Communication method and device

Abstract

The present application relates to a communication method and a communication device. The method comprises: on the basis of a measured result and a predicted result related to mobility management, a first communication device obtains a performance monitoring result related to the mobility management. According to embodiments of the present application, the performance related to mobility management of a communication device can be monitored, facilitating managing the performance related to the mobility management of the communication device.

Description

Communication method and device Technical Field

[0001] The present application relates to the field of communications, and more specifically, to a communication method and device. Background Art

[0002] The 3rd Generation Partnership Project (3GPP) has proposed the application of artificial intelligence / machine learning (AI / ML) algorithm models in communication scenarios. These models, for example, are used in beam measurement prediction, channel state information (CSI) compression and decompression, and positioning prediction. The performance of these models in communication scenarios requires monitoring.

[0003] Summary of the Invention

[0004] The embodiments of the present application provide a communication method and device that can monitor the performance related to mobility management of a communication device.

[0005] An embodiment of the present application provides a communication method, including:

[0006] The first communication device obtains a performance monitoring result related to mobility management based on the measured result and the predicted result related to mobility management.

[0007] An embodiment of the present application provides a communication method, including:

[0008] The second communication device receives first information, where the first information is used to indicate a performance monitoring result related to mobility management, where the performance monitoring result related to mobility management is obtained based on a measured result and a predicted result related to mobility management.

[0009] An embodiment of the present application provides a first communication device, including:

[0010] The first processing unit is configured to obtain a performance monitoring result related to mobility management based on a measured result and a predicted result related to mobility management.

[0011] An embodiment of the present application provides a second communication device, including:

[0012] The second communication unit is configured to receive first information, where the first information is used to indicate a performance monitoring result related to mobility management, where the performance monitoring result related to mobility management is obtained based on a measured result and a predicted result related to mobility management.

[0013] An embodiment of the present application provides a terminal device, comprising: a transceiver, a processor, and a memory. The memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to call and execute the computer program stored in the memory so that the terminal device executes the above-mentioned communication method.

[0014] An embodiment of the present application provides a network device, comprising: a transceiver, a processor, and a memory. The memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to call and execute the computer program stored in the memory so that the network device executes the above-mentioned communication method.

[0015] An embodiment of the present application provides a chip for implementing the above-mentioned communication method.

[0016] Specifically, the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned communication method.

[0017] An embodiment of the present application provides a computer-readable storage medium for storing a computer program, which, when executed by a device, enables the device to execute the above-mentioned communication method.

[0018] An embodiment of the present application provides a computer program product, including computer program instructions, which enable a computer to execute the above-mentioned communication method.

[0019] An embodiment of the present application provides a computer program, which, when executed on a computer, enables the computer to execute the above-mentioned communication method.

[0020] Through the embodiments of the present application, the performance related to the mobility management of the communication device can be monitored, which facilitates the management of the performance related to the mobility management of the communication device. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] FIG1 is a schematic diagram of an application scenario according to an embodiment of the present application.

[0022] FIG2 is a schematic diagram of a measurement event trigger.

[0023] FIG3 is a schematic diagram of the measurement model.

[0024] FIG4 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0025] FIG5 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0026] FIG6 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0027] FIG7 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0028] FIG8 is a schematic flowchart of a communication method according to another embodiment of the present application.

[0029] FIG9 is a schematic diagram of an embodiment of the present application using a model to predict L3 cell measurement results.

[0030] FIG10 is a schematic diagram of an embodiment of the present application using a model to predict mobility events.

[0031] 11a to 11c are schematic diagrams of counting conditions of a counter.

[0032] FIG12 is a schematic block diagram of a first communication device according to an embodiment of the present application.

[0033] FIG13 is a schematic block diagram of a second communication device according to an embodiment of the present application.

[0034] FIG14 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0035] FIG15 is a schematic block diagram of a chip according to an embodiment of the present application.

[0036] FIG16 is a schematic block diagram of a communication system according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0038] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-based access to unlicensed spectrum, NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), Fifth Generation (5G) system or other communication systems.

[0039] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.

[0040] In one embodiment, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, and a standalone (SA) networking scenario.

[0041] In one embodiment, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, wherein the authorized spectrum can also be considered as an unshared spectrum.

[0042] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0043] The terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0044] In an embodiment of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0045] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0046] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0047] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in a WLAN, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.

[0048] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.

[0049] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

[0050] FIG1 exemplarily illustrates a communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one embodiment, the communication system 100 may include multiple network devices 110, and each network device 110 may include a different number of terminal devices 120 within its coverage area, which is not limited in this embodiment of the present application.

[0051] In one embodiment, the communication system 100 may further include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which is not limited in this embodiment of the present application.

[0052] Among them, the network equipment may include access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks for communicating with the access network equipment. The access network equipment can be an evolutionary base station (evolutional node B, abbreviated as eNB or e-NodeB) macro base station, micro base station (also called "small base station"), pico base station, access point (AP), transmission point (TP) or new generation base station (new generation Node B, gNodeB), etc. in a long-term evolution (LTE) system, a next-generation (mobile communication system) (next radio, NR) system or an authorized auxiliary access long-term evolution (LAA-LTE) system.

[0053] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system shown in Figure 1 as an example, the communication device may include a network device and a terminal device having a communication function. The network device and the terminal device may be specific devices in the embodiments of the present application and will not be described in detail here. The communication device may also include other devices in the communication system, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0054] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.

[0055] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0056] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0057] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0058] 1. AI / ML Research in 3GPP

[0059] 3GPP is studying whether AI / ML algorithm models can be applied to some physical layer technologies, including whether to compress and decompress the channel state information (CSI) of the radio interface, predict the optimal beam or beam pair in the spatial or temporal domain, and predict positioning.

[0060] A technical report (TR) describes how to use AI / ML algorithms to perform beam measurement predictions for beam management purposes. One use case is prediction applied to the spatial domain, that is, by measuring a subset of beams in a set and using the spatial correlation between beams, the best beam (with the strongest wireless signal) in the full set of beams or a pair of beams (downlink transmission and reception) is predicted. Another use case is beam prediction applied to the time domain, that is, based on the measurement results of historically measured beams (and predicted beams), the temporal correlation of the beams is used to predict the measurement results of the beams in the current time slot. Judging from the recorded evaluation results, these two use cases are not only technically feasible, but also provide higher performance improvements.

[0061] In addition to documenting the core evaluation methods and results, this TR also documents the steps and content for managing AI / ML on the network side, the UE side, or both sides. These contents are referred to as life cycle management (LCM) in the TR. LCM can include data collection, model training, function / model identification, model transmission, model inference, function / model selection, activation, deactivation, replacement and fallback, function / model monitoring, model updates, and UE capability reporting.

[0062] Among these processes, the function / model monitoring process generally refers to the network monitoring the operation of the AI / ML model on the UE side, and determining further management steps based on the operating indicators reported by the UE, such as deactivating or replacing the model. As can be seen in the model monitoring content of the TR on beam management, from the perspective of the process, it can be combined according to two dimensions:

[0063] 1. Where are the indicators reflecting the model's operational performance calculated? Either on the UE or on the network. If calculated on the UE, the UE needs to calculate these performance indicators and then report them to the network. If calculated on the network side, the UE needs to report relevant auxiliary information to the network, and the network then calculates the performance indicators based on this auxiliary information.

[0064] 2. Based on the model monitoring results, who will take further management actions on the model? If the UE makes the decision, it must first send a monitoring request, and then the network will send the relevant auxiliary information to the UE. If the decision is made by the network, the network will proactively initiate this process.

[0065] Examples of combinations between the above two dimensions can be found in Table 1:

[0066] Table 1

[0067] 2. Background Knowledge of Radio Resource Management (RRM) Measurement

[0068] In 3GPP cellular communication systems, the UE measures the strength or quality of the radio signals in its current serving cell and neighboring cells, and then reports this information to the network via Radio Resource Control (RRC) messages called measurement reports. The network can then make handover decisions based on this information.

[0069] In second-generation communication systems, measurement reports are usually reported periodically. Starting with third-generation communication systems, such as Wideband Code Division Multiple Access (WCDMA), including fourth-generation communication systems Long Term Evolution (LTE), and fifth-generation communication systems (NR), measurement reports are mainly divided into the following types based on the reporting method:

[0070] 1. Periodic reporting;

[0071] 2. Reporting based on measurement events;

[0072] 3. Report based on measurement events and continue reporting periodically thereafter.

[0073] Regardless of the reporting method (or form) of the measurement report, the measurement report may include specific measurement events and / or measurement results, such as the cell's signal strength (e.g., the reference signal received power (RSRP) value, measured in dBm), or the reference signal received quality (e.g., the reference signal received quality (RSRQ), measured in dB). The reported cells may include the current serving cell and neighboring cells. The measurement object may be the same frequency, different frequency, or the frequency of a different communication system.

[0074] The triggering of a measurement event may include at least one of the following basic elements:

[0075] 1. Measurement results: Measurement results of the serving cell and / or neighboring cells, such as cell signal strength.

[0076] 2. Comparison parameters, such as thresholds, hysteresis values, offset values, etc. The dimensions of general measurement results in standard protocols are such that the larger the value, the higher the signal strength or quality. Absolute comparison refers to comparing the measurement value of a cell with a certain threshold. In this case, a measurement result greater than (threshold + hysteresis value) indicates that the entry condition is met, and a measurement result less than (threshold - hysteresis value) indicates that the exit condition is met. Relative comparison usually refers to comparing the measurement results of adjacent cells with those of the serving cell. Before comparison, each cell needs to add its own relevant offset value. For the serving cell, an offset value (Off_event) related to the corresponding event must also be added. Finally, the hysteresis value (Hys) also needs to be considered when comparing. Taking the A3 event (A3 event) as an example, assuming that the offset value of the measurement result of the serving cell is marked with s and the adjacent cell is marked with n, then the examples of entry and exit conditions are as follows:

[0077] Examples of entry conditions:

[0078] Mn+Ofn>Ms+Ofs+Hys+Off_event

[0079] Example of a leave condition:

[0080] Mn+Ofn <Ms+Ofs-Hys+Off_event

[0081] In the above conditions, Mn can represent the measurement value of a neighboring cell, Ofn can represent the offset value related to at least one of the cell, frequency, and measurement event, Ms can represent the measurement value of the source cell, and Ofs can represent the offset value related to at least one of the cell, frequency, and measurement event.

[0082] 3. Timers that indicate the robustness of measurement results, such as the time to trigger (TTT) timer. As shown in Figure 2, the rectangular blocks represent the L3 cell measurement results for the target cell. When a cell meets the entry criteria for an event, the TTT timer starts. If the TTT timer expires and the cell continues to meet the entry criteria for the event, it indicates that the cell has triggered the measurement event.

[0083] The 3GPP specification protocol describes how the UE performs intra-frequency or inter-frequency measurements, how to perform measurement sampling according to beams at Layer 1, and how to determine measurement events based on network configuration parameters.

[0084] Several reference points in Figure 3 are as follows:

[0085] A: The UE performs physical layer measurement sampling at the beam granularity (e.g., gNB beam1, gNB beam1…gNB beamK).

[0086] A1: The UE performs Layer 1 filtering on the beam measurement results. Generally, the protocol specifies the length of the measurement period under specific RRC configurations. This measurement period mandates that the UE perform at least one sampling, and that the beam measurement results after L1 filtering meet the performance requirements specified in the 3GPP specification. At reference point A, the UE performs a specific number of samplings within a measurement period. In test cases, an oversampling of 4 to 5 is typically used.

[0087] B: The beam measurement results within a certain cell obtained at A1 are consolidated to synthesize the L1 cell-level measurement results.

[0088] C: L1 cell-level measurement results of a certain cell, which are filtered through Layer 3 (Layer 3, L3) (Layer 3 Beam filtering) to obtain L3 cell-level measurement results in sequence.

[0089] D: The measurement results of the serving cell and / or neighboring cells are used to determine whether a specific measurement event is established according to certain judgment conditions (configured by the network). For example, whether the measurement result of the neighboring cell is higher than the measurement result of the primary cell (PCell) of the cell by an offset value (A3 event), etc.

[0090] 3. AI Mobility Project

[0091] 3GPP has established a project to study the application of the aforementioned beamformation prediction technology to RRM measurements. Simulation studies have confirmed the technical feasibility of this concept. For the network to make further handover decisions based on the results of the UE-side AI / ML algorithm, the UE needs to report the algorithm's output to the network. Discussions are underway on how to report this and what has already been reported.

[0092] In addition, 3GPP has studied what factors affect mobility performance when deploying multi-layer networks (hetnets). In these studies, some key indicators were defined, including:

[0093] 1. Handover failure: When the network sends a handover command message to the UE, if the timer T310 used to determine the radio link failure is running or has timed out, this situation is determined as a handover failure. The determination of radio link failure is made according to the LTE protocol. After receiving N310 consecutive indications of link deterioration (Qout), the UE will start the T310 timer. If the T310 timer times out, the UE will assume that a radio link failure has occurred. When T310 is running, if N311 indications of link improvement (Qin) are received, the timer T310 will be stopped. The length of the T310 timer, counters N310 and N311 are all configured by the network.

[0094] 2. Ping-pong handover: When a UE switches from cell A to cell B and then switches back to cell A within a specified time threshold (e.g., 1 second), such a handover is considered a ping-pong handover.

[0095] 3. Too short handover: When a UE switches from cell A to cell B and then switches back to cell C within a specified time threshold (e.g., 1 second), and cell C is not cell A, such handover is considered too short.

[0096] These models and switching metric definitions can be reused in the research of the AI ​​mobility project.

[0097] 3GPP plans to launch a research project on improving mobility management (handover) in the 19th generation release (Rel 19), which will support AI / ML models for mobility management, especially models on the UE side. The solution provided by the embodiments of the present application can provide mobility-related model monitoring functions such as mobility measurement results and / or mobility events.

[0098] FIG4 is a schematic flow chart of a communication method 400 according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes at least part of the following contents.

[0099] S410: The first communication device obtains a performance monitoring result related to mobility management based on a measured result and a predicted result related to mobility management.

[0100] In an embodiment of the present application, the first communication device may be a terminal device or a network device. If the first communication device is a terminal device, the terminal device may obtain a prediction result based on its own measured results related to mobility management, and then compare the measured results with the predicted results to obtain a performance monitoring result related to mobility management. If the first communication device is a network device, the network device may obtain a performance monitoring result related to mobility management based on the measured results and predicted results related to mobility management reported by the terminal device, and then compare the measured results with the predicted results.

[0101] In one embodiment, the prediction result related to mobility management includes at least one of a predicted measurement result, a predicted measurement event, and a predicted mobility event related to mobility management. In this embodiment of the present application, the terminal device may first send the predicted measurement event (or the predicted result of the measurement event) to the network device in advance. The network device may subsequently compare the actual measurement event (the actual measurement result of the measurement event) reported by the terminal device to obtain a performance monitoring result related to mobility management.

[0102] In one embodiment, the mobility management-related performance monitoring result includes at least one of the following:

[0103] a performance indicator corresponding to the predicted measurement result related to the mobility management;

[0104] The predicted measurement events and / or performance indicators corresponding to the mobility management-related mobility events;

[0105] Other performance indicators.

[0106] In the embodiment of the present application, the measurement results may include RSRP, RSRQ, Signal to Interference plus Noise Ratio (SINR), etc. The measurement event may be determined based on a comparison relationship between the measurement result and a comparison parameter, for example, whether the measurement result of the neighboring cell is higher than the measurement result of the primary cell (PCell) of the cell by an offset value (A3 event).

[0107] In one embodiment, the performance indicator corresponding to the predicted measurement result includes at least one of the following: measurement result prediction accuracy; and measurement reduction degree.

[0108] In one embodiment, the calculation method of the measurement result prediction accuracy includes at least one of the following:

[0109] Calculating the measurement result prediction accuracy based on the number of measurement result pairs whose absolute error value between the predicted measurement result and the measured measurement result is less than a first threshold, and the total number of measurement result pairs;

[0110] Calculate the prediction accuracy of the measurement result based on the root mean square error between the predicted measurement result and the measured measurement result;

[0111] The measurement result prediction accuracy is calculated based on the absolute error value between the predicted measurement result and the measured measurement result, and the number of total measurement result pairs.

[0112] For example, the measurement result prediction accuracy can be equal to the number of measurement result pairs whose absolute error between the predicted measurement result and the measured measurement result is less than a first threshold, as a percentage of the total number n of predicted measurement result pairs. See the formula: Measurement Accuracy = num(abs(Xi - Yi) < threshold) / n*100%, where the operator abs() represents the absolute value, and the operator num() represents the number of subscript i pairs that meet the requirement.

[0113] For another example, the prediction accuracy of the measurement result can be equal to the root mean square error between the predicted measurement result and the measured measurement result. See the formula: Measurement Accuracy = RMSE(Xi, Yi), where RMSE is the root mean square error operator, RMSE(Xi, Yi) = squ(Xigma(Xi-Yi) 2 ), where the Xigma() operator is a summation operator and the squ() operator is a square root operator.

[0114] For another example, the measurement result prediction accuracy can be equal to the sum of the absolute errors between the predicted measurement result and the measured measurement result, divided by the total number of predicted measurement results n. See the formula: Measurement Accuracy = Xigma (abs (Xi - Yi)) / n.

[0115] In one embodiment, the calculation method of the measurement reduction degree includes at least one of the following:

[0116] Calculating the measurement reduction based on the number of predicted measurement results and the measured measurement results;

[0117] Calculating the degree of measurement reduction based on the number of measured beams and the predicted beams;

[0118] For each cell at each predicted frequency point, the measurement reduction degree is calculated based on the actual measured frequency points and the number of cells measured at each of the actual measured frequency points.

[0119] For example, in time-domain prediction, the predicted measurement results are {X1, X2, ...Xn}, and the actual measurement results measured by the terminal device at the reference point are {Z1, Z2, ...Zm}. The degree of measurement reduction can be expressed as 1-m / (m+n)*100%. For another example, in spatial-domain prediction, if the number of measured and predicted results matches, and the measured beam is part of the predicted beam, the degree of measurement reduction can be expressed as 1-m / n, where m is the number of beams in the full set of n beams. For another example, in frequency-domain prediction, for each cell at each predicted frequency point, assuming the number of measured frequencies is m and the number of cells measured at each frequency point is n, the degree of measurement reduction can be expressed as 1-m*n / (1+m*n).

[0120] In the embodiment of the present application, at least one of the following counters may be set inside the communication device for measurement events and / or mobility events: a first counter, a second counter, and a third counter.

[0121] In one embodiment, the first counter is used to count events that were predicted by the model but did not actually occur.

[0122] In one embodiment, the counting condition of the first timer includes: the mobility event and / or measurement event does not occur on the cell within a time period not exceeding a set time range before or after the time point at which the model predicts the mobility event and / or measurement event to occur on the cell. For example, if the model predicts that a mobility event, such as a ping-pong handover event, will occur on a cell at time T1, and the mobility event does not occur on the cell within a time period not exceeding T0 before or after T1, the value of the first counter n1 is incremented by 1.

[0123] In one embodiment, the second counter is used to count events that are predicted by the model and actually occur.

[0124] In one embodiment, the counting condition of the second counter includes: the mobility event and / or measurement event occurs on the cell within a time period not exceeding a set time range before or after the time point at which the model predicts the mobility event and / or measurement event to occur on the cell. For example, the time point at which the model predicts the occurrence of a mobility event, such as a too-short-time handover event, on a certain cell is T2. If the mobility event occurs on the cell within a time period not exceeding T0 before or after T2, the value of the second counter n2 is incremented by 1.

[0125] In one embodiment, the second counter also includes events that were predicted by the model and would have occurred but were avoided.

[0126] In one embodiment, the method for determining an event that would have occurred but was avoided as predicted by the model includes:

[0127] After the network device performs an avoidance operation on the relevant cell based on the predicted mobility event, the terminal device continues to perform actual measurement on the relevant cell of the predicted mobility event to determine whether the predicted mobility event is an event that was predicted by the model to occur but was avoided; or

[0128] After the network device performs an avoidance operation on the relevant cell based on the predicted measurement event, the terminal device continues to perform actual measurement on the relevant cell to determine whether the predicted measurement event is an event that was predicted by the model to occur but was avoided.

[0129] For example, the terminal device reports the predicted measurement events and / or mobility events to the network device in advance. The network device takes some measures, for example, for the ping-pong switching event between the serving cell A and the adjacent cell B, it does not switch to cell B. In this case, the predicted event is avoided. Since the terminal device can continue to measure or predict the signals of the serving cell A and the adjacent cell B, it can be judged whether there is a possibility of ping-pong switching based on the criteria of measurement event A3, for example. Because the trajectory of the terminal device and the measured results will not change because the network device takes measures to avoid ping-pong switching, even if the ping-pong switching event is avoided, the terminal device can still judge whether the prediction result of the model is accurate.

[0130] In one embodiment, the third counter is used to count events that are not predicted by the model but actually occur.

[0131] In one embodiment, the counting condition of the third counter includes: the model does not predict the mobility event and / or measurement event within a time period not exceeding a set time range before or after the time point when the mobility event and / or measurement event occurs on the cell. For example, the model does not predict that a ping-pong handover event will occur in a certain cell at T3, but the mobility event occurs in the cell within a time period not exceeding T0 before or after T3.

[0132] In one embodiment, the performance indicators corresponding to the predicted measurement events and / or mobility events include at least one of the following: model prediction accuracy; model false positive rate; model prediction completeness; model missed detection rate; model comprehensive performance indicator.

[0133] In one embodiment, the model prediction accuracy and / or the model false positive rate are determined based on a first counter and a second counter. For example, the first counter is represented as n1, the second counter is represented as n2, and the third counter is represented as n3. Model prediction accuracy = (n2) / (n1+n2), and model false positive rate = 1-model prediction accuracy.

[0134] In one embodiment, the model prediction completeness and / or the model missed detection rate are determined based on the second counter and the third counter. For example, model prediction completeness = (n2) / (n3+n2), model missed detection rate = 1-model prediction completeness.

[0135] In one embodiment, the model comprehensive performance index is determined based on the first counter, the second counter, and the third counter. For example, the model comprehensive performance index = 2*(1 / (1 / model prediction accuracy + 1 / model prediction completeness)).

[0136] In one embodiment, the other performance indicators include at least one of the following:

[0137] Model stability information;

[0138] Model scoring information;

[0139] Model input data quality information.

[0140] FIG5 is a schematic flow chart of a communication method 500 according to another embodiment of the present application. The method may include one or more features of the communication method 400 described above.

[0141] In one embodiment, the method further includes: S510, the first communication device inputs the measured measurement results related to mobility management into the model to obtain the prediction results related to the mobility management. In an embodiment of the present application, the first communication device, such as a terminal device, can deploy an AI / ML model related to mobility management. By inputting the measured measurements related to mobility management into the model, the prediction results related to mobility management can be output. Then, the terminal device can compare the prediction results with the measured results to obtain the performance monitoring results of the model. After S510, S520 can be included: the first communication device obtains the performance monitoring results related to mobility management based on the measured results and the predicted results related to mobility management. For a detailed description of S520, please refer to S410.

[0142] In one embodiment, the method further includes: S530, the first communication device sends first information, where the first information is used to indicate a performance monitoring result related to the mobility management.

[0143] In an embodiment of the present application, a first communication device may send first information to a second communication device. If the first communication device is a terminal device, the second device may be a network device or another terminal device. The first information may include performance monitoring results related to mobility management, and may also include indication information corresponding to the performance monitoring results related to mobility management.

[0144] In one embodiment, the first information includes a quantified value of the performance monitoring result.

[0145] In an embodiment of the present application, the first information may include multiple bits, and different bit values ​​may represent different quantized values ​​of the performance monitoring results. The performance monitoring results, such as percentages, dBm (decibel milliwatts), dB (decibel) and other dimensional values, are quantized into values ​​or ranges corresponding to information bits (bits), such as index values. For example, if the performance monitoring result of an AI / ML model related to mobility management is a percentage of 93%, according to the quantized values ​​{00, 01, 10, 11} corresponding to the percentage range {<80%, 80% to 90%, 90% to 95%, 96% to 100%} in the quantization table, the quantized value corresponding to this percentage of 93% can be obtained as 10.

[0146] In one embodiment, the method further includes: the first communication device receiving a first model monitoring command, the first model monitoring command being used to instruct the first communication device to report a performance indicator of the model. This step may be before S410 or S520.

[0147] In an embodiment of the present application, a first communication device, such as a terminal device, may receive a first model monitoring command from a second communication device, such as a network device. The first model monitoring command may include performance monitoring results that need to be reported by the first communication device, such as one or more performance indicators of the model, and may also include a specific reporting method.

[0148] In one embodiment, the first model monitoring command is used to indicate at least one of the following:

[0149] The performance metrics of the model that need to be monitored;

[0150] The control parameters of the model that need to be monitored;

[0151] Reporting method.

[0152] In one embodiment, the performance indicator includes measurement result prediction accuracy and / or measurement reduction degree, and the control parameter includes a threshold corresponding to the measurement result prediction accuracy.

[0153] In one embodiment, the reporting method of the performance indicators and / or control parameters includes at least one of the following: single reporting; periodic reporting; event-triggered reporting; and periodic reporting after event triggering.

[0154] In one embodiment, the method further comprises:

[0155] The first communication device performs at least one of data collection, calculation, and quantification on the performance indicator based on the control parameter in the first model monitoring command, and reports the performance indicator in accordance with the reporting method.

[0156] For example, the performance indicator of the model to be monitored, as indicated by the first model monitoring command, is the measurement result prediction accuracy, the control parameter is a set threshold, and the reporting method is periodic reporting. If the measurement result prediction accuracy is greater than the set threshold, the measurement result prediction accuracy may be reported according to the set period. The content reported may be the measurement result prediction accuracy or a quantified value of the measurement result prediction accuracy. If the measurement result prediction accuracy is less than or equal to the set threshold, the measurement result prediction accuracy may not be reported.

[0157] In one embodiment, the method further includes: the first communications device sending a first performance indicator monitoring request message, where the first performance indicator monitoring request message includes performance indicator information of the model that the first communications device requests monitoring and / or a reason for the monitoring request. This step may occur before S410 or S520. This step may also occur before the first communications device receives the first model monitoring command.

[0158] In an embodiment of the present application, a first communication device, such as a terminal device, may send a first performance indicator monitoring request message to a second communication device, such as a network device. The performance indicator information in the message may include the name and identifier of the performance indicator. The reason for requesting monitoring in the message may include reasons for model maintenance needs, such as model update, switching, activation, deactivation, etc. If the second communication device allows the first communication device to monitor some or all of the requested performance indicators, the second communication device may send the performance indicator information allowed to be monitored and / or control parameters related to these performance indicators to the first communication device. These information and / or parameters may be indicated by a first model monitoring command.

[0159] Figure 6 is a schematic flow chart of a communication method 600 according to another embodiment of the present application. The method may include one or more features of the above-mentioned communication method 400. In one embodiment, the method further includes: S610, the first communication device receives the second information, and the second information is used to indicate the measured results and predicted results related to the mobility management. In an embodiment of the present application, the first communication device can receive the second information from the second communication device. If the first communication device is a network device, the second device can be a terminal device. After the network device receives the measured results related to mobility management and the predicted results of the AI / ML model, it can compare the predicted results and the measured results to obtain the performance monitoring results of the model. After S610, it can include S620: the first communication device obtains the performance monitoring results related to mobility management based on the measured results and the predicted results related to mobility management. The specific description of S620 can be found in S410.

[0160] In one embodiment, the method further includes: the first communication device sends a second model monitoring command, where the second model monitoring command is used to instruct the second communication device to report measurement results and / or measurement events related to mobility management. In an embodiment of the present application, the first communication device, such as a network device, can send a second model monitoring command to the second communication device, such as a terminal device. The second model monitoring command may include content that needs to be measured, predicted, or reported by the terminal device, and may also include a reporting method. This step may be before S410 or S620.

[0161] In one embodiment, the second model monitoring command is used to indicate at least one of the following:

[0162] Measurement results that require actual measurement;

[0163] The measurement results that need to be predicted;

[0164] The measured results of the measurement event;

[0165] Measured results of mobility events;

[0166] Reporting method.

[0167] For example, if the second model monitoring command indicates that the measurement results required to be measured by the terminal device include RSRP and RSRQ. The terminal device can perform RSRP measurement and RSRQ measurement. The terminal device can also input the measured RSRP and the measured RSRQ into the corresponding model to obtain the predicted RSRP and the predicted RSRQ. For another example, the terminal device first reports the event information predicted by the model to the network device. If the network device sends a second model monitoring command to the terminal device indicating the measured result of the measurement event, the terminal device can report the measured measurement event, such as a switching event, to the network device. The network device can compare the predicted result of the measurement event with the measured result to obtain the performance monitoring result of the model.

[0168] In one embodiment, the first communications device obtains, based on the measured results and the predicted results related to mobility management, a performance monitoring result related to mobility management, including at least one of the following:

[0169] The first communication device calculates a performance indicator corresponding to the measurement result based on the actual measurement result and the corresponding predicted measurement result;

[0170] The first communications device calculates a performance indicator corresponding to the event based on statistical results of the predicted measurement event and / or the predicted mobility event.

[0171] For example, the network device calculates the performance indicator corresponding to the actual measurement result reported by the terminal device and its corresponding predicted measurement result. For another example, the network device calculates the performance indicator corresponding to the measurement event based on the statistical results of the predicted measurement event reported by the terminal device. For another example, the network device calculates the performance indicator corresponding to the mobility event based on the statistical results of the predicted mobility event reported by the terminal device.

[0172] In one embodiment, the method further includes: the first communications device receiving a second performance indicator monitoring request message, where the second performance indicator monitoring request message includes performance indicator information of the model that the second communications device requests monitoring and / or a reason for the monitoring request. This step may occur before S410 or S620. This step may also occur before the first communications device sends the second model monitoring command.

[0173] In an embodiment of the present application, a first communication device, such as a network device, may receive a second performance indicator monitoring request message from a second communication device, such as a terminal device. The performance indicator information in the message may include the name and identifier of the performance indicator. The reason for requesting monitoring in the message may include the reason for model maintenance needs, such as model update, switching, activation, deactivation, etc. If the first communication device allows the second communication device to monitor some or all of the requested performance indicators, the first communication device KEYI sends the performance indicator information allowed to be monitored and / or control parameters related to these performance indicators to the first communication device. These information and / or parameters can be indicated by the first model monitoring command.

[0174] In one embodiment, the reporting method indicated by the second model monitoring command includes at least one of the following: single reporting; periodic reporting; event-triggered reporting; and periodic reporting after event triggering.

[0175] FIG7 is a schematic flow chart of a communication method 700 according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes at least part of the following contents.

[0176] S710. A second communication device receives first information, where the first information is used to indicate a performance monitoring result related to mobility management, where the performance monitoring result related to mobility management is obtained based on a measured result and a predicted result related to mobility management.

[0177] In one embodiment, the first information includes a quantified value of the performance monitoring result.

[0178] In one embodiment, the prediction result related to mobility management is obtained by the first communications device inputting the actual measurement result related to mobility management into a model.

[0179] In one embodiment, the method further includes: the second communication device sending a first model monitoring command, wherein the first model monitoring command is used to instruct the first communication device to report the performance indicator of the model. This step may be performed before S710.

[0180] In one embodiment, the first model monitoring command is used to indicate at least one of the following:

[0181] The performance metrics of the model that need to be monitored;

[0182] The control parameters of the model that need to be monitored;

[0183] Reporting method.

[0184] In one embodiment, the performance indicator includes measurement result prediction accuracy and / or measurement reduction degree, and the control parameter includes a threshold corresponding to the measurement result prediction accuracy.

[0185] In one embodiment, the method further includes: the second communication device receiving a first performance indicator monitoring request message, where the first performance indicator monitoring request message includes performance indicator information of the model that the first communication device requests monitoring and / or a reason for the monitoring request. This step may occur before S710. This step may also occur before the second communication device sends the first model monitoring command.

[0186] Figure 8 is a schematic flow chart of a communication method 800 according to another embodiment of the present application. This method may include one or more features of the communication method 700 described above. In one embodiment, the method further includes: S810: The second communication device sends second information, where the second information is used to indicate the measured results and predicted results related to mobility management. This step may be followed by S820: The second communication device receives the first information. For a detailed description of S820, see S710.

[0187] In one embodiment, the method further includes: the second communication device receiving a second model monitoring command, the second model monitoring command being used to instruct the second communication device to report measurement results and / or measurement events related to mobility management. This step may be performed before S710 or S820.

[0188] In one embodiment, the second model monitoring command is used to indicate at least one of the following:

[0189] Measurement results that require actual measurement;

[0190] The measurement results that need to be predicted;

[0191] The measured results of the measurement event;

[0192] Measured results of mobility events;

[0193] Reporting method.

[0194] In one embodiment, the method further includes: the second communication device sending a second performance indicator monitoring request message, where the second performance indicator monitoring request message includes performance indicator information of the model that the second communication device requests to monitor and / or a reason for the monitoring request. This step may occur before S710 or S820. This step may also occur before the second communication device receives the second model monitoring command.

[0195] In one embodiment, the reporting method includes at least one of the following: single reporting; periodic reporting; event-triggered reporting; and periodic reporting after event triggering.

[0196] In one embodiment, the prediction result related to mobility management includes at least one of a predicted measurement result, a predicted measurement event, and a predicted mobility event related to mobility management.

[0197] In one embodiment, the mobility management-related performance monitoring result includes at least one of the following:

[0198] a performance indicator corresponding to the predicted measurement result related to the mobility management;

[0199] The predicted measurement events and / or performance indicators corresponding to the mobility management-related mobility events;

[0200] Other performance indicators.

[0201] In one embodiment, the performance indicator corresponding to the predicted measurement result includes at least one of the following:

[0202] Prediction accuracy of measurement results;

[0203] Measure the reduction.

[0204] In one embodiment, the calculation method of the measurement result prediction accuracy includes at least one of the following:

[0205] Calculating the measurement result prediction accuracy based on the number of measurement result pairs whose absolute error value between the predicted measurement result and the measured measurement result is less than a first threshold, and the total number of measurement result pairs;

[0206] Calculate the prediction accuracy of the measurement result based on the root mean square error between the predicted measurement result and the measured measurement result;

[0207] The measurement result prediction accuracy is calculated based on the absolute error value between the predicted measurement result and the measured measurement result, and the number of total measurement result pairs.

[0208] In one embodiment, the calculation method of the measurement reduction degree includes at least one of the following:

[0209] Calculating the measurement reduction based on the number of predicted measurement results and the measured measurement results;

[0210] Calculating the degree of measurement reduction based on the number of measured beams and the predicted beams;

[0211] For each cell at each predicted frequency point, the measurement reduction degree is calculated based on the actual measured frequency points and the number of cells measured at each of the actual measured frequency points.

[0212] In one embodiment, the performance indicator corresponding to the predicted measurement event and / or mobility event includes at least one of the following:

[0213] Model prediction accuracy;

[0214] Model false positive rate;

[0215] Model prediction completeness;

[0216] Model missed detection rate;

[0217] Comprehensive performance indicators of the model.

[0218] In one embodiment, the model prediction accuracy and / or the model false detection rate are determined based on the first counter and the second counter; or

[0219] The model prediction completeness and / or the model missed detection rate are determined based on the second counter and the third counter; or

[0220] The comprehensive performance index of the model is determined based on the first counter, the second counter and the third counter;

[0221] The first counter is used to count events that were predicted by the model but did not actually occur; the second counter is used to count events that were predicted by the model and actually occurred; and the third counter is used to count events that were not predicted by the model but actually occurred.

[0222] In one embodiment, the counting condition of the first timer includes: the mobility event and / or measurement event does not occur on the cell within a time period not exceeding a set time range before or after the time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or

[0223] The counting condition of the second counter includes: the mobility event and / or measurement event occurs on the cell within a time period not exceeding a set time range before or after a time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or

[0224] The counting condition of the third counter includes: the model does not predict the mobility event and / or measurement event within a time period not exceeding a set time range before or after a time point when the mobility event and / or measurement event occurs on the cell.

[0225] In one embodiment, the second counter also includes events that were predicted by the model and would have occurred but were avoided.

[0226] In one embodiment, the method for determining an event that would have occurred but was avoided as predicted by the model includes:

[0227] After the network device performs an avoidance operation on the relevant cell based on the predicted mobility event, the terminal device continues to perform actual measurement and / or prediction on the relevant cell of the predicted mobility event to determine whether the predicted mobility event is an event that was predicted by the model to occur but was avoided; or

[0228] After the network device performs an avoidance operation on the relevant cell based on the predicted measurement event, the terminal device continues to perform actual measurement on the relevant cell to determine whether the predicted measurement event is an event that was predicted by the model to occur but was avoided.

[0229] In one embodiment, the other performance indicators include at least one of the following:

[0230] Model stability information;

[0231] Model scoring information;

[0232] Model input data quality information.

[0233] For specific examples of the second communication device executing methods 700 and 800 of this embodiment, reference can be made to the relevant descriptions about the second communication device in the above methods 400, 500, and 600, which will not be repeated here for the sake of brevity.

[0234] In an embodiment of the present application, when the UE side has AI / ML models for mobility measurement and mobility event prediction, the network needs to monitor the operation of these models through certain methods in order to manage these models.

[0235] The AI / ML model on the UE side may include an algorithm model using a neural network, and its main functions may include one or more of the following examples.

[0236] Example 1: L3 cell measurement results are predicted based on partial actual measurement results in a certain dimension (such as time domain or spatial domain), as shown in FIG9 .

[0237] Example 2: Based on actual measurement results, certain mobility events are predicted, such as measurement events, radio link failure events, handover failure events, ping-pong handover events, and too-short-time handover events, as shown in FIG10 .

[0238] Before AI / ML models can run on the UE, they must be trained. Even then, the network must monitor the performance of these AI / ML models. If the AI / ML model's performance fails to meet network expectations, the network must take appropriate action, such as adjusting parameters or replacing the model.

[0239] Before monitoring AI / ML models, you need to first determine the performance indicators of the model. For the example in Figure 9, the following model performance statistical indicators are mainly included:

[0240] (1) Accuracy of measurement result prediction

[0241] During the AI / ML model's operation, some measurement results require actual measurements from the UE. This process, as well as the final cell-level L3 measurement results obtained at reference point C, is identical to those in related technologies. Some measurement results can be generated using the process shown in Figure 9. When monitoring the model, in addition to the predicted results, an actual measurement result in the same domain is also required as a reference value for comparison.

[0242] Taking the reference signal strength RSRP as an example (unit: dB), assuming the predicted measurement result is represented by {X1, X2, ...Xn}, and the corresponding measured measurement result is {Y1, Y2, ...Yn}, then the measurement accuracy can be expressed as:

[0243] Option 1: Measurement accuracy = num(abs(Xi - Yi) < threshold) / n * 100%, where the operator abs() represents the absolute value, the operator num() represents the number of subscripts i that meet the requirement, and the threshold is in decibels. Assuming a threshold of 1dB, Option 1 represents the percentage of predicted and measured results for which the absolute value of the difference between the predicted and measured results is less than 1dB. A larger threshold value lowers the threshold, while a higher threshold value lowers the threshold. The key parameter in Option 1 is the threshold.

[0244] Option 2: Measurement accuracy = RMSE(Xi, Yi) dB, where RMSE is the root mean square error operator, RMSE(Xi, Yi) = squ(Xigma(Xi-Yi)^2), where the Xigma() operator is a summation operation and the squ() operator is a square root operation. The root mean square error between the measured and predicted measurement results can represent an absolute error value between the two.

[0245] Option 3: Measurement accuracy = Xigma(abs(Xi - Yi)) / n dB, which represents the absolute error between the two.

[0246] The above-mentioned predicted and measured measurement results may be the measurement results of the reference point where the model output is located in FIG9 .

[0247] (2) Measuring the degree of reduction

[0248] The model shown in Figure 9 predicts the UE's performance in a specific domain, such as the time domain (or spatial or frequency domain). Using the RSRP (reference signal strength) as an example, the unit is decibels. Assuming the predicted measurement results are {X1, X2, ...Xn}, and the actual measurement results obtained by the UE at the reference point in Figure 9 are {Z1, Z2, ...Zm}, the performance metric can be expressed as 1-m / (m+n)*100%.

[0249] In spatial domain prediction, the number of measured results and predicted results is the same, and the measured beam is part of the predicted beam, so the measurement reduction degree can be expressed as 1-m / n, where m is the part of the n beams in the full beam set.

[0250] In frequency domain prediction, for each cell at each predicted frequency point, assuming that the number of measured frequency points is m and the number of cells measured at each frequency point is n, the measurement reduction degree is 1-m*n / (1+m*n).

[0251] For mobility events, there are several model performance statistical indicators:

[0252] The following counters can be set in the UE for measurement events and / or mobility events:

[0253] 1. Counter n1: measurement events and / or mobility events that were predicted by the model but did not actually occur.

[0254] 2. Counter n2: measurement events and / or mobility events that were predicted by the model and actually occurred or would have occurred but were avoided.

[0255] 3. Counter n3: measurement events and / or mobility events that were not predicted by the model but actually occurred.

[0256] For events that are avoided in counter n2, for example, if the UE reports a predicted ping-pong handover event to the network in advance, the network takes measures to prevent the handover to cell B. In this case, the predicted event is avoided. However, because the UE can continue to measure or predict the signals of serving cell A and neighboring cell B, based on the criteria of measurement event A3, for example, the UE can determine whether a ping-pong handover is likely to occur (assuming that a handover will occur after the event is triggered). Because the UE's trajectory and measured results do not change due to the network's measures to avoid ping-pong handovers, even if an event is avoided, the UE still has a way to determine whether the prediction result is accurate.

[0257] Measurement events are generally not avoided. The base station typically requires the UE to predict measurement events so that the UE can report them and take appropriate handover actions. However, the handover actions taken by the network may occur before the measurement event occurs. Therefore, if the serving cell changes, the predicted measurement event itself will not occur. However, the UE can continue to perform actual measurements on the relevant cells to determine if the predictions are accurate.

[0258] When using AI / ML models to predict mobility events, in addition to predicting whether the event will occur, it is also necessary to predict when the event will occur. The UE can also know whether the predicted event will occur through actual measurement reports. Since the prediction and measurement of mobility events are ongoing, to determine whether a predicted mobility event has occurred, it is also necessary to look at the degree of proximity on the time axis between the predicted mobility event and the mobility event determined based on the actual measurement report in the relevant serving cell or neighboring cell. This is because there is generally a certain gap between the time predicted by the model and the time determined based on the actual measurement report. Assuming that the maximum time difference between the two is defined as the parameter MAX_TIME_GAP, the counting conditions of counters n1, n2 and n3 are as follows:

[0259] The counting condition of the counter n1 is: the mobility event does not occur on a certain cell within a time period not exceeding MAX_TIME_GAP before or after the time point of occurrence of a mobility event on the certain cell predicted by the model.

[0260] The counting condition of the counter n2 is: a mobility event occurs on a certain cell within a time not exceeding MAX_TIME_GAP before or after the time point of occurrence of a mobility event on the certain cell predicted by the model.

[0261] The counting condition of counter n3 is: a mobility event occurs in a certain cell, and the model does not predict the mobility event within a time not exceeding MAX_TIME_GAP.

[0262] For example, Figures 11a to 11b are schematic diagrams of the counting conditions of the counter. As shown in Figure 11a, the counting conditions of n1 may include: the model can predict in advance the time point at which a certain measurement event (Measured event) and / or mobility event (Mobility event) will occur (the predicted event is represented by a black star), and the event is not measured before or after this time point (the measured measurement event and / or mobility event is represented by a white star). As shown in Figure 11b, the counting conditions of n2 may include: the model can predict in advance the time point at which a certain measurement event and / or mobility event will occur (black star), and this time point (black star) may be before or after the time point at which the event is measured (white star). As shown in Figure 11c, the counting conditions of n3 may include: the model does not predict the event before or after the time point (white star) of the measured measurement event and / or mobility event.

[0263] For example, the above timer can be represented by the following table:

[0264] Table 2 Mobility event counter allocation

[0265] Examples of performance indicators related to mobility events include:

[0266] Model prediction accuracy = (n2) / (n1+n2), model false positive rate = 1-model prediction accuracy;

[0267] Model prediction completeness = (n2) / (n3+n2), model missed detection rate = 1-model prediction completeness;

[0268] The comprehensive performance index of the model is F1 = 2*(1 / (1 / model prediction accuracy + 1 / model prediction completeness)).

[0269] The above-mentioned mobility measurement prediction and mobility event prediction may also include the following performance indicators:

[0270] 1. Model stability information, which is used to describe the deviation between multiple model inference results. It can include information such as the mean square error, root mean square error, mean absolute error, coefficient of determination R2_score, confidence level, and continuous / significant performance degradation between performance indicators.

[0271] 2. Model scoring information, which provides an overall description of the model's performance. It combines model performance statistics with model stability information. This scoring information can be used to compare different models on a consistent basis. For example, the scoring information can be a percentage score, such as 95.

[0272] 3. Model input data quality information, which includes the integrity, sparsity and measurement accuracy of the model input data.

[0273] The aforementioned performance indicators can be quantified. For performance indicator results, a standardized quantization method can be used to convert continuous scalar quantities (percentages, dBm, dB, and other dimensionless values) into values ​​or ranges that can be represented by information bits (index values). Different quantization methods result in varying degrees of information loss during this quantization process. For example, for percentages, Option 1 for the predicted accuracy of measurement results and the measurement reduction degree method may differ. For example, in Option 1, an accuracy below 80% is essentially insignificant and can be considered inaccurate. Results above 80% require further detailed reporting. For example, the table for the predicted accuracy of measurement results could be {<80%, 80%-85%, 85%-90%, 90%-93%, 93%-96%, 96%-98%, 98%-99%, >99%}. Different ranges can correspond to different bit values, i.e., using three-bit quantization. For values ​​below the measurement reduction degree, a savings of, say, 20% is sufficient, and an average pacing is more reasonable. As for Option 2 and Option 3 of the measurement result prediction accuracy, after predicting the approximate range, they can be quantified in a similar way.

[0274] Referring to Table 1, the following is a description of the Uu interface process:

[0275] Method 1: In order to manage the UE-side model, the network requires the UE to monitor the model performance indicators and report the final performance monitoring results.

[0276] Step 1: The network sends a model monitoring command to the UE. This command contains at least the following content:

[0277] (1) Performance indicators that need to be monitored and related control parameters.

[0278] Performance indicators include the measurement result prediction accuracy and measurement reduction mentioned above. If the measurement result prediction accuracy is the key, for Option 1, the network needs to configure a threshold.

[0279] (2) The method of reporting the monitoring performance.

[0280] Step 2: After receiving the RRC message of the performance monitoring command of S1, the UE collects data of the required performance indicator according to the control parameters, calculates and quantifies it, and reports it according to the reporting method.

[0281] Method 2: In order to manage the UE side model, the network requires the UE to report relevant measurement results so that the network side can calculate performance indicators and report the final performance monitoring results.

[0282] Step 1: The network sends a model monitoring command to the UE, including the required reporting content and reporting method.

[0283] For the performance indicators of measurement prediction, this command may include at least the following required reporting content: the UE reports the actual measurement result at a certain reference point and the corresponding predicted measurement result.

[0284] For performance indicators of measurement events and / or mobility events, this command may include at least the following required reporting content:

[0285] For measurement events, this command can indicate:

[0286] (1) The UE reports the predicted measurement event.

[0287] (2) The UE reports the actual measurement events triggered by the actual measurement reports and marks whether such measurement events are predicted by the model.

[0288] For other mobility events, this command can indicate:

[0289] (1) The UE reports measurement events and / or measurement results based on actual measurements.

[0290] (2) The UE reports the predicted mobility event.

[0291] Step 2: The network calculates the performance indicators of the model based on the content reported by the UE. For measurement prediction, the network calculates the predicted performance indicators based on the actual measurement results reported by the UE and the corresponding predicted measurement results. For example, for measurement event prediction, based on the information reported by the UE, the network can perform statistics in the manner shown in Table 2 and calculate the relevant performance indicators according to the formula. For other reported mobility events, the network can choose not to trust the UE's judgment, and then determine whether the UE's judgment is accurate based on the actual situation; the network can choose to trust the UE's judgment, thereby avoiding the mobility event. Based on the actual measurement events and / or measurement results reported by the UE, the network can determine whether the avoided mobility event is likely to occur. For these judgments of mobility events, the network can calculate the corresponding counters respectively in the manner shown in Table 2, thereby obtaining the performance of the model operation according to the formula.

[0292] The signaling overhead of the radio interface in the above method 1 is lower than that in the above method 2.

[0293] Method 3: UE requests the network to perform performance testing to manage the UE-side model

[0294] Step 1: The UE sends a performance indicator monitoring request message, which may include the performance indicator information requested for monitoring and possible reasons.

[0295] Step 2: If the network allows the UE to monitor performance indicators, it sends the performance indicators that are allowed to be monitored, as well as the control parameters related to these performance indicators, such as the thresholds in Option 1. This message may also include threshold parameters used to evaluate model performance indicators or stability indicators or scores, such as the threshold at which a model with a score less than 90 is considered to be deactivated.

[0296] Step 3: The UE monitors the corresponding performance indicators and manages the model based on these network control parameters. The UE can inform the network of the results of the model management through signaling.

[0297] Method 4: UE requests the network to perform performance testing in order to manage the UE-side model

[0298] Step 1: The UE sends a performance indicator monitoring request message, which may include the performance indicator information requested for monitoring and possible reasons.

[0299] Step 2: If the network allows the UE to monitor performance indicators, it sends a message requesting the UE to report relevant content and how to report. For the content part, refer to Method 2.

[0300] Step 3: The UE reports the required content based on the network's control parameters. The network evaluates the performance of the UE-side model based on the reported content and takes model management measures, such as sending model management signaling to change the model.

[0301] In the above process, the network may require the UE to report in a certain way: This refers to the way in which the network controls the UE to report the quantified performance indicators to the network after obtaining the above required performance indicators. For example, the following methods can be adopted:

[0302] Single reporting means that after receiving the control parameters of the performance monitoring, the UE calculates them in the prescribed manner. When the required performance indicator parameters are ready, these quantified indicators are reported to the network through RRC signaling.

[0303] Periodic reporting. In this case, the network needs to configure periodic parameters.

[0304] Event-triggered reporting. In this case, the network needs to be configured to report when, for example, the prediction accuracy falls below a certain threshold, or when the measurement reduction falls below a certain threshold. If the threshold is not met, the UE needs to monitor but does not need to report.

[0305] After the event is triggered, it is reported periodically.

[0306] The solution of the embodiment of the present application effectively monitors the operating performance of the UE-side model through signaling interaction between the network and the UE, so as to further manage the UE-side model, including activation or deactivation, replacement, fallback, etc.

[0307] The handover mentioned in the embodiment of the present application can also be replaced by a change in the secondary cell group (SCG), that is, adding or replacing the SCG without changing the master cell group (MCG). The SCG change can also occur at the same time as the MCG change.

[0308] The above UE capabilities may include time domain measurement prediction capabilities, spatial domain measurement prediction capabilities, that is, predicting the measurement results of other beams based on the measurement results of some beams; and frequency domain measurement prediction capabilities, for example, predicting the measurement results of other frequency points based on the measurement results of one or more frequency points.

[0309] FIG12 is a schematic block diagram of a first communication device 1200 according to an embodiment of the present application. The first communication device 1200 may include:

[0310] The first processing unit 1210 is configured to obtain a performance monitoring result related to mobility management based on the measured result and the predicted result related to mobility management.

[0311] In one embodiment, the first communication device further includes:

[0312] The first communication unit 1220 is configured to send first information, where the first information is used to indicate a performance monitoring result related to the mobility management.

[0313] In one embodiment, the first information includes a quantified value of the performance monitoring result.

[0314] In one embodiment, the first processing unit 1210 is further configured to input actual measurement results related to mobility management into the model to obtain prediction results related to mobility management.

[0315] In one embodiment, the first communication unit 1220 is further configured to receive a first model monitoring command, where the first model monitoring command is used to instruct the first communication device to report a performance indicator of the model.

[0316] In one embodiment, the first model monitoring command is used to indicate at least one of the following:

[0317] The performance metrics of the model that need to be monitored;

[0318] The control parameters of the model that need to be monitored;

[0319] Reporting method.

[0320] In one embodiment, the performance indicator includes measurement result prediction accuracy and / or measurement reduction degree, and the control parameter includes a threshold corresponding to the measurement result prediction accuracy.

[0321] In one embodiment, the first processing unit 1210 is further configured to perform at least one of data collection, calculation, and quantification on the performance indicator based on the control parameter in the first model monitoring command, and report the performance indicator in accordance with the reporting method.

[0322] In one embodiment, the first communication unit 1220 is further configured to send a first performance indicator monitoring request message, where the first performance indicator monitoring request message includes performance indicator information of the model that the first communication device requests to monitor and / or a reason for requesting monitoring.

[0323] In one embodiment, the first communication unit 1220 is further configured to receive second information, where the second information is used to indicate the measured results and predicted results related to the mobility management.

[0324] In an implementation, the first communication unit 1220 is further configured to send a second model monitoring command, where the second model monitoring command is used to instruct the second communication device to report measurement results and / or measurement events related to mobility management.

[0325] In one embodiment, the second model monitoring command is used to indicate at least one of the following:

[0326] Measurement results that require actual measurement;

[0327] The measurement results that need to be predicted;

[0328] The measured results of the measurement event;

[0329] Measured results of mobility events;

[0330] Reporting method.

[0331] In one embodiment, the first communications device obtains, based on the measured results and the predicted results related to mobility management, a performance monitoring result related to mobility management, including at least one of the following:

[0332] The first communication device calculates a performance indicator corresponding to the measurement result based on the actual measurement result and the corresponding predicted measurement result;

[0333] The first communications device calculates a performance indicator corresponding to the event based on statistical results of the predicted measurement event and / or the predicted mobility event.

[0334] In one embodiment, the first communication unit 1220 is further configured to receive a second performance indicator monitoring request message, where the second performance indicator monitoring request message includes performance indicator information of the model that the second communication device requests to monitor and / or a reason for requesting monitoring.

[0335] In one embodiment, the reporting method includes at least one of the following:

[0336] Single report;

[0337] Periodic reporting;

[0338] Event trigger reporting;

[0339] After the event is triggered, it is reported periodically.

[0340] In one embodiment, the prediction result related to mobility management includes at least one of a predicted measurement result, a predicted measurement event, and a predicted mobility event related to mobility management.

[0341] In one embodiment, the mobility management-related performance monitoring result includes at least one of the following:

[0342] a performance indicator corresponding to the predicted measurement result related to the mobility management;

[0343] The predicted measurement events and / or performance indicators corresponding to the mobility management-related mobility events;

[0344] Other performance indicators.

[0345] In one embodiment, the performance indicator corresponding to the predicted measurement result includes at least one of the following:

[0346] Prediction accuracy of measurement results;

[0347] Measure the reduction.

[0348] In one embodiment, the calculation method of the measurement result prediction accuracy includes at least one of the following:

[0349] Calculating the measurement result prediction accuracy based on the number of measurement result pairs whose absolute error value between the predicted measurement result and the measured measurement result is less than a first threshold, and the total number of measurement result pairs;

[0350] Calculate the prediction accuracy of the measurement result based on the root mean square error between the predicted measurement result and the measured measurement result;

[0351] The measurement result prediction accuracy is calculated based on the absolute error value between the predicted measurement result and the measured measurement result, and the number of total measurement result pairs.

[0352] In one embodiment, the calculation method of the measurement reduction degree includes at least one of the following:

[0353] Calculating the measurement reduction based on the number of predicted measurement results and the measured measurement results;

[0354] Calculating the degree of measurement reduction based on the number of measured beams and the predicted beams;

[0355] For each cell at each predicted frequency point, the measurement reduction degree is calculated based on the actual measured frequency points and the number of cells measured at each of the actual measured frequency points.

[0356] In one embodiment, the performance indicator corresponding to the predicted measurement event and / or mobility event includes at least one of the following:

[0357] Model prediction accuracy;

[0358] Model false positive rate;

[0359] Model prediction completeness;

[0360] Model missed detection rate;

[0361] Comprehensive performance indicators of the model.

[0362] In one embodiment, the model prediction accuracy and / or the model false detection rate are determined based on the first counter and the second counter; or

[0363] The model prediction completeness and / or the model missed detection rate are determined based on the second counter and the third counter; or

[0364] The comprehensive performance index of the model is determined based on the first counter, the second counter and the third counter;

[0365] The first counter is used to count events that were predicted by the model but did not actually occur; the second counter is used to count events that were predicted by the model and actually occurred; and the third counter is used to count events that were not predicted by the model but actually occurred.

[0366] In one embodiment, the counting condition of the first timer includes: the mobility event and / or measurement event does not occur on the cell within a time period not exceeding a set time range before or after the time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or

[0367] The counting condition of the second counter includes: the mobility event and / or measurement event occurs on the cell within a time period not exceeding a set time range before or after a time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or

[0368] The counting condition of the third counter includes: the model does not predict the mobility event and / or measurement event within a time period not exceeding a set time range before or after a time point when the mobility event and / or measurement event occurs on the cell.

[0369] In one embodiment, the second counter also includes events that were predicted by the model and would have occurred but were avoided.

[0370] In one embodiment, the method for determining an event that would have occurred but was avoided as predicted by the model includes:

[0371] After the network device performs an avoidance operation on the relevant cell based on the predicted mobility event, the terminal device continues to perform actual measurement on the relevant cell of the predicted mobility event to determine whether the predicted mobility event is an event that was predicted by the model to occur but was avoided; or

[0372] After the network device performs an avoidance operation on the relevant cell based on the predicted measurement event, the terminal device continues to perform actual measurement on the relevant cell to determine whether the predicted measurement event is an event that was predicted by the model to occur but was avoided.

[0373] In one embodiment, the other performance indicators include at least one of the following:

[0374] Model stability information;

[0375] Model scoring information;

[0376] Model input data quality information.

[0377] The first communication device 1200 of the embodiment of the present application can implement the corresponding functions of the first communication device in the aforementioned method embodiment. The processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the first communication device 1200 can be found in the corresponding descriptions in the above-mentioned method embodiments, and will not be repeated here. It should be noted that the functions described in the various modules (sub-modules, units or components, etc.) in the first communication device 1200 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.) or by the same module (sub-module, unit or component, etc.).

[0378] FIG13 is a schematic block diagram of a second communication device 1300 according to an embodiment of the present application. The second communication device 1300 may include:

[0379] The second communication module 1310 is configured to receive first information, where the first information is used to indicate a performance monitoring result related to mobility management, where the performance monitoring result related to mobility management is obtained based on a measured result and a predicted result related to mobility management.

[0380] In one embodiment, the first information includes a quantified value of the performance monitoring result.

[0381] In one embodiment, the prediction result related to mobility management is obtained by the first communications device inputting the actual measurement result related to mobility management into a model.

[0382] In one embodiment, the second communication module 1310 is further configured to send a first model monitoring command, where the first model monitoring command is configured to instruct the first communication device to report a performance indicator of the model.

[0383] In one embodiment, the first model monitoring command is used to indicate at least one of the following:

[0384] The performance metrics of the model that need to be monitored;

[0385] The control parameters of the model that need to be monitored;

[0386] Reporting method.

[0387] In one embodiment, the performance indicator includes measurement result prediction accuracy and / or measurement reduction degree, and the control parameter includes a threshold corresponding to the measurement result prediction accuracy.

[0388] In one embodiment, the second communication module 1310 is further configured to receive a first performance indicator monitoring request message, where the first performance indicator monitoring request message includes performance indicator information of the model that the first communication device requests to monitor and / or a reason for requesting monitoring.

[0389] In one embodiment, the second communication module 1310 is further configured to send second information, where the second information is used to indicate the measured results and predicted results related to the mobility management.

[0390] In one embodiment, the second communication module 1310 is further configured to receive a second model monitoring command, where the second model monitoring command is configured to instruct the second communication device to report measurement results and / or measurement events related to mobility management.

[0391] In one embodiment, the second model monitoring command is used to indicate at least one of the following:

[0392] Measurement results that require actual measurement;

[0393] The measurement results that need to be predicted;

[0394] The measured results of the measurement event;

[0395] Measured results of mobility events;

[0396] Reporting method.

[0397] In one embodiment, the second communication module 1310 is further configured to send a second performance indicator monitoring request message, where the second performance indicator monitoring request message includes performance indicator information of the model that the second communication device requests to monitor and / or a reason for requesting monitoring.

[0398] In one embodiment, the reporting method includes at least one of the following:

[0399] Single report;

[0400] Periodic reporting;

[0401] Event trigger reporting;

[0402] After the event is triggered, it is reported periodically.

[0403] In one embodiment, the prediction result related to mobility management includes at least one of a predicted measurement result, a predicted measurement event, and a predicted mobility event related to mobility management.

[0404] In one embodiment, the mobility management-related performance monitoring result includes at least one of the following:

[0405] a performance indicator corresponding to the predicted measurement result related to the mobility management;

[0406] The predicted measurement events and / or performance indicators corresponding to the mobility management-related mobility events;

[0407] Other performance indicators.

[0408] In one embodiment, the performance indicator corresponding to the predicted measurement result includes at least one of the following:

[0409] Prediction accuracy of measurement results;

[0410] Measure the reduction.

[0411] In one embodiment, the calculation method of the measurement result prediction accuracy includes at least one of the following:

[0412] Calculating the measurement result prediction accuracy based on the number of measurement result pairs whose absolute error value between the predicted measurement result and the measured measurement result is less than a first threshold and the total number of measurement result pairs;

[0413] Calculate the prediction accuracy of the measurement result based on the root mean square error between the predicted measurement result and the measured measurement result;

[0414] The measurement result prediction accuracy is calculated based on the absolute error value between the predicted measurement result and the measured measurement result, and the number of total measurement result pairs.

[0415] In one embodiment, the calculation method of the measurement reduction degree includes at least one of the following:

[0416] Calculating the measurement reduction based on the number of predicted measurement results and the measured measurement results;

[0417] Calculating the degree of measurement reduction based on the number of measured beams and the predicted beams;

[0418] For each cell at each predicted frequency point, the measurement reduction degree is calculated based on the actual measured frequency points and the number of cells measured at each of the actual measured frequency points.

[0419] In one embodiment, the performance indicator corresponding to the predicted measurement event and / or mobility event includes at least one of the following:

[0420] Model prediction accuracy;

[0421] Model false positive rate;

[0422] Model prediction completeness;

[0423] Model missed detection rate;

[0424] Comprehensive performance indicators of the model.

[0425] In one embodiment, the model prediction accuracy and / or the model false detection rate are determined based on the first counter and the second counter; or

[0426] The model prediction completeness and / or the model missed detection rate are determined based on the second counter and the third counter; or

[0427] The comprehensive performance index of the model is determined based on the first counter, the second counter and the third counter;

[0428] The first counter is used to count events that were predicted by the model but did not actually occur; the second counter is used to count events that were predicted by the model and actually occurred; and the third counter is used to count events that were not predicted by the model but actually occurred.

[0429] In one embodiment, the counting condition of the first timer includes: the mobility event and / or measurement event does not occur on the cell within a time period not exceeding a set time range before or after the time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or

[0430] The counting condition of the second counter includes: the mobility event and / or measurement event occurs on the cell within a time period not exceeding a set time range before or after a time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or

[0431] The counting condition of the third counter includes: the model does not predict the mobility event and / or measurement event within a time period not exceeding a set time range before or after a time point when the mobility event and / or measurement event occurs on the cell.

[0432] In one embodiment, the second counter also includes events that were predicted by the model and would have occurred but were avoided.

[0433] In one embodiment, the method for determining an event that would have occurred but was avoided as predicted by the model includes:

[0434] After the network device performs an avoidance operation on the relevant cell based on the predicted mobility event, the terminal device continues to perform actual measurement and / or prediction on the relevant cell of the predicted mobility event to determine whether the predicted mobility event is an event that was predicted by the model to occur but was avoided; or

[0435] After the network device performs an avoidance operation on the relevant cell based on the predicted measurement event, the terminal device continues to perform actual measurement on the relevant cell to determine whether the predicted measurement event is an event that was predicted by the model to occur but was avoided.

[0436] In one embodiment, the other performance indicators include at least one of the following:

[0437] Model stability information;

[0438] Model scoring information;

[0439] Model input data quality information.

[0440] The second communication device 1300 of the embodiment of the present application can implement the corresponding functions of the second communication device in the aforementioned method embodiment. The processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the second communication device 1300 can be found in the corresponding descriptions in the above-mentioned method embodiments, and will not be repeated here. It should be noted that the functions described in the various modules (sub-modules, units or components, etc.) in the second communication device 1300 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.) or by the same module (sub-module, unit or component, etc.).

[0441] Figure 14 is a schematic structural diagram of a communication device 1400 according to an embodiment of the present application. The communication device 1400 includes a processor 1410, which can call and execute a computer program from a memory to enable the communication device 1400 to implement the method in the embodiment of the present application.

[0442] In one embodiment, the communication device 1400 may further include a memory 1420. The processor 1410 may call and execute a computer program from the memory 1420 to enable the communication device 1400 to implement the method in the embodiment of the present application.

[0443] The memory 1420 may be a separate device independent of the processor 1410 , or may be integrated into the processor 1410 .

[0444] In one embodiment, the communication device 1400 may further include a transceiver 1430 , and the processor 1410 may control the transceiver 1430 to communicate with other devices. Specifically, the transceiver 1430 may send information or data to other devices, or receive information or data sent by other devices.

[0445] The transceiver 1430 may include a transmitter and a receiver. The transceiver 1430 may further include an antenna, and the number of antennas may be one or more.

[0446] In one embodiment, the communication device 1400 may be the first communication device of the embodiment of the present application, and the communication device 1400 may implement the corresponding processes implemented by the first communication device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0447] In one embodiment, the communication device 1400 may be the second communication device of the embodiment of the present application, and the communication device 1400 may implement the corresponding processes implemented by the second communication device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0448] 15 is a schematic structural diagram of a chip 1500 according to an embodiment of the present application. The chip 1500 includes a processor 1510, which can call and execute a computer program from a memory to implement the method according to the embodiment of the present application.

[0449] In one embodiment, the chip 1500 may further include a memory 1520. The processor 1510 may call and execute a computer program from the memory 1520 to implement the method executed by the first communication device or the second communication device in the embodiment of the present application.

[0450] The memory 1520 may be a separate device independent of the processor 1510 , or may be integrated into the processor 1510 .

[0451] In one embodiment, the chip 1500 may further include an input interface 1530. The processor 1510 may control the input interface 1530 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0452] In one embodiment, the chip 1500 may further include an output interface 1540. The processor 1510 may control the output interface 1540 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0453] In one embodiment, the chip can be applied to the first communication device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the first communication device in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0454] In one embodiment, the chip can be applied to the second communication device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the second communication device in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0455] The chips used in the first communication device and the second communication device may be the same chip or different chips.

[0456] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0457] The processor mentioned above may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. The general-purpose processor mentioned above may be a microprocessor or any conventional processor, etc.

[0458] The memory mentioned above may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM).

[0459] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0460] FIG16 is a schematic block diagram of a communication system 1600 according to an embodiment of the present application. The communication system 1600 includes a first communication device 1610 and a second communication device 1620 .

[0461] The first communication device 1610 is configured to obtain a performance monitoring result related to mobility management based on a measured result and a predicted result related to mobility management.

[0462] The second communication device 1620 is configured to receive first information, where the first information is used to indicate a performance monitoring result related to mobility management, where the performance monitoring result related to mobility management is obtained based on a measured result and a predicted result related to mobility management.

[0463] The first communication device 1610 can be used to implement the corresponding functions implemented by the first communication device in the above method, and the second communication device 1620 can be used to implement the corresponding functions implemented by the second communication device in the above method. For the sake of brevity, they are not described here in detail.

[0464] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function in accordance with the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0465] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0466] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0467] The above is only a specific embodiment of the present application, but the scope of protection of this application is not limited to this. Any changes or substitutions that can be easily conceived by any person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, comprising: The first communication device obtains a performance monitoring result related to mobility management based on the measured result and the predicted result related to mobility management.

2. The method according to claim 1, wherein The method further comprises: The first communication device sends first information, where the first information is used to indicate a performance monitoring result related to the mobility management.

3. The method according to claim 2, wherein: The first information includes a quantitative value of the performance monitoring result.

4. The method according to any one of claims 1 to 3, wherein The method further comprises: The first communication device inputs the actual measurement results related to mobility management into the model to obtain the prediction results related to mobility management.

5. The method according to any one of claims 1 to 4, wherein The method further comprises: The first communication device receives a first model monitoring command, where the first model monitoring command is used to instruct the first communication device to report a performance indicator of a model.

6. The method according to claim 5, wherein: The first model monitoring command is used to indicate at least one of the following: The performance metrics of the model that need to be monitored; The control parameters of the model that need to be monitored; Reporting method.

7. The method according to claim 6, wherein: The performance indicator includes measurement result prediction accuracy and / or measurement reduction degree, and the control parameter includes a threshold corresponding to the measurement result prediction accuracy.

8. The method according to any one of claims 6 or 7, wherein The method further comprises: The first communication device performs at least one of data collection, calculation and quantification on the performance indicator based on the control parameter in the first model monitoring command, and reports the performance indicator in accordance with the reporting method.

9. The method according to any one of claims 5 to 8, wherein The method further comprises: The first communication device sends a first performance indicator monitoring request message, where the first performance indicator monitoring request message includes performance indicator information of the model that the first communication device requests to monitor and / or a reason for requesting monitoring.

10. The method according to claim 1, wherein The method further comprises: The first communication device receives second information, where the second information is used to indicate the measured results and predicted results related to the mobility management.

11. The method according to claim 10, wherein: The method further comprises: The first communication device sends a second model monitoring command, where the second model monitoring command is used to instruct the second communication device to report measurement results and / or measurement events related to mobility management.

12. The method according to claim 11, wherein The second model monitoring command is used to indicate at least one of the following: Measurement results that require actual measurement; The measurement results that need to be predicted; The measured results of the measurement event; Measured results of mobility events; Reporting method.

13. The method according to claim 12, wherein: The first communications device obtains, based on the measured results and the predicted results related to the mobility management, a performance monitoring result related to the mobility management, including at least one of the following: The first communication device calculates a performance indicator corresponding to the measurement result based on the actual measurement result and the corresponding predicted measurement result; The first communication device calculates a performance indicator corresponding to the event based on statistical results of the predicted measurement event and / or the predicted mobility event.

14. The method according to any one of claims 10 to 13, wherein The method further comprises: The first communication device receives a second performance indicator monitoring request message, where the second performance indicator monitoring request message includes performance indicator information of the model that the second communication device requests to monitor and / or a reason for requesting monitoring.

15. The method according to claim 6 or 12, wherein: The reporting method includes at least one of the following: Single report; Periodic reporting; Event trigger reporting; After the event is triggered, it is reported periodically.

16. The method according to any one of claims 1 to 15, wherein The mobility management-related prediction result includes at least one of a mobility management-related predicted measurement result, a predicted measurement event, and a predicted mobility event.

17. The method according to any one of claims 1 to 16, wherein The performance monitoring result related to mobility management includes at least one of the following: a performance indicator corresponding to the predicted measurement result related to the mobility management; The predicted measurement events and / or performance indicators corresponding to the mobility management-related mobility events; Other performance indicators.

18. The method according to claim 17, wherein The performance indicator corresponding to the predicted measurement result includes at least one of the following: Prediction accuracy of measurement results; Measure the reduction.

19. The method according to claim 7 or 18, wherein The calculation method of the measurement result prediction accuracy includes at least one of the following: Calculating the measurement result prediction accuracy based on the number of measurement result pairs whose absolute error value between the predicted measurement result and the measured measurement result is less than a first threshold, and the total number of measurement result pairs; Calculating the prediction accuracy of the measurement result based on the root mean square error between the predicted measurement result and the measured measurement result; The measurement result prediction accuracy is calculated based on the absolute error value between the predicted measurement result and the measured measurement result, and the number of total measurement result pairs.

20. The method according to claim 7 or 18, wherein The calculation method of the measurement reduction degree includes at least one of the following: calculating the degree of measurement reduction based on the number of predicted measurement results and measured measurement results; Calculating the measurement reduction degree based on the number of measured beams and the predicted beams; For each cell at each predicted frequency point, the measurement reduction degree is calculated based on the measured frequency points and the number of cells measured at each of the measured frequency points.

21. The method according to claim 17, wherein The performance indicator corresponding to the predicted measurement event and / or mobility event includes at least one of the following: Model prediction accuracy; Model false positive rate; Model prediction completeness; Model missed detection rate; Comprehensive performance indicators of the model.

22. The method according to claim 21, wherein The model prediction accuracy and / or the model false detection rate are determined based on the first counter and the second counter; or The model prediction completeness and / or the model missed detection rate are determined based on the second counter and the third counter; or The comprehensive performance index of the model is determined based on the first counter, the second counter and the third counter; The first counter is used to count events that are predicted by the model but do not actually occur; the second counter is used to count events that are predicted by the model and actually occur; and the third counter is used to count events that are not predicted by the model but actually occur.

23. The method according to claim 22, wherein The counting condition of the first timer includes: the mobility event and / or measurement event does not occur on the cell within a time period not exceeding a set time range before or after a time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or The counting condition of the second counter includes: the mobility event and / or measurement event occurs on the cell within a time not exceeding a set time range before or after the time point of the mobility event and / or measurement event occurring on the cell predicted by the model; or The counting condition of the third counter includes: the model does not predict the mobility event and / or measurement event within a time period not exceeding a set time range before or after a time point when a mobility event and / or measurement event occurs on a cell.

24. The method according to claim 22 or 23, characterized in that The second counter also includes events that were predicted by the model and would have occurred but were avoided.

25. The method according to claim 24, wherein Events that the model predicted would have occurred but were avoided are identified by: After the network device performs an avoidance operation on the relevant cell based on the predicted mobility event, the terminal device continues to perform actual measurement on the relevant cell of the predicted mobility event to determine whether the predicted mobility event is an event that was predicted by the model to occur but was avoided; or After the network device performs an avoidance operation on the relevant cell based on the predicted measurement event, the terminal device continues to perform actual measurement on the relevant cell to determine whether the predicted measurement event is an event that was predicted by the model to occur but was avoided.

26. The method according to claim 17, wherein The other performance indicators include at least one of the following: Model stability information; Model scoring information; Model input data quality information.

27. A communication method, comprising: The second communication device receives first information, where the first information is used to indicate a performance monitoring result related to mobility management, where the performance monitoring result related to mobility management is obtained based on a measured result and a predicted result related to mobility management.

28. The method according to claim 27, wherein The first information includes a quantitative value of the performance monitoring result.

29. The method according to claim 27 or 28, wherein The prediction result related to mobility management is obtained by the first communication device inputting the actual measurement result related to mobility management into a model.

30. The method according to any one of claims 27 to 29, wherein The method further comprises: The second communication device sends a first model monitoring command, where the first model monitoring command is used to instruct the first communication device to report a performance indicator of the model.

31. The method according to claim 30, wherein The first model monitoring command is used to indicate at least one of the following: The performance metrics of the model that need to be monitored; The control parameters of the model that need to be monitored; Reporting method.

32. The method according to claim 31, wherein The performance indicator includes measurement result prediction accuracy and / or measurement reduction degree, and the control parameter includes a threshold corresponding to the measurement result prediction accuracy.

33. The method according to claim 31 or 32, wherein The method further comprises: The second communication device receives a first performance indicator monitoring request message, where the first performance indicator monitoring request message includes performance indicator information of the model that the first communication device requests to monitor and / or a reason for requesting monitoring.

34. The method of claim 27, wherein: The method further comprises: The second communication device sends second information, where the second information is used to indicate the measured results and predicted results related to the mobility management.

35. The method according to claim 34, wherein The method further comprises: The second communication device receives a second model monitoring command, where the second model monitoring command is used to instruct the second communication device to report measurement results and / or measurement events related to mobility management.

36. The method according to claim 35, wherein The second model monitoring command is used to indicate at least one of the following: Measurement results that require actual measurement; The measurement results that need to be predicted; The measured results of the measurement event; Measured results of mobility events; Reporting method.

37. The method according to any one of claims 34 to 36, wherein The method further comprises: The second communication device sends a second performance indicator monitoring request message, where the second performance indicator monitoring request message includes performance indicator information of the model that the second communication device requests to monitor and / or a reason for requesting monitoring.

38. The method according to claim 31 or 36, wherein The reporting method includes at least one of the following: Single report; Periodic reporting; Event trigger reporting; After the event is triggered, it is reported periodically.

39. The method according to any one of claims 27 to 38, wherein The mobility management-related prediction result includes at least one of a mobility management-related predicted measurement result, a predicted measurement event, and a predicted mobility event.

40. The method according to any one of claims 27 to 39, wherein The performance monitoring result related to mobility management includes at least one of the following: a performance indicator corresponding to the predicted measurement result related to the mobility management; The predicted measurement events and / or performance indicators corresponding to the mobility management-related mobility events; Other performance indicators.

41. The method according to claim 40, wherein The performance indicator corresponding to the predicted measurement result includes at least one of the following: Prediction accuracy of measurement results; Measure the reduction.

42. The method according to claim 32 or 41, wherein The calculation method of the measurement result prediction accuracy includes at least one of the following: Calculating the measurement result prediction accuracy based on the number of measurement result pairs whose absolute error value between the predicted measurement result and the measured measurement result is less than a first threshold, and the total number of measurement result pairs; Calculating the prediction accuracy of the measurement result based on the root mean square error between the predicted measurement result and the measured measurement result; The measurement result prediction accuracy is calculated based on the absolute error value between the predicted measurement result and the measured measurement result, and the number of total measurement result pairs.

43. The method according to claim 32 or 41, wherein The calculation method of the measurement reduction degree includes at least one of the following: calculating the degree of measurement reduction based on the number of predicted measurement results and measured measurement results; Calculating the measurement reduction degree based on the number of measured beams and the predicted beams; For each cell at each predicted frequency point, the measurement reduction degree is calculated based on the measured frequency points and the number of cells measured at each of the measured frequency points.

44. The method of claim 40, wherein The performance indicator corresponding to the predicted measurement event and / or mobility event includes at least one of the following: Model prediction accuracy; Model false positive rate; Model prediction completeness; Model missed detection rate; Comprehensive performance indicators of the model.

45. The method of claim 44, wherein: The model prediction accuracy and / or the model false detection rate are determined based on the first counter and the second counter; or The model prediction completeness and / or the model missed detection rate are determined based on the second counter and the third counter; or The comprehensive performance index of the model is determined based on the first counter, the second counter and the third counter; The first counter is used to count events that are predicted by the model but do not actually occur; the second counter is used to count events that are predicted by the model and actually occur; and the third counter is used to count events that are not predicted by the model but actually occur.

46. ​​The method of claim 45, wherein The counting condition of the first timer includes: the mobility event and / or measurement event does not occur on the cell within a time period not exceeding a set time range before or after a time point at which the mobility event and / or measurement event occurs on the cell predicted by the model; or The counting condition of the second counter includes: the mobility event and / or measurement event occurs on the cell within a time not exceeding a set time range before or after the time point of the mobility event and / or measurement event occurring on the cell predicted by the model; or The counting condition of the third counter includes: the model does not predict the mobility event and / or measurement event within a time period not exceeding a set time range before or after a time point when a mobility event and / or measurement event occurs on a cell.

47. The method according to claim 45 or 46, characterized in that The second counter also includes events that were predicted by the model and would have occurred but were avoided.

48. The method of claim 47, wherein Events that the model predicted would have occurred but were avoided are identified by: After the network device performs an avoidance operation on the relevant cell based on the predicted mobility event, the terminal device continues to perform actual measurement and / or prediction on the relevant cell of the predicted mobility event to determine whether the predicted mobility event is an event that was predicted by the model to occur but was avoided; or After the network device performs an avoidance operation on the relevant cell based on the predicted measurement event, the terminal device continues to perform actual measurement on the relevant cell to determine whether the predicted measurement event is an event that was predicted by the model to occur but was avoided.

49. The method of claim 40, wherein The other performance indicators include at least one of the following: Model stability information; Model scoring information; Model input data quality information.

50. A first communication device, comprising: The first processing unit is configured to obtain a performance monitoring result related to mobility management based on a measured result and a predicted result related to mobility management.

51. A second communication device, comprising: The second communication unit is used to receive first information, where the first information is used to indicate a performance monitoring result related to mobility management, where the performance monitoring result related to mobility management is obtained based on a measured result and a predicted result related to mobility management.

52. A communication device comprising: A transceiver, a processor and a memory, wherein the memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to call and run the computer program stored in the memory so that the communication device performs the method as described in any one of claims 1 to 49.

53. A chip comprising: A processor, configured to call and execute a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 49.

54. A computer-readable storage medium for storing a computer program, which, when executed by a device, causes the device to perform the method according to any one of claims 1 to 49.

55. A computer program product comprising computer program instructions for causing a computer to perform the method of any one of claims 1 to 49.

56. A computer program causing a computer to perform the method of any one of claims 1 to 49.

57. A communication system comprising: A first communication device, configured to perform the method according to any one of claims 1 to 26; A second communication device, configured to execute the method according to any one of claims 27 to 49.

Images