Communication methods, devices, apparatuses, chips, storage media and software products

Abstract

This application relates to communication methods, devices, apparatuses, chips, storage media, and program products. In this method, a terminal device receives configuration from a network device for performance monitoring of a predictive model for Radio Resource Management (RRM) measurements. Based on the configuration, the terminal device performs performance monitoring for the predictive model. Based on the performance monitoring, the terminal device sends information related to the performance monitoring to the network device.

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 radio resource management (RRM) measurement and prediction. Background Technology

[0002] RRM measurement refers to the process by which network and terminal devices continuously collect, analyze, and evaluate information about the wireless environment and resource status. This information 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. Currently, RRM measurement prediction based on artificial intelligence / machine learning (AI / ML) predictive models has been identified as an AI / ML mobility management use case. However, the implementation of performance monitoring for RRM measurement prediction models is still imperfect and requires further research. Summary of the Invention

[0003] In view of the above problems, the embodiments of this application aim to provide a communication scheme for configuring and implementing performance monitoring of RRM measurement prediction models, thereby improving the stability of RRM measurement prediction functions and providing a reference for model management.

[0004] According to a first aspect of the embodiments of this application, a communication method is provided. The method can be executed by a terminal device. The method includes: receiving a configuration from a network device, the configuration being used for performance monitoring of a predictive model for Radio Resource Management (RRM) measurements; performing performance monitoring of the predictive model based on the configuration; and sending information related to the performance monitoring to the network device based on the performance monitoring.

[0005] According to a second aspect of the embodiments of this application, a communication method is provided. The method can be executed by a network device. The method includes: sending a configuration from the network device to a terminal device, the configuration being used for performance monitoring of a predictive model for RRM measurement; receiving information related to the performance monitoring from the terminal device; and based on the information, sending an instruction to the terminal device for managing the model.

[0006] According to a third aspect of the embodiments of this application, a communication apparatus is provided. The apparatus includes: a receiving component configured to receive a configuration for performance monitoring of a predictive model for RRM measurement; a processing component configured to perform performance monitoring of the predictive model based on the configuration; and a transmitting component configured to transmit information related to the performance monitoring to a network device based on the performance monitoring.

[0007] According to a fourth aspect of the embodiments of this application, a communication apparatus is provided. The apparatus includes: a transmitting component configured to transmit a configuration for performance monitoring of a predictive model for RRM measurement; a receiving component configured to receive information related to performance monitoring from a terminal device; and a transmitting component configured to transmit an instruction for managing the model to the terminal device based on the information.

[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 computer program code that, when executed by the processor, causes the method described according to the first or second aspect to be performed.

[0009] According to a sixth aspect of the embodiments of this application, a chip is provided. The chip includes a processor connected to a memory located inside or outside the chip, the memory being used to store a computer program, and the processor being used to call and run the computer program from the memory to cause the method according to the first aspect or the second aspect to be executed.

[0010] According to a seventh aspect of the embodiments of this application, a computer-readable storage medium is provided. The computer-readable storage medium includes machine-executable instructions that, when executed by a device, cause 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 computer program product is provided. The computer program product includes computer program code that, when executed by a device, causes the method described according to the first or second aspect to be performed.

[0012] 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

[0013] 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:

[0014] Figure 1A A schematic diagram of an example communication system that may be implemented in accordance with embodiments of this application is shown;

[0015] Figure 1B An example of RRM measurement prediction associated with an embodiment of this application is shown;

[0016] Figure 1CAnother example of RRM measurement prediction associated with embodiments of this application is shown;

[0017] Figure 1D A flowchart illustrating the configuration process of radio resource control (RRC) based on AI / ML functions associated with embodiments of this application is shown.

[0018] Figure 2 Signaling interaction diagrams according to some embodiments of this application are shown;

[0019] Figure 3 An example of RRM measurement prediction according to some embodiments of this application is shown;

[0020] Figure 4 Another example of RRM measurement prediction according to some embodiments of this application is shown;

[0021] Figure 5 Another example of RRM measurement prediction according to some embodiments of this application is shown;

[0022] Figure 6 An example process for performance monitoring according to some embodiments of this application is shown;

[0023] Figure 7 A flowchart illustrating a communication method implemented at a terminal device according to some embodiments of this application is shown;

[0024] Figure 8 A flowchart illustrating a communication method implemented at a network device according to some embodiments of this application is shown;

[0025] Figure 9 A schematic block diagram of an example communication device according to some embodiments of this application is shown;

[0026] Figure 10 A schematic block diagram of another example communication device according to some embodiments of this application is shown;

[0027] Figure 11 A simplified block diagram of a device suitable for implementing embodiments of this application is shown. Detailed Implementation

[0028] 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.

[0029] The term "terminal device" as used in this document refers to any terminal device capable of wireless communication. By way of example and not limitation, a terminal device may also be referred to as a communication device, user equipment (UE), user station (SS), portable user station, mobile station (MS), or access terminal (AT). Terminal devices may 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. In the following description, the terms “terminal equipment”, “communication equipment”, “terminal”, “user equipment” and “UE” are used interchangeably.

[0030] In this document, the term "network device" refers to a node in a communication network, including radio access network (RAN) nodes (also known as RAN devices) and / or core network (CN) nodes (also known as CN devices). The term "network side" can refer to the RAN device and / or CN device side.

[0031] The term "RAN equipment" refers to a RAN node through which terminal devices access the network and receive services. Depending on the terminology and technology used, network equipment 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 radiohead (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.

[0032] RAN equipment 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 a CU can also be called a gNB-CU, and a DU can also be called a 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, RAN equipment can also be implemented as a non-separated architecture.

[0033] The term "CN device" refers to a CN node, which terminal devices can access and receive services from via RAN devices. A CN device can provide one or more CN functions, such as access and mobility management (AMF), location management (LMF), application function (AF), ambient Internet of Things (A-IoT) function (AIOTF), network exposure function (NEF), authentication server function (AUSF), unified data management (UDM), session management function (SMF), and user plane function (UPF). It should be understood that a CN device can also provide any other known or future-developed CN functions.

[0034] 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.

[0035] 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.

[0036] Figure 1AA schematic diagram of an example communication system 100 that may be implemented according to embodiments of this application is shown. Figure 1A As shown, the communication system 100 may include at least one terminal device ( Figure 1A The diagram shows terminal devices 110-1 and 110-2 (hereinafter referred to as terminal device 110 for convenience) and at least one RAN device ( Figure 1A The diagram shows RAN devices 120-1 and 120-2, which, for convenience, will be collectively referred to as RAN device 120 below. RAN device 120 can provide one or more cells ( Figure 1A The diagram shows cell 121) used to serve one or more terminal devices.

[0037] Terminal device 110 can connect to RAN device 120 wirelessly. Terminal devices 110-1 and 110-2 can connect via wired or wireless means. RAN devices 120-1 and 120-2 can connect via wired or wireless means.

[0038] like Figure 1A As shown, the communication system 100 may further include a CN 130. The terminal device 110 can communicate with one or more CN devices (not shown) in the CN 130 via the RAN device 120. The RAN device 120 can be connected to the CN 130 wirelessly or via a wired connection. The RAN device 120 can be implemented as a physical device independent of the CN devices, or it can be implemented as a physical device integrating some of the functions of the CN devices.

[0039] It should be understood that Figure 1A 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.

[0040] The communication in communication system 100 can conform to any suitable communication standard, including but not limited to Global System for Mobile Communications (GSM), Long Term Evolution (LTE), LTE Evolution, LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), GSM EDGE Radio Access Network (GERAN), 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), 5G, sixth-generation (6G) communication protocols, or other existing or future suitable communication protocols.

[0041] 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.

[0042] In 5G NR systems regulated by the Third Generation Partnership Project (3GPP), the RRC protocol, as a core Layer 3 control protocol, has a measurement configuration mechanism that is a key technological foundation supporting mobility management and network optimization. This mechanism enables the network to intelligently perceive the wireless environment by dynamically configuring the measurement behavior of terminals, and provides data support for decisions such as handover and load balancing.

[0043] In 5G NR, RRC measurement configuration is primarily sent to terminals in the RRC_CONNECTED or RRC_INACTIVE state via dedicated signaling (such as RRCReconfiguration or RRCResume messages). The network uses a set of structured configuration parameters to precisely guide terminals on "when to measure," "what to measure," and "how to report." Key configuration elements include the measurement object (MeasObject), report configuration (ReportConfig), measurement identifier (MeasId), quantity configuration (quantityConfig), and measurement gap (measGapConfig & measGapSharingConfig).

[0044] The measurement object defines the target that the terminal needs to measure, such as a specific NR frequency or LTE carrier frequency. For NR measurement objects, MeasObject contains parameters such as frequency information, time location, and subcarrier spacing of the reference signal under test. The reference signal under test may include channel state information reference signal (CSI-RS), synchronization signal block (SSB), etc.

[0045] The report configuration specifies the triggering conditions for the terminal to report measurement results, mainly including event triggering, periodic triggering, and other methods.

[0046] Measurement identifiers act as a "bridge" connecting measurement objects and report configurations, associating a measurement object with a report configuration. By configuring multiple measurement identifiers, flexible measurement strategies can be implemented.

[0047] The quantity configuration is used to configure how the terminal calculates and filters the measured values ​​when performing RRM measurements. The measured values ​​may include reference signal receiving power (RSRP), reference signal receiving quality (RSRQ), signal to interference plus noise ratio (SINR), etc.

[0048] When a terminal needs to measure a signal at a different frequency than the current serving cell (inter-frequency / inter-system measurement), the network will configure a specific measurement interval for it. During this period, the terminal will suspend data transmission and reception with the serving cell and tune its radio frequency unit to the target frequency for measurement.

[0049] To address the characteristics of 5G NR multi-beam transmission, its measurement model incorporates multi-layer filtering and processing mechanisms to ensure the accuracy and stability of measurement results. The advanced measurement model is defined to cover the following processing flow from the physical layer to the RRC layer: physical layer filtering, beam combining / selection, and layer-3 filtering.

[0050] First, the terminal performs preliminary filtering on measurement samples of individual beams (such as SSB measurements) at the physical layer to obtain beam-specific measurements. Then, the terminal merges or selects measurements from multiple beams to synthesize a cell-level quality measurement (such as the cell's SS-RSRP). This process is identical for the serving cell and neighboring cells. Finally, the RRC layer filters the cell-level quality measurements again to smooth out the effects of rapid channel fluctuations. The filtered result is used for the final reporting criterion evaluation.

[0051] In addition, the network can be configured to report beam measurement information. The terminal will select several beams with the best signal quality from all measured beams, and report their identification and measurement results together, providing a more refined basis for the network's beam-level management.

[0052] The terminal's measurement capabilities cover all its RRC states, but its behavior varies depending on the state. In the RRC_IDLE and RRC_INACTIVE states, measurements are primarily used for cell selection and reselection. In the RRC_CONNECTED state, measurements serve more complex radio resource management tasks such as handover and beam management. The terminal needs to support intra-frequency, inter-frequency, and inter-system measurements, for example, during handover to an LTE system.

[0053] Key measurements include synchronization signal reference signal receiving power (SS-RSRP) and synchronization signal reference signal receiving quality (SS-RSRQ). These measurements are essential for evaluating the signal strength and quality of cells and beams.

[0054] RRC measurement configuration mechanism is the cornerstone of 5G NR mobility management. Based on the measurement results reported by the terminal, the network can intelligently trigger the handover process. For example, when the terminal detects that the signal quality of the neighboring cell is better than that of the current serving cell and meets a certain offset (i.e., triggering the "A3 event"), it will report a measurement report, and the network will initiate a handover accordingly, thereby ensuring service continuity.

[0055] Furthermore, this mechanism also supports automatic neighbor cell relationship functionality. When a terminal moves towards a cell that is not configured as a neighbor cell but has good signal quality, it can report the physical cell identifier (PCI) of that cell. The network can then automatically add it as a neighbor cell by configuring the terminal to read information such as the cell global identifier (CGI), significantly reducing manual maintenance costs.

[0056] Recent detailed discussions on the application of AI / ML in mobility management have identified use cases for AI / ML algorithms in mobility management. These studies primarily explore RRM measurement and measurement event prediction in the time and frequency domains to understand the feasibility and performance of achieving measurement reduction or handover performance improvement based on AI / ML algorithms. Simulation evaluations were used to analyze the impact of user equipment-side and network-side models on specifications for the described scenarios.

[0057] In time-domain measurement prediction, the RSRP of SSB is used as both the input and output of the model, and both time-domain prediction use cases are studied in the standardization work. The following section combines... Figure 1B and Figure 1C Some examples describing time-domain measurement prediction methods.

[0058] Figure 1B An example of RRM measurement prediction associated with an embodiment of this application is shown. This RRM measurement prediction is an example of time-domain use case A for co-frequency measurement. Figure 1B As shown, the prediction model deployed on the UE side takes RRM measurements at time instances within the OW (Open Time) as input data and outputs predicted values ​​at time instances within the PW (Predicted Time). Then, the OW and PW slide forward in units of sampling periods or measurement periods. In this use case A, measurement and prediction occur simultaneously; that is, each prediction instance has its corresponding measurement instance.

[0059] Figure 1C Another example of RRM measurement prediction associated with an embodiment of this application is shown. This RRM measurement prediction is Example 2 of the omitted mode of co-frequency measurement time domain use case B. The prediction model deployed on the UE side skips measurements on partial time instances according to a preset skipping pattern, taking the data in the measured time slot as input and outputting the predicted value in the skipped time slot. OW and PW slide forward in units of sampling period (with sliding L1 / L3 filtering option) or measurement period (with non-sliding L1 / L3 filtering option), where measurement results in the previous PW are skipped during window sliding. In this use case B, measurement and prediction are performed separately, i.e., measurement or prediction is performed within a certain time slot.

[0060] In addition to time-domain measurements, the model will also be used for inter-frequency measurement prediction, that is, to predict measurement data at other frequencies using data from the measured frequency.

[0061] In Release-19, AI / ML-based RRM measurement prediction was identified as effective in reducing measurement and handover failure rates. However, relying on model-based predictions also introduces inherent instability. Therefore, when deploying measurement prediction models, appropriate performance monitoring should be configured to monitor the model's output. When model performance deteriorates, the performance monitoring module can pinpoint the issue in real time and manage the model through the Lifecycle Management (LCM) module to ensure the stability of mobility management.

[0062] LCM is mainly divided into the model training, distribution and deployment phase and the model operation and management phase.

[0063] The application of AI / ML models in networks can be mainly divided into two stages. The first stage is model generation, which involves the training, distribution, and deployment of the model. Currently, 3GPP has not yet finalized the training, transmission, and specific deployment methods for AI / ML models, but a preliminary consensus has been reached on the aspects that need to be standardized. These mainly include the following modules: data collection, model training, model identification, and model delivery.

[0064] The data collection module provides data support for model training, inference, and performance monitoring. The model training module trains the model using the collected data to meet different functional requirements. The model identification module identifies the model to ensure consistency in model perception among different network entities. The model transmission module enables the transmission of the model between network entities in a standard format.

[0065] Once the model is deployed and operational in the network, network entities need to provide the necessary data support and implement real-time monitoring of the model through a management framework to ensure its long-term stable operation within the network. This stage primarily involves the following functional modules: Model Inference, Model Management, and Model Monitoring.

[0066] The model inference module performs inference operations based on input data and outputs results. The model management module includes operations such as selection, deactivation, switching, and updating, used to dynamically manage deployed models to adapt to changes in network and wireless environments. The model monitoring module monitors model performance in real time to prevent potential performance degradation, model failure, and other problems.

[0067] In the AI ​​air interface standard, a general-function-based LCM procedure has been proposed, and model performance monitoring is also configured through this procedure. As shown in 1D, the network obtains the UE's AI / ML suitability information through RRC signaling, and configures the UE's AI / ML functions (including activation, deactivation, inference, and performance monitoring) through RRC reconfiguration signaling.

[0068] In CSI prediction use cases, model performance monitoring is configured using a reused CSI configuration framework, and the monitoring report is configured as a dedicated CSI feedback report. Relevant configuration parameters are included in the newly added information element (IE) "configurationForCSI-Monitoring-r19". The dedicated performance monitoring CSI report is sent via L1 signaling and supports semi-persistent and aperiodic reporting. After receiving the configuration from the network side, the UE calculates performance metrics using the corresponding measurement and inference resources. When the network side triggers monitoring reporting via signaling, the UE will send the monitoring report to the network side according to the report configuration.

[0069] In 5G-Advanced and 6G communication systems, AI / ML models have been deeply applied in the field of Radio Resource Management (RRM). In the 3GPP Release 19 / 20 standard, AI / ML models are deployed in the Mobility Management Module (MLM) to receive time-domain / frequency-domain RRM measurement parameters (such as SSB Reference Signal Received Power (RSRP)) and output predicted results based on a predetermined prediction window, thus assisting in handover decisions. However, limitations in model generalization ability still exist.

[0070] When the statistical characteristics of the input data during the inference phase (such as the distribution of measured values ​​and channel characteristics) produce a domain shift compared to the training dataset, or when there is a sudden change in the electromagnetic propagation environment of the terminal device, the model's predicted output will deviate significantly from the actual measured values. This prediction bias will directly lead to suboptimal decisions such as handover being too early or too late, or incorrect target cell selection, severely impacting key performance indicators of user equipment such as throughput and latency.

[0071] Furthermore, the current 5G NR system has not yet established a standardized performance monitoring framework for AI / ML mobility management models. If the traditional measurement reporting mechanism is used (e.g., the UE periodically reports measurement reports and the base station performs real-time calculation and verification), it will face three core contradictions: latency conflict, data confusion, and model interference.

[0072] Latency discrepancy refers to the mismatch between the measurement reporting period (typically 20-640ms) and the model prediction window (typically 5-40ms), causing performance verification to lag behind decision execution. Data confusion refers to the base station simultaneously receiving actual measurement values ​​and model prediction values, making it difficult to establish a reliable benchmark in dynamic network environments. Model interference refers to the coupling of prediction outputs between different models in scenarios with multiple models deployed in parallel, making it impossible to effectively trace the model whose performance has deteriorated.

[0073] The aforementioned shortcomings restrict the reliable application of AI / ML models in mobility management scenarios. It is necessary to establish a performance monitoring system that matches the characteristics of AI / ML to provide a closed-loop control basis for the model's LCM.

[0074] In view of this, embodiments of this application propose a communication scheme. In this scheme, a terminal device receives a configuration from a network device, which is used for performance monitoring of a predictive model for RRM measurement. Based on this configuration, the terminal device performs performance monitoring for the predictive model. Based on the performance monitoring, the terminal device sends information related to the performance monitoring to the network device.

[0075] Therefore, performance monitoring of the prediction model can be performed on the terminal device side, and information related to performance monitoring can be reported to the network side. The network device side can then manage the model based on the received performance monitoring information. This enables performance monitoring of the RRM measurement prediction model, thereby improving its performance and enhancing the real-time performance and reliability of mobility decision-making and beam management.

[0076] The following is in conjunction with the appendix Figures 2 to 11 The principles and implementation of this solution are described in detail.

[0077] Figure 2 A schematic diagram of an example communication process 200 according to some embodiments of this application is shown. Communication process 200 may involve a terminal device 201 and a network device 202. Terminal device 201 may be implemented as follows: Figure 1A The terminal device 110 and network device 202 shown can be implemented as follows: Figure 1A The RAN device 120 and / or CN device 130 are shown. It should be understood that...

[0078] like Figure 2As shown, in step 210, network device 202 sends a configuration to terminal device 201, which is used for performance monitoring of the prediction model for RRM measurement. Correspondingly, terminal device 201 receives the configuration from network device 202. For example, when configuring RRM measurement, the network side can add an IE (Internet Interface) for configuring RRM measurement prediction model performance monitoring to the measurement configuration and send this configuration information to the UE.

[0079] In some embodiments, the configuration indicates: one or more objects of the performance monitoring, first periodic information for performing the performance monitoring, second periodic information for sending the information, a first number of time instances for performing the performance monitoring, threshold information for determining the result of the performance monitoring, trigger information for sending the information, or a combination of one or more of the above. The bearer signaling carrying this configuration includes, but is not limited to, RRC reconfiguration messages.

[0080] Additionally or alternatively, one or more of the objects of the performance monitoring include: a predictive model for the RRM measurement, the functionality of the predictive model, or a combination of the two.

[0081] In one example, the configuration may include a first performance monitoring indication for informing the terminal device 201 of the applicable objects of the performance monitoring configuration. The first performance monitoring indication may include a model identifier (ID) for uniquely identifying the AI / ML model for time-domain use case A or time-domain use case B. The first performance monitoring indication may include a function ID for identifying a functional module related to RRM measurement prediction, such as a prediction module.

[0082] Alternatively or concurrently, the first period information may include: a second number of consecutive monitoring periods, a period value based on a time unit, or a combination of the two.

[0083] The first cycle information is used to instruct the terminal device 201 on the timing rules for the UE to perform performance monitoring, which can indicate the cycle in which the performance monitoring is performed. When the prediction model is deployed and running, the terminal device 201 can monitor the predicted values ​​output by the model and calculate performance indicators according to this cycle.

[0084] In one example, the first period information can be configured based on the number of monitoring periods. For instance, the first period information could include a positive integer X, representing the number of executions over X consecutive monitoring periods. Figure 3 In the time-domain use case A shown, each monitoring period can include one observation window and one prediction window. In, for example... Figure 4 or Figure 5 In the time-domain use case B shown, each monitoring cycle can contain N "measurement-prediction pairs".

[0085] In another example, the first period information can be configured based on a time unit. For example, the first period information can include a period value in units of slot, millisecond (ms), or system frame number (SFN).

[0086] Alternatively or concurrently, the second period information may include: a third number of continuous monitoring periods, a period value based on a time unit, or a combination of the two.

[0087] The second period information is used to indicate the period at which the terminal device 201 feeds back performance monitoring results to the network device 202.

[0088] In one example, the second period information can be configured based on the number of monitoring periods. For instance, the second period information could include a positive integer Y, indicating that a result report is triggered after every Y monitoring periods are completed.

[0089] In another example, the second period information can be configured based on a time unit. For example, the second period information can include feedback intervals in time slots, milliseconds, or absolute timestamps.

[0090] Alternatively or additionally, the configuration may include a first parameter, namely a first number of time instances for performing performance monitoring, which indicates the number N of time instances N used by the UE to calculate model performance metrics. In other words, the first parameter may indicate a fourth number of time instances used by the terminal device 201 to calculate or determine whether the model performance metrics meet a threshold. The unit of time instance is a time slot or subframe, and N is a dynamically configurable positive integer.

[0091] In such Figure 3 In the time-domain use case A shown, the terminal device 201 can perform statistical calculations by taking the measured values ​​and corresponding predicted values ​​within the most recent N time instances based on the sliding window mechanism.

[0092] In such Figure 4 or Figure 5 In the time-domain use case B shown, the first parameter indicates the “measurement-prediction pair” over the most recent N time instances used for performance metric calculation.

[0093] Additionally or alternatively, the threshold information may include: a first threshold for the average difference between the predicted and measured values ​​for RRM measurements; a second threshold for the difference between the predicted and measured values ​​determined based on historical RRM measurement statistics; a joint judgment condition for one or more performance indicators of the predicted and measured values ​​for RRM measurements; or a combination of one or more of the above.

[0094] Threshold information is used to instruct terminal device 201 on metrics for judging model performance. Threshold information may include thresholds used to determine whether model performance meets requirements. When terminal device 201 calculates that the model performance metric for the most recent one or more times is less than or greater than the threshold, it indicates that the model performance has deteriorated. In this case, terminal device 201 needs to report the monitoring results and perform model management operations based on feedback from network device 202 to ensure the stability of mobility management.

[0095] In the first example, the first threshold can be an absolute threshold value. For example, the upper limit of the average deviation between the predicted value and the measured value, expressed in decibels (dB).

[0096] In the second example, the second threshold can be a relative threshold value. For example, a dynamic threshold based on historical data statistics (such as mean ± K times standard deviation).

[0097] In the third example, the joint decision condition can be a combination of multiple indicators (such as mean square error and confidence interval).

[0098] Additionally or alternatively, the trigger information may include: an identifier of the type of trigger event used to send the information, threshold information used to determine the results of performance monitoring, a fourth number of time instances used to perform performance monitoring, the type of RRM measurement used to determine one or more trigger conditions of the trigger event, or a combination of one or more of the above.

[0099] Trigger information, also known as event-triggered reporting configuration, is used to instruct terminal device 201 to trigger the reporting of monitoring results when it detects a degradation in the performance of the measurement prediction model.

[0100] In the first example, the triggering information may include an event type identifier to specify the type of event that triggered the event. For example, the event type could be AI / ML related, indicating the status of the AI / ML model corresponding to the performance monitoring result report, such as performance degradation.

[0101] In the second example, the triggering information may include a first threshold, i.e., threshold information. The first threshold can be configured as a decibel value to represent the threshold of the average deviation between the predicted value and the measured value.

[0102] In the third example, the triggering information may include a first parameter, namely, a fourth number of time instances used to perform performance monitoring. The first parameter indicates the number of time instances used by the terminal device 201 to calculate or determine whether the model performance metrics meet a first threshold. It should be understood that the fourth number may be the same as or different from the first number mentioned above.

[0103] In the fourth example, the trigger information may include a trigger quantity, indicating the type of measurement used for event determination, including RSRP, RSRQ, or SINR.

[0104] In this way, an optional configuration method for reporting monitoring results is provided for AI / ML-based event types that may be added in 6G. This method is suitable for scenarios where user equipment, after receiving configuration from the network side, autonomously judges and reports performance monitoring results based on preset event conditions.

[0105] Continue to refer to Figure 2 In step 220, the terminal device 201 performs performance monitoring of the prediction model based on the configuration.

[0106] In some embodiments, in order to perform performance monitoring for a predictive model, terminal device 201 may determine, based on first period information, the average difference between the predicted and measured values ​​of the RRM measurement over a first consecutive number of time instances. Based on determining whether the average difference is greater than a first threshold, terminal device 201 may determine whether the performance monitoring is normal.

[0107] In some embodiments, to perform performance monitoring for a predictive model, terminal device 201 may determine, based on first period information, the average difference between predicted and measured values ​​of RRM measurements over a first consecutive number of time instances. Based on whether the average difference is greater than a second threshold, terminal device 201 may determine whether the performance monitoring is normal. This second threshold is determined based on historical RRM measurement statistics.

[0108] Additionally or alternatively, in order to determine the average difference between the predicted and measured values ​​of RRM measurements over a first number of consecutive time instances, the terminal device 201 may determine the average difference based on the difference between the predicted and measured values ​​for each of the first number of time instances.

[0109] In such Figure 3 In the time-domain use case A shown, one possible way to calculate the average difference is as follows: (1)

[0110] in, This represents the performance metric, specifically the average difference. N is the first number of time instances in the configuration used to perform the performance monitoring. Represents the first metric used to calculate performance indicators. One RRM measurement value, Represents the first metric used to calculate performance indicators. One RRM prediction value.

[0111] Alternatively, in order to determine the average difference between the predicted and measured values ​​of RRM measurements over a first consecutive number of time instances, the terminal device 201 may determine the average difference based on the difference between the predicted value of at least one first time instance and the measured value of the RRM measurement of at least one corresponding second time instance in the first consecutive number of time instances.

[0112] In such Figure 4 In the time-domain use case B shown, there are N measurement prediction pairs in one measurement cycle, where the number of measurement time instances and prediction time instances are the same. It should be understood that the number of measurement time instances and prediction time instances may also be different.

[0113] One possible way to calculate the average difference is as follows: (2)

[0114] in, This represents the performance metric, specifically the average difference. N is the number of "measurement-prediction pairs". Represents the first metric used to calculate performance indicators. One RRM measurement value, Represents the first metric used to calculate performance indicators. One RRM prediction value. When performance metrics When the value exceeds the threshold, it indicates that the performance of the measurement prediction model has deteriorated, and the results of this performance monitoring are abnormal.

[0115] In addition, the terminal device 201 can also perform performance monitoring of the prediction model based on the difference between the measured prediction pairs.

[0116] In such Figure 5 In the time-domain use case B shown, one possible way to calculate the average difference is as follows: (3)

[0117] in, Indicates the first The performance metric for each "measurement-prediction pair" is the difference. N is the number of measurement-prediction pairs. Represents the first metric used to calculate performance indicators. One RRM measurement value, Represents the first metric used to calculate performance indicators. RRM predicted values. When N consecutive performance metrics... When the value exceeds the threshold, it indicates that the performance of the measurement prediction model has deteriorated, and the results of this performance monitoring are abnormal.

[0118] Continue to refer to Figure 2In step 230, the terminal device 201 sends performance monitoring-related information to the network device 202 based on performance monitoring.

[0119] In some embodiments, terminal device 201 may send performance monitoring-related information to network device 202 based on second periodic information.

[0120] For example, if the configuration includes second periodic information for sending the information, the terminal device 201 reports the most recent or multiple performance monitoring results according to the period indicated by the second periodic information.

[0121] In some embodiments, if at least one of one or more triggering conditions is met, the terminal device 201 may send information related to performance monitoring to the network device 202.

[0122] As an additional embodiment where at least one of one or more triggering conditions is met, terminal device 201 can determine the average difference between the predicted and measured values ​​of RRM measurements over a first consecutive number of time instances. Based on determining whether the average difference is greater than a first threshold, terminal device 201 can determine whether to send performance monitoring-related information to the network device.

[0123] As an additional embodiment where at least one of one or more triggering conditions is met, terminal device 201 can determine the average difference between predicted and measured values ​​of RRM measurements over a first consecutive number of time instances. Based on determining whether the average difference is greater than a second threshold, terminal device 201 can determine whether to send performance monitoring-related information to the network device. This second threshold is determined based on historical RRM measurement statistics.

[0124] In an example of SSB-RSRP measurement prediction in a time-domain use case A, terminal device 201 periodically performs performance monitoring of the prediction model after receiving configuration including trigger information. When the average deviation of the "predicted value - measured value" pair over the most recent N time instances, i.e., the performance metric of the prediction model, exceeds a first threshold or a second threshold, terminal device 201 triggers a performance monitoring result report.

[0125] With the above configuration, network device 202 can flexibly transform any threshold-based monitoring logic into a standardized event-triggered mechanism, thereby significantly reducing signaling overhead.

[0126] In some embodiments, the information may include at least one of the following: the results of performance monitoring, indicating whether the performance of the prediction model is normal; performance metrics at at least one time instance before sending the information, the performance metrics being determined based on the predicted and measured values ​​of the RRM measurement; the average value of the performance metrics at at least one time instance before sending the information; the predicted value of the RRM measurement at at least one time instance before sending the information; or the measured value of the RRM measurement at at least one time instance before sending the information.

[0127] In the first example, the information may include a first result indication to indicate to network device 202 the result of performance monitoring, i.e., whether model performance degradation has been detected (whether the performance metric meets the threshold information). When terminal device 201 is configured to periodically report monitoring results, the first result indication may indicate whether the performance monitoring result is normal or abnormal. When terminal device 201 is configured to trigger a threshold, the first result indication indicates that the performance monitoring result is abnormal.

[0128] In the second example, the information may include model performance metrics calculated from predicted and measured values ​​from one or more time instances prior to the reporting of this monitoring result.

[0129] In the third example, this information may include measurements or sequences, that is, measurements taken at one or more time instances prior to the reporting of monitoring results. For example, .

[0130] In the fourth example, this information may include predicted values ​​or sequences, i.e., predicted values ​​at one or more time instances prior to the reporting of monitoring results, for example, .

[0131] Additionally, the signaling that carries information related to performance monitoring includes, but is not limited to, RRC signaling (e.g., MeasurementReport), medium access control element (MAC CE), and uplink control information (UCI).

[0132] Continue to refer to Figure 2 In step 240, after receiving performance monitoring-related information from terminal device 201, network device 202 sends an instruction for management model to terminal device 201 based on the information.

[0133] In summary, process 200 provides a performance monitoring configuration method for RRM measurement and prediction. Network device 202 uses this method to configure a performance monitoring module for the RRM measurement and prediction model on terminal device 201. Through this configuration, terminal device 201 performs performance monitoring according to the requirements of network device 202 and feeds back the monitoring results to network device 202, assisting it in performing lifecycle management of the model when its performance deteriorates, thereby improving the real-time performance and reliability of mobility decision-making and beam management.

[0134] Figure 6 An example process 600 for performance monitoring according to some embodiments of this application is illustrated. Process 600 may include a network side 601 and a user side 602. Process 600 can be considered as an example implementation of process 200. For ease of discussion, process 600 will be referred to Figure 2 Describe it. The network side 601 can be... Figure 2 Example of network device 202, network device 202 can be Figure 2 Example of a terminal device 201.

[0135] In step 610, network side 601 sends an RRC reconfiguration message to user side 602, performing measurement configuration on the UE through RRC reconfiguration, and carrying first performance monitoring configuration information in the measurement settings. This first performance monitoring configuration information includes: first performance monitoring indication, first monitoring period, first reporting period, first threshold, and first parameter. This first performance monitoring configuration information is the same as the configuration in process 200, and will not be described again here.

[0136] In step 620, after receiving the RRC reconfiguration and confirming the configuration completion, the user-side 602 performs performance monitoring based on the obtained first performance monitoring configuration. For example, performance monitoring is performed according to the first monitoring cycle. Specific embodiments are described in process 200, and will not be repeated here.

[0137] In step 630, the user-side 602 calculates performance metrics according to the first parameter of the configured time instance and determines whether they meet the first threshold. If the performance metrics of the prediction model in the most recent one or more measurements do not meet the first threshold, it indicates that the model performance has deteriorated, and the user-side 602 reports the performance monitoring results. Simultaneously, if the first performance monitoring information includes a first reporting period, the user-side 602 reports the performance monitoring results of the most recent one or more measurements according to the first reporting period.

[0138] In step 640, network side 601 performs model management operations, including activation / deactivation, model switching, and updates. Network side 601 can determine the model management strategy based on the trigger information and / or reported information received in step 630, and issue corresponding model management instructions to user side 602, so that user side 602 can complete the activation, deactivation, switching, or updating of the model according to the instructions.

[0139] Corresponding to the communication process 200 described above, embodiments of this application also provide a communication method that can be implemented at terminal devices and network devices. Figure 7 A flowchart of a communication method 700 implemented at a terminal device according to an embodiment of this application is shown. It should be understood that method 700 may include other additional steps not shown, or some steps shown may be omitted. The scope of this application is not limited thereto.

[0140] In step 710, the terminal device (e.g., terminal device 201) receives a configuration for performance monitoring of the predictive model for RRM measurement.

[0141] In step 720, the terminal device performs performance monitoring on the prediction model based on the configuration.

[0142] In step 730, the terminal device sends performance monitoring-related information to the network device based on performance monitoring.

[0143] In some embodiments, the configuration may indicate at least one of the following: one or more objects for performance monitoring; first periodic information for performing performance monitoring; second periodic information for sending information; a first number of time instances for performing performance monitoring; threshold information for determining the results of performance monitoring; or trigger information for sending information.

[0144] In some embodiments, one or more objects of performance monitoring may include at least one of the following: a predictive model for RRM measurement; or the functionality of the predictive model.

[0145] In some embodiments, the first period information may include at least one of the following: a second number of consecutive monitoring periods; or a period value based on a time unit.

[0146] In some embodiments, the second period information may include at least one of the following: a third number of continuous monitoring periods; or a period value based on a time unit.

[0147] In some embodiments, the threshold information may include at least one of the following: a first threshold for the average difference between the predicted value and the measured value for RRM measurement; a second threshold for the difference between the predicted value and the measured value determined based on historical RRM measurement statistics; or a joint judgment condition for one or more performance metrics of the predicted value and the measured value for RRM measurement.

[0148] In some embodiments, the trigger information may include at least one of the following: an identifier of the type of trigger event used to send the information; threshold information used to determine the result of performance monitoring; a fourth number of time instances used to perform performance monitoring; and the type of RRM measurement used to determine one or more trigger conditions of the trigger event.

[0149] In some embodiments, performing performance monitoring for the predictive model may include: determining, based on first period information, the average difference between the predicted and measured values ​​of RRM measurements over a first consecutive number of time instances; and determining whether the performance monitoring is normal based on whether the average difference is greater than a first threshold or a second threshold, wherein the second threshold is determined based on historical RRM measurement statistics.

[0150] In some embodiments, sending performance monitoring-related information to a network device may include one of the following: sending performance monitoring-related information to a network device based on second periodic information; or sending performance monitoring-related information to a network device based on determining that at least one of one or more trigger conditions is met.

[0151] In some embodiments, determining that at least one of one or more trigger conditions is met may include: determining the average difference between predicted and measured values ​​of RRM measurements over a first consecutive number of time instances; and determining whether to send performance monitoring-related information to the network device based on whether the average difference is greater than a first threshold or a second threshold, wherein the second threshold is determined based on historical RRM measurement statistics.

[0152] In some embodiments, determining the average difference between the predicted and measured values ​​of RRM measurements over a first consecutive number of time instances may include one of the following: determining the average difference based on the difference between the predicted and measured values ​​of each time instance in the first number of time instances; or determining the average difference based on determining the difference between the predicted value of at least one first time instance and the measured value of the RRM measurement of at least one corresponding second time instance in the first consecutive number of time instances.

[0153] In some embodiments, the information may include at least one of the following: the results of performance monitoring, indicating whether the performance of the prediction model is normal; performance metrics at at least one time instance before sending the information, the performance metrics being determined based on the predicted and measured values ​​of the RRM measurement; the average value of the performance metrics at at least one time instance before sending the information; the predicted value of the RRM measurement at at least one time instance before sending the information; or the measured value of the RRM measurement at at least one time instance before sending the information.

[0154] Figure 8 A flowchart of a communication method 800 implemented at a network device according to an embodiment of this application is shown. It should be understood that method 800 may include other additional steps not shown, or some steps shown may be omitted. The scope of this application is not limited thereto.

[0155] In step 810, the network device (e.g., network device 202) sends a configuration to configure performance monitoring of the predictive model for RRM measurement.

[0156] In step 820, the network device receives information related to performance monitoring from the terminal device.

[0157] In step 830, the network device sends an instruction for the management model to the terminal device based on the information.

[0158] In some embodiments, the configuration may indicate at least one of the following: one or more objects for performance monitoring; first periodic information for performing performance monitoring; second periodic information for sending information; a first number of time instances for performing performance monitoring; threshold information for determining the results of performance monitoring; or trigger information for sending information.

[0159] In some embodiments, one or more objects of performance monitoring may include at least one of the following: a predictive model for RRM measurement; or the functionality of the predictive model.

[0160] In some embodiments, the first period information may include at least one of the following: a second number of consecutive monitoring periods; or a period value based on a time unit.

[0161] In some embodiments, the second period information may include at least one of the following: a third number of continuous monitoring periods; or a period value based on a time unit.

[0162] In some embodiments, the threshold information may include at least one of the following: a first threshold for the average difference between the predicted value and the measured value for RRM measurement; a second threshold for the difference between the predicted value and the measured value determined based on historical RRM measurement statistics; or a joint judgment condition for one or more performance metrics of the predicted value and the measured value for RRM measurement.

[0163] In some embodiments, the trigger information may include at least one of the following: an identifier of the type of trigger event used to send the information; threshold information used to determine the result of performance monitoring; a fourth number of time instances used to perform performance monitoring; and the type of RRM measurement used to determine one or more trigger conditions of the trigger event.

[0164] In some embodiments, the information may include at least one of the following: the results of performance monitoring, indicating whether the performance of the prediction model is normal; performance metrics at at least one time instance before sending the information, the performance metrics being determined based on the predicted and measured values ​​of the RRM measurement; the average value of the performance metrics at at least one time instance before sending the information; the predicted value of the RRM measurement at at least one time instance before sending the information; or the measured value of the RRM measurement at at least one time instance before sending the information.

[0165] It should be understood that the description of communication process 200 also applies to the above-mentioned communication methods 700 and 800, so other details will not be repeated.

[0166] Corresponding to the above communication method, embodiments of this application also provide a communication device, which is described below in conjunction with... Figure 9 and Figure 10 This will be described.

[0167] Figure 9 A schematic block diagram of an example communication device 900 according to an embodiment of this application is shown. The communication device 900 may be implemented at a terminal device (e.g., terminal device 201). The communication device 900 may be part of the terminal device or the terminal device itself. It should be understood that the communication device 900 may include more additional components than those shown or omit some of the components shown, and this embodiment of the application does not limit this.

[0168] like Figure 9 As shown, the communication device 900 may include a receiving unit 910, a processing unit 920, and a transmitting unit 930. The receiving unit 910 may be configured to receive configuration for performance monitoring of a predictive model used for RRM measurement. The processing unit 920 may be configured to perform performance monitoring of the predictive model based on the configuration. The transmitting unit 930 may be configured to send performance monitoring-related information to network devices based on the performance monitoring.

[0169] In some embodiments, the configuration may indicate at least one of the following: one or more objects for performance monitoring; first periodic information for performing performance monitoring; second periodic information for sending information; a first number of time instances for performing performance monitoring; threshold information for determining the results of performance monitoring; or trigger information for sending information.

[0170] In some embodiments, one or more objects of performance monitoring may include at least one of the following: a predictive model for RRM measurement; or the functionality of the predictive model.

[0171] In some embodiments, the first period information may include at least one of the following: a second number of consecutive monitoring periods; or a period value based on a time unit.

[0172] In some embodiments, the second period information may include at least one of the following: a third number of continuous monitoring periods; or a period value based on a time unit.

[0173] In some embodiments, the threshold information may include at least one of the following: a first threshold for the average difference between the predicted value and the measured value for RRM measurement; a second threshold for the difference between the predicted value and the measured value determined based on historical RRM measurement statistics; or a joint judgment condition for one or more performance metrics of the predicted value and the measured value for RRM measurement.

[0174] In some embodiments, the trigger information may include at least one of the following: an identifier of the type of trigger event used to send the information; threshold information used to determine the result of performance monitoring; a fourth number of time instances used to perform performance monitoring; and the type of RRM measurement used to determine one or more trigger conditions of the trigger event.

[0175] In some embodiments, performing performance monitoring for the predictive model may include: determining, based on first period information, the average difference between the predicted and measured values ​​of RRM measurements over a first consecutive number of time instances; and determining whether the performance monitoring is normal based on whether the average difference is greater than a first threshold or a second threshold, wherein the second threshold is determined based on historical RRM measurement statistics.

[0176] In some embodiments, sending performance monitoring-related information to a network device may include one of the following: sending performance monitoring-related information to a network device based on second periodic information; or sending performance monitoring-related information to a network device based on determining that at least one of one or more trigger conditions is met.

[0177] In some embodiments, determining that at least one of one or more trigger conditions is met may include: determining the average difference between predicted and measured values ​​of RRM measurements over a first consecutive number of time instances; and determining whether to send performance monitoring-related information to the network device based on whether the average difference is greater than a first threshold or a second threshold, wherein the second threshold is determined based on historical RRM measurement statistics.

[0178] In some embodiments, determining the average difference between the predicted and measured values ​​of RRM measurements over a first consecutive number of time instances may include one of the following: determining the average difference based on the difference between the predicted and measured values ​​of each time instance in the first number of time instances; or determining the average difference based on determining the difference between the predicted value of at least one first time instance and the measured value of the RRM measurement of at least one corresponding second time instance in the first consecutive number of time instances.

[0179] In some embodiments, the information may include at least one of the following: the results of performance monitoring, indicating whether the performance of the prediction model is normal; performance metrics at at least one time instance before sending the information, the performance metrics being determined based on the predicted and measured values ​​of the RRM measurement; the average value of the performance metrics at at least one time instance before sending the information; the predicted value of the RRM measurement at at least one time instance before sending the information; or the measured value of the RRM measurement at at least one time instance before sending the information.

[0180] Figure 10 A schematic block diagram of another example communication device 1000 according to an embodiment of this application is shown. The communication device 1000 may be implemented at a network device (e.g., network device 202). The communication device 1000 may be part of the network device or the network device itself. It should be understood that the communication device 1000 may include more additional components than those shown or omit some of the components shown, and this embodiment of the application does not impose limitations in this regard.

[0181] like Figure 10 As shown, the communication device 1000 may include a first transmitting unit 1010, a processing unit 1020, and a second transmitting unit 1030. The first transmitting unit 1010 may be configured to transmit a configuration to a terminal device for performance monitoring of a predictive model for RRM measurements. The processing unit 1020 may be configured to receive information related to performance monitoring from the terminal device. The transmitting unit 1030 may be configured to send instructions for managing the model to the terminal device based on the information.

[0182] In some embodiments, the configuration may indicate at least one of the following: one or more objects for performance monitoring; first periodic information for performing performance monitoring; second periodic information for sending information; a first number of time instances for performing performance monitoring; threshold information for determining the results of performance monitoring; or trigger information for sending information.

[0183] In some embodiments, one or more objects of performance monitoring may include at least one of the following: a predictive model for RRM measurement; or the functionality of the predictive model.

[0184] In some embodiments, the first period information may include at least one of the following: a second number of consecutive monitoring periods; or a period value based on a time unit.

[0185] In some embodiments, the second period information may include at least one of the following: a third number of continuous monitoring periods; or a period value based on a time unit.

[0186] In some embodiments, the threshold information may include at least one of the following: a first threshold for the average difference between the predicted value and the measured value for RRM measurement; a second threshold for the difference between the predicted value and the measured value determined based on historical RRM measurement statistics; or a joint judgment condition for one or more performance metrics of the predicted value and the measured value for RRM measurement.

[0187] In some embodiments, the trigger information may include at least one of the following: an identifier of the type of trigger event used to send the information; threshold information used to determine the result of performance monitoring; a fourth number of time instances used to perform performance monitoring; and the type of RRM measurement used to determine one or more trigger conditions of the trigger event.

[0188] In some embodiments, the information may include at least one of the following: the results of performance monitoring, indicating whether the performance of the prediction model is normal; performance metrics at at least one time instance before sending the information, the performance metrics being determined based on the predicted and measured values ​​of the RRM measurement; the average value of the performance metrics at at least one time instance before sending the information; the predicted value of the RRM measurement at at least one time instance before sending the information; or the measured value of the RRM measurement at at least one time instance before sending the information.

[0189] It should be understood that the communication devices 900 and 1000 mentioned above correspond to the communication methods 700 and 800 mentioned above, respectively, and correspond to the description in the communication process 200 mentioned above. Therefore, other details will not be repeated.

[0190] Figure 11This is a simplified block diagram of a device 1100 suitable for implementing embodiments of this application. Device 1100 can be provided to implement terminal device 201 or network device 202, or a communication device (e.g., a chip) that can support the functionality of terminal device 201 or network device 202. As shown, device 1100 includes one or more processors 1110 and one or more memories 1120 coupled to the processors 1110. Optionally, the one or more memories 1120 may also be integrated with the one or more processors 1110.

[0191] Processor 1110 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 1100 can have multiple processors, such as application-specific integrated circuit chips, which are time-subordinate to a clock synchronized with the main processor.

[0192] Memory 1120 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) 1124, 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) 1122 and other volatile memories that do not persist during power-off periods.

[0193] Computer program 1130 includes computer-executable instructions that are executed by the associated processor 1110. Program 1130 may be stored in ROM 1120. Processor 1110 can perform any suitable actions and processes by loading program 1130 into RAM 1120.

[0194] The embodiments of this application can be implemented by means of program 1130, so that device 1100 performs as shown in Figures 1 to 1. Figure 10The embodiments of this application describe a solution. Device 1100 can correspond to the aforementioned communication device 900 or 10000, and the functional modules in communication device 900 or 1000 can be implemented using software in device 1100. In other words, the functional modules included in communication device 900 or 1000 can be generated by the processor 1110 of device 110 reading program code stored in memory 1120. Embodiments of this application can also be implemented using hardware or a combination of software and hardware.

[0195] In some embodiments, program 1130 may be tangibly contained in a computer-readable medium, which may include in device 1100 (such as in memory 1120) or other storage devices accessible by device 1100. Program 1130 may be loaded from the computer-readable medium into RAM 1122 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.

[0196] In some embodiments, device 1100 may further include one or more communication modules (not shown). These communication modules may be coupled to processor 1110. 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.

Claims

1. A method of communication, comprising: The terminal device receives configuration from the network device, the configuration being used for performance monitoring of a predictive model for Radio Resource Management (RRM) measurements; Based on the configuration, perform performance monitoring for the prediction model; as well as Based on the performance monitoring, information related to the performance monitoring is sent to the network device.

2. The method of claim 1, wherein the configuration indicates at least one of the following: One or more of the objects being monitored; First-cycle information used to perform the performance monitoring; Second periodic information used to send the information; The first number of time instances used to perform the performance monitoring; Threshold information used to determine the results of the performance monitoring; or Triggering information used to send the aforementioned information.

3. The method of claim 2, wherein the one or more objects of the performance monitoring include at least one of the following: Predictive models used for the RRM measurement; or The function of the prediction model.

4. The method of claim 2, wherein the first periodic information comprises at least one of the following: The second number of consecutive monitoring cycles; or Periodic values ​​based on time units.

5. The method of claim 2, wherein the second periodic information comprises at least one of the following: The third number of consecutive monitoring cycles; or Periodic values ​​based on time units.

6. The method of claim 2, wherein the threshold information includes at least one of the following: A first threshold for the average difference between the predicted value and the measured value of the RRM measurement; A second threshold for the difference between predicted and measured values, determined based on historical RRM measurement statistics; or A joint determination criterion for one or more performance metrics of the RRM measurement, predicted value, and measured value.

7. The method of claim 2, wherein the triggering information includes at least one of the following: An identifier for the type of triggering event used to send the information; Threshold information used to determine the results of the performance monitoring; A fourth number of time instances used to perform the performance monitoring; The type of RRM measurement used to determine one or more triggering conditions of the triggering event.

8. The method of claim 2, wherein performing the performance monitoring for the prediction model comprises: Based on the first period information, determine the average difference between the predicted value and the measured value of the RRM measurement over a first consecutive number of time instances; Based on whether the average difference is greater than a first threshold or a second threshold, it is determined whether the performance monitoring is normal, wherein the second threshold is determined based on historical RRM measurement statistics.

9. The method of claim 7, wherein sending information related to the performance monitoring to the network device includes one of the following: Based on the second periodic information, information related to the performance monitoring is sent to the network device; or Based on the determination that at least one of the one or more triggering conditions is met, the information related to the performance monitoring is sent to the network device.

10. The method of claim 9, wherein determining that at least one of the one or more trigger conditions is satisfied comprises: Determine the average difference between the predicted and measured values ​​of the RRM measurement over a first consecutive number of time instances; Based on whether the average difference is greater than a first threshold or a second threshold, it is determined whether to send the information related to the performance monitoring to the network device, wherein the second threshold is determined based on historical RRM measurement statistics.

11. The method of claim 8 or 10, wherein determining the average difference between the predicted and measured values ​​of the RRM measurement over a first consecutive number of time instances comprises one of the following: The average difference is determined based on the difference between the predicted and measured values ​​for each time instance in the first number of time instances; or The average difference is determined based on the difference between the predicted value of at least one first time instance in a first consecutive number of time instances and the measured value of the RRM measurement of the corresponding at least one second time instance.

12. The method of claim 1, wherein the information comprises at least one of the following: The results of the performance monitoring indicate whether the performance of the prediction model is normal. Performance metrics at at least one time instance prior to sending the information, the performance metrics being determined based on the predicted and measured values ​​of the RRM measurement; The average performance metric across at least one time instance prior to sending the information; The predicted value of the RRM measurement at at least one time instance prior to sending the information; or The measurement value of the RRM measurement at least once before the information was sent.

13. A communication method, comprising: The network device sends a configuration to the terminal device, the configuration being used for performance monitoring of the predictive model for Radio Resource Management (RRM) measurements; Receive information related to the performance monitoring from the terminal device; as well as Based on the information, an instruction for managing the model is sent to the terminal device.

14. The method of claim 13, wherein the configuration indicates at least one of the following: One or more of the objects being monitored; First-cycle information used to perform the performance monitoring; Second periodic information used to send the information; The first number of time instances used to perform the performance monitoring; Threshold information used to determine the results of the performance monitoring; or Triggering information used to send the aforementioned information.

15. The method of claim 14, wherein the one or more objects of the performance monitoring include at least one of the following: Predictive models used for the RRM measurement; or The function of the prediction model.

16. The method of claim 14, wherein the first periodic information comprises at least one of the following: The second number of consecutive monitoring cycles; or Periodic values ​​based on time units.

17. The method of claim 14, wherein the second periodic information comprises at least one of the following: The third number of consecutive monitoring cycles; or Periodic values ​​based on time units.

18. The method of claim 14, wherein the threshold information comprises at least one of the following: A first threshold for the average difference between the predicted value and the measured value of the RRM measurement; A second threshold for the difference between predicted and measured values, determined based on historical RRM measurement statistics; or A joint determination criterion for one or more performance metrics of the RRM measurement, predicted value, and measured value.

19. The method of claim 14, wherein the triggering information comprises at least one of the following: An identifier for the type of triggering event used to send the information; Threshold information used to determine the results of the performance monitoring; A fourth number of time instances used to perform the performance monitoring; The type of RRM measurement used to determine one or more triggering conditions of the triggering event.

20. The method of claim 13, wherein the information comprises at least one of the following: The results of the performance monitoring indicate whether the performance of the prediction model is normal. Performance metrics at at least one time instance prior to sending the information, the performance metrics being determined based on the predicted and measured values ​​of the RRM measurement; The average performance metric across at least one time instance prior to sending the information; The predicted value of the RRM measurement at at least one time instance prior to sending the information; or The measurement value of the RRM measurement at least once before the information was sent.

21. A communication device, comprising: processor; as well as Memory, including computer program code, The computer program code, when run by the processor, causes the method according to any one of claims 1 to 12 or any one of claims 13 to 20 to be performed.

22. A communication device comprising components for performing the method according to any one of claims 1 to 12 or any one of claims 13 to 20.

23. A chip comprising a processor connected to a memory located inside or outside the chip, the memory for storing a computer program, the processor for calling and running the computer program from the memory to cause the method according to any one of claims 1 to 12 or any one of claims 13 to 20 to be performed.

24. A computer-readable storage medium comprising machine-executable instructions, which, when executed by a device, cause the method according to any one of claims 1 to 12 or any one of claims 13 to 20 to be performed.

25. A computer program product comprising a computer program that, when run on a device, causes the method according to any one of claims 1 to 12 or any one of claims 13 to 20 to be performed.

Images