Communication method, device, apparatus, chip, storage medium and program product

Abstract

Embodiments of the present application relate to a communication method, device, apparatus, chip, storage medium and program product. In the method, a first communication apparatus, for example, a terminal device, receives a first configuration message. The first configuration message is used to indicate a first trigger condition, and the first trigger condition is used to trigger the first communication apparatus to send a radio resource management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction. In addition, the first communication apparatus sends the RRM measurement report based on AI / ML prediction or activates AI / ML prediction according to the first trigger condition. In this way, the first communication apparatus, for example, a terminal device, can trigger the RRM measurement report based on AI / ML prediction based on the trigger condition, for example, based on the specific state of the terminal device, network service demand, etc., thereby saving the energy consumption of the terminal device and prolonging the battery life under the condition of meeting the quality of service (QoS) demand.

Description

Technical Field

[0001] This application relates to the field of communications, and more specifically to communication methods, communication devices, communication apparatuses, computer-readable storage media, and computer program products for RRM measurement and prediction. Background Technology

[0002] When terminal devices perform Radio Resource Management (RRM) measurements and reporting, they can employ RRM measurement predictions based on Artificial Intelligence / Machine Learning (AI / ML). How to manage AI / ML-based RRM measurement predictions is a critical issue that urgently needs to be addressed. Summary of the Invention

[0003] In view of the above problems, the embodiments of this application aim to provide a communication solution to solve or improve the above problems.

[0004] According to a first aspect of the embodiments of this application, a communication method is provided. The method can be executed by a first communication device, such as a terminal device. The method includes: receiving a first configuration message. The first configuration message is used to indicate the first triggering condition, which is used to trigger the first communication device to send a Radio Resource Management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate AI / ML prediction. The method further includes: sending the RRM measurement report based on AI / ML prediction according to the first triggering condition.

[0005] According to a second aspect of the embodiments of this application, a communication method is provided. The method can be performed by a second communication device, such as a network device. The method includes: sending a first configuration message, wherein the first configuration message is used to indicate the first triggering condition, the first triggering condition being used to trigger a first communication device to send a Radio Resource Management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate AI / ML prediction. The method further includes: receiving an RRM measurement report based on AI / ML prediction.

[0006] According to a third aspect of the embodiments of this application, a first communication device is provided. The first communication device includes: a receiving module, configured to receive a first configuration message, wherein the first configuration message is used to configure an indication of a first triggering condition, the first triggering condition being used to trigger the first communication device to send a Radio Resource Management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate AI / ML prediction. The first communication device includes: a sending module, configured to send an RRM measurement report based on AI / ML prediction according to the first triggering condition.

[0007] According to a fourth aspect of the embodiments of this application, a second communication device is provided. The second communication device includes: a transmitting module, configured to transmit a first configuration message, wherein the first configuration message is configured to indicate a first triggering condition, the first triggering condition being used to trigger the first communication device to transmit a Radio Resource Management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate AI / ML prediction. The second communication device further includes: a receiving module, configured to receive an RRM measurement report based on AI / ML prediction.

[0008] According to a fifth aspect of the embodiments of this application, a communication device is provided. The device includes a processor and a memory, the memory including instructions that, when executed by the processor, cause the method according to the first or second aspect to be performed.

[0009] According to a sixth aspect of the embodiments of this application, a computer-readable storage medium is provided. The computer-readable storage medium includes instructions that, when executed by a communication device, cause the method described according to the first or second aspect to be performed.

[0010] According to a seventh aspect of the embodiments of this application, a computer program is provided. When executed by a communication device, the computer program causes the method described according to the first or second aspect to be performed.

[0011] According to an eighth aspect of the embodiments of this application, a chip is provided. The chip includes processing circuitry that performs the method described in the first or second aspect.

[0012] As will be understood from the following description of exemplary embodiments, according to the technical solutions presented herein, for example, a first communication device of a terminal device can determine the timing for triggering the first communication device to send an RRM measurement report based on AI / ML prediction or activating AI / ML prediction by receiving a first configuration message. When a first triggering condition is met, the first communication device sends an RRM measurement report based on AI / ML prediction. Thus, for example, the first communication device of the terminal device can trigger an RRM measurement report based on AI / ML prediction based on triggering conditions, such as the specific state of the terminal device, network service requirements, etc., thereby saving power consumption of the terminal device and extending battery life while meeting Quality of Service (QoS) requirements.

[0013] It should be understood that the description in the Summary Section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will be readily understood from the following description. Attached Figure Description

[0014] The above and other features, advantages, and aspects of the embodiments of this application will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A schematic diagram of an example communication system that may be implemented in accordance with embodiments of this application is shown; Figure 2 A schematic diagram of event prediction based on indirect measurement related to embodiments of this application is shown; Figure 3A A flowchart illustrating event prediction based on indirect measurement, relevant to embodiments of this application, is shown. Figure 3B A flowchart illustrating event prediction based on direct measurement, relevant to embodiments of this application, is shown; Figure 4 A signaling diagram of an example communication process according to an embodiment of this application is shown; Figure 5 This diagram illustrates the signaling diagram showing the direct effect of AI / ML measurement reporting according to an embodiment of this application; Figure 6 The following is a signaling diagram illustrating the activation triggered by AI / ML measurement reporting according to an embodiment of this application; Figure 7 The signaling diagram for enabling and disabling model prediction function using RRC configuration according to an embodiment of this application is shown; Figure 8 The signaling diagram for collecting training data of the UE-side triggered model according to an embodiment of this application is shown; Figure 9 The diagram illustrates a signaling diagram of network-side triggered model training data collection according to an embodiment of this application; Figure 10 A flowchart illustrating a communication method implemented at a terminal device according to an embodiment of this application is shown; Figure 11 A flowchart illustrating a communication method implemented at a network device according to an embodiment of this application is shown; Figure 12 A schematic block diagram of an example first communication device according to an embodiment of this application is shown; Figure 13 A schematic block diagram of an example second communication device according to an embodiment of this application is shown; and Figure 14 A simplified block diagram of a communication device suitable for implementing embodiments of this application is shown. Detailed Implementation

[0015] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0016] The term "terminal device" as used in this document refers to any terminal device capable of wireless communication. As an example and not a limitation, a terminal device may also be referred to as a communication device, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). Terminal devices can include, but are not limited to, mobile phones, smartphones, Voice over Internet Protocol (VoIP) phones, wireless local loop phones, tablets, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image acquisition terminal devices such as digital cameras, gaming terminal devices, music storage and playback devices, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded equipment (LEE), laptop mounted equipment (LME), universal serial bus (USB) dongles, smart devices, wireless customer premises equipment (CPE), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (such as remote surgery), industrial devices and applications (such as robots and / or other wireless devices in industrial and / or automated processing chain contexts), consumer electronics devices, and devices operating on commercial and / or industrial wireless networks. "Terminal devices" can also be relay devices. In the following description, the terms “terminal equipment”, “communication equipment”, “terminal”, “user equipment” and “UE” are used interchangeably.

[0017] The term "network device" in this document refers to a node in a communication network through which terminal devices access the network and receive services. Depending on the terminology and technology used, a network device can refer to a base station (BS) or access point (AP), such as a Node B (NodeB or NB), an evolved Node B (eNodeB or eNB), a new radio (NR) NB (also known as a gNB), a remote radio unit (RRU), a remote radio head (RRH), a relay, a low-power node such as a pico or femtocell, and so on. In some embodiments, the BS or AP can be mobile, such as a satellite associated with a non-terrestrial network.

[0018] Network devices can be implemented as a central unit (CU) - distributed unit (DU) separation architecture. This CU-DU separation architecture can include one CU and one or more DUs. It should be understood that the CU can also be called gNB-CU, and the DU can also be called gNB-DU. The CU carries the radio resource control (RRC) layer, the service data adaptation protocol (SDAP) layer, and the packet data convergence protocol (PDCP). The DU carries the radio link control (RLC) layer, the medium access control (MAC) layer, and the physical (PHY) layer. The CU controls the one or more DUs. Of course, network devices can also be implemented as a non-separated architecture.

[0019] In this document, the term "communication device" refers to a device that enables the functionality of a terminal device or network device. A communication device can be the terminal device or network device itself, or it can be a component of the terminal device or network device, such as a chip. A chip can be, for example, a system-on-a-chip (SoC), a modem, etc.

[0020] The term "comprising" or similar expressions in this document mean open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "this embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., can refer to different or the same objects. The term "and / or" means at least one of the two items associated with it. For example, "a and / or b" means a, b, or "a and b". The character " / " generally indicates that the related objects are in an "or" relationship. The term "at least one" means one or more items. The term "at least one of the following" or similar expressions mean any combination of these items, including any combination of single items or multiple items. For example, "at least one of a, b, c" can mean a, b, c, "a and b", "a and c", "b and c", or "a, b and c". Other terms will be defined in the description below.

[0021] As mentioned earlier, terminal devices can employ AI / ML-based RRM measurement prediction when performing radio resource management (RRM) measurements and reporting. Managing AI / ML-based RRM measurement predictions is a critical issue that urgently needs to be addressed.

[0022] In view of this, embodiments of this application propose a scheme for RRM measurement and prediction. In this scheme, for example, a second communication device of a network device sends a first configuration message. The first configuration message is used to indicate a first triggering condition, which is used to trigger the first communication device to send a Radio Resource Management (RRM) measurement report based on Artificial Intelligence (AI) / Machine Learning (ML) prediction or to activate AI / ML prediction. For example, a first communication device of a terminal device receives the first configuration message. Furthermore, the first communication device sends an RRM measurement report based on AI / ML prediction according to the first triggering condition.

[0023] According to the scheme of the embodiments of this application, for example, the first communication device of the terminal device can determine the timing of sending an RRM measurement report based on AI / ML prediction or activating AI / ML prediction based on the first triggering condition indicated by the first configuration message, and send the RRM measurement report based on AI / ML prediction when the timing is met. In this way, the terminal device can trigger the RRM measurement report based on AI / ML prediction based on specific triggering conditions, such as the specific state of the terminal device, network service requirements, etc., thereby saving the power consumption of the terminal device and extending the battery life while meeting the quality of service (QoS) requirements.

[0024] The principles and implementation of this solution will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 A schematic diagram of an example communication system 100 that may be implemented according to embodiments of this application is shown. Figure 1 As shown, the communication system 100 may include at least one terminal device ( Figure 1 The diagram shows terminal devices 110-1 and 110-2 (hereinafter referred to as terminal device 110 for convenience) and at least one network device ( Figure 1 The image shows network device 120 and satellite 130. Network device 120 and satellite 130 in this document are radio access network (RAN) devices. Network device 120 and satellite 130 can provide one or more cells ( Figure 1 Cell 121 is shown in the diagram, serving one or more terminal devices. Satellite 130 can employ a transparent forwarding mode, acquiring downlink data from access network device 120 and forwarding it to terminal device 110, as well as forwarding uplink data received from terminal device 110 to access network device 120, performing only filtering, frequency conversion, RF amplification, and RF transceiver on-board. Satellite 130 can also employ a regenerative forwarding mode, possessing all or part of the functions of a gNB, performing functions such as modulation, demodulation, and channel coding / decoding. When using regenerative forwarding mode, satellite 130 itself becomes a network device, such as an access network device.

[0026] Terminal device 110 can connect wirelessly to network device 120 and satellite 130. Terminal devices 110-1 and 110-2 can connect wirelessly. Network device 120 and satellite 130 can connect wirelessly.

[0027] like Figure 1 As shown, the communication system 100 may further include a core network (CN) 140. Terminal device 110 can communicate with one or more CN devices (not shown) in CN 140 via network device 120 and satellite 130. Network device 120 and satellite 130 can be connected to CN 140 wirelessly or via wired means. Network device 120 can be implemented as a physical device independent of CN devices, or it can be implemented as a physical device integrating some of the functions of CN devices.

[0028] In the following text, for the sake of brevity, network device 120 can be used in a broad sense, which may include satellite 130. In this case, satellite 130 adopts regenerative forwarding mode and has all or part of the functions of gNB.

[0029] It should be understood that Figure 1 The number and type of terminal devices or network devices described are merely examples and do not imply any limitation on this application. Communication system 100 may involve any suitable number of terminal devices and / or network devices and / or cells suitable for implementing embodiments of this application.

[0030] The communication in communication system 100 can conform to any suitable communication standard, including but not limited to wideband code division multiple access (WCDMA), code division multiple access (CDMA), long-term evolution (LTE), LTE evolution, LTE-Advanced (LTE-A), machine-type communication (MTC), etc. Furthermore, communication between terminal equipment and network equipment can be performed according to any suitable generation communication protocol, including but not limited to fourth-generation (4G), fifth-generation (4G), sixth-generation (6G) communication protocols, future wireless communication protocols, or other existing or future suitable communication protocols.

[0031] It should be noted that the embodiments of this application can be applied to various suitable communication systems. Considering the rapid development of communication technology, there will naturally be future types of communication technologies and systems, which this application may incorporate. Communication system 100 is merely an example and does not imply that the scope of this application is limited to a specific system.

[0032] Continue to refer to Figure 1 Terminal device 110 and network device 120 can communicate via a wireless communication channel. The channel from terminal device 110 to network device 120 can be referred to as the uplink channel. The channel from network device 120 to terminal device 110 can be referred to as the downlink channel.

[0033] Radio resource management (RRM) measurement refers to the process by which base stations and user equipment (UE) continuously collect, analyze, and evaluate information about the radio environment and resource status. It supports key functions such as resource scheduling, interference management, handover decisions, and load balancing, ensuring efficient utilization of the wireless network and a positive user experience. UEs measure received signals and periodically report the results via the uplink channel, or trigger reporting when the measurement results meet a certain threshold. The reference signals for RRM measurements mainly include the channel state information reference signal (CSI-RS) and the synchronization signal block (SSB). The network side configures a measurement object identifier (MeasObjectId) for each measurement object (MeasObject, MO) and a reporting configuration identifier (ReportConfigId) for each measurement report, and uses the MeasIdToAddMod parameter to map the measurement object to the measurement report. Each measurement object can be matched with multiple measurement reports, and the same measurement report can correspond to multiple measurement objects. The network side configures monitoring signal-related information to the UE via MeasConfig --> MeasObjectiveToAddModList, including signal frequency, subcarrier spacing, and physical cell identifier (PCI). It also configures reporting types and timed synchronization messages to the UE via MeasConfig --> reportConfigToAddModList. Reporting types can be configured as periodic reporting or event-triggered reporting. If the reporting type corresponding to ReportConfigId is configured as periodic reporting, the reporting period and number of reports can be configured through PeriodicReportConfig. If the reporting type corresponding to ReportConfigId is configured as event-triggered reporting, the event type (e.g., A1, A2, A3), trigger threshold, and trigger time can be configured in EventTriggerConfig.

[0034] In the third generation partnership program (3 rdIn the discussion on AI / ML in mobility management at the Generation Partnership Project (3GPP) Release 19 (R19) meeting, two objectives for AI / ML in mobility management use cases were identified: (1) to reduce measurements in the time, spatial, and frequency domains through predictive measurements using AI / ML models; and (2) to improve handover-related performance through predictive measurements. The time-domain measurement prediction method based on the AI / ML model discussed is shown in Figure 2. The UE receives the reference signal in the observation window (OW) and uses the measurement results as input to the AI / ML model. AI / ML models predict reference signal measurement results within a future period, i.e., the prediction window (PW), such as reference signal receiving power (RSRP) and reference signal receiving quality (RSRQ), which are then used as the results of RRM measurement prediction. The process by which the UE starts using the AI / ML model and outputs the prediction results is called inference. Event prediction methods can be divided into two types: indirect prediction and direct prediction, as shown below. Figure 3A , Figure 3B As shown, and explained below.

[0035] In example 300 of indirect prediction, the indirect measurement event prediction refers to the AI / ML model, namely the RRM measurement prediction model (310), which uses the actual measurement results of the serving cell or neighboring cells as input to perform measurement prediction, and its output is the predicted numerical result, such as the RSRP of the L3 layer. Subsequently, post-processing (320) is performed based on the output of the AI / ML model to determine whether to trigger the event. The triggering condition is not directly obtained by the RRM measurement prediction model (310) and requires post-processing (320), which belongs to the indirect prediction method.

[0036] In Example 330 of direct prediction, the AI / ML model (340) related to direct measurement event prediction takes the actual measurement results of the serving cell or neighboring cells as input to make measurement predictions, and its output is the result of event prediction, that is, the predicted measurement event, such as the type of event that occurs, the time of occurrence, etc.

[0037] When performing RRM measurements and reporting, radio resource control (RRC) signaling can be used to configure the measurement objects and measurement reports, as described below.

[0038] The configuration parameters of the measurement object are shown in the pseudocode of the following information element (IE) 1.

[0039] IE1 pseudocode MeasObjectToAddModList ::= SEQUENCE(SIZE (l..maxNrofObjectld)) OFMeasObjectToAddMod MeasObjectToAddModList ::= SEQUENCE { measObjectId MeasObjectId, measObject CHOICE { measObjectnR MeasObjectnR ... measObjectEUTRA MeasObjectEUTRA, measObjectUTRA-FDD-r16 MeasObjectUTRA-FDD-r16, measObjectNR-SL-r16 MeasObjectNR-SL-r16, measObjectCLI-r16 MeasObjectCLI-r16, measObjectRxTxDiff-r17 MeasObjectRxTxDiff-r17, measObjectRelay-r17 MeasObjectRelay-r17, measObjectNR-SL-rl8 MeasObjectNR-SL-rl8 } } The configuration parameters for RRC measurement reporting are shown in the following IE2 pseudocode.

[0040] IE 2 pseudocode ReportConfigToAddModList ::= SEQUENCE (SIZE(1.. maxReportConfigld))OF ReportConfigToAddMod ReportConfigToAddMod : := SEQUENCE { reportConfigld ReportConfigld, reportConfig CHOICE { reportConfigNR ReportConfigNR, ... reportConfigInterRAT ReportConfigInterRAT reportConfigNR-SL-r16 ReportConfigNR-SL-r16 } } The configuration parameters for RRC measurement reporting NR are shown in the following IE3 pseudocode.

[0041] IE 3 pseudocode ReportConfigNR ::= SEQUENCE { reportType CHOICE { periodical PeriodicalReportConfig, eventTriggered EventTriggeredConfig, ... ReportCGI ReportCGI, reportSFTD ReportSFTD-NR, condTriggerConfig-r16 CondTriggerConfig-r16, cli-Periodical-r16 CLI-PeriodicalReportConfig-r16, cli-EventTriggered-r16 CLI-EventTriggerConfig-r16, rxTXPeriodical-r17 RxTXPeriodical-r17, reportOnScellActivation-r18 ReportOnScellActivation-r18, } } In this application embodiment, the pseudocode of the above-mentioned RRC IE can be modified for AI / ML-based measurement objects and measurement reporting.

[0042] In this embodiment, the logical channel identifier (LCID) can also be extended. The LCID function of the downlink shared channel is shown in Table 1 below.

[0043] Table 1. LCID Function of Downlink Shared Channel

[0044] The LCID function of the uplink shared channel is shown in Table 2 below.

[0045] Table 2. LCID Function of Uplink Shared Channel

[0046] In the embodiments of this application, the values ​​of the above-mentioned LCID and / or eLCID can be expanded for AI / ML-based measurement objects and measurement reporting.

[0047] When performing Radio Resource Management (RRM) measurements and reporting, terminal devices can employ RRM measurement predictions based on Artificial Intelligence / Machine Learning (AI / ML). How to manage AI / ML-based RRM measurement predictions is a critical issue that urgently needs to be addressed. In this embodiment, a first configuration message is used to indicate a first triggering condition, which is used to trigger, for example, a first communication device of the UE to send an AI / ML-based RRM measurement report or activate AI / ML prediction.

[0048] For example, terminal device 110 uses a variety of communication devices with varying mobility. If AI / ML-based RRM measurement reporting is triggered immediately upon configuration, it will result in energy waste for devices with low mobility. For instance, when a UE is in the middle of a cell, the channel environment is good, and reporting based on actual measurement results is sufficient to meet service requirements, while AI / ML-based reporting will increase UE power consumption. Therefore, when a UE is in the middle of a cell and AI / ML-based RRM measurement reporting is configured, it can be deactivated immediately, and reporting based on actual measurement results can continue to be used. AI / ML-based RRM measurement reporting can be dynamically activated after configuration. For example, when the UE moves to the cell edge, AI / ML-based RRM measurement reporting can be triggered by the UE or the network (NW) based on the channel condition degradation to predict RRM measurement results, improve the accuracy of cell handover, and prevent service interruption. Figure 1Cell handover can be between terrestrial cells, between satellite cells, or between terrestrial and satellite cells. This application does not limit this. It can also be triggered by the network based on AI / ML RRM measurement reporting according to service requirements, such as load balancing requirements. In this way, it is possible to trigger UE RRM measurement reporting based on AI / ML more flexibly, save power consumption, and improve system reliability. Therefore, how to trigger UE to perform AI / ML model inference / reporting needs to be reasonably configured by the network side according to the UE device type, for example, by using RRC signaling. Through RRC configuration, the AI / ML model inference function or the reporting of AI / ML model inference results can be configured as follows: (1) effective immediately after configuration; (2) not effective after configuration, need to be triggered to take effect, and the corresponding parameters need to be configured. In this way, different types of UE devices can be reasonably configured to reduce the power consumption of at least some UE devices.

[0049] Figure 4 A signaling diagram of an example communication process 400 according to an embodiment of this application is shown. For convenience, reference will be made to... Figure 1 The communication process 400 is described using examples. The communication process 400 may involve, for example, a first communication device 410 of a terminal device 110, and a second communication device 420 of a network device 120. It should be understood that the communication process 400 can be executed between the terminal device 110 and the network device 120, or between the first communication device 410 supporting the functionality of the terminal device 110 and the network device 120, or between the terminal device 110 and the second communication device 420 supporting the functionality of the network device 120, or between the first communication device 410 supporting the functionality of the terminal device 110 and the second communication device 420 supporting the functionality of the network device 120. For example, the first communication device 410 and the second communication device 420 may be chips such as a system-on-a-chip (SoC), a modem, or modules in a communication device; this application does not limit the scope of the application.

[0050] like Figure 4As shown, for example, a second communication device 420 of network device 120 sends (423) a first configuration message 425 to a first communication device 410 of terminal device 110. The first configuration message 425 is used to indicate a first triggering condition, which is used to trigger the first communication device 410 to send an RRM measurement report based on AI / ML prediction or to activate AI / ML prediction. The first communication device 410 receives (423) the first configuration message 425. The first triggering condition can be triggered directly by the terminal device 110 after receiving the first configuration, sending an RRM measurement report based on AI / ML prediction. The first triggering condition can also be triggered by the terminal device 110 after receiving an instruction from network device 120, or by the terminal device 110 based on its own RRM measurement results. The first configuration message 425 can be an RRC message. Based on the first triggering condition, the first communication device 410 sends (428) an RRM measurement report 430 based on AI / ML prediction to the second communication device 420. The second communication device 420 receives the RRM measurement report 430 based on AI / ML prediction. Thus, for example, the first communication device 410 of terminal device 110 can trigger an AI / ML-predicted RRM measurement report based on triggering conditions, such as the specific state of terminal device 110 or network service requirements, thereby saving energy consumption of terminal device 110 and extending battery life while meeting quality of service (QoS) requirements. The first communication device 410 and the second communication device 420 can also be relay devices, and this application does not limit this.

[0051] In the example embodiments of this application, the first triggering condition includes one of the following: receiving a first configuration message, the first RRM measurement result in the first communication device being lower than a first threshold within a first predetermined time period, or receiving first indication information from a second communication device, wherein the first indication information instructs the first communication device to send an RRM measurement report based on AI / ML prediction. Thus, the first communication device 410 can flexibly choose when to use the measurement report based on AI / ML prediction according to the first triggering condition. For example, the first communication device 410 of the terminal device 110 can directly use the measurement report based on AI / ML prediction after receiving the first configuration message, thereby reducing measurements in the time, spatial, and frequency domains and improving handover-related performance. Alternatively, if the channel conditions are good when the terminal device 110 is in the middle of the cell, it can not directly initiate the measurement report based on AI / ML prediction, but can initiate it based on its own RRM measurement results. For example, when moving to the cell edge, if its measured RSRP / RSRQ is lower than a first threshold within a predetermined time period, it triggers the use of the measurement report based on AI / ML prediction. This can save energy consumption of the first communication device, avoid prematurely initiating the measurement report based on AI / ML prediction, and save power consumption. Alternatively, if the terminal device 110 is in the middle of the cell and the channel conditions are good, it may not need to directly initiate the measurement report based on AI / ML prediction. Instead, it can initiate it upon receiving a first indication message from a second communication device 420, such as network device 120. The first indication message may be issued by network device 120 based on RRM measurement results. This also saves power consumption of the terminal device 110 by avoiding premature initiation of the measurement report based on AI / ML prediction, thus conserving power. The following will combine... Figure 5 , Figure 6 State the various triggering conditions.

[0052] Figure 5 A signaling diagram illustrating the direct effect of AI / ML measurement reporting according to an embodiment of this application is shown. In embodiment 500, the user side 510 can correspond to... Figure 1 Terminal equipment 110 in China Figure 4 The first communication device 410 and the network side 520 can correspond to the network device 120 and the second communication device 420.

[0053] In the example embodiments of this application, for example, the first communication device 410 of terminal device 110 receives a capability query message. The query message is used to query the capability of the first communication device 410 to support RRM measurement reports based on AI / ML prediction. Furthermore, the first communication device 410 sends a capability response message, which is used to instruct the first communication device 410 to support RRM measurement reports based on AI / ML prediction. In this way, errors can be avoided, such as errors caused by a second communication device 420 of network device 120 initiating an AI / ML model-based RRM measurement report in terminal device 110 which lacks an AI / ML model, thus improving system reliability.

[0054] In the example embodiment of this application, after the user side 510 (i.e., UE) accesses a network or cell, in step (1), the network side 520 sends (523) UE capability query 525, which includes whether the UE supports the function of RRM prediction based on the UE-side AI / ML model. In step (2), the user side 510 reports (528) UE capability 530, reporting that it supports the function. In step (3), the network side 520 sends (533) RRC configuration 535, configuring the first parameter in RRC configuration 533 to be directly effective, and can add a report configuration suitable for 6G or future communication standards under MeasConfig-->reportConfigToAddModList-->reportConfig, which can be added in the IE2 pseudocode of the configuration parameters for RRC measurement reporting mentioned above. It can also be added in other places, or in the form of other fields or terms, which is not limited in this application. In this embodiment of the application, the configuration for reporting the RRM prediction results based on the AI / ML model deployed by the user side 510 can also be completed in the RRM report configuration of the RRC configuration 535. This reporting configuration can be set to periodic reporting or event-triggered reporting.

[0055] In the example embodiments of this application, for instance, the first communication device 410 of the terminal device 110 sends a first response message, wherein the first response message indicates that the configuration for AI / ML prediction is applicable to the first communication device 410. Thus, the first communication device 410 can directly initiate an AI / ML model-based RRM measurement report based on the first configuration message or based on other triggering conditions, avoiding errors caused by initiating an AI / ML model-based RRM measurement report in a terminal device 110 that does not have an AI / ML model, thereby improving system reliability.

[0056] In the example embodiment of this application, when the first triggering condition is receiving a first configuration message, sending an AI / ML-predicted RRM measurement report according to the first triggering condition includes: sending an AI / ML-predicted RRM measurement report immediately upon receiving the first configuration message. Thus, the terminal device 110 can directly use the AI / ML-predicted measurement report after receiving the first configuration message, thereby reducing measurements in the time, spatial, and frequency domains and improving handover-related performance.

[0057] In the example embodiment of this application, when the user side 510 receives the RRM configuration message sent by the network side with the first parameter configured to take effect directly, it checks whether the configured inference configuration is applicable to the user side 510, and in step (4), it feeds back (538) to the network side 520 in the RRM configuration feedback 540 that the configured inference configuration is applicable to the user side 510. Thereafter, the user side 510 will directly start the function of using the RRM prediction model inference based on the UE-side AI / ML model. In step (5), when the user side 510 sends (543) the measurement result report 545 based on the AI / ML prediction, it performs periodic or event-triggered prediction result reporting based on the reporting configuration of the reportConfigId corresponding to the relevant AI / ML prediction result configured by the network side 520 (see the aforementioned IE2 pseudocode for the configuration parameters of RRC measurement reporting). In the configuration for reporting based on the UE-side AI / ML model, the numerical results predicted by the model and the event information corresponding to the predicted event can be added to the periodic reporting and event-triggered reporting configurations. For example, a time reporting parameter can be added to the PeriodicReportConfig of the IE3 pseudocode for the aforementioned configuration parameters for RRC measurement reporting NR. The predicted value is matched at each predicted time point. This value can be one or more of RSRQ, RSRQ, and signal-to-interference-and-noise ratio (SINR). One time point can be matched with one value. Thus, it can be known what the predicted measurement value is at that predicted time point. In this embodiment, a time parameter can also be added to EventTriggerConfig to indicate the expected trigger time of the event, and a confidence parameter can be added to indicate the probability of the predicted event occurring. The network side 520 can choose whether to initiate a handover request based on the RRM prediction measurement results reported by the user side 510. The above parameters can be added to other locations in the IE and can be added using other terms or forms; this application does not limit this.

[0058] Figure 6The diagram illustrates a signaling diagram for AI / ML measurement reporting activation according to an embodiment of this application. Specifically, AI / ML measurement reporting may not be activated directly after configuration; the UE may trigger activation subsequently, or activation may be triggered based on network indication. In embodiment 600, the user side 610 may correspond to... Figure 1 Terminal equipment 110 in China Figure 4 The first communication device 410 and the network side 620 can correspond to the network device 120 and the second communication device 420.

[0059] In embodiment 600, in step (1), the network side 620 initiates (623) UE capability query 625. In step (2), the user side 610 reports (628) UE capability 630, indicating that it supports the function of RRM prediction based on the AI / ML model deployed on the UE side. In step (3), the network side 620 sends (633) RRC configuration 635. In this RRC configuration 635, the network side 620 configures the first parameter to trigger activation, that is, the function of RRM prediction inference based on the AI / ML model deployed on the UE side needs to be activated after trigger activation. The measurement results reported before triggering are based on the real measurement results. The reported report configuration depends on the existing real result measurement report configuration, such as ReportConfigNR, ReportConfigInterRAT, etc. in the ReportConfigToAddMod configuration (see the IE2 pseudocode of the configuration parameters of the aforementioned RRC measurement reporting). In step (4), after receiving the RRC configuration 635 from the network side 620 (633), the user side 610 will send back (638) an RRC configuration-related confirmation signaling 640, such as the RRCReconfigurationComplete signaling. This feedback signaling 640 can provide feedback on whether the configuration for AI / ML prediction is applicable to the user side 610 based on the configuration of the network side 620. Assuming that the feedback signaling indicates that the configuration for AI / ML prediction is not applicable to the user side 610, in step (5), by default, subsequent RRM measurements will be reported based on the results of the actual measurement values ​​(643). In this embodiment, if the RRC feedback signaling 640 indicates that the configuration for AI / ML prediction is applicable to the user side 610, in step (6), when the network side 620 or the user side 610 triggers the AI / ML model prediction function, the user side 610 starts to perform RRM result prediction inference based on its own deployed AI / ML model, inputs the collected historical data into the AI / ML model for prediction, and outputs the prediction result. For possible triggering scenarios of network side 620, in addition to channel state triggering such as RSRP, RSRQ, and SINR, it may also be triggered by service scenarios such as load balancing. Subsequently, in step (7), user side 610 generates prediction measurement result 655 and reports (653) to network side 620 based on the report format corresponding to the AI / ML prediction result configured by network side 620. Among them, in the RRM measurement report configuration of RRC configuration 635 sent by network side 620 (633), the reportConfigId parameter (IE2 pseudocode of the configuration parameter mentioned above for RRC measurement reporting) is used to distinguish different reporting configurations.The reporting configuration ID based on AI / ML model prediction is different from the reporting configuration ID based on actual results. In the RRM report configuration, MeasIdToAddModList can also be added to add measurement tasks and assign a MeasId. This ID will also be reported in the RRM measurement report to determine which measurement task the UE is currently reporting. When the network side 620 receives the measurement report, it can know which measurement task the user side 610 reported by parsing the MeasId.

[0060] In this embodiment, when the first triggering condition is that the first RRM measurement result in the first communication device 410 is lower than a first threshold within a first predetermined time period, the first communication device 410 sends an AI / ML-based RRM measurement report according to the first triggering condition in the following manner: The first communication device 410 determines that the first RRM measurement result is lower than the first threshold within the first predetermined time period. Furthermore, the first communication device 410 sends an AI / ML-based RRM measurement report. The first RRM measurement result includes one or more of the following: Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), or Signal-to-Interference-plus-Noise Ratio (SINR). Thus, for example, the first communication device 410 of the terminal device 110 can, based on its own RRM measurement results such as RSRP, RSRQ, and SINR being lower than the predetermined threshold, activate the AI / ML-based RRM measurement prediction function at an appropriate time when moving to the cell edge, avoiding premature activation of the AI / ML-based RRM measurement prediction function in the good channel environment of the cell center, thereby saving power consumption and improving battery life. Moreover, the AI / ML-based RRM measurement prediction function is initiated automatically by the terminal device 110, which has high flexibility.

[0061] In step (6), the activation method for the RRM prediction function using the AI / ML model on the UE side can be either network side 620 trigger or user side 610 trigger. The user side 610 trigger (UE) can be implemented in the following way.

[0062] (1) UE triggering based on network configuration parameters: The network side 620 increases the threshold of corresponding parameters through RRM configuration, such as RSRP, RSRQ, SINR. When the UE gradually moves from the cell center to the cell edge, the actual measured signal quality will gradually deteriorate. When the actual measured parameters are lower than the set threshold, the user side 610 actively triggers the AI / ML prediction model inference function. By changing the MeasId in the measurement report, the reporting based on the AI / ML prediction results is completed according to the AI / ML model prediction reporting configuration.

[0063] (2) UE-based triggering: The user-side 610 actively triggers the inference function of the AI / ML model according to its own situation. When the user-side 610 reports the prediction results of the AI / ML model, the MeasId in the measurement report will change to the measurement task ID corresponding to the AI / ML model. The network-side 620 determines whether the reported content is based on the results obtained by the AI / ML prediction model of the user-side 610 based on the received MeasId information.

[0064] In the example embodiments of this application, the first indication information includes AI / ML activation identification information, used to activate RRM measurement reports based on AI / ML prediction. Alternatively or additionally, the first indication information includes AI / ML index information, used to identify the corresponding Media Access Control-Control Unit (MAC-CE) indication related to functions associated with AI / ML prediction-based RRM measurement inference and measurement reporting. Alternatively or additionally, the first indication information includes RRM measurement task identification information, used to identify measurement tasks associated with AI / ML prediction. Thus, for example, when the second communication device 420 of network device 120 activates the AI / ML model on the UE side for RRM measurement prediction through the first indication information, it can specifically configure the RRM measurement prediction based on the AI / ML model, improve the accuracy of the prediction, thereby improving the accuracy of scenarios such as handover, and improving system performance such as communication reliability.

[0065] In the example embodiment of this application, the activation of AI / ML-based RRM measurement prediction in the user-side 610 by the network side 620 can be triggered based on the media access control – control element (MAC-CE). When the network side 620 decides to trigger the AI / ML model deployed on the user-side 610 (UE) to perform RRM prediction, the network side 620 generates a corresponding MAC CE, adds the LCID / eLCID field (AI / ML index information) corresponding to activating / deactivating the UE-side AI / ML model inference function to the MAC header information, that is, adds the corresponding LCID / eLCID field to the aforementioned Tables 1 and 2, and sets the third parameter (AI / ML activation identifier information) to 1, indicating that the user-side 610 is activated to perform RRM inference function using the AI / ML model. The specific activated RRM prediction for a certain task can be identified by the fourth parameter (RRM measurement task identifier information), which matches and corresponds to the MeasId in MeasConfig-->MeasIdToAddModList to identify the activated measurement prediction task. MeasID connects the Measurement Object (MO) and the Measurement Report Configuration to form a measurement task. One MO can be associated with multiple Measurement Report Configurations, and one Measurement Report Configuration can also be associated with multiple MOs. Thus, different measurement and reporting methods are used for different MOs and measurement reports, constituting different measurement tasks. The fourth parameter triggers a specific measurement task by marking the MeasID. When the user-side 610 receives this MAC CE message, it uses the LCID / eLCID field and the third parameter to determine that the message indicates the activation of the AI / ML model for RRM prediction. By parsing the fourth parameter, it determines which measurement task's AI / ML model prediction is being implemented.

[0066] In this embodiment, for example, the second communication device 420 of network device 120 can also enable or disable the AI / ML model-based RRM measurement prediction function in the first communication device 410 of terminal device 110 via signaling. In this embodiment, the first communication device 410 receives a first configuration message, which instructs the first communication device 410 to enable the AI / ML-based RRM measurement report. Alternatively, the first configuration message instructs the first communication device to disable the AI / ML-based RRM measurement report and send an RRM measurement report based on the measurement results. Thus, for different channel conditions or service requirements, network device 120 can flexibly enable the AI / ML-based RRM measurement report in terminal device 110 to achieve more accurate predictions, or disable the AI / ML-based RRM measurement report to achieve energy saving on the UE side, providing more flexible options for RRM measurement reports and improving the overall system performance.

[0067] Figure 7 The diagram illustrates the signaling diagram for enabling and disabling model prediction functionality using RRC configuration according to an embodiment of this application. In implementation 700, the user side 710 can correspond to... Figure 1 Terminal equipment 110 in China Figure 4 The first communication device 410 and the network side 720 can correspond to the network device 120 and the second communication device 420.

[0068] In embodiment 700, the enabling / disabling of the predictive model inference function on the user side 710 can be directly configured based on the first parameter in the RRC configuration sent by the network side 720, which corresponds to Figure 4 The first configuration message 425 in the middle. In this way, the design of RRC signaling can be simplified. In steps (1) and (2), the network side 720 queries (723) the user's capabilities, and the user side 710 provides feedback (728) that it supports RRM measurement reporting based on AI / ML model prediction results 730. Its functions and Figure 5 , Figure 6Correspondingly, no further details are provided. After receiving the capability reporting information 730 from the UE (728), the network side 720 sends the RRC configuration message 735 (733) in step (3) to configure the first parameter to enable the RRM prediction inference function of the user side 710. After receiving the message 735 (733), the user side 710 sends the RRC configuration feedback 740 (738) in step (4) to confirm that the configuration for AI / ML prediction is applicable to the user side 710, and enables its own RRM prediction inference function, predicting future measurement data based on the configuration information in MeasConfig and the measurement data. In step (5), when the user side 710 performs RRM prediction reporting, it sends the measurement report 745 (743) based on the prediction result. According to the configuration of the RRC signaling 735, the user side 710 matches the measurement report 745 with the MeasId of the measurement task based on the prediction result, and completes the reporting based on the RRM prediction result according to the configuration. If the network side 720 does not change the configuration, the user side 710 continues to report AI / ML model predictions, as shown by the dashed line after step (5). In step (6), the network side 720 sends (748) RRC configuration message 750 to disable the model prediction inference function of the user side 710. The reason may be that the network side 720 detects that the AI / ML model performance is not up to standard, or other factors. After receiving (748) the RRC configuration 750, the user side 710 sends (753) RRC configuration feedback 755 for confirmation and disables its own AI / ML model prediction function. Subsequent reports (758) are based on the actual measurement results 760.

[0069] In this embodiment, when the AI / ML model prediction in the first communication device 410 of terminal device 110 is inaccurate, terminal device 110 can collect training data of the AI / ML model to train and update the AI / ML model in terminal device 110 or network device 120. The collection of training data for the AI / ML model can be triggered by, for example, the first communication device 410 of terminal device 110, or by, for example, the second communication device 420 of network device 120, and will be further combined with subsequent... Figure 8 , Figure 9 A detailed analysis will be conducted.

[0070] In this embodiment, for example, the first communication device 410 of terminal device 110 receives a second configuration message. The second configuration message indicates a second triggering condition, which triggers the first communication device to collect data for AI / ML model updates. Furthermore, the first communication device 410 collects data for AI / ML model updates according to the second triggering condition. In this embodiment, AI / ML model updates include: AI / ML model training, and updating the AI / ML model based on the training results. Thus, by collecting measurement data and updating the AI / ML model, more accurate RRM measurement predictions can be made, resulting in more accurate RRM measurement reports, improving, for example, the accuracy of cell handover, and enhancing system performance such as system reliability.

[0071] In this embodiment, the second triggering condition includes one of the following: receiving a second configuration message; the difference between the RRM measurement result based on AI / ML prediction and the measured RRM measurement result in the first communication device 410 being greater than or equal to a second threshold; or receiving second indication information from the second communication device 420, the second indication information being used to instruct the first communication device 410 to collect data for AI / ML model updates. Thus, the first communication device 410 can be triggered to start data collection for AI / ML model training and updates in multiple ways, improving the flexibility of triggering.

[0072] Figure 8 A signaling diagram of UE-side triggered model training data collection according to an embodiment of this application is shown. In embodiment 800, the user-side 810 may correspond to... Figure 1 Terminal equipment 110 in China Figure 4 The first communication device 410 and the network side 820 can correspond to the network device 120 and the second communication device 420.

[0073] In this embodiment, the user-side 810 (UE) deploys an AI / ML model related to RRM prediction for measurement prediction, and the network-side 820 (NW) is responsible for the lifecycle management of the AI / ML model. In step (2), when the user-side 810 indicates in its capability report 830 that it supports the measurement prediction data collection function of RRM, the network-side 820 can complete the trigger configuration related to data collection based on the capability parameters reported by the user-side 810 in the UE capability report 830. In step (3), the network-side 820 sends (833) RRC configuration signaling message 835 to configure the second parameter as actively triggered by the user-side 810.

[0074] In this embodiment, when the second triggering condition is that the difference between the RRM measurement result predicted by AI / ML and the measured RRM measurement result in the first communication device 410 is greater than or equal to a second threshold, the first communication device 410 collects data for AI / ML model updates according to the second triggering condition in the following manner: The first communication device 410 determines that the difference between the RRM measurement result predicted by AI / ML and the measured RRM measurement result is greater than or equal to the second threshold. Furthermore, the first communication device 410 collects data for AI / ML model updates. Thus, the second threshold can accurately control the first communication device 410 of, for example, terminal device 110, to initiate data collection for AI / ML model training and updates, avoiding excessive performance degradation of the AI / ML model and preventing the waste of resources due to premature data collection and AI / ML model training and updates.

[0075] The user-side 810 can be triggered actively based on the relevant parameter thresholds configured by the network side 820 or by its own implementation. After receiving the RRC configuration 835 (833), the user-side 810 sends the RRC configuration feedback 840 (838) to the network side 820 in step (4) depending on whether it can collect data. For the trigger-related parameter thresholds configured by the network side 820, the specific network configuration parameters can be added to the RRM prediction model performance threshold parameters of the user-side 810 in the RRC configuration 835. For example, the RSRP difference threshold (the difference between the predicted value and the actual measurement value) can be used. When the UE-side model performance index exceeds / below the network configuration threshold, it indicates that the error between the model prediction result and the actual measurement result is large, and model training data collection and model update are required.

[0076] In this embodiment of the application, the format of the data collected by the UE can also be configured by the RRC.

[0077] Figure 9 A signaling diagram of network-side triggered model training data collection according to an embodiment of this application is shown. In embodiment 900, the user side 910 may correspond to... Figure 1 Terminal equipment 110 in China Figure 4 The first communication device 410 and the network side 920 can correspond to the network device 120 and the second communication device 420.

[0078] As shown in Example 900, the network side 920 (NW) sets the second parameter (933) to be triggered by the network side 920 in step (3) in the RRC configuration 935 based on the UE capability 930 reported (928) by the user side 910 (UE) in step (2). That is, the data collection function of the user side 910 needs to be triggered by the network side 920 sending a second message, such as a MAC CE command. When the network side 920 sends the second message to trigger the data collection function of the user side 910 depends on the implementation of the network side 920 itself. When user data collection is required, the network side 920 sends (943) a corresponding second message 943, such as a MAC CE command, in step (5) to trigger the data collection function of the user side 910. Specifically, the network side 920 can monitor the performance of the AI / ML prediction model deployed by the user side 910 based on the comparison between the prediction results reported by the user side 910 and the actual results. When the actual measurement data and the predicted data differ significantly, the network side 920 triggers the data collection function of the user side 910 to complete the storage of training data samples and subsequent model update and training.

[0079] In this embodiment, the second indication message is also used to indicate the amount of data used for AI / ML model updates. Thus, the network side 820 can accurately control the amount of data collected by the user side 810 based on channel conditions and specific scenarios, meeting the training and update requirements of the AI / ML model while avoiding excessive data collection, saving UE power consumption and network data transmission volume.

[0080] In this embodiment, when the network side 920 activates the user's data collection function through MAC CE (943), the user side 910 determines that the function of the MAC CE is to activate data collection by parsing LCID / eLCID, and determines the data collection size by parsing the newly added fifth parameter in the MAC CE, thereby completing the activation of the data collection function. The network side 920 needs to obtain the actual measurement results and prediction results of RRM from the user side 910 to measure the performance of the model. The model prediction results can be obtained by adding a report configuration related to communication standards such as 6G or future higher standards to the RRM reporting configuration of RRC configuration 935. When the user side 910 activates AI / ML model prediction, it reports the predicted RRM data according to the report configuration. As for the actual result data, the implementation can be achieved by configuring the actual result measurement records in the minimization of drive tests (MDT) configuration configured on the network side. The characteristic of this real result measurement record reporting is that it reports multiple sampling points, and the reporting configuration includes parameters such as the number of real measurement values ​​and the time corresponding to each real measurement value. For example, the recorded MDT completes the reporting of real measurement results. Therefore, after receiving the real RRM measurement values, the network side 920 can compare and analyze them with the reported RRM prediction values ​​to determine whether to switch to real result reporting and activate the model training data collection function of the user side 910.

[0081] Figure 10 A flowchart of a communication method 1000 implemented at a first communication device 410 according to an embodiment of this application is shown. For convenience, it will be combined with... Figure 1 Example description of method 1000. For example, method 1000 can be used in... Figure 1 The method is implemented at terminal device 110. It should be understood that method 1000 may include other additional steps not shown, or some steps shown may be omitted. The scope of this application is not limited thereto.

[0082] In step 1010, the first communication device 410 receives a first configuration message, wherein the first configuration message is used to indicate a first trigger condition, which is used to trigger the first communication device to send a Radio Resource Management (RRM) measurement report based on Artificial Intelligence (AI) / Machine Learning (ML) prediction or to activate AI / ML prediction. In step 1020, the first communication device 410 sends an RRM measurement report based on AI / ML prediction according to the first trigger condition.

[0083] In some embodiments, the first triggering condition includes one of the following: receiving a first configuration message, the first RRM measurement result in the first communication device being lower than a first threshold within a first predetermined time period, or receiving first indication information from a second communication device, wherein the first indication information instructs the first communication device to send an RRM measurement report based on AI / ML prediction.

[0084] In some embodiments, the first indication information includes one or more of the following: AI / ML activation identification information for activating AI / ML-based RRM measurement reports; AI / ML index information for identifying the corresponding Media Access Control-Control Unit (MAC-CE) indication of functions related to AI / ML-based RRM measurement inference and measurement reports; or RRM measurement task identification information for identifying measurement tasks associated with AI / ML predictions.

[0085] In some embodiments, the first communication device 410 sends a first response message, wherein the first response message indicates that a configuration for AI / ML prediction is applicable to the first communication device 410.

[0086] In some embodiments, when the first triggering condition is receiving a first configuration message, the first communication device 410 sending an AI / ML-predicted RRM measurement report according to the first triggering condition includes: the first communication device 410 sends an AI / ML-predicted RRM measurement report upon receiving the first configuration message.

[0087] In some embodiments, when the first triggering condition is that the first RRM measurement result in the first communication device 410 is lower than the first threshold within a first predetermined time period, the first communication device 410 sending an RRM measurement report based on AI / ML prediction according to the first triggering condition includes: the first communication device 410 determining that the first RRM measurement result is lower than the first threshold within a first predetermined time period; and sending an RRM measurement report based on AI / ML prediction.

[0088] In some embodiments, the first RRM measurement result includes one or more of the following: reference signal received power (RSRP), reference signal received quality (RSRQ), or signal-to-interference-plus-noise ratio (SINR).

[0089] In some embodiments, when the first triggering condition is receiving the first indication information from the second communication device 420, the first communication device 410 sending the RRM measurement report based on AI / ML prediction according to the first triggering condition includes: the first communication device 410 receiving the first indication information; and sending the RRM measurement report based on AI / ML prediction.

[0090] In some embodiments, the first communication device 410 receives a capability query message, wherein the query message is used to query the capability of the first communication device 410 to support AI / ML prediction-based RRM measurement reporting. Furthermore, the first communication device 410 sends a capability response message, wherein the capability response message is used to instruct the first communication device 410 to support AI / ML prediction-based RRM measurement reporting. Additionally, the first communication device 410 receives a first configuration message, wherein the first configuration message is used to instruct the first communication device to enable AI / ML prediction-based RRM measurement reporting.

[0091] In some embodiments, the first configuration message is used to instruct the first communication device 410 to disable RRM measurement reports based on AI / ML predictions. Additionally, the first communication device 410 sends RRM measurement reports based on the measurement results.

[0092] In some embodiments, the first communication device 410 receives a second configuration message, wherein the second configuration message is used to indicate a second triggering condition, the second triggering condition being used to trigger the first communication device to collect data for AI / ML model updates. Furthermore, the first communication device 410 collects data for AI / ML model updates according to the second triggering condition.

[0093] In some embodiments, the second triggering condition includes one of the following: receiving a second configuration message, wherein the difference between the RRM measurement result based on AI / ML prediction and the measured RRM measurement result in the first communication device 410 is greater than or equal to a second threshold, or receiving second indication information from the second communication device 420, wherein the second indication information is used to instruct the first communication device 410 to collect data for AI / ML model updates.

[0094] In some embodiments, when the second triggering condition is receiving a second configuration message, the first communication device 410 collects data for AI / ML model updates according to the second triggering condition, which includes: the first communication device 410 receives the second configuration message, that is, it collects data for AI / ML model updates according to the second triggering condition.

[0095] In some embodiments, when the second triggering condition is that the difference between the AI / ML-predicted RRM measurement result and the measured RRM measurement result in the first communication device 410 is greater than or equal to a second threshold, the first communication device 410 collects data for AI / ML model updating according to the second triggering condition, including: the first communication device 410 determines that the difference between the AI / ML-predicted RRM measurement result and the measured RRM measurement result is greater than or equal to the second threshold. Furthermore, the first communication device 410 collects data for AI / ML model updating.

[0096] In some embodiments, when the second triggering condition is receiving the second instruction information from the second communication device 420, the first communication device 410 collects data for AI / ML model updates according to the second triggering condition, including: the first communication device 410 receiving the second instruction information; and collecting data for AI / ML model updates.

[0097] In some embodiments, the second instruction message is also used to indicate the amount of data used for AI / ML model updates.

[0098] In some embodiments, AI / ML model updating includes: AI / ML model training, and updating the AI / ML model based on the results of AI / ML model training.

[0099] In some embodiments, the first communication device includes a terminal device, and the second communication device includes a network device.

[0100] According to method 1000, for example, the first communication device 410 of terminal device 110 can trigger an AI / ML-predicted RRM measurement report based on triggering conditions, such as the specific state of the terminal device, network service requirements, etc., thereby saving the power consumption of the terminal device and extending its battery life while meeting the quality of service (QoS) requirements.

[0101] Figure 11 A flowchart of a communication method 1100 implemented at a second communication device 420 according to an embodiment of this application is shown. For convenience, it will be combined with... Figure 1 Example description of method 1100. For example, method 1100 can be used in... Figure 1 The method is implemented at network device 120. It should be understood that method 1100 may include other additional steps not shown, or some steps shown may be omitted. The scope of this application is not limited thereto.

[0102] In step 1110, the second communication device 420 sends a first configuration message, wherein the first configuration message is used to indicate a first triggering condition, which is used to trigger the first communication device 410 to send a Radio Resource Management (RRM) measurement report based on Artificial Intelligence (AI) / Machine Learning (ML) prediction or to activate AI / ML prediction. In step 1120, the second communication device 420 receives the RRM measurement report based on AI / ML prediction.

[0103] In some embodiments, the first triggering condition includes one of the following: the first communication device 410 receives a first configuration message; the first RRM measurement result in the first communication device 410 is lower than a first threshold within a first predetermined time period; the first communication device 410 receives first indication information from the second communication device 420, wherein the first indication information is used to instruct the first communication device 410 to send an RRM measurement report based on AI / ML prediction.

[0104] In some embodiments, the first indication information includes one or more of the following: AI / ML activation identification information for activating AI / ML-based RRM measurement reports; AI / ML index information for identifying the corresponding Media Access Control-Control Unit (MAC-CE) indication of functions related to AI / ML-based RRM measurement inference and measurement reports; or RRM measurement task identification information for identifying measurement tasks associated with AI / ML predictions.

[0105] In some embodiments, the second communication device 420 receives a first response message, wherein the first response message is used to indicate that a configuration for AI / ML prediction is applicable to the first communication device 410.

[0106] In some embodiments, when the first triggering condition is receiving first indication information from the second communication device 420, the second communication device 420 determines that the second RRM measurement result sent by the first communication device 410 is lower than a third threshold within a second predetermined time period; and sends the first indication information.

[0107] In some embodiments, the second RRM measurement result includes one or more of the following: reference signal received power (RSRP), reference signal received quality (RSRQ), or signal-to-interference-plus-noise ratio (SINR).

[0108] In some embodiments, the second communication device 420 sends a capability query message, wherein the query message is used to query the capability of the first communication device 410 to support AI / ML prediction-based RRM measurement reporting. Furthermore, the second communication device 420 receives a capability response message, wherein the capability response message is used to instruct the first communication device 410 to support AI / ML prediction-based RRM measurement reporting. Additionally, the second communication device 420 sends a first configuration message, wherein the first configuration message is used to instruct the first communication device 410 to enable AI / ML prediction-based RRM measurement reporting.

[0109] In some embodiments, a first configuration message is used to instruct the first communication device 410 to disable RRM measurement reports based on AI / ML predictions. Additionally, the second communication device 420 receives RRM measurement reports based on measurement results.

[0110] In some embodiments, the second communication device 420 sends a second configuration message, wherein the second configuration message is used to indicate a second triggering condition, and the second triggering condition is used to trigger the first communication device 410 to collect data for AI / ML model updates.

[0111] In some embodiments, the second triggering condition includes one of the following: receiving a second configuration message, wherein the difference between the RRM measurement result based on AI / ML prediction and the measured RRM measurement result in the first communication device 410 is greater than or equal to a second threshold, or receiving second indication information from the second communication device 420, wherein the second indication information is used to instruct the first communication device 410 to collect data for AI / ML model updates.

[0112] In some embodiments, when the second triggering condition is receiving second indication information from the second communication device 420, the second communication device 420 determines that the difference between the RRM measurement result based on AI / ML prediction and the measured RRM measurement result is greater than or equal to a fourth threshold. Furthermore, the second communication device 420 sends the second indication information.

[0113] In some embodiments, the second instruction message is also used to indicate the amount of data used for AI / ML model updates.

[0114] In some embodiments, AI / ML model updating includes: AI / ML model training, and updating the AI / ML model based on the results of AI / ML model training.

[0115] In some embodiments, the first communication device 410 includes a terminal device, and the second communication device 420 includes a network device.

[0116] According to method 1100, for example, the first communication device 410 of terminal device 110 can trigger an AI / ML-predicted RRM measurement report based on triggering conditions, such as the specific state of the terminal device, network service requirements, etc., thereby saving the power consumption of the terminal device and extending its battery life while meeting the quality of service (QoS) requirements.

[0117] It should be understood that the description of communication process 400 also applies to the above-mentioned communication methods 1000 and 1100, so other details will not be repeated.

[0118] Corresponding to the above communication method, embodiments of this application also provide a communication device, which is described below in conjunction with... Figure 12 and Figure 13 This will be described.

[0119] Figure 12A schematic block diagram of an example first communication device 1200 according to an embodiment of this application is shown. The first communication device 1200 can be used in a terminal device (e.g., Figure 1 The first communication device 1200 is implemented at the terminal device 110. The first communication device 1200 may be part of the terminal device or may be an integral part of the terminal device. It should be understood that the first communication device 1200 may include more additional components than those shown or may omit some of the shown components; this application embodiment does not impose limitations in this regard.

[0120] like Figure 12 As shown, the first communication device 1200 may include a receiving module 1210 and a transmitting module 1220. The receiving module 1210 may be configured to receive a first configuration message, wherein the first configuration message is used to configure an indication of a first trigger condition, which is used to trigger the first communication device 1200 to send a Radio Resource Management (RRM) measurement report based on Artificial Intelligence (AI) / Machine Learning (ML) prediction or to activate AI / ML prediction. The transmitting module 1220 may be configured to send an RRM measurement report based on AI / ML prediction according to the first trigger condition.

[0121] In some embodiments, the first triggering condition includes one of the following: receiving a first configuration message, the first RRM measurement result in the first communication device being lower than a first threshold within a first predetermined time period, or receiving first indication information from a second communication device, wherein the first indication information instructs the first communication device to send an RRM measurement report based on AI / ML prediction.

[0122] In some embodiments, the first indication information includes one or more of the following: AI / ML activation identification information for activating AI / ML-based RRM measurement reports; AI / ML index information for identifying the corresponding Media Access Control-Control Unit (MAC-CE) indication of functions related to AI / ML-based RRM measurement inference and measurement reports; or RRM measurement task identification information for identifying measurement tasks associated with AI / ML predictions.

[0123] In some embodiments, the first communication device 1200 sends a first response message, wherein the first response message indicates that a configuration for AI / ML prediction is applicable to the first communication device 1200.

[0124] In some embodiments, when the first triggering condition is receiving a first configuration message, the first communication device 1200 sending an AI / ML-predicted RRM measurement report according to the first triggering condition includes: the first communication device 1200 receiving the first configuration message and then sending an AI / ML-predicted RRM measurement report.

[0125] In some embodiments, when the first triggering condition is that the first RRM measurement result in the first communication device 1200 is lower than the first threshold within a first predetermined time period, the first communication device 1200 sending an RRM measurement report based on AI / ML prediction according to the first triggering condition includes: the first communication device 1200 determining that the first RRM measurement result is lower than the first threshold within a first predetermined time period; and sending an RRM measurement report based on AI / ML prediction.

[0126] In some embodiments, the first RRM measurement result includes one or more of the following: reference signal received power (RSRP), reference signal received quality (RSRQ), or signal-to-interference-plus-noise ratio (SINR).

[0127] In some embodiments, when the first triggering condition is receiving the first indication information from the second communication device 420, the first communication device 410 sending the RRM measurement report based on AI / ML prediction according to the first triggering condition includes: the first communication device 1200 receiving the first indication information; and sending the RRM measurement report based on AI / ML prediction.

[0128] In some embodiments, the first communication device 1200 receives a capability query message, wherein the query message is used to query the capability of the first communication device 1200 to support AI / ML prediction-based RRM measurement reporting. Furthermore, the first communication device 1200 sends a capability response message, wherein the capability response message is used to instruct the first communication device 1200 to support AI / ML prediction-based RRM measurement reporting. Additionally, the first communication device 1200 receives a first configuration message, wherein the first configuration message is used to instruct the first communication device to enable AI / ML prediction-based RRM measurement reporting.

[0129] In some embodiments, the first configuration message is used to instruct the first communication device 1200 to disable RRM measurement reports based on AI / ML predictions. Additionally, the first communication device 1200 sends RRM measurement reports based on the measurement results.

[0130] In some embodiments, the first communication device 1200 receives a second configuration message, wherein the second configuration message is used to indicate a second triggering condition, the second triggering condition being used to trigger the first communication device to collect data for AI / ML model updates. Furthermore, the first communication device 1200 collects data for AI / ML model updates according to the second triggering condition.

[0131] In some embodiments, the second triggering condition includes one of the following: receiving a second configuration message, wherein the difference between the RRM measurement result based on AI / ML prediction and the measured RRM measurement result in the first communication device 1200 is greater than or equal to a second threshold, or receiving second indication information from the second communication device 1300, wherein the second indication information is used to instruct the first communication device 1200 to collect data for AI / ML model updates.

[0132] In some embodiments, when the second triggering condition is receiving a second configuration message, the first communication device 1200 collects data for AI / ML model updates according to the second triggering condition, which includes: the first communication device 1200 receives the second configuration message, that is, it collects data for AI / ML model updates according to the second triggering condition.

[0133] In some embodiments, when the second triggering condition is that the difference between the AI / ML-predicted RRM measurement result and the measured RRM measurement result in the first communication device 1200 is greater than or equal to a second threshold, the first communication device 1200 collects data for AI / ML model updating according to the second triggering condition, including: the first communication device 1200 determines that the difference between the AI / ML-predicted RRM measurement result and the measured RRM measurement result is greater than or equal to the second threshold. Furthermore, the first communication device 1200 collects data for AI / ML model updating.

[0134] In some embodiments, when the second triggering condition is receiving the second instruction information from the second communication device 1300, the first communication device 1200 collects data for AI / ML model updates according to the second triggering condition, including: the first communication device 1200 receiving the second instruction information; and collecting data for AI / ML model updates.

[0135] In some embodiments, the second instruction message is also used to indicate the amount of data used for AI / ML model updates.

[0136] In some embodiments, AI / ML model updating includes: AI / ML model training, and updating the AI / ML model based on the results of AI / ML model training.

[0137] In some embodiments, the first communication device 1200 includes a terminal device, and the second communication device 1300 includes a network device.

[0138] Figure 13 A schematic block diagram of an example second communication device 1300 according to an embodiment of this application is shown. The second communication device 1300 can be used in network devices (e.g., Figure 1The second communication device 1300 is implemented at the network device 120. The second communication device 1300 may be part of the network device or may be an integral part of the network device. It should be understood that the second communication device 1300 may include more additional components than those shown or may omit some of the components shown; this embodiment of the application does not impose limitations in this regard.

[0139] like Figure 13 As shown, the second communication device 1300 may include a transmitting module 1310 and a receiving module 1320. The transmitting module 1310 may be configured to transmit a first configuration message, wherein the first configuration message is configured to indicate a first trigger condition, which is used to trigger the first communication device to transmit a Radio Resource Management (RRM) measurement report based on Artificial Intelligence (AI) / Machine Learning (ML) prediction or to activate AI / ML prediction. The receiving module 1320 is configured to receive an RRM measurement report based on AI / ML prediction.

[0140] In some embodiments, the first triggering condition includes one of the following: the first communication device 1200 receives a first configuration message; the first RRM measurement result in the first communication device 1200 is lower than a first threshold within a first predetermined time period; the first communication device 1200 receives first indication information from the second communication device 1300, wherein the first indication information is used to instruct the first communication device 1200 to send an RRM measurement report based on AI / ML prediction.

[0141] In some embodiments, the first indication information includes one or more of the following: AI / ML activation identification information for activating AI / ML-based RRM measurement reports; AI / ML index information for identifying the corresponding Media Access Control-Control Unit (MAC-CE) indication of functions related to AI / ML-based RRM measurement inference and measurement reports; or RRM measurement task identification information for identifying measurement tasks associated with AI / ML predictions.

[0142] In some embodiments, the second communication device 1300 receives a first response message, wherein the first response message is used to indicate that a configuration for AI / ML prediction is applicable to the first communication device 1200.

[0143] In some embodiments, when the first triggering condition is receiving first indication information from the second communication device 1300, the second communication device 1300 determines that the second RRM measurement result sent by the first communication device 1200 is lower than a third threshold within a second predetermined time period; and sends the first indication information.

[0144] In some embodiments, the second RRM measurement result includes one or more of the following: reference signal received power (RSRP), reference signal received quality (RSRQ), or signal-to-interference-plus-noise ratio (SINR).

[0145] In some embodiments, the second communication device 1300 sends a capability query message, wherein the query message is used to query the capability of the first communication device 1200 to support AI / ML prediction-based RRM measurement reporting. Furthermore, the second communication device 1300 receives a capability response message, wherein the capability response message is used to instruct the first communication device 1200 to support AI / ML prediction-based RRM measurement reporting. Additionally, the second communication device 1300 sends a first configuration message, wherein the first configuration message is used to instruct the first communication device 1200 to enable AI / ML prediction-based RRM measurement reporting.

[0146] In some embodiments, a first configuration message is used to instruct the first communication device 1200 to disable RRM measurement reports based on AI / ML predictions. Additionally, the second communication device 1300 receives RRM measurement reports based on the measurement results.

[0147] In some embodiments, the second communication device 1300 sends a second configuration message, wherein the second configuration message is used to indicate a second triggering condition, and the second triggering condition is used to trigger the first communication device 410 to collect data for AI / ML model updates.

[0148] In some embodiments, the second triggering condition includes one of the following: receiving a second configuration message, wherein the difference between the RRM measurement result based on AI / ML prediction and the measured RRM measurement result in the first communication device 1200 is greater than or equal to a second threshold, or receiving second indication information from the second communication device 1300, wherein the second indication information is used to instruct the first communication device 1200 to collect data for AI / ML model updates.

[0149] In some embodiments, when the second triggering condition is receiving second indication information from the second communication device 1300, the second communication device 1300 determines that the difference between the RRM measurement result based on AI / ML prediction and the measured RRM measurement result is greater than or equal to a fourth threshold. Furthermore, the second communication device 1300 sends the second indication information.

[0150] In some embodiments, the second instruction message is also used to indicate the amount of data used for AI / ML model updates.

[0151] In some embodiments, AI / ML model updating includes: AI / ML model training, and updating the AI / ML model based on the results of AI / ML model training.

[0152] In some embodiments, the first communication device 1200 includes a terminal device, and the second communication device 1300 includes a network device.

[0153] It should be understood that the communication devices 1200 and 1300 described above correspond to the communication methods 1000 and 1100 described above, respectively, and correspond to the description in the communication process 400 described above. Therefore, other details will not be described again.

[0154] This application also provides communication devices in its embodiments. Figure 14 This is a simplified block diagram of a communication device 1400 suitable for implementing embodiments of this application. The device 1400 can be provided to implement a terminal device or a network device. As shown, the device 1400 includes one or more processors 1410 and one or more memories 1420 coupled to the processors 1410. Optionally, the one or more memories 1420 may also be integrated with the one or more processors 1410.

[0155] Processor 1410 can be of any type suitable for a local technology network, and by way of limiting examples, can include one or more of the following: general-purpose computer, special-purpose computer, microprocessor, digital signal processor, and processor based on a multi-core processor architecture. Device 1400 can have multiple processors, such as application-specific integrated circuit chips, which are time-subordinate to a clock synchronized with the main processor.

[0156] Memory 1420 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 1424, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD), and other magnetic and / or optical storage devices. Examples of volatile memories include, but are not limited to, random access memory (RAM) 1422 and other volatile memories that do not persist during power-off periods.

[0157] Computer program 1430 includes computer-executable instructions that are executed by the associated processor 1410. Program 1430 may be stored in ROM 1420. Processor 1410 can perform any suitable actions and processes by loading program 1430 into RAM 1420.

[0158] The embodiments of this application can be implemented by means of program 1430, such that device 1400 performs as described in the reference. Figures 1 to 13 The embodiments of this application describe a solution. Device 1400 can correspond to the first communication device 1200 or the second communication device 1300 described above. The functional modules in the first communication device 1200 or the second communication device 1300 can be implemented using software in device 1400. In other words, the functional modules included in the first communication device 1200 or the second communication device 1300 can be generated by the processor 1410 of device 1400 reading program code stored in memory 1420. Embodiments of this application can also be implemented using hardware or a combination of software and hardware.

[0159] In some embodiments, program 1430 may be tangibly contained in a computer-readable medium, which may include in device 1400 (such as in memory 1420) or other storage device accessible by device 1400. Program 1430 may be loaded from the computer-readable medium into RAM 1422 for execution. The computer-readable medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc.

[0160] In some embodiments, device 1400 may further include one or more communication modules (not shown). These communication modules may be coupled to processor 1410. The communication modules may be used for bidirectional communication. The communication modules may have a communication interface to facilitate communication. The communication interface may represent any interface required for communication with other network elements.

[0161] As used in this document, the term "circuit" refers to one or more of the following: • Hardware circuit implementation only, such as implementation of analog and / or digital circuits only; and • Combinations of hardware circuits and software, such as: 1) combinations of analog and / or digital hardware circuits with software / firmware, 2) any part of a hardware processor with software, including digital signal processors, software and memory (these components work together to enable devices such as terminal devices or network devices to perform various functions), and 3) hardware circuits and / or processors that require software / firmware to operate.

[0162] The term “circuit” as used herein also covers an implementation of hardware circuitry or a processor, or a portion of a hardware circuitry or processor and its accompanying software / firmware.

[0163] Generally, the various exemplary embodiments of this application can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of the embodiments of this application are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof. Examples of hardware devices that can be used to implement the embodiments of this application include, but are not limited to: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), SoCs, complex programmable logic devices (CPLDs), etc.

[0164] As an example, embodiments of this application can be described in the context of machine-executable instructions, such as program modules that execute on a device running on a real or virtual processor of the target. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc., which perform specific tasks or implement specific abstract data structures. In various embodiments, the functionality of program modules may be combined or divided among the described program modules. The machine-executable instructions for a program module can execute within a local or distributed device. In a distributed device, the program module can reside on both local and remote storage media.

[0165] The computer program code used to implement the methods of this application may be written in one or more programming languages. This computer program code may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the computer or other programmable data processing device, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0166] In the context of this application, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, wireless, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, etc. A machine-readable medium may be any tangible medium that contains or stores a program for or relating to an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. More detailed examples of machine-readable storage media include electrical connections with one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM, or flash memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0167] Furthermore, although the operations are depicted in a specific order, this should not be construed as requiring such operations to be performed in the specific order shown or in a sequential order, or to execute all illustrated operations to obtain the desired result. In some cases, multitasking or parallel processing may be beneficial. Similarly, although the foregoing discussion includes certain specific implementation details, this should not be construed as limiting the scope of any invention or claim, but rather as a description of specific embodiments that may be implemented with respect to a particular invention. Certain features described in this specification in the context of separate embodiments may also be implemented in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination.

[0168] Although the subject matter has been described in language specific to structural features and / or methodological actions, it should be understood that the subject matter defined in the appended claims is not limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms of implementing the claims.

[0169] Glossary: RRM: Radio Resource Management UE: User Equipment CSI-RS: Channel State Information Reference Signal SSB: Synchronization signal block OW: observation window PW: prediction window RSRP: Reference signal received power RSRQ: Reference signal received quality RRC: Radio Resource Control LCID: Logical Channel Identifier eLCID: Enhanced Logical Channel Identifier MDT: Minimization of drive tests.

Claims

1. A communication method, comprising: Receive a first configuration message, wherein the first configuration message is used to indicate a first trigger condition, the first trigger condition being used to trigger a first communication device to send a wireless resource management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate the AI / ML prediction; and Send an RRM measurement report based on AI / ML prediction according to the first trigger condition.

2. The communication method according to claim 1, wherein the first triggering condition includes one of the following: Receive the first configuration message, The first RRM measurement result in the first communication device is lower than the first threshold within a first predetermined time period, or Receive first indication information from the second communication device, wherein the first indication information instructs the first communication device to send the AI / ML-predicted RRM measurement report.

3. The communication method according to claim 2, wherein the first indication information includes one or more of the following: AI / ML activation identifier information is used to activate RRM measurement reports based on AI / ML predictions. AI / ML index information is used to identify the corresponding Media Access Control-Control Unit (MAC-CE) indications and functions related to AI / ML-based RRM measurement inference and measurement reporting, or RRM measurement task identification information is used to identify the measurement task associated with the AI / ML prediction.

4. The communication method according to claim 1 further includes: Send a first response message, wherein the first response message indicates that the configuration for the AI / ML prediction is applicable to the first communication device.

5. The communication method according to any one of claims 2-4, wherein when the first triggering condition is receiving the first configuration message, sending the RRM measurement report based on AI / ML prediction according to the first triggering condition includes: Upon receiving the first configuration message, an RRM measurement report based on AI / ML prediction is sent.

6. The communication method according to any one of claims 2-4, wherein when the first triggering condition is that the first RRM measurement result in the first communication device is lower than a first threshold within a first predetermined time period, sending the RRM measurement report based on AI / ML prediction according to the first triggering condition comprises: Determine that the first RRM measurement result is below a first threshold within a first predetermined time period; as well as Send RRM measurement reports based on AI / ML predictions.

7. The communication method according to claim 6, wherein the first RRM measurement result includes one or more of the following: Reference signal received power (RSRP). Reference signal reception quality (RSRQ), or Signal-to-interference-plus-noise ratio (SINR).

8. The communication method according to any one of claims 2-4, wherein, when the first triggering condition is receiving first indication information from a second communication device, sending an RRM measurement report based on AI / ML prediction according to the first triggering condition comprises: Receive the first instruction message; as well as Send RRM measurement reports based on AI / ML predictions.

9. The communication method according to any one of claims 1-4, further comprising: Receive capability query messages, wherein the query messages are used to query the capability of the first communication device to support the AI / ML-predicted RRM measurement report; Send a capability response message, wherein the capability response message is used to instruct the first communication device to support the AI / ML prediction-based RRM measurement report; as well as The first configuration message is received, wherein the first configuration message is used to instruct the first communication device to enable the AI / ML prediction-based RRM measurement report.

10. The communication method according to any one of claims 1-4, wherein, The first configuration message is used to instruct the first communication device to disable the AI / ML-predicted RRM measurement report; as well as Send an RRM measurement report based on the measurement results.

11. The communication method according to any one of claims 1-4, further comprising: Receive a second configuration message, wherein the second configuration message is used to indicate a second triggering condition, and the second triggering condition is used to trigger the first communication device to collect data for AI / ML model updates; The data used for AI / ML model updates is collected based on the second trigger condition.

12. The communication method according to claim 11, wherein the second triggering condition includes one of the following: Receive the second configuration message, The difference between the RRM measurement result predicted by AI / ML in the first communication device and the measured RRM measurement result is greater than or equal to the second threshold, or The first communication device receives a second instruction message, which is used to instruct the first communication device to collect the data used for AI / ML model updates.

13. The communication method according to claim 12, wherein when the second triggering condition is receiving the second configuration message, collecting the data for AI / ML model updating according to the second triggering condition includes: Upon receiving the second configuration message, the data used for AI / ML model updates is collected according to the second triggering condition.

14. The communication method according to claim 12, wherein, when the second triggering condition is that the difference between the RRM measurement result based on AI / ML prediction in the first communication device and the measured RRM measurement result is greater than or equal to a second threshold, the collection of the data for AI / ML model updating according to the second triggering condition includes: The difference between the AI / ML-predicted RRM measurement result and the measured RRM measurement result is greater than or equal to a second threshold. as well as Collect the data used for updating the AI / ML model.

15. The communication method according to claim 12, wherein when the second triggering condition is receiving second indication information from the second communication device, collecting the data for AI / ML model updating according to the second triggering condition comprises: Receive the second instruction information; as well as Collect the data used for updating the AI / ML model.

16. The communication method according to claim 15, wherein, The second instruction message is also used to indicate the amount of data used for AI / ML model updates.

17. The communication method according to any one of claims 11-16, wherein, The AI / ML model update includes: AI / ML model training, and The AI / ML model is updated based on the training results.

18. The communication method according to any one of claims 1-17, wherein, The first communication device includes a terminal device, and the second communication device includes a network device.

19. A communication method, comprising: Sending a first configuration message, wherein the first configuration message is used to indicate a first trigger condition, the first trigger condition being used to trigger a first communication device to send a wireless resource management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate the AI / ML prediction; and Receive RRM measurement reports based on AI / ML predictions.

20. The communication method according to claim 19, wherein the first triggering condition includes one of the following: The first communication device receives the first configuration message. The first RRM measurement result in the first communication device is lower than the first threshold within a first predetermined time period. The first communication device receives first indication information from the second communication device, wherein the first indication information is used to instruct the first communication device to send the AI / ML-predicted RRM measurement report.

21. The communication method according to claim 20, wherein the first indication information includes one or more of the following: AI / ML activation identifier information is used to activate RRM measurement reports based on AI / ML predictions. AI / ML index information is used to identify the corresponding Media Access Control-Control Unit (MAC-CE) indications and functions related to AI / ML-based RRM measurement inference and measurement reporting, or RRM measurement task identification information is used to identify the measurement task associated with the AI / ML prediction.

22. The communication method according to claim 19, further comprising: Receive a first response message, wherein the first response message is used to indicate that the configuration for the AI / ML prediction is applicable to the first communication device.

23. The communication method according to any one of claims 20-22, further comprising, when the first triggering condition is receiving first indication information from a second communication device: It is determined that the second RRM measurement result sent by the first communication device is lower than the third threshold within a second predetermined time period; as well as Send the first instruction message.

24. The communication method of claim 23, wherein the second RRM measurement result includes one or more of the following: Reference signal received power (RSRP). Reference signal reception quality (RSRQ), or Signal-to-interference-plus-noise ratio (SINR).

25. The communication method according to any one of claims 19-22, further comprising: Send a capability query message, wherein the query message is used to query the capability of the first communication device to support the AI / ML prediction-based RRM measurement report; Receive a capability response message, wherein the capability response message is used to instruct the first communication device to support the AI / ML-predicted RRM measurement report; and Send the first configuration message, wherein the first configuration message is used to instruct the first communication device to enable the AI / ML-predicted RRM measurement report.

26. The communication method according to any one of claims 19-22, wherein, The first configuration message is used to instruct the first communication device to disable the AI / ML-predicted RRM measurement report; as well as Receive RRM measurement reports based on the measurement results.

27. The communication method according to any one of claims 19-22, further comprising: Send a second configuration message, wherein the second configuration message is used to indicate a second triggering condition, the second triggering condition being used to trigger the first communication device to collect data for AI / ML model updates.

28. The communication method of claim 27, wherein the second triggering condition includes one of the following: Receive the second configuration message, The difference between the RRM measurement result predicted by AI / ML in the first communication device and the measured RRM measurement result is greater than or equal to the second threshold, or The first communication device receives a second instruction message, which is used to instruct the first communication device to collect the data used for AI / ML model updates.

29. The communication method according to claim 28, further comprising, when the second triggering condition is receiving second indication information from the second communication device: The difference between the AI / ML-predicted RRM measurement result and the measured RRM measurement result is greater than or equal to the fourth threshold. as well as Send the second instruction message.

30. The communication method according to claim 29, wherein, The second instruction message is also used to indicate the amount of data used for AI / ML model updates.

31. The communication method according to any one of claims 27-30, wherein, The AI / ML model update includes: AI / ML model training, and The AI / ML model is updated based on the training results.

32. The communication method according to any one of claims 19-31, wherein, The first communication device includes a terminal device, and the second communication device includes a network device.

33. A first communication device, comprising: A receiving module is configured to receive a first configuration message, wherein the first configuration message is used to configure an indication of a first triggering condition, and the first triggering condition is used to trigger a first communication device to send a wireless resource management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate the AI / ML prediction; as well as The sending module is used to send an RRM measurement report based on AI / ML prediction according to the first triggering condition.

34. A second communication device, comprising: A sending module is configured to send a first configuration message, wherein the first configuration message is configured to indicate a first triggering condition, and the first triggering condition is configured to trigger a first communication device to send a wireless resource management (RRM) measurement report based on artificial intelligence (AI) / machine learning (ML) prediction or to activate the AI / ML prediction; as well as The receiving module is used to receive RRM measurement reports based on AI / ML predictions.

35. A communication device, comprising: A processor and a memory storing instructions, which, when executed by the processor, cause the communication device to perform the method according to any one of claims 1 to 32.

36. A computer-readable storage medium storing instructions that, when executed, cause a communication device to perform the method according to any one of claims 1 to 32.

37. A chip comprising processing circuitry configured to perform the method according to any one of claims 1 to 32.

Images