single AI / ML model / function is configured or defined.

28. The method according to any one of claims 1 to 27, wherein The wireless communication method also includes triggering a fallback operation of the AI / ML model / function and notifying the network side device of the fallback operation.

29. The method according to claim 28, wherein The events / conditions that trigger the rollback operation of the AI / ML model / function include failure to load the AI / ML model / function, inability to implement the corresponding function based on the current AI / ML model / function, or monitoring that the system performance degrades by more than a defined threshold, triggering the rollback operation of the AI / ML model / function.

30. The method according to claim 29, wherein If the monitoring of at least one AI / ML model under the same function is performed, or the result of the monitoring of a function implemented based on the AI / ML model is the fallback operation, and the monitoring of the AI / ML model / function and the decision of the lifecycle management LCM of the AI / ML model / function after monitoring are not on the same side, then the first signaling is also used to instruct the UE to perform the fallback operation, or the UE notifies the network side device to perform the fallback operation.

31. The method according to any one of claims 1 to 30, wherein The number of AI / ML models loaded by a single function of the network side device and / or the UE is configured or defined.

32. The method according to any one of claims 1 to 31, wherein The number of AI / ML models loaded by a single function of the UE is reported as a capability item of the UE.

33. The method according to claim 31 or 32, wherein Upgrade or update the AI / ML model that has been loaded under a function. If the AI / ML model is deployed on the UE side and downloaded from the network side device, the UE receives the parameter / architecture information of the AI / ML model upgrade or update sent by the network side device, and the UE also receives the upgraded or updated AI / ML model indicated by the network side device.

34. A wireless communication method for monitoring artificial intelligence / machine learning AI / ML models / functions, executed on a user equipment (UE), wherein: The wireless communication method comprises: Based on the first condition and / or the second condition, decide whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, wherein the first condition is that the monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is lower than, higher than or equal to the defined threshold or the occurrence of an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, and the first condition is related to the second condition.

35. The method according to claim 34, wherein The window length for performing monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is defined, or configured by a network side device, or controlled by the UE.

36. The method according to claim 35, wherein An event-triggered approach is used to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model. The event-triggered approach is based on the first condition and / or the second condition to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model.

37. The method of claim 34, wherein: Whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is determined according to the instruction of the network side device. The instruction of the network side device is based on the first condition and / or the second condition to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model.

38. The method of claim 34, wherein: Determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model based on the request information and the indication information in response to the request information, wherein the UE decides whether to send the request information to the network side device based on the first condition and / or the second condition.

39. The method of claim 34, wherein: For a dual-sided AI / ML model, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on an AI / ML model is performed by the UE or the UE requests the network-side device to perform.

40. The method according to any one of claims 1 to 39, wherein The occurrence of an event related to the monitoring of at least one AI / ML model performing the same function or the monitoring of a function implemented based on the AI / ML model refers to whether the monitored quantity matches the reference value or the error is within a defined range.

41. The method according to any one of claims 1 to 40, wherein The second condition is that the first condition persists for a period of time, or the second condition is how many times the first condition occurs consecutively within a period of time, or the total number of times the first condition occurs within a period of time is greater than, less than, or equal to the defined threshold, or the probability distribution of the occurrence of the first condition within a period of time is greater than, less than, or equal to the defined threshold.

42. The method according to any one of claims 1 to 41, wherein The wireless communication method further includes deciding a lifecycle management (LCM) event based on the first condition and / or the second condition.

43. According to the method described in any one of claims 1 to 42, if the first condition and / or the second condition are met, the UE performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model to obtain a monitoring result, and decides an LCM event based on the monitoring result.

44. The method according to claim 43, wherein The decision of the LCM event is further determined based on a third condition, wherein the third condition is a defined threshold value, and the defined threshold value determines the type of the LCM event.

45. A wireless communication method for monitoring artificial intelligence / machine learning AI / ML models / functions, executed on a user equipment (UE), wherein: The wireless communication method comprises: receiving a plurality of first monitoring time windows and at least one second monitoring time window configured by a network-side device, wherein the plurality of first monitoring time windows are periodic; and Based on the behavior of the UE during the at least one second window, decide whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

46. ​​The method of claim 45, wherein Also based on the first condition and / or the second condition, it is determined whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows, wherein the first condition is that the monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is lower than, higher than or equal to the defined threshold, or the occurrence of an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, and the first condition is related to the second condition.

47. The method of claim 46, wherein The occurrence of an event related to the monitoring of at least one AI / ML model performing the same function or the monitoring of a function implemented based on the AI / ML model refers to whether the monitored quantity matches the reference value or the error is within a defined range.

48. The method according to claim 46 or 47, wherein The second condition is that the first condition persists for a period of time, or the second condition is how many times the first condition occurs consecutively within a period of time, or the total number of times the first condition occurs within a period of time is greater than, less than, or equal to the defined threshold, or the probability distribution of the occurrence of the first condition within a period of time is greater than, less than, or equal to the defined threshold.

49. The method according to any one of claims 45 to 48, wherein The at least one second monitoring time window includes a monitoring time window based on event triggering and a pre-monitoring time window based on event triggering.

50. The method according to any one of claims 45 to 49, wherein The at least one second monitoring time window includes a periodic pre-monitoring time window, and the behavior of the UE during the at least one second window refers to monitoring the system performance, the reasoning accuracy or indicators of the currently activated AI / ML model / function in the pre-monitoring time window of the period to obtain a monitoring result. If the monitoring result meets the defined threshold, it is decided to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

51. The method of claim 50, wherein: If the monitoring result does not meet the defined threshold, it is decided not to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

52. A wireless communication method for monitoring artificial intelligence / machine learning AI / ML models / functions, executed on a network-side device, wherein: The wireless communication method comprises: configuring a plurality of monitoring time windows, wherein the plurality of monitoring time windows are periodic; and Before monitoring the AI / ML model / function during a first monitoring time window of the multiple monitoring time windows, decide whether to monitor at least one AI / ML model performing the same function or a function implemented based on the AI / ML model during the first monitoring time window.

53. The method of claim 52, wherein: The network-side device is also used to decide whether to activate or deactivate monitoring of the AI / ML model / function.

54. The method of claim 53, wherein: When the network side device decides to activate the monitoring of the AI / ML model / function during the first monitoring time window, the network side device performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the next monitoring time window of the first monitoring time window and the monitoring time window after the next monitoring time window, until the network side device decides to deactivate the monitoring of the AI / ML model / function.

55. The method of claim 53, wherein When the network-side device decides to deactivate the monitoring of the AI / ML model / function during the first monitoring time window, the network-side device immediately stops or stops performing the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model during the next monitoring time window.

56. The method according to any one of claims 52 to 55, wherein The network side device is further used to configure or update the periods and window lengths of the multiple monitoring time windows.

57. The method according to any one of claims 52 to 56, wherein The multiple monitoring time windows have multiple candidate periods and window lengths.

58. The method of claim 57, wherein The multiple candidate periods and window lengths of the multiple monitoring time windows are configured by a network-side device.

59. The method according to any one of claims 52 to 58, wherein The monitoring of the AI / ML model / function is the monitoring of the currently activated or working AI / ML model / function, or the monitoring of all or part of the AI / ML models under the same function.

60. The method according to any one of claims 52 to 59, wherein The monitoring of at least one AI / ML model executing the same function, or the monitoring of a function implemented based on the AI / ML model, further includes: constraining the monitoring of at least one AI / ML model executing the same function, or the monitoring of a function implemented based on the AI / ML model.

61. The method of claim 60, wherein: The constraints include that the outputs of the monitored AI / ML model / function and the activated AI / ML model / function are based on the reference signal measurement results of the same or multiple adjacent time slots.

62. The method of claim 61, wherein Inputs of the monitored AI / ML model / function and the activated AI / ML model / function are based on reference signal measurement results of the same or multiple adjacent time slots.

63. The method of claim 61, wherein If the output result reporting of the activated AI / ML model / function is periodic, the output result reporting of the monitored AI / ML model / function is semi-continuous or aperiodic.

64. The method of claim 61, wherein The period for reporting the output results of the monitored AI / ML model / function and the period for reporting the output results of the activated AI / ML model / function satisfy an integer multiple relationship.

65. The method of claim 61, wherein The starting / earliest reporting time / time slot of the output result of the monitored AI / ML model / function coincides with a reporting time / time slot of the periodic reporting of the output result of the activated AI / ML model / function.

66. The method of claim 61, wherein If the output result reporting of the activated AI / ML model / function is semi-continuous, the output result reporting of the monitored AI / ML model / function is semi-continuous or aperiodic.

67. The method of claim 61, wherein If the output result reporting of the activated AI / ML model / function is aperiodic, the output result reporting of the monitored AI / ML model / function is aperiodic.

68. The method according to any one of claims 52 to 67, wherein The output results of multiple AI / ML models under the same function of monitoring are reported independently or jointly, and when the output results of the multiple AI / ML models are multiple channel state information CSIs, the reporting of the multiple CSIs satisfies the priority order relationship.

69. The method of claim 68, wherein The priority order relationship means that the CSI corresponding to the output result of the currently activated or working AI / ML model has the highest priority for reporting.

70. The method according to any one of claims 52 to 69, wherein The number of AI / ML models with the same function that the network side device simultaneously monitors is used as the capability item of the network side device.

71. The method according to any one of claims 52 to 70, wherein Based on the number of AI / ML models under the same function simultaneously monitored by the network side device as the capability item of the network side device, monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is performed.

72. The method of claim 71, wherein If the total number of monitored AI / ML models / functions exceeds the number of AI / ML models / functions simultaneously monitored by the network-side device, the network-side device monitors different AI / ML models / functions in batches during the configured monitoring time window, with the same or different number of AI / ML models / functions monitored each time.

73. The method of any one of claims 52 to 72, wherein: The minimum effective monitoring time window length or the effective monitoring time window length of a single AI / ML model / function is configured or defined.

74. The method of any one of claims 52 to 73, wherein The wireless communication method further includes triggering a fallback operation of the AI / ML model / function and notifying a user equipment UE of the fallback operation.

75. The method of claim 74, wherein The events / conditions that trigger the rollback operation of the AI / ML model / function include failure to load the AI / ML model / function, inability to implement the corresponding function based on the current AI / ML model / function, or monitoring that the system performance degrades by more than a defined threshold, triggering the rollback operation of the AI / ML model / function.

76. The method of claim 75, wherein If the result of performing the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is the fallback operation, and the monitoring of the AI / ML model / function and the decision of the lifecycle management LCM of the AI / ML model / function after monitoring are not on the same side, the network side device performs the fallback operation, or the network side device notifies the UE to perform the fallback operation.

77. The method of any one of claims 52 to 76, wherein The number of AI / ML models loaded by a single function of the network side device and / or the UE is configured or defined.

78. The method of any one of claims 52 to 77, wherein The number of AI / ML models loaded by a single function of the network side device is reported as a capability item of the network side device.

79. The method according to claim 77 or 78, wherein Upgrading or updating an AI / ML model that has been loaded under a function. If the AI / ML model is deployed on the UE side and downloaded from the network side device, the network side device sends parameter / architecture information of the AI / ML model upgrade or update to the UE, and the network side device also indicates the upgraded or updated AI / ML model to the UE.

80. A wireless communication method for monitoring artificial intelligence / machine learning AI / ML models / functions, executed on a network-side device, wherein: The wireless communication method comprises: Based on the first condition and / or the second condition, decide whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, wherein the first condition is that the monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is lower than, higher than or equal to the defined threshold or the occurrence of an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, and the first condition is related to the second condition.

81. The method of claim 80, wherein The window length for performing monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is defined, or configured by the network side device, or controlled by the network side device.

82. The method of claim 81, wherein An event-triggered approach is used to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model. The event-triggered approach is based on the first condition and / or the second condition to determine whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model.

83. The method of claim 80, wherein Based on the received request information and the indication information in response to the request information, it is determined whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model.

84. The method of claim 80, wherein For the dual-sided AI / ML model, the monitoring of at least one AI / ML model under the same function or the monitoring of a function implemented based on the AI / ML model is performed by the network side device or the network side device requests the UE to perform.

85. The method according to any one of claims 82 to 84, wherein The occurrence of an event related to the monitoring of at least one AI / ML model performing the same function or the monitoring of a function implemented based on the AI / ML model refers to whether the monitored quantity matches the reference value or the error is within a defined range.

86. The method according to any one of claims 82 to 85, wherein The second condition is that the first condition persists for a period of time, or the second condition is how many times the first condition occurs consecutively within a period of time, or the total number of times the first condition occurs within a period of time is greater than, less than, or equal to the defined threshold, or the probability distribution of the occurrence of the first condition within a period of time is greater than, less than, or equal to the defined threshold.

87. The method according to any one of claims 52 to 86, wherein The wireless communication method further includes deciding a lifecycle management (LCM) event based on the first condition and / or the second condition.

88. According to the method described in any one of claims 52 to 87, if the first condition and / or the second condition are met, the network side device performs monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model to obtain a monitoring result, and decides an LCM event based on the monitoring result.

89. The method of claim 88, wherein The decision of the LCM event is further determined based on a third condition, wherein the third condition is a defined threshold value, and the defined threshold value determines the type of the LCM event.

90. A wireless communication method for monitoring artificial intelligence / machine learning AI / ML models / functions, executed on a network-side device, wherein: The wireless communication method comprises: Configuring multiple first monitoring time windows and at least one second monitoring time window, wherein the multiple first monitoring time windows are periodic; and based on the behavior of the network-side device during the at least one second window, determining whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

91. The method of claim 90, wherein Also based on the first condition and / or the second condition, it is determined whether to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows, wherein the first condition is that the monitoring quantity related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model is lower than, higher than or equal to the defined threshold or the occurrence of an event related to the monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model, and the first condition is related to the second condition.

92. The method of claim 91, wherein The occurrence of an event related to the monitoring of at least one AI / ML model performing the same function or the monitoring of a function implemented based on the AI / ML model refers to whether the monitored quantity matches the reference value or the error is within a defined range.

93. The method according to claim 91 or 92, wherein The second condition is that the first condition persists for a period of time, or the second condition is how many times the first condition occurs consecutively within a period of time, or the total number of times the first condition occurs within a period of time is greater than, less than, or equal to the defined threshold, or the probability distribution of the occurrence of the first condition within a period of time is greater than, less than, or equal to the defined threshold.

94. The method according to any one of claims 90 to 93, wherein The at least one second monitoring time window includes a monitoring time window based on event triggering and a pre-monitoring time window based on event triggering.

95. The method according to any one of claims 90 to 94, wherein The at least one second monitoring time window includes a periodic pre-monitoring time window. The behavior of the network-side device during the at least one second window refers to monitoring the system performance, the reasoning accuracy or indicators of the currently activated AI / ML model / function in the periodic pre-monitoring time window to obtain a monitoring result. If the monitoring result meets the defined threshold, it is decided to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

96. The method of claim 95, wherein If the monitoring result does not meet the defined threshold, it is decided not to perform monitoring of at least one AI / ML model under the same function or monitoring of a function implemented based on the AI / ML model during the multiple first monitoring time windows.

97. A wireless communication device comprising: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 96.

Images