WO2025010664A1 - 一种时域移动性预测方法及装置、设备、芯片和存储介质 - Google Patents

一种时域移动性预测方法及装置、设备、芯片和存储介质 Download PDF

Info

Publication number
WO2025010664A1
WO2025010664A1 PCT/CN2023/107045 CN2023107045W WO2025010664A1 WO 2025010664 A1 WO2025010664 A1 WO 2025010664A1 CN 2023107045 W CN2023107045 W CN 2023107045W WO 2025010664 A1 WO2025010664 A1 WO 2025010664A1
Authority
WO
WIPO (PCT)
Prior art keywords
measurement
downlink reference
prediction
reference signal
terminal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2023/107045
Other languages
English (en)
French (fr)
Inventor
曹建飞
刘文东
史志华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority to PCT/CN2023/107045 priority Critical patent/WO2025010664A1/zh
Priority to CN202380100229.XA priority patent/CN121533064A/zh
Publication of WO2025010664A1 publication Critical patent/WO2025010664A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic

Definitions

  • the embodiments of the present application relate to the field of communication technology, and specifically to a time domain mobility prediction method and apparatus, device, chip and storage medium.
  • Embodiments of the present application provide a time domain mobility prediction method and apparatus, device, chip, and storage medium.
  • an embodiment of the present application provides a mobility prediction method, the method comprising:
  • the terminal obtains K measurement instances corresponding to a first downlink reference signal set, where the K measurement instances are obtained based on the terminal measuring the downlink reference signals in the first downlink reference signal set at K measurement moments, and the first downlink reference signal set includes a first downlink reference signal subset of N cells; wherein the K measurement instances are used to obtain F prediction instances corresponding to a second downlink reference signal set based on a first model, where different prediction instances correspond to different prediction moments, and the second downlink reference signal set includes a second downlink reference signal subset of P cells; K, N, F and P are integers greater than or equal to 1.
  • an embodiment of the present application provides a mobility prediction method, the method comprising:
  • a network device receives K measurement instances corresponding to a first downlink reference signal set sent by a terminal, the K measurement instances are obtained based on the terminal measuring the downlink reference signals in the first downlink reference signal set at K measurement times, the first downlink reference signal set includes a first downlink reference signal subset of N cells; wherein the K measurement instances are used to obtain F prediction instances corresponding to a second downlink reference signal set based on a first model, different prediction instances correspond to different prediction times, the second downlink reference signal set includes a second downlink reference signal subset of P cells; K, N, F and P are integers greater than or equal to 1.
  • an embodiment of the present application provides a mobility prediction device, which is applied to a terminal, and the device includes:
  • An acquisition unit is used to acquire K measurement instances corresponding to a first downlink reference signal set, where the K measurement instances are obtained based on the terminal measuring the downlink reference signals in the first downlink reference signal set at K measurement moments, and the first downlink reference signal set includes a first downlink reference signal subset of N cells; wherein the K measurement instances are used to acquire F prediction instances corresponding to a second downlink reference signal set based on a first model, where different prediction instances correspond to different prediction moments, and the second downlink reference signal set includes a second downlink reference signal subset of P cells; K, N, F and P are integers greater than or equal to 1.
  • an embodiment of the present application provides a mobility prediction device, which is applied to a network device, and the device includes:
  • a receiving unit is used to receive K measurement instances corresponding to a first downlink reference signal set sent by a terminal, where the K measurement instances are obtained based on the terminal measuring the downlink reference signals in the first downlink reference signal set at K measurement moments, and the first downlink reference signal set includes a first downlink reference signal subset of N cells; wherein the K measurement instances are used to obtain F prediction instances corresponding to a second downlink reference signal set based on a first model, different prediction instances correspond to different prediction moments, and the second downlink reference signal set includes a second downlink reference signal subset of P cells; K, N, F and P are integers greater than or equal to 1.
  • an embodiment of the present application provides a communication device, which includes a memory and a processor; wherein the memory is used to store computer-executable instructions; the processor is connected to the memory and is used to implement a method as described in any of the above aspects by executing the computer-executable instructions.
  • an embodiment of the present application provides a chip, which includes: a processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes any of the above methods.
  • an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by at least one processor, implements a method as described in any of the above aspects.
  • the K measurement instances are historical measurement results obtained by the terminal measuring the downlink reference signal in the first downlink reference signal set at K measurement times. Based on the first model, F future prediction instances can be predicted according to the historical measurement results.
  • This mobility solution is a proactive solution with strong foresight. The mobility management process can be triggered in time through the F prediction instances, thereby avoiding the degradation of communication performance due to the lag of the mobility management process.
  • FIG1 is a schematic diagram of an application scenario of an embodiment of the present application.
  • FIG2 is a schematic diagram of an example of downlink beam management in an NR system
  • Fig. 3 is a schematic diagram of an example of a neuron structure
  • FIG4 is a schematic diagram of an example of a neural network
  • Figure 5 is a schematic diagram of an LSTM network
  • FIG6 is a schematic diagram of an example of a neural network model applicable to an embodiment of the present application.
  • FIG7 is another schematic diagram of a neural network model applicable to an embodiment of the present application.
  • FIG9 is a schematic diagram of a time domain mobility measurement and prediction provided in an embodiment of the present application.
  • FIG10 is a schematic diagram of a timing relationship between a measurement instance and a prediction instance provided in an embodiment of the present application.
  • FIG11 is another schematic diagram of the timing relationship between the measurement instance and the prediction instance provided in an embodiment of the present application.
  • FIG12 is a flow chart of a method for predicting time-domain mobility according to an embodiment of the present application.
  • FIG13 is a schematic diagram of the input-output relationship of the time domain mobility prediction model provided in an embodiment of the present application.
  • FIG14 is a second schematic diagram of the input-output relationship of the time domain mobility prediction model provided in an embodiment of the present application.
  • FIG15 is a third schematic diagram of the input-output relationship of the time domain mobility prediction model provided in an embodiment of the present application.
  • FIG16 is a second flow chart of a time domain mobility prediction method provided in an embodiment of the present application.
  • FIG17 is a third flow chart of a time domain mobility prediction method provided in an embodiment of the present application.
  • FIG18 is a schematic diagram of the first structure of a mobility prediction device provided in an embodiment of the present application.
  • FIG19 is a second schematic diagram of the structure of the mobility prediction device provided in an embodiment of the present application.
  • FIG20 is a schematic structural diagram of a communication device provided in an embodiment of the present application.
  • FIG21 is a schematic structural diagram of a chip according to an embodiment of the present application.
  • Figure 22 is a schematic block diagram of a communication system provided in an embodiment of the present application.
  • FIG. 1 is a schematic diagram of an application scenario of an embodiment of the present application.
  • the communication system 100 may include a terminal (such as the terminal 110 in FIG. 1 ) and a network device (such as the network device 120, the network device 130, and the network device 140 in FIG. 1 ).
  • the network device may communicate with the terminal through an air interface.
  • the network device 120, the network device 130, and the network device 140 may be located in different cells, or in other words, may serve different cells.
  • the network device 120 is located in cell #1
  • the network device 130 is located in cell #2
  • the network device 130 is located in cell #3.
  • the terminal 110 may be located in one or more cells, for example, in the communication system 100, the terminal 110 is located in cell #1. In this scenario, cell #1 is the serving cell of the terminal 110, and cells #2 and #3 are non-serving cells of the terminal 110.
  • the union of the beams (pairs) represented by solid lines and dotted lines is the full set of beams (pairs) between each cell and the terminal.
  • the beams (pairs) represented by solid lines are beams (pairs) that need to be measured by the terminal or network equipment
  • the beams (pairs) represented by dotted lines are beams (pairs) that do not need to be measured by the terminal or network equipment but belong to the full set of beams (pairs).
  • LTE Long Term Evolution
  • TDD LTE Time Division Duplex
  • UMTS Universal Mobile Telecommunication System
  • IoT Internet of Things
  • NB-IoT Narrow Band Internet of Things
  • eMTC enhanced Machine Type Communications
  • 5G communication system also called New Radio (NR) communication system
  • NR New Radio
  • the network devices may be access network devices that communicate with terminals (such as terminal 110).
  • the access network devices may provide communication coverage for a specific geographical area and may communicate with terminals (such as UEs) located in the coverage area.
  • the network device may be an evolved Node B (eNB or eNodeB) in a Long Term Evolution (LTE) system, or a Next Generation Radio Access Network (NGRAN) device, or a gNB in an NR system, or a wireless controller in a Cloud Radio Access Network (CRAN), or the network device may be a macro base station, a micro base station (also called a small station), a satellite, a Radio Network Controller (RNC), a Node B (N B), Base Station Controller (BSC), Base Transceiver Station (BTS), Home Base Station (e.g., Home Evolved NodeB, or Home Node B, HNB), Baseband Unit (BBU), Access Point (AP) in Wireless Fidelity (WiFi) system, Wireless Relay Node, Wireless Backhaul Node, Transmission Point (TP) or Transmission and Reception Point (TRP), etc.
  • the network device can also be a relay station, access point, vehicle-mounted device, wearable device, hub, switch, bridge, router,
  • the terminal may be any terminal, including but not limited to a terminal connected to a network device or other terminal by wire or wireless connection.
  • the terminal may refer to an access terminal, a user equipment (UE), a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user device.
  • UE user equipment
  • the terminal may refer to an access terminal, a user equipment (UE), a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user device.
  • UE user equipment
  • the access terminal may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, an IoT device, a satellite handheld terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal in a 5G network or a terminal in a future evolution network, etc.
  • SIP Session Initiation Protocol
  • IoT IoT device
  • satellite handheld terminal a Wireless Local Loop (WLL) station
  • PDA Personal Digital Assistant
  • a handheld device with wireless communication function a computing device or other processing device connected to a wireless modem
  • a vehicle-mounted device a wearable device
  • a terminal in a 5G network or a terminal in a future evolution network etc.
  • the terminal can be used for device to device (Device to Device, D2D) communication.
  • D2D Device to Device
  • the wireless communication system 100 may also include a core network device (not shown in FIG. 1 ) for communicating with the network device.
  • the core network device may be a 5G core network (5G Core, 5GC) device, such as an Access and Mobility Management Function (AMF), an Authentication Server Function (AUSF), a User Plane Function (UPF), or a Session Management Function (SMF).
  • the core network device may also be an Evolved Packet Core (EPC) device of an LTE network, such as a Session Management Function + Core Packet Gateway (SMF+PGW-C) device of a core network.
  • EPC Evolved Packet Core
  • SMF+PGW-C Session Management Function + Core Packet Gateway
  • SMF+PGW-C can simultaneously implement the functions that can be implemented by SMF and PGW-C.
  • the above-mentioned core network equipment may also be called other names, or new network entities may be formed by dividing the functions of the core network, which is not
  • the various functional units in the communication system 100 can also establish connections and achieve communication through the next generation network (NG) interface.
  • NG next generation network
  • the terminal establishes an air interface connection with the access network device through the NR interface for transmitting user plane data and control plane signaling; the terminal can establish a control plane signaling connection with the AMF through the NG interface 1 (N1 for short); the access network device, such as the next-generation wireless access base station (gNB), can establish a user plane data connection with the UPF through the NG interface 3 (N3 for short); the access network device can establish a control plane signaling connection with the AMF through the NG interface 2 (N2 for short); the UPF can establish a control plane signaling connection with the SMF through the NG interface 4 (N4 for short); the UPF can exchange user plane data with the data network through the NG interface 6 (N6 for short); the AMF can establish a control plane signaling connection with the SMF through the NG interface 11 (N11 for short); the SMF can establish a control plane signaling connection with the PCF through the NG interface 7 (N7 for short).
  • the access network device such as the next-generation wireless access base station
  • FIG1 exemplarily shows three network devices and one terminal.
  • the wireless communication system 100 may include one or more network devices and each network device may include other numbers of terminals within its coverage area, which is not limited in the embodiments of the present application.
  • FIG. 1 is only an example of the system to which the present application is applicable.
  • the method shown in the embodiment of the present application can also be applied to other systems.
  • system and “network” are often used interchangeably in this article.
  • the term “and/or” in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships.
  • a and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone.
  • the character "/" in this article generally indicates that the associated objects before and after are in an "or” relationship.
  • the "indication" mentioned in the embodiment of the present application can be a direct indication, an indirect indication, or an indication of an association relationship.
  • a indicates B which 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, B can be obtained through C; it can also mean that A and B have an association relationship.
  • the "correspondence” mentioned in the embodiment of the present application can mean that there is a direct or indirect correspondence relationship between the two, or it can mean that there is an association relationship between the two, or it can mean that there is an indication and being indicated, configuration and being configured, etc.
  • predefined or “predefined rules” mentioned in the embodiments of the present application can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in devices (for example, including terminals and network devices), and the present application does not limit its specific implementation method.
  • predefined may refer to the definition in the protocol.
  • protocol may refer to a standard protocol in the field of communications, such as LTE protocols, NR protocols, and related protocols used in future communication systems, and the present application does not limit this.
  • the technical solution of the embodiment of the present application is proposed.
  • the technical solution of the embodiment of the present application is based on historical measurement results, and predicts the link performance of multiple cells in the future, so as to select the optimal cell. It is a proactive solution with strong foresight, so it can also save the delay of cell switching and reduce the risk of wireless link failure. Allow the terminal to directly transition from a cell with better link quality to another cell with better link quality, and will not experience the performance degradation caused by untimely cell switching.
  • the first version of the NR system introduced millimeter wave frequency band communications, that is, the beam management mechanism.
  • Beam management can be divided into uplink and downlink beam management.
  • downlink beam management includes: downlink beam scanning (Beam Sweeping), UE beam measurement and reporting (Measurement & Reporting), network (NW) downlink beam indication (Beam Indication) and other processes;
  • uplink beam management includes: uplink beam scanning (UE sends beam scanning SRS), NW beam measurement, and uplink beam indication and configuration for UE.
  • FIG2 is a schematic diagram of an example of downlink beam management in the NR system.
  • the downlink beam scanning process can be divided into three processes, namely, P1, P2 and P3 processes.
  • the P1 process refers to the NW scanning different transmit beams and the UE scanning different receive beams
  • the P2 process refers to the NW scanning different transmit beams and the UE using the same receive beam
  • the P3 process refers to the NW using the same transmit beam and the UE scanning different receive beams.
  • the P1 process can be executed before the P2 and P3 processes.
  • the execution order can be P1, P2 and P3.
  • the NW completes the above beam scanning process by sending a downlink reference signal-synchronization signal block (Synchronization Signal and PBCH Block, SSB) and/or a channel state information-reference signal (CSI-RS).
  • SSB downlink reference signal-synchronization Signal Block
  • CSI-RS channel state information-reference signal
  • the beam reporting mechanism in NR Rel.15 includes: the UE measures multiple transmit beams (P2 process) or transmit-receive beam pairs (P1 process), and reports the L transmit beams with the highest layer 1 reference signal receiving power (L1-Reference Signal Receiving Power, RSRP, L1-RSRP) and their quality to the NW in the form of channel state information (CSI).
  • the NW can consider the downlink transmission channel and signal, and carry the transmission configuration indicator (TCI) state (including SSB or CSI-RS resource index as a reference for the UE) through the media access control (MAC) and/or downlink control information (DCI) signaling, thereby indicating the beam information to the UE.
  • TCI transmission configuration indicator
  • MAC media access control
  • DCI downlink control information
  • NR defines three uplink beam scanning processes, namely U1, U2 and U3.
  • the U1 process includes: the UE scans different transmit beams, and the NW scans different receive beams
  • the U2 process includes: the UE uses the same transmit beam, and the NW scans different receive beams
  • the U3 process includes: the UE scans different transmit beams, and the NW uses the same receive beam.
  • the uplink beam scanning process since the NW measures the beam from the UE, the UE beam report is not required.
  • the NW can select the appropriate uplink beam indication or configure it to the UE for uplink transmission from the measured uplink beam. At the same time, the NW can prepare the corresponding receive beam.
  • NR's inter-cell beam management is only applicable to downlink scenarios.
  • the NW can configure and/or activate beam management functions for non-serving cells for the UE, including beam measurement, beam reporting and beam indication.
  • the UE can measure non-serving cells other than the serving cell.
  • the non-serving cells have a different physical cell identifier (PCI) from the serving cell.
  • PCI physical cell identifier
  • the UE capability supports the number of non-serving cells that can be measured to be 1, 2, 3, or 7.
  • the UE can select a downlink beam with better beam quality. In one beam report, the UE can only report up to 4 downlink transmit beams from a non-serving cell, including the resource index and link quality corresponding to the beam. Such as L1-RSRP.
  • NW can implement it through a unified TCI State. For example, NW can configure the reference signal from the non-serving cell (identify whether it is a non-serving cell through PCI) in TCI State. If the TCI state is indicated to the UE, it means that the UE will use the downlink beam from the cell.
  • the standardization has given a certain degree of enhancement in measurement and reporting compared to the inter-cell beam management in Rel.17.
  • the specific enhancements are as follows: the UE can perform measurements in the service cell and target cell configured by the NW, and give the measurement results of up to M ⁇ L downlink reference signals in one report. The maximum values of M and L are determined based on the capabilities of the UE. Obviously, for the measurement of a large number of candidate cells, a large amount of downlink reference signal overhead is required, as well as the delay required for the UE to measure these downlink reference signals. After all, the UE often cannot measure multiple beams (pairs) of multiple candidate cells at the same time.
  • a neural network is a computational model consisting of multiple interconnected neuron nodes, where the connection between nodes represents the weighted value from the input signal to the output signal, called the weight; each node performs a weighted summation on different input signals and outputs them through a specific activation function.
  • the neuron structure is shown in Figure 3, where a 1 , a 2 , ..., an and 1 are the inputs of the neuron, w 1 , w 2 , ..., w n and b represent weights, Sum represents the summation function, f represents the activation function, and t represents the output result.
  • FIG4 shows a simple neural network.
  • the neural network includes an input layer, a hidden layer, and an output layer. Through different connection modes of multiple neurons, combined with different weights and activation functions, different outputs can be generated, thereby fitting the mapping relationship from input to output.
  • each upper-level node can be connected to all its lower-level nodes to form a fully connected model.
  • the fully connected model can also be called a deep neural network (DNN).
  • the NN model can be used for spatial-domain DL beam prediction or temporal DL beam prediction.
  • Figure 5 shows an LSTM model.
  • the LSTM model can be understood as extending K moments as input in terms of time series, which is equivalent to the cascade of K LSTM units.
  • the input of each LSTM unit is the L1-RSRP of the beam (pair) in Set B k (1 ⁇ k ⁇ K), where Set B k represents Set B corresponding to time k.
  • the index of the beam (pair) in Set B k can be implicitly input through the fixed order of L1-RSRP.
  • the LSTM model can predict the beam prediction instances at the next F moments.
  • Each beam prediction instance contains the optimal beam (pair) index, the link quality corresponding to the optimal beam (pair) index, and the duration of the optimal beam (pair).
  • An NN model can be trained through the processes of data set construction, training, verification and testing.
  • the NN models have been trained in advance through offline training or online training.
  • offline training and online training are not mutually exclusive.
  • the NW can first obtain a static training result through offline training of the data set, and this process can be called offline training.
  • the NN model can continue to collect more data and perform real-time online training to optimize the parameters of the NN model, thereby achieving better inference and prediction results.
  • AI/ML-based beam management is the main use case of the R18AI project, and two use cases are defined: spatial-domain DL beam prediction and temporal DL beam prediction.
  • BM-Case1 The spatial domain prediction of downlink beams in Set A is performed by measuring the beams (pairs) in Set B.
  • Set B is either a subset of Set A, or Set B and Set A are two different sets of beams (pairs).
  • Set B can be understood as a partial subset of beams (pairs);
  • Set A can be understood as the full set of beams (pairs).
  • BM-Case2 The optimal beam (pair) in future F times of Set A is predicted by measuring the beam (pair) in Set B for K times.
  • Set B can be a subset of Set A or the same as Set A.
  • beam prediction is simply beam prediction in time domain; when Set B is a subset of Set A, beam prediction is beam prediction in space domain and time domain.
  • Set B and Set A can also be two different sets, Set B is a set of a small number of wide beams, and Set A is a set of a large number of narrow beams.
  • the small number of wide beams in Set B can roughly cover the large number of narrow beams in Set A in space.
  • the technical solution of the embodiment of the present application can use a DNN model to predict time domain mobility, or, considering the time domain factors, an LSTM model can also be used to predict time domain mobility.
  • a DNN model to predict time domain mobility
  • an LSTM model can also be used to predict time domain mobility.
  • the technical solutions of the examples of the present application are all illustrated using the DNN model as an example, they are not limited to this.
  • Other models that can achieve time domain mobility prediction (such as LSTM models) are applicable to the technical solutions of the embodiments of the present application.
  • the DNN model shown in Figures 6 to 8 is used as an example to illustrate the implementation of the model.
  • FIG6 is a schematic diagram of an example of a neural network model applicable to an embodiment of the present application, which is an optimal beam (pair) prediction model, and it can be considered that the model solves a multi-classification problem.
  • the model can be used to fit the relationship between the measurement results of Set B (such as the L1-RSRP of the reference signal/beam (pair) in Set B) and the optimal L beams (pairs) in Set A.
  • the measurement results of Set B can be used as the input of the model, and the output can be the optimal J beam (pair) indexes selected from the full set (Set A), that is, the J beams (pairs) with the highest L1-RSRP in Set A.
  • the number of beams (pairs) in Set B is M
  • the number of beams (pairs) in Set A is M'
  • J 1
  • beam (pair) #2 is the beam (pair) with the highest L1-RSRP, that is, the optimal beam (pair).
  • the label used by the model is the optimal (i.e., the highest L1-RSRP) beam (pair) index measured in the full set.
  • FIG7 is another schematic diagram of a neural network model applicable to an embodiment of the present application, which is an optimal beam quality prediction model and can be understood as a linear regression problem.
  • the input and output relationship of the model is: the relationship from the partial subset input L1-RSRP to the optimal L1-RSRP of the K beams (pairs).
  • the input part of the model is the same as the input of the model shown in FIG6, except that the output of the model is J (J ⁇ 1) optimal L1-RSRPs.
  • the number of beams (pairs) in Set B is M.
  • the labels used by the model are the optimal K L1-RSRPs measured in the full set, and the corresponding K beam (pair) indexes.
  • FIG8 is another schematic diagram of a neural network model applicable to an embodiment of the present application, which is an optimal beam quality and optimal beam index prediction model, which can be understood as a linear regression problem.
  • the input part of the model is the same as the input of the model shown in FIG6, except that the output of the model is the L1-RSRP of all beams (pairs) in the full set (Set A).
  • the optimal J i.e., Top-J
  • the optimal J L1-RSRPs can be selected, and then according to the output position corresponding to the optimal J L1-RSRPs, the corresponding optimal J beam (pair) indexes can be found. Therefore, the model shown in FIG8 can realize the functions of the two models of FIG6 and FIG7.
  • the DNN model it can be understood as two different models, using the same input (i.e., Set B), with two different outputs, namely, one output is the index of the best J (i.e., Top-J) beams (pairs), and the other is the link quality of the best J (i.e., Top-J) beams (pairs), i.e., L1-RSRP, as shown in Figures 6 and 7.
  • the functions of the two models in Figures 6 and 7 can be realized by one model, as shown in Figure 8.
  • the output of the model can also be understood as an inference or prediction result, that is, inference and prediction can represent the same meaning and can be interchangeable.
  • the "beam (pair)" in the embodiments of the present application may refer to a beam, including a transmit beam or a receive beam, or may refer to a beam pair, such as a pair of transmit beams and a receive beam.
  • the meaning of the "beam (pair)” in the embodiments of the present application is applicable to the case of downlink transmission.
  • the "beam (pair)” in the embodiments of the present application may also be referred to as a spatial filter, that is, a beam (pair) and a spatial filter may be interchangeable.
  • the "downlink reference signal resource index" in the embodiment of the present application can also be referred to as a beam (pair) index or a downlink reference signal index or a spatial filter index, that is, the downlink reference signal resource index, the beam (pair) index, the downlink reference signal index and the spatial filter index can be interchangeable.
  • the downlink reference signal resource index can be a CSI-RS resource indication (CRI) or an SSB resource indication (SSBRI).
  • the downlink reference signal in the embodiment of the present application may include: Channel State Information-Reference Signal (CSI-RS) and/or SSB.
  • CSI-RS Channel State Information-Reference Signal
  • the measurement result obtained by measuring the downlink reference signal characterizes the link quality.
  • the link quality may include at least one of the following: Reference Signal Receiving Power (RSRP) (such as L1-RSRP), Signal to Interference plus Noise Ratio (SINR) (such as L1-SINR), Received Signal Strength Indicator (RSSI) (such as L1-RSSI), Reference Signal Receiving Quality (RSRQ) (such as L1-RSRQ).
  • RSRP Reference Signal Receiving Power
  • SINR Signal to Interference plus Noise Ratio
  • RSSI Received Signal Strength Indicator
  • RSSI Reference Signal Strength Indicator
  • RSSQ Reference Signal Receiving Quality
  • a first downlink reference signal set and a second downlink reference signal set are defined.
  • Set B may be a subset of Set A.
  • Set B may be understood as a partial subset of beams (pairs)
  • Set A may be understood as the full set of beams (pairs).
  • Set B and Set A may also be two different sets of beams (pairs).
  • Set B may be used as a measurement set
  • Set A may be used as a prediction set.
  • a neural network model (referred to as model) may perform beam prediction in Set A by measuring beams in Set B.
  • Set B is the measurement set and also the input set of the model.
  • Set C is the measurement set, and the best M beams (pairs) are selected from Set C as Set B, which is the input set of the model. That is, Set B is a subset of Set C.
  • the first downlink reference signal set may include N (N ⁇ 1) first downlink reference signal subsets, wherein each first downlink reference signal subset may correspond to a cell. It can be understood that the first downlink reference signal set includes the first downlink reference signal subsets of N cells. As an example, the nth (1 ⁇ n ⁇ N) first downlink reference signal subset in Set B/Set C may be recorded as Set B n /Set C n .
  • the first first downlink reference signal subset in Set B/Set C may be recorded as Set B 1 /Set C 1 , and the index of Set B 1 /Set C 1 is 1, and the second first downlink reference signal subset in Set B/Set C may be recorded as Set B 2 /Set C 2 , and the index of Set B 2 /Set C 2 is 2, and so on.
  • the order of the N first downlink reference signal subsets in Set B/Set C is exemplary, and the order may be changed, and the embodiments of the present application are not limited to this.
  • the second downlink reference signal set may include P (P ⁇ 1) second downlink reference signal subsets, wherein each second downlink reference signal subset may correspond to a cell, and it can be understood that the second downlink reference signal set includes second downlink reference signal subsets of P cells.
  • the pth (1 ⁇ p ⁇ P) second downlink reference signal subset in Set A may be recorded as Set A p .
  • the first second downlink reference signal subset in Set A may be recorded as Set A 1 , and the index of Set A 1 is 1, the second second downlink reference signal subset in Set A may be recorded as Set A 2 , and the index of Set A 2 is 2, and so on.
  • the order of the P second downlink reference signal subsets in Set A is exemplary, and the order may be changed, and the embodiments of the present application are not limited to this.
  • the value of N may be equal to the value of P.
  • the value of N may be different from the value of P.
  • the value of N may be much smaller than the value of P, so that the number of downlink reference signals that need to be actually measured can be greatly reduced, thereby achieving the purpose of reducing calculation overhead and delay.
  • the first model is used for mobility prediction, and the first model can be a neural network model, such as the above-mentioned DNN model, or an LSTM model.
  • the technical solution of the embodiment of the present application can use a DNN model for mobility prediction, or, considering the time domain factors, an LSTM model can also be used for mobility prediction.
  • an LSTM model can also be used for mobility prediction.
  • the technical solutions of the examples of the present application are all illustrated using the DNN model as an example, they are not limited to this, and other models that can realize time domain mobility prediction (such as an LSTM model) are applicable to the technical solutions of the embodiments of the present application.
  • the first model is a model on the terminal side (also referred to as a model on the UE side), or in other words, the first model is a model deployed on the terminal side.
  • the first model can implement beam prediction in the time domain, and the beam prediction in the time domain can be a beam prediction in the pure time domain, or a beam prediction in the time domain and the space domain.
  • the first model is a model on the network device side (also referred to as a model on the NW side), or in other words, the first model is a model deployed on the network device side.
  • the first model can implement beam prediction in the time domain, and the beam prediction in the time domain can be a beam prediction in the pure time domain, or a beam prediction in the time domain and the space domain.
  • the input of the first model is K (K ⁇ 1) measurement instances. Different measurement instances correspond to different measurement times.
  • Each measurement instance is obtained by the terminal measuring the downlink reference signal in the first downlink reference signal set. That is, the measurement instance can be understood as the terminal's measurement result of Set B or partial measurement result of Set C (such as the measurement result of the optimal M beams (pairs) in Set C).
  • the output of the first model is F (F ⁇ 1) prediction instances, different prediction instances correspond to different prediction moments, and each prediction instance includes the optimal L (L ⁇ 1) cell indices among P (P ⁇ 1) cells, and/or the optimal J (J ⁇ 1) beam (pair) indices in each optimal area, and/or the link quality corresponding to each optimal beam (pair) index.
  • the neural network model can also be called an AI model or an ML model.
  • FIG9 is a schematic diagram of a time domain mobility measurement and prediction provided by an embodiment of the present application.
  • the coverage range of TRP1 is cell #1
  • the coverage range of TRP2 is cell #2
  • the coverage range of TRP3 is cell #3.
  • the UE roams in multiple cells (cell #1, cell #2, cell #1) at a certain speed, and the trajectory of the UE movement is shown as a dotted line.
  • the UE performs measurements at K (K ⁇ 1) measurement moments to obtain K measurement instances (measurement instance), and predicts the future F (F ⁇ 1) prediction instances (prediction instance) according to the K measurement instances through the first model, each prediction instance includes the optimal L (L ⁇ 1) cell indexes, and/or the optimal J (J ⁇ 1) beam (pair) indexes in each optimal cell, and/or the link quality corresponding to each optimal beam (pair), such as L1-RSRP.
  • the UE performs two measurements on the measurement set (i.e., Set B/Set C) in cell #1 to obtain two measurement instances; two prediction instances are obtained by predicting the prediction set (i.e., Set A) based on the two measurement instances through the first model; the reference signal actually measured by the UE is represented by a solid ellipse, and the reference signal that is not measured but in the prediction set (i.e., Set A) is represented by a dotted ellipse.
  • the measurement time corresponding to the measurement instance and the prediction time corresponding to the prediction instance may satisfy a certain timing relationship.
  • the measurement moments corresponding to the K measurement instances are within a first time period
  • the prediction moments corresponding to the F prediction instances are within a second time period
  • the second time period does not overlap with the first time period
  • FIG10 illustrates a timing relationship between a measurement instance and a prediction instance (which may be referred to as a timing relationship of type 1).
  • the terminal performs K measurements on Set B/Set C to obtain K measurement instances.
  • F prediction instances within T2 can be predicted.
  • the measurement moments corresponding to the K measurement instances are located within the K first time periods, and the prediction moments corresponding to the F prediction instances are located within the last first time period of the K first time periods.
  • FIG11 illustrates another timing relationship between a measurement instance and a prediction instance (which may be referred to as a timing relationship of type 2).
  • the terminal performs K measurements on Set B/Set C to obtain K measurement instances, wherein one T1 time is performed in each T1 time.
  • F prediction instances in the last T1 time of the K T1 times can be predicted.
  • FIG. 12 is a flow chart of a time domain mobility prediction method provided in an embodiment of the present application. As shown in FIG. 12 , the method includes the following steps:
  • measurement moment index and “measurement instance index” may be replaced with each other.
  • each prediction moment may correspond to an index, called a prediction moment index
  • each prediction instance may correspond to an index, called a prediction instance index.
  • prediction moment index and “prediction instance index” may be interchangeable.
  • the first downlink reference signal set is recorded as Set B/Set C
  • the second downlink reference signal set is recorded as Set A
  • the first downlink reference signal set may also be referred to as a measurement set
  • the second downlink reference signal set may also be referred to as a prediction set.
  • the downlink reference signal (or downlink reference signal resource) may include, for example: CSI-RS (or CSI-RS resource) and/or SSB (or SSB resource).
  • the network device may configure the first downlink reference signal set and/or the second downlink reference signal set for the terminal.
  • the network device sends the first configuration information and/or the second configuration information to the terminal; the terminal receives the first configuration information and/or the second configuration information sent by the network device; the first configuration information is used to configure the first downlink reference signal set; the second configuration information is used to configure the second downlink reference signal set.
  • the first configuration information and/or the second configuration information is carried in RRC signaling.
  • the first configuration information is further used to configure first time domain information corresponding to the first downlink reference signal set, and the first time domain information is used to determine K measurement moments corresponding to the K measurement instances.
  • the first time domain information includes at least one of the following: a measurement period, a first offset, and a number K of measurement moments.
  • the network device configures Set B/Set C for the terminal using RRC signaling
  • Set B/Set C includes N (N ⁇ 1) first downlink reference signal subsets, each of which may correspond to a cell.
  • the nth (1 ⁇ n ⁇ N) first downlink reference signal subset in Set B/Set C may be recorded as Set Bn /Set Cn .
  • the downlink reference signal (or downlink reference signal resource) in Set B/Set C may include, for example: CSI-RS (or CSI-RS resource) and/or SSB (or SSB resource) for mobility.
  • the network device may also use RRC signaling to configure the measurement period, offset, and number of measurement moments K of Set B/Set C, so that the terminal can know at which moments to perform measurements, and then store the measurement results as input to the first model.
  • the Set B n /Set C n the Set B n /Set C n corresponding to measurement time k (1 ⁇ k ⁇ K) can be recorded as Set B n,k /Set C n,k .
  • the Set B n /Set C n corresponding to measurement time 1 can be recorded as Set B n,1 /Set C n,1
  • the index of Set B n,1 /Set C n,1 is ⁇ n,1 ⁇ .
  • the Set B n /Set C n corresponding to measurement time 2 can be recorded as Set B n,2 /Set C n,2 , and the index of Set B n,2 /Set C n,2 is ⁇ n,2 ⁇ , and so on.
  • the second configuration information is further used to configure second time domain information corresponding to the second downlink reference signal set, and the second time domain information is used to determine F prediction moments corresponding to F prediction instances.
  • the second time domain information includes at least one of the following: a prediction period, a second offset, and a number F of prediction moments.
  • the network device uses RRC signaling to configure Set A for the terminal,
  • Set A includes P (P ⁇ 1) second downlink reference signal subsets, each second downlink reference signal subset may correspond to a cell, as an example, the pth (1 ⁇ p ⁇ P) second downlink reference signal subset in Set A may be recorded as Set A p .
  • the downlink reference signal (or downlink reference signal resource) in Set A may include, for example: CSI-RS (or CSI-RS resource) and/or SSB (or SSB resource) for mobility.
  • the network device may also use RRC signaling to configure the measurement period, offset, and number of measurement moments F of Set A, so that the terminal can know at which moments to make predictions.
  • the Set A p corresponding to the prediction time f (1 ⁇ f ⁇ F) can be recorded as Set A p,f .
  • the Set A p corresponding to the prediction time 1 can be recorded as Set A p,1 , and the index of Set A p,1 is ⁇ p,1 ⁇ .
  • the Set A p corresponding to the prediction time 2 can be recorded as Set A p,2 , and the index of Set A p,2 is ⁇ p,2 ⁇ , and so on.
  • the first configuration information and/or the second configuration information are related to the capability information of the terminal.
  • the network device configures the first downlink reference signal set and/or the second downlink reference signal set for the terminal according to the capability information of the terminal.
  • Different terminals have different measurement and/or prediction capabilities, so the terminal needs to report its measurement and/or prediction related capabilities.
  • the terminal sends the capability information of the terminal to the network device, and the network device receives the capability information of the terminal sent by the terminal, where the capability information of the terminal includes at least one of the following:
  • First information where the first information is used to indicate whether the terminal supports measurement and/or prediction of time domain mobility
  • the second information is used to indicate at least one of the following: the maximum number of cells that the terminal supports measuring on all downlink carrier components (Carrier Component, CC) or bandwidth parts (Bandwidth Part, BWP); the maximum number of configured first downlink reference signal subsets that the terminal supports on all downlink CCs or BWPs; the maximum number of first downlink reference signal subsets that the terminal supports measuring on all downlink CCs or BWPs;
  • the third information is used to indicate at least one of the following: the maximum number of predicted cells supported by the terminal on all downlink CCs or BWPs; the maximum number of configured second downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs; the maximum number of predicted first downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs;
  • the fourth information is used to indicate at least one of the following: the maximum number of cells supported for measurement by the terminal on each downlink CC or BWP; the maximum number of configured first downlink reference signal subsets supported by the terminal on each downlink CC or BWP; the maximum number of first downlink reference signal subsets supported for measurement by the terminal on each downlink CC or BWP;
  • the fifth information is used to indicate at least one of the following: the maximum number of predicted cells supported by the terminal on each downlink CC or BWP; the maximum number of configured second downlink reference signal subsets supported by the terminal on each downlink CC or BWP; the maximum number of predicted second downlink reference signal subsets supported by the terminal on each downlink CC or BWP;
  • sixth information is used to indicate a maximum number of downlink reference signals that the terminal supports measuring in each first downlink reference signal subset
  • the seventh information is used to indicate the maximum number of predicted downlink reference signals supported by the terminal in each second downlink reference signal subset
  • the eighth information is used to indicate the number of measurement moments supported by the terminal.
  • the ninth information is used to indicate the number of prediction moments supported by the terminal.
  • the above-mentioned first information indicating capability can be recorded as capability 1.
  • the second information indicating capability can be recorded as capability 2
  • the third information indicating capability can be recorded as capability 3
  • the fourth information indicating capability can be recorded as capability 4
  • the fifth information indicating capability can be recorded as capability 5
  • the sixth information indicating capability can be recorded as capability 6
  • the seventh information indicating capability can be recorded as capability 7
  • the eighth information indicating capability can be recorded as capability 8
  • the ninth information indicating capability can be recorded as capability 9.
  • capability 1 may be understood as whether the terminal supports measurement and/or prediction of time domain mobility of a terminal side model.
  • capability 1 may be understood as whether the terminal supports measurement and/or prediction of time domain mobility of a network side model.
  • capability 2 can be understood as the maximum number of cells that the terminal supports measurement on all downlink CCs or BWPs, or the maximum number of first downlink reference signal subsets that the terminal supports being configured on all downlink CCs or BWPs, or the maximum number of first downlink reference signal subsets that can be measured simultaneously on all downlink CCs or BWPs.
  • capability 3 can be understood as the maximum number of cell predictions supported by the terminal on all downlink CCs or BWPs, or the maximum number of second downlink reference signal subsets that the terminal supports being configured on all downlink CCs or BWPs, or the maximum number of second downlink reference signal subsets that can be predicted simultaneously on all downlink CCs or BWPs.
  • capability 4 can be understood as the maximum number of cells that the terminal supports for measurement on each downlink CC or BWP, or the maximum number of first downlink reference signal subsets that the terminal supports to be configured on each downlink CC or BWP, or the maximum number of first downlink reference signal subsets that can be measured simultaneously on each downlink CC or BWP.
  • capability 5 can be understood as the maximum number of cell predictions supported by the terminal on each downlink CC or BWP, or the maximum number of second downlink reference signal subsets that the terminal supports to be configured on each downlink CC or BWP, or the maximum number of second downlink reference signal subsets that can be predicted simultaneously on each downlink CC or BWP.
  • capability 6 may understand how many downlink reference signals the terminal supports measuring at most in each first downlink reference signal subset.
  • capability 7 may understand how many downlink reference signals the terminal supports predicting at most in each second downlink reference signal subset.
  • capability 8 may understand how many measurement moments the terminal supports measuring, that is, the value of K.
  • capability 9 may understand how many prediction moments the terminal supports to predict, that is, the value of F.
  • the capability information of the terminal includes the above-mentioned first information.
  • the capability information of the terminal may include at least one of the above-mentioned second to ninth information.
  • the capability information of the terminal includes at least one of the first to ninth information described above.
  • the terminal measures the downlink reference signal (or downlink reference signal resource) in the first downlink reference signal set through the physical layer, such as SSB (or SSB resource) and/or CSI-RS (or CSI-RS resource for mobile).
  • the nth (1 ⁇ n ⁇ N) first downlink reference signal subset measured at the kth (1 ⁇ k ⁇ K) measurement moment can be recorded as Set B n,k /Set C n,k , and the index of Set B n,k /Set C n,k is ⁇ n,k ⁇ , n represents the first downlink reference signal subset index, and k represents the measurement moment index.
  • N first downlink reference signal subsets can correspond to N cells, and each first downlink reference signal subset can correspond to one cell. Therefore, the first downlink reference signal subset index can correspond to a cell index.
  • the cell index can be a physical cell identifier (PCI), a PCI index, or a cell configuration index. That is to say, the first downlink reference signal subset index, PCI, PCI index, and cell configuration index may be interchangeable.
  • the N cells may include one current serving cell (such as SpCell) and (N-1) candidate cells.
  • the current serving cell may also be understood as a candidate cell. Based on this understanding, the N cells may be described as N candidate cells.
  • the first model is used for mobility prediction, and the first model can be a neural network model, such as the above-mentioned DNN model, or an LSTM model.
  • the technical solution of the embodiment of the present application can use a DNN model for mobility prediction, or, considering the time domain factors, an LSTM model can also be used for mobility prediction.
  • an LSTM model can also be used for mobility prediction.
  • the technical solutions of the examples of the present application are all illustrated using the DNN model as an example, they are not limited to this, and other models that can realize time domain mobility prediction (such as an LSTM model) are applicable to the technical solutions of the embodiments of the present application.
  • the input of the first model includes K measurement instances.
  • the input of K measurement instances can be in the following two ways:
  • K measurement instances include K ⁇ N groups of link qualities.
  • K measurement instances include: K ⁇ N indexes and K ⁇ N groups of link qualities, and the K ⁇ N indexes and the K ⁇ N link qualities have a corresponding relationship; each index in the K ⁇ N indexes corresponds to a measurement time index and a cell index.
  • the terminal measures N downlink reference signal subsets in the first downlink reference signal set to obtain N groups of link qualities, and each downlink reference signal subset corresponds to a group of link qualities. Assuming that a downlink reference signal subset includes M (M ⁇ 1) downlink reference signals, then each group of link qualities includes M link qualities. For K measurement instances, K ⁇ N groups of link qualities can be obtained, wherein each group of link qualities includes M link qualities.
  • the terminal measures all Set B n,k /Set C n,k (1 ⁇ n ⁇ N, 1 ⁇ k ⁇ K) to obtain K ⁇ N groups of link qualities, wherein the nth (1 ⁇ n ⁇ N) first downlink reference signal subset measured at the kth (1 ⁇ k ⁇ K) measurement moment is denoted as Set B n,k /Set C n,k , and the index of Set B n,k /Set C n,k is ⁇ n,k ⁇ , where n represents the first downlink reference signal subset index, and k represents the measurement moment index.
  • each link quality corresponds to a downlink reference signal resource index (such as CRI or SSBRI), a first downlink reference signal subset index (such as n index), and a measurement time index (such as k index).
  • the first downlink reference signal subset index can also be replaced by a cell index (such as PCI, PCI index, cell configuration index, etc.), that is, the first downlink reference signal subset index and the cell index (such as PCI, PCI index, cell configuration index, etc.) can be replaced with each other.
  • K ⁇ N groups of link qualities i.e., link qualities of all downlink reference signals in Set B n,k /Set C n,k
  • the order is related to the index corresponding to the link quality
  • the index corresponding to the link quality includes: a downlink reference signal resource index, a first downlink reference signal subset index, and a measurement time index.
  • the input of the first model includes K ⁇ N groups of link qualities corresponding to K ⁇ N indexes (i.e., link qualities of all downlink reference signals in Set B n,k /Set C n,k ), and each of the K ⁇ N indexes corresponds to a measurement time index (such as k index) and a cell index (such as PCI, PCI index, cell configuration index, etc.), wherein the cell index may also be replaced by the first downlink reference signal subset index (such as n index).
  • K ⁇ N groups of link qualities corresponding to K ⁇ N indexes i.e., link qualities of all downlink reference signals in Set B n,k /Set C n,k
  • each of the K ⁇ N indexes corresponds to a measurement time index (such as k index) and a cell index (such as PCI, PCI index, cell configuration index, etc.), wherein the cell index may also be replaced by the first downlink reference signal subset index (such as n index).
  • the output of the first model includes F prediction instances.
  • each of the F prediction instances includes at least one of the following: the best L cell indexes among the P cells; the best J downlink reference signal resource indexes in each best cell; the link quality corresponding to each best downlink reference signal resource index.
  • each prediction instance also includes: the prediction time index corresponding to the prediction instance.
  • each prediction instance includes a prediction time index, and the optimal L (L ⁇ 1) cell indices among P (P ⁇ 1) cells, and/or the optimal J (J ⁇ 1) beam (pair) indices in each optimal area, and/or the link quality corresponding to each optimal beam (pair) index.
  • the output of F prediction instances can be in the following two ways:
  • the first model includes two models, namely, model 1 and model 2.
  • the output of model 1 includes: the optimal L cell indexes in P cells corresponding to each prediction instance in F prediction instances, and the optimal J downlink reference signal resource indexes in each optimal cell;
  • the output of model 2 includes: the link quality corresponding to each optimal beam (pair) index corresponding to each prediction instance in F prediction instances.
  • the second method The first model is a model.
  • the output of the model includes: the optimal L cell indexes in the P cells corresponding to each prediction instance in the F prediction instances, the optimal J downlink reference signal resource indexes in each optimal cell, and the link quality corresponding to each optimal beam (pair) index.
  • model 1 infers the optimal L cell indices corresponding to all prediction moments f (1 ⁇ f ⁇ F) and the optimal J downlink reference signal resource indices in each optimal cell.
  • model 2 infers the link quality corresponding to each optimal beam (pair) index in each optimal cell corresponding to the prediction moment f (1 ⁇ f ⁇ F).
  • the model predicts the link quality of all Set A p,f (1 ⁇ p ⁇ P, 1 ⁇ f ⁇ F). For each of the F prediction instances, the optimal L cell indexes, the optimal J downlink reference signal resource indexes in each optimal cell, and the link quality corresponding to each optimal beam (pair) index are selected according to the order of link quality from high to low.
  • the first model responsible for mobility prediction can be deployed on the terminal side or on the network device side.
  • the technical solutions of the embodiment of the present application are described below in combination with these two deployment modes.
  • the model is located on the terminal side
  • the first model in the above solution is located at the terminal side.
  • the terminal obtains K measurement instances, it predicts F prediction instances based on the local first model.
  • the terminal sends F prediction instances to the network device.
  • the reporting manner of the F prediction instances includes at least one of the following: periodic reporting, semi-persistent reporting, non-periodic reporting, and mobility event reporting based on layer 1 and/or layer 2.
  • the network device for periodic reporting or semi-continuous reporting, before the terminal sends F prediction instances to the network device, the network device sends third configuration information to the terminal, and the terminal receives the third configuration information sent by the network device, and the third configuration information is used to configure the reporting period and reporting offset corresponding to the periodic reporting or semi-continuous reporting.
  • the third configuration information is carried in RRC signaling.
  • the terminal periodically or semi-continuously reports the prediction instances corresponding to F prediction moments according to the reporting period and reporting offset configured by the network device and the number of prediction moments F.
  • the terminal For periodic reporting, once the terminal obtains the measurement configuration (such as the first configuration information and/or the second configuration information) and the reporting configuration (such as the third configuration information) sent by the network device, it will periodically report the prediction instance.
  • the terminal For semi-continuous reporting, after obtaining the measurement configuration and the reporting configuration, the terminal also needs to obtain an instruction to activate the configuration. After obtaining the instruction to activate the configuration, the prediction instance is periodically reported.
  • the terminal receives first downlink control information (Downlink Control Information, DCI) sent by the network device, and the first DCI is used to trigger the non-periodic reporting.
  • DCI Downlink Control Information
  • the terminal after obtaining the measurement configuration (such as the first configuration information and/or the second configuration information mentioned above) and the reporting configuration (such as the third configuration information mentioned above), the terminal also needs to obtain an instruction to trigger measurement and reporting.
  • the network device can trigger the terminal to perform measurement and reporting through DCI (i.e., trigger instruction). After obtaining the trigger instruction, the terminal measures K measurement instances and reports F prediction instances.
  • the terminal determines that a mobility event of layer 1 and/or layer 2 is triggered, and sends a report request to the network device; the terminal receives a second DCI sent by the network device, and the second DCI is used to schedule a physical uplink shared channel (Physical Uplink Shared Channel, PUSCH) for reporting. Further, the terminal uses the PUSCH to send the F prediction instances.
  • PUSCH Physical Uplink Shared Channel
  • the output of the first model on the terminal side triggers a mobility event based on layer 1 and/or layer 2, and the terminal sends a reporting request to the network device, where the reporting request is used to request resources for mobility reporting; the network device agrees to the reporting request of the terminal, sends a DCI, and schedules a PUSCH through the DCI; the terminal carries the mobility-related reporting content, i.e., the prediction instance, through the PUSCH scheduled by the DCI.
  • the above-mentioned layer 1 and/or layer 2 mobility events include at least one of the following:
  • a first event the first event is: at some or all of the F prediction moments, the predicted link performance of the current serving cell is better than the first threshold or weaker than the second threshold;
  • the second event is: at some or all of the F prediction moments, the predicted link performance of the current serving cell is better or weaker than the predicted link performance of the candidate cell plus an offset;
  • a third event, the third event is: at some or all of the F prediction moments, the predicted link performance of the candidate cell is better than the third threshold or weaker than the fourth threshold;
  • the fourth event is: at some or all of the F prediction moments, the predicted link performance of the current serving cell is weaker than the fifth threshold, and the predicted link performance of the candidate cell is better than the sixth threshold.
  • the current cell is one of the P cells, and the candidate cell is one of the P cells except the current cell.
  • the current cell may also be called the current serving cell, and the current cell may also be understood as a candidate cell in the mobility management process.
  • the terminal compares the above-defined layer 1 and/or layer 2 mobility events and the prediction results of the first model to determine whether the layer 1 and/or layer 2 mobility events occur (or are triggered), and then autonomously chooses whether to report F prediction instances.
  • the terminal does not need to report the prediction instance, and does not need to trigger subsequent mobility operations.
  • the terminal can determine that the second event has occurred, triggering the terminal to make a reporting request.
  • the reporting request can be carried by uplink control information (UCI).
  • UCI uplink control information
  • the network device schedules PUSCH for the reporting request through DCI, and the terminal uses the PUSCH to send the prediction instance.
  • the terminal can determine that the third event has occurred, triggering the terminal to make a reporting request.
  • the reporting request can be carried by UCI, and the network device schedules PUSCH for the reporting request through DCI, and the terminal uses the PUSCH to send the prediction instance.
  • each prediction instance includes an optimal cell index selected from all Set A p,f (1 ⁇ p ⁇ P, 1 ⁇ f ⁇ F), and/or an optimal beam (pair) index of the optimal cell, and/or a link quality corresponding to the optimal beam (pair) index, and the terminal reports the prediction result to the network device in one or more reports.
  • the terminal may report the cell index of the optimal cell or the index of Set A p,f corresponding to the optimal cell (i.e., p index), where the cell index may be PCI, PCI index, or configuration index of candidate cell; for the optimal beam (pair) index of the optimal cell, a downlink reference signal resource index in the NR system may be used, such as SSBRI or CRI; for link quality, L1-RSRP is taken as an example in some examples, and other link quality indicators such as L1-SINR, L1-RSSI, L1-RSRQ or CQI are not excluded.
  • the reporting granularity of F prediction instances is one prediction instance.
  • the above-mentioned report has a first format, and the first format includes: a predicted time index, L cell indexes, X1 downlink reference signal resource indexes, and X1 link qualities; wherein the L cell indexes are the optimal L cell indexes among the P cells; the X1 downlink reference signal resource indexes include the optimal J downlink reference signal resource indexes in each of the L cells; the X1 link qualities have a corresponding relationship with the X1 downlink reference signal resource index.
  • the cell index may be a PCI, a PCI index, a configuration index of a candidate cell, or an index of Set A (ie, a p index).
  • the downlink reference signal resource index may also be replaced by a beam (pair) index, a downlink reference signal index or a spatial filter index.
  • X1 link qualities can be reported in a differential manner, or in a non-differential manner.
  • X1 link qualities are represented by a reference link quality and X1-1 differential values.
  • the reference link quality can be the best link quality among the X1 link qualities
  • a differential value and a reference link quality can determine a link quality
  • X1-1 differential values and a reference link quality can determine X1-1 link qualities.
  • the above-mentioned reporting format may also include a downlink reference signal resource index corresponding to the reference link quality.
  • X1 link qualities are directly represented by an X1 link quality.
  • the reporting format adopted by the prediction example is given below.
  • the downlink reference signal resource index (CRI or SSBR) or beam (pair) index may also be replaced by a downlink reference signal index or a spatial filter index.
  • the reporting format of the prediction instance corresponding to the f-th prediction moment is given, and the X1 link qualities are reported in a differential manner.
  • the reporting format includes the prediction moment index, that is, the f value.
  • their PCI, or PCI index, or the configuration index of the candidate cell, or the corresponding Set A index can be directly reported.
  • the optimal beam (pair) index if it is for the downlink transmit beam, it can be represented by the conventional CRI or SSBRI. If it is for the downlink transmit receive beam pair, it can be represented by the beam (pair) index.
  • the reporting granularity of F prediction instances is F prediction instances.
  • the terminal may report F prediction instances to the network device in one report.
  • the above-mentioned report has a second format, and the second format includes F groups of information, and the F groups of information have a corresponding relationship with the F prediction instances; each group of information in the F groups of information includes: a prediction time index, L cell indexes, X1 downlink reference signal resource indexes, and X1 link qualities; or, each group of information in the F groups of information includes: L cell indexes, X1 downlink reference signal resource indexes, and X1 link qualities; wherein the L cell indexes are the optimal L cell indexes among the P cells; the X1 downlink reference signal resource index includes the optimal J downlink reference signal resource indexes in each of the L cells; the X1 link quality has a corresponding relationship with the X1 downlink reference signal resource index.
  • the cell index can be PCI, PCI index, configuration index of candidate cell, or index of Set A (i.e., p index).
  • the downlink reference signal resource index may also be replaced by a beam (pair) index, a downlink reference signal index or a spatial filter index.
  • X1 link qualities can be reported in a differential manner, or in a non-differential manner.
  • X1 link qualities are represented by a reference link quality and X1-1 differential values.
  • the reference link quality can be the best link quality among the X1 link qualities
  • a differential value and a reference link quality can determine a link quality
  • X1-1 differential values and a reference link quality can determine X1-1 link qualities.
  • the above-mentioned reporting format may also include a downlink reference signal resource index corresponding to the reference link quality.
  • X1 link qualities are directly represented by an X1 link quality.
  • the reporting format adopted by the prediction example is given below.
  • the downlink reference signal resource index (CRI or SSBR) or beam (pair) index may also be replaced by a downlink reference signal index or a spatial filter index.
  • the reporting format of the prediction instance corresponding to F prediction moments is given, and the link quality is reported in a differential manner.
  • the prediction instance corresponding to F prediction moments can be reported with or without [prediction moment index], which does not affect the network device's understanding of the prediction result.
  • the reporting format includes F groups of information, each group of information represents a prediction instance.
  • each prediction instance its content may include [prediction moment index] (i.e., f value), or may not include [prediction moment index].
  • the content of each prediction instance is similar to that in Table 1 above.
  • the model is located on the network device side
  • the first model in the above solution is located on the network device side.
  • the terminal after the terminal obtains K measurement instances, the terminal sends K measurement instances to the network device, and the network device receives the K measurement instances sent by the terminal.
  • the network device predicts F prediction instances based on the local first model.
  • the reporting manner of the K measurement instances includes at least one of the following: periodic reporting, semi-persistent reporting, and aperiodic reporting.
  • the network device sends fourth configuration information to the terminal, and the terminal receives the fourth configuration information sent by the network device, and the fourth configuration information is used to configure the reporting period and reporting offset corresponding to the periodic reporting or semi-continuous reporting.
  • the fourth configuration information is carried in RRC signaling.
  • the terminal periodically or semi-continuously reports the measurement instances corresponding to K measurement moments according to the reporting period and reporting offset configured by the network device and the number of measurement moments K.
  • the terminal For periodic reporting, once the terminal obtains the measurement configuration (such as the first configuration information and/or the second configuration information) and the reporting configuration (such as the fourth configuration information) sent by the network device, it will periodically report the measurement instance.
  • the terminal For semi-continuous reporting, after obtaining the measurement configuration and the reporting configuration, the terminal also needs to obtain an instruction to activate the configuration, and after obtaining the instruction to activate the configuration, the terminal periodically reports the measurement instance.
  • the network device sends a third DCI to the terminal, and the terminal receives the third DCI sent by the network device, where the third DCI is used to trigger the non-periodic reporting.
  • the terminal after obtaining the measurement configuration (such as the first configuration information and/or the second configuration information mentioned above) and the reporting configuration (such as the fourth configuration information mentioned above), the terminal also needs to obtain an instruction to trigger measurement and reporting.
  • the network device can trigger the terminal to perform measurement and reporting through DCI (i.e., trigger instruction). After obtaining the trigger instruction, the terminal measures and reports K measurement instances.
  • each measurement instance includes the link quality measured from all Set B n,k /Set C n,k (1 ⁇ n ⁇ N, 1 ⁇ k ⁇ K), and the terminal reports the measurement result to the network device in one or more reports.
  • link quality in some examples, L1-RSRP is used as an example, and other link quality indicators such as L1-SINR, L1-RSSI, L1-RSRQ or CQI are not excluded.
  • the reporting granularity of K measurement instances is one measurement instance.
  • the network device may configure the terminal to report after each measurement. This reporting method reduces the load of each report, but requires K reports.
  • the report has a third format, the third format including: a measurement time index and X2 link qualities; wherein the X2 link qualities include link qualities of M downlink reference signals of each cell in N cells, and M is a positive integer.
  • the content of the report does not include the N cell indexes.
  • the report has a fourth format, and the fourth format includes: a measurement time index, N cell indexes, and X2 link qualities; wherein the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, and M is a positive integer.
  • the content of the report includes N cell indexes.
  • the format of reporting the above X2 link qualities adopts a differential reporting format or a non-differential reporting format.
  • X2 link qualities are represented by X2 link qualities, as shown in Table 3 below.
  • X2 link qualities are divided into N groups of link qualities, and each group of link qualities is represented by a reference link quality and M-1 differential values, as shown in Tables 5 and 9 below.
  • the reference link quality can be the best link quality among the M link qualities
  • a differential value and a reference link quality can determine a link quality
  • M-1 differential values and a reference link quality can determine M-1 link qualities.
  • the above reporting format may also include a downlink reference signal resource index corresponding to the reference link quality.
  • X2 link qualities are represented by a reference link quality and X2-1 differential values, as shown in the following Table 7.
  • the reference link quality may be the best link quality among the X2 link qualities
  • a differential value and a reference link quality may determine a link quality
  • X2-1 differential values and a reference link quality may determine X2-1 link qualities.
  • the above-mentioned reporting format may also include a downlink reference signal resource index corresponding to the reference link quality.
  • the reporting granularity of K measurement instances is K measurement instances.
  • the network device may configure the terminal to report K measurement instances together after K measurements. This reporting method makes the load of one report larger, but only one report is required.
  • the report has a fifth format, and the fifth format includes: K groups of information, the K groups of information have a corresponding relationship with the K measurement instances; each group of information in the K groups of information includes: X2 link qualities; wherein the X2 link qualities include the link qualities of M downlink reference signals of each cell in the N cells, and M is a positive integer.
  • the content of the report does not include the N cell indexes.
  • the report has a sixth format, the sixth format includes: N cell indexes and K group information, or the sixth format includes: N cell indexes, K measurement instance indexes and K group information; the K group information has a corresponding relationship with the K measurement instance indexes; each group of information in the K group information includes: X2 link qualities; wherein the X2 link qualities include the link qualities of M downlink reference signals of each cell in the N cells, and M is a positive integer.
  • the content of the report includes N cell indexes and/or K measurement instance indexes.
  • the format of reporting the above X2 link qualities adopts a differential reporting format or a non-differential reporting format.
  • X2 link qualities are represented by X2 link qualities, as shown in Table 4 below.
  • K ⁇ X2 link qualities are divided into K ⁇ N groups of link qualities, and each group of link qualities is represented by a reference link quality and M-1 differential values, as shown in Tables 6 and 10 below.
  • the reference link quality can be the best link quality among the M link qualities
  • a differential value and a reference link quality can determine a link quality
  • M-1 differential values and a reference link quality can determine M-1 link qualities.
  • the above reporting format may also include a downlink reference signal resource index corresponding to the reference link quality.
  • K ⁇ X2 link qualities are represented by a reference link quality and K ⁇ X2-1 differential values, as shown in Table 8 below.
  • the reference link quality may be the best link quality among the K ⁇ X2 link qualities
  • a differential value and a reference link quality may determine a link quality
  • K ⁇ X2-1 differential values and a reference link quality may determine K ⁇ X2-1 link qualities.
  • the above reporting format may also include a downlink reference signal resource index corresponding to the reference link quality.
  • the reporting granularity of the K measurement instances is the measurement result of one cell in one measurement instance.
  • the report has a sixth format, which includes: a measurement time index, a cell index, and M link qualities; wherein the M link qualities include link qualities of M downlink reference signals of the cell corresponding to the cell index, and M is a positive integer.
  • the format of reporting the above-mentioned M link qualities adopts a differential reporting format or a non-differential reporting format.
  • the qualities of the M links are represented by M link qualities.
  • M link qualities are represented by a reference link quality and M-1 differential values, as shown in the following Table 11.
  • the reference link quality may be the best link quality among the M link qualities
  • a differential value and a reference link quality may determine a link quality
  • M-1 differential values and a reference link quality may determine M-1 link qualities.
  • the above-mentioned reporting format may also include a downlink reference signal resource index corresponding to the reference link quality.
  • the reporting format adopted by the measurement example is given below.
  • the downlink reference signal resource index (CRI or SSBR) or beam (pair) index may also be replaced by a downlink reference signal index or a spatial filter index.
  • the reporting format of the measurement instance corresponding to the kth measurement moment is given, and the link quality is reported in a non-differential manner.
  • the reporting format includes the measurement moment index (i.e., k value) and N ⁇ M link qualities.
  • the link quality can be reported from small to large according to the corresponding downlink reference signal resource index (i.e., SSBRI or CRI or beam (pair) index), so the downlink reference signal resource index can be omitted.
  • the downlink reference signal resource index can be first reported from small to large according to the n index (i.e., cell index), and then reported from small to large according to the k index (i.e., measurement moment index).
  • the reporting format of the measurement instances corresponding to K measurement moments (i.e., all K measurement instances) is given, and the link quality is reported in a non-differential manner.
  • each measurement instance needs to include the link quality of N cells, and the link quality of each cell includes the link quality of M downlink reference signals. Therefore, the terminal needs to report a total of K ⁇ N ⁇ M link qualities.
  • the measurement moment index may not be included. In this case, the measurement instances corresponding to each measurement moment need to be arranged in sequence in the reporting format; or, the measurement moment index may be included. In this case, the measurement instances corresponding to each measurement moment can be flexibly arranged in the reporting format.
  • the reporting format of the measurement instance corresponding to the kth measurement moment is given, and the link quality is reported in a differential manner.
  • the difference between Table 5 and Table 3 is that the link quality is reported in a differential manner.
  • the reference link quality the highest link quality among the M link qualities is used as the reference link quality, and the downlink reference signal resource index (such as SSBRI or CRI) corresponding to the reference link quality is marked, and the other link qualities are differentially reported in a fixed order of the downlink reference signal resource index resources (such as from small to large).
  • the differential reporting here means reporting only the difference between the other link qualities and the reference link quality.
  • Table 6 the reporting format of the measurement instances corresponding to K measurement moments (i.e., all K measurement instances) is given, and the link quality is reported in a differential manner.
  • Table 6 contains the contents of K measurement instances, and the content of each measurement instance is similar to that of Table 5.
  • the measurement moment index may not be included, in which case the measurement instances corresponding to each measurement moment need to be arranged in sequence in the reporting format; or, the measurement moment index may be included, in which case the measurement instances corresponding to each measurement moment can be flexibly arranged in the reporting format.
  • the reporting format of the measurement instance corresponding to the kth measurement moment is given, and the link quality is reported in a differential manner.
  • the difference between Table 7 and Table 5 is that the highest link quality is selected from the link qualities of all cells as the reference link quality, and the downlink reference signal resource index (such as SSBRI or CRI) corresponding to the reference link quality is marked.
  • the cell index corresponding to the reference link quality needs to be marked, and the other link qualities are differentially reported in a fixed order of the downlink reference signal resource index resources (such as from small to large).
  • the differential reporting here means reporting only the difference between the other link qualities and the reference link quality.
  • Table 8 the reporting format of the measurement instances corresponding to K measurement moments (i.e., all K measurement instances) is given, and the link quality is reported in a differential manner.
  • Table 8 contains the contents of K measurement instances, and the contents of each measurement instance are similar to those of Table 7.
  • the measurement moment index i.e., k value
  • the reference link quality needs to be included.
  • Table 9 the reporting format of the measurement instance corresponding to the kth measurement moment is given, and the link quality is reported in a differential manner.
  • Table 9 contains N cell indexes, and the content of the quality is similar to that of Table 5.
  • Table 9 does not give the measurement moment index.
  • Table 9 can contain the measurement moment index.
  • the terminal can flexibly report part or all of the measurement results. Specifically, the terminal can report part of the cell index and the link quality corresponding to each cell in the part of the cell.
  • Table 10 the reporting format of the measurement instances corresponding to K measurement moments (i.e., all K measurement instances) is given, and the link quality is reported in a differential manner.
  • Table 10 contains K measurement instances, and the content of each measurement instance is similar to that of Table 9.
  • Table 10 also contains a measurement moment index.
  • the measurement instance corresponding to each measurement moment can be flexibly arranged in the reporting format.
  • Table 10 may not contain a measurement moment index.
  • the measurement instance corresponding to each measurement moment is arranged in sequence in the reporting format.
  • the reporting format of the measurement result of a cell in a measurement instance corresponding to one measurement moment is given, and the link quality is reported in a differential manner.
  • the reporting format includes a cell index, a measurement moment index, and the corresponding link quality, and M link qualities are reported in a differential manner.
  • the terminal can report only the measurement result of one first downlink reference signal subset in each report, and the network device needs to collect multiple reports from the terminal as input to the first model.
  • the network device side does not necessarily need to wait until the measurement results of all first downlink reference signal subsets are collected before making predictions.
  • the network device after the network device obtains F prediction instances, the network device sends a cell switching command (Cell Switch Command, CSC) to the terminal, and the terminal receives the cell switching command sent by the network device.
  • CSC Cell Switch Command
  • the cell switching command is used to instruct the terminal to switch to a target cell, and the target cell is determined based on some or all of the F prediction instances.
  • the F prediction instances obtained by the network device can be the F prediction instances sent by the terminal to the network device in the above scheme (refer to the scheme in which the above model is located on the terminal side), or can be the F prediction instances predicted by the network device based on the K measurement instances obtained (refer to the scheme in which the above model is located on the network device side).
  • the network device may use a cell switching command based on a unified TCI state, which is carried by the MAC CE.
  • the unified TCI state may be a DL/joint TCI state, which includes a cell index (such as PCI, PCI index, cell configuration index, etc.), through which the terminal may indicate the target cell to which it switches.
  • the terminal after the terminal obtains K measurement instances and predicts F prediction instances, the terminal sends a cell switching request (Cell Switch reQuest, CSQ) to a network device.
  • Cell Switch reQuest Cell Switch reQuest, CSQ
  • the cell switching request carries a target prediction instance, and the target prediction instance is determined based on the F prediction instances.
  • the terminal may not report the F prediction instances, but send a cell switching request to the network device based on the F prediction instances, and the cell switching request is carried by MAC CE.
  • the cell switching request may include at least one of the following information: prediction time index (i.e., f value); cell index of the target cell, such as PCI, PCI index, candidate cell configuration index, or p index; downlink reference signal resource index corresponding to the target cell, such as CRI/SSBRI or beam (pair) index; link quality corresponding to the downlink reference signal resource index, such as L1-RSRP.
  • the network device After receiving the cell switching request, the network device only needs to send a confirmation command to the terminal, and the terminal can complete the subsequent switching operation.
  • the result of the optimal beam predicted by the model is evaluated according to the link quality corresponding to the beam, that is, the highest L1-RSRP.
  • the link quality corresponding to the beam that is, the highest L1-RSRP.
  • a common method for selecting the best cell is to perform a weighted average of the link qualities of multiple beams in the cell to obtain the best cell (ranked from high to low by the mean L1-RSRP).
  • the model used to predict the best cell also refers to the selection mechanism of the best cell, namely, cell-level mobility.
  • the technical solution of the embodiment of the present application proposes a model-based mobility prediction technology, which uses the measurement results of multiple cells at multiple historical measurement moments as the input of the model, and predicts (outputs) the optimal cell at multiple future prediction moments, and/or the optimal beam (pair) under the cell, and/or the link quality corresponding to the beam (pair), thereby realizing mobility management from passive to active and reducing the overhead and delay of downlink mobility measurement.
  • the terminal is referred to as UE and the network device is referred to as NW.
  • the input set of the model can be a measurement set Set B or generated from a measurement set Set C.
  • Set B itself can be a measurement set, or Set B can be generated from a measurement set Set C, that is, Set B is the optimal multiple beams (pairs) and their link qualities measured in Set C.
  • Set B can be a measurement set or generated from a measurement set Set C.
  • the model is deployed on the UE side, so that the UE can use the measurement result of the downlink reference signal as the input of the model for inference.
  • FIG16 is a schematic diagram of a flow chart of a time domain mobility prediction method. As shown in FIG16 , the method includes the following steps:
  • Step 1601 The UE reports the capability information of the UE to the NW.
  • the UE capability information may refer to the aforementioned related solutions.
  • Step 1602 NW configures Set A and Set B for UE.
  • NW can refer to the aforementioned related solutions to configure Set A and Set B for UE.
  • Step 1603 The UE performs measurement according to the configuration of the NW to obtain K measurement instances.
  • the contents of the K measurement instances can refer to the aforementioned related schemes.
  • the kth (1 ⁇ k ⁇ K) measurement instance among the K measurement instances is called measurement instance #k.
  • measurement instance #k includes the measurement results corresponding to Set B_1,k, Set B_2,k, ..., Set B_N,k respectively.
  • Set B_n,k (1 ⁇ n ⁇ N, 1 ⁇ k ⁇ K) has the same meaning as Set B n,k in the above scheme.
  • Step 1604 The UE-side model predicts, based on the measurement instance: the optimal L (L ⁇ 1) cell indices, the optimal J (J ⁇ 1) beam (pair) indices in each optimal area, and the link quality corresponding to each optimal beam (pair) index.
  • the UE side model performs predictions corresponding to F prediction moments. Specifically, the UE side model requires K historical measurement instances as input, so as to predict the measurement instances of the subsequent F prediction moments.
  • Step 1605 The UE reports a prediction instance or a cell switching request to the NW.
  • prediction instance content or cell switching request can refer to the aforementioned related scheme.
  • the fth (1 ⁇ f ⁇ F) prediction instance among F prediction instances is called prediction instance #f.
  • prediction instance #f contains the prediction results corresponding to Set A_1,f, Set A_2,f,..., Set A_P,f respectively.
  • Set A_p,f (1 ⁇ p ⁇ P, 1 ⁇ f ⁇ F) here has the same meaning as Set A p,f in the above scheme.
  • Step 1606 The NW sends a cell switching command or a confirmation command to the UE.
  • the cell switching command or confirmation command can refer to the aforementioned related solutions.
  • step 1606 is indicated by a dotted line because the optimal cell predicted by the model may be the current serving cell, so there is no need to perform cell switching, so step 1606 is an optional step.
  • the ellipse represents the measurement set Set B n,k , where n (1 ⁇ n ⁇ N) represents the index of the first downlink reference signal subset (i.e., the measurement subset), and k (1 ⁇ k ⁇ K) represents the measurement time index.
  • the dotted ellipse represents the downlink reference signal that the UE has not measured but is included in the prediction set Set A p,f , where p (1 ⁇ p ⁇ P) represents the index of the second downlink reference signal subset (i.e., the prediction subset), and f (1 ⁇ f ⁇ F) represents the prediction time index.
  • the number of prediction subsets P may not be equal to the number of measurement subsets N.
  • a typical deployment method is that P is equal to N, that is, the number of prediction subsets is the same as the number of measurement subsets, and each prediction subset/measurement subset corresponds to a cell.
  • Set B and Set A can be the same (i.e., only time domain prediction), or Set B and Set A can be different (i.e., prediction in both spatial and time domains).
  • the result of the optimal beam predicted by the model is evaluated according to the link quality corresponding to the beam, that is, the highest L1-RSRP.
  • the link quality corresponding to the beam that is, the highest L1-RSRP.
  • a common method for selecting the best cell is to perform a weighted average of the link qualities of multiple beams in the cell to obtain the best cell (ranked from high to low by the mean L1-RSRP).
  • the model used to predict the best cell also refers to the selection mechanism of the best cell, namely, cell-level mobility.
  • the model is deployed on the NW side, and the UE measures the time domain mobility, that is, measures Set B, and reports the measurement results to the NW.
  • the model deployed on the NW side can then predict the time domain mobility.
  • FIG17 is a flow chart of a method for predicting time-domain mobility. As shown in FIG17 , the method includes the following steps:
  • Step 1701 The UE reports the capability information of the UE to the NW.
  • the UE capability information may refer to the aforementioned related solutions.
  • Step 1702 NW configures Set A and Set B for UE.
  • NW can refer to the aforementioned related solutions to configure Set A and Set B for UE.
  • Step 1703 The UE performs measurement according to the configuration of the NW to obtain K measurement instances.
  • the contents of the K measurement instances can refer to the aforementioned related schemes.
  • the kth (1 ⁇ k ⁇ K) measurement instance among the K measurement instances is called measurement instance #k.
  • measurement instance #k includes the measurement results corresponding to Set B_1,k, Set B_2,k, ..., Set B_N,k respectively.
  • Set B_n,k (1 ⁇ n ⁇ N, 1 ⁇ k ⁇ K) has the same meaning as Set B n,k in the aforementioned scheme.
  • Step 1704 The UE may report a measurement instance to the NW each time it obtains a measurement instance, or the UE may obtain K measurement instances by measurement and then report K measurement instances to the NW.
  • Step 1705 The NW side model predicts, based on the measurement instance: the optimal L (L ⁇ 1) cell indices, the optimal J (J ⁇ 1) beam (pair) indices in each optimal area, and the link quality corresponding to each optimal beam (pair) index.
  • prediction instance #f contains the prediction results corresponding to Set A_1,f, Set A_2,f,..., Set A_P,f respectively.
  • Set A_p,f (1 ⁇ p ⁇ P, 1 ⁇ f ⁇ F) has the same meaning as Set A p,f in the above scheme.
  • Step 1706 The NW sends a cell switching command to the UE.
  • the cell switching command or confirmation command can refer to the aforementioned related solutions.
  • step 1706 is indicated by a dotted line because the optimal cell predicted by the model may be the current serving cell, so there is no need to perform cell switching, so step 1706 is an optional step.
  • the ellipse represents the measurement set Set B n,k , where n (1 ⁇ n ⁇ N) represents the index of the first downlink reference signal subset (i.e., the measurement subset), and k (1 ⁇ k ⁇ K) represents the measurement time index.
  • the dotted ellipse represents the downlink reference signal that the UE has not measured but is included in the prediction set Set A p,f , where p (1 ⁇ p ⁇ P) represents the index of the second downlink reference signal subset (i.e., the prediction subset), and f (1 ⁇ f ⁇ F) represents the prediction time index.
  • the number of prediction subsets P may not be equal to the number of measurement subsets N.
  • the NW can infer the optimal cell from 16 prediction subsets (such as 1 serving cell and 15 candidate cells' prediction subsets), and/or the optimal beam (pair) index corresponding to the optimal cell, and/or the link quality corresponding to the optimal beam (pair) index.
  • P is equal to N, that is, the number of prediction subsets is the same as the number of measurement subsets, and each prediction subset/measurement subset corresponds to a cell.
  • Set B and Set A can be the same (i.e., only time domain prediction), or Set B and Set A can be different (i.e., prediction in both spatial and time domains).
  • the result of the optimal beam predicted by the model is evaluated according to the link quality corresponding to the beam, that is, the highest L1-RSRP.
  • the link quality corresponding to the beam that is, the highest L1-RSRP.
  • a common method for selecting the best cell is to perform a weighted average of the link qualities of multiple beams in the cell to obtain the best cell (ranked from high to low by the mean L1-RSRP).
  • the model used to predict the best cell also refers to the selection mechanism of the best cell, namely, cell-level mobility.
  • the size of the sequence number of each process does not mean the order of execution, and 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 embodiment of the present application.
  • downlink indicates that the transmission direction of the signal or data
  • uplink is used to indicate that the transmission direction of the signal or data is the second direction sent from the user equipment of the cell to the site
  • side is used to indicate that the transmission direction of the signal or data is the third direction sent from user equipment 1 to user equipment 2.
  • downlink signal indicates that the transmission direction of the signal is the first direction.
  • the term "and/or” is only a description of the association relationship of the associated objects, indicating that three relationships can exist. Specifically, A and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character “/" in this article generally indicates that the front and back associated objects are in an "or" relationship.
  • FIG. 18 is a schematic diagram of the structure of a mobility prediction device provided in an embodiment of the present application.
  • the device is applied to a terminal. As shown in FIG. 18 , the device includes:
  • An acquisition unit 1801 is configured to acquire K measurement instances corresponding to a first downlink reference signal set, where the K measurement instances are obtained based on the terminal measuring the downlink reference signals in the first downlink reference signal set at K measurement moments, where the first downlink reference signal set includes a first downlink reference signal subset of N cells; wherein the K measurement instances are used to acquire F prediction instances corresponding to a second downlink reference signal set based on a first model, where different prediction instances correspond to different prediction moments, and the second downlink reference signal set includes a second downlink reference signal subset of P cells; and K, N, F and P are integers greater than or equal to 1.
  • the apparatus further includes: a receiving unit 1802, configured to receive first configuration information and/or second configuration information sent by a network device; the first configuration information is used to configure the first downlink reference signal set; the second configuration information is used to configure the second downlink reference signal set.
  • a receiving unit 1802 configured to receive first configuration information and/or second configuration information sent by a network device; the first configuration information is used to configure the first downlink reference signal set; the second configuration information is used to configure the second downlink reference signal set.
  • the first configuration information is further used to configure first time domain information corresponding to the first downlink reference signal set, and the first time domain information is used to determine K measurement moments corresponding to the K measurement instances; and/or, the second configuration information is further used to configure second time domain information corresponding to the second downlink reference signal set, and the second time domain information is used to determine F prediction moments corresponding to the F prediction instances.
  • the first time domain information includes at least one of the following: a measurement period, a first offset, and the number of measurement moments K; and/or the second time domain information includes at least one of the following: a prediction period, a second offset, and the number of prediction moments F.
  • the first configuration information and/or the second configuration information is related to capability information of the terminal.
  • the apparatus further includes: a sending unit 1803, configured to send the capability information of the terminal to the network device, where the capability information of the terminal includes at least one of the following:
  • first information where the first information is used to indicate whether the terminal supports measurement and/or prediction of time domain mobility
  • the second information is used to indicate at least one of the following: the maximum number of cells supported for measurement by the terminal on all CCs or BWPs; the maximum number of configured first downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs; the maximum number of first downlink reference signal subsets supported for measurement by the terminal on all downlink CCs or BWPs;
  • the third information is used to indicate at least one of the following: the maximum number of predicted cells supported by the terminal on all downlink CCs or BWPs; the maximum number of configured second downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs; the maximum number of predicted first downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs;
  • the fourth information is used to indicate at least one of the following: the maximum number of cells supported for measurement by the terminal on each downlink CC or BWP; the maximum number of configured first downlink reference signal subsets supported by the terminal on each downlink CC or BWP; the maximum number of first downlink reference signal subsets supported for measurement by the terminal on each downlink CC or BWP;
  • the fifth information is used to indicate at least one of the following: the number of predicted cells supported by the terminal on each downlink CC or BWP at most; the number of configured second downlink reference signal subsets supported by the terminal on each downlink CC or BWP at most; the number of predicted second downlink reference signal subsets supported by the terminal on each downlink CC or BWP;
  • sixth information is used to indicate a maximum number of downlink reference signals that the terminal supports measuring in each first downlink reference signal subset
  • the seventh information is used to indicate a maximum number of predicted downlink reference signals supported by the terminal in each second downlink reference signal subset;
  • Eighth information where the eighth information is used to indicate the number of measurement moments supported by the terminal;
  • the ninth information is used to indicate the number of prediction moments supported by the terminal.
  • the K measurement instances include:
  • K ⁇ N indexes and K ⁇ N groups of link qualities the K ⁇ N indexes and the K ⁇ N link qualities have a corresponding relationship; each of the K ⁇ N indexes corresponds to a measurement time index and a cell index.
  • each of the F prediction instances includes at least one of the following:
  • the best J downlink reference signal resource indexes in each best cell
  • each prediction instance further includes: a prediction time index corresponding to the prediction instance.
  • the first model is located at the terminal side.
  • the sending unit 1803 is configured to send the F prediction instances to a network device.
  • the reporting manner of the F prediction instances includes at least one of the following: periodic reporting, semi-persistent reporting, non-periodic reporting, and mobility event reporting based on layer 1 and/or layer 2.
  • the receiving unit 1802 is used to receive third configuration information sent by a network device, and the third configuration information is used to configure a reporting period and a reporting offset corresponding to the periodic reporting or the semi-persistent reporting.
  • the receiving unit 1802 is configured to receive a first DCI sent by a network device, where the first DCI is used to trigger the aperiodic reporting.
  • the layer 1 and/or layer 2 mobility events include at least one of the following:
  • a first event wherein the first event is that at some or all of the F predicted moments, the predicted link performance of the current serving cell is better than the first threshold or weaker than the second threshold;
  • a second event wherein the second event is that at some or all of the F prediction moments, the predicted link performance of the current serving cell is better or weaker than the predicted link performance of the candidate cell plus an offset;
  • a third event wherein the third event is: at some or all of the F prediction moments, the predicted link performance of the candidate cell is better than the third threshold or weaker than the fourth threshold;
  • a fourth event wherein the fourth event is: at some or all of the F prediction moments, the predicted link performance of the current serving cell is weaker than the fifth threshold, and the predicted link performance of the candidate cell is better than the sixth threshold;
  • the current cell is one of the P cells
  • the candidate cell is one of the P cells except the current cell.
  • the sending unit 1803 is used to determine that the mobility event of layer 1 and/or layer 2 is triggered, and send a reporting request to the network device; the receiving unit 1802 is used to receive a second DCI sent by the network device, and the second DCI is used to schedule the PUSCH for reporting.
  • the reporting granularity of the F prediction instances is one prediction instance.
  • the report has a first format, the first format including: a prediction time index, L cell indexes, X1 downlink reference signal resource indexes, and X1 link qualities;
  • the L cell indexes are the best L cell indexes among the P cells; the X1 downlink reference signal resource indexes include the best J downlink reference signal resource indexes in each of the L cells; and the X1 link qualities have a corresponding relationship with the X1 downlink reference signal resource indexes.
  • the reporting granularity of the F prediction instances is F prediction instances.
  • the reporting has a second format, the second format includes F groups of information, and the F groups of information have a corresponding relationship with the F prediction instances;
  • Each group of information in the F groups of information includes: a prediction time index, L cell indexes, X1 downlink reference signal resource indexes and X1 link qualities; or,
  • Each group of information in the F groups of information includes: L cell indexes, X1 downlink reference signal resource indexes and X1 link qualities;
  • the L cell indexes are the best L cell indexes among the P cells; the X1 downlink reference signal resource indexes include the best J downlink reference signal resource indexes in each of the L cells; and the X1 link qualities have a corresponding relationship with the X1 downlink reference signal resource indexes.
  • the first model is located at a network device side.
  • the sending unit 1803 is configured to send the K measurement instances to a network device.
  • the reporting manner of the K measurement instances includes at least one of the following: periodic reporting, semi-continuous reporting, and non-periodic reporting.
  • the receiving unit 1802 is used to receive fourth configuration information sent by a network device, and the fourth configuration information is used to configure a reporting period and a reporting offset corresponding to the periodic reporting or the semi-persistent reporting.
  • the receiving unit 1802 is configured to receive a third DCI sent by a network device, where the third DCI is used to trigger the aperiodic reporting.
  • the reporting granularity of the K measurement instances is one measurement instance.
  • the reporting has a third format, the third format including: a measurement time index and X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the report has a fourth format, the fourth format including: a measurement time index, N cell indexes, and X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the reporting granularity of the K measurement instances is K measurement instances.
  • the report has a fifth format, the fifth format including: K groups of information, the K groups of information corresponding to the K measurement instances; each group of information in the K groups of information including: X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the report has a sixth format, the sixth format includes: N cell indexes and K group information, or the sixth format includes: N cell indexes, K measurement instance indexes and K group information; the K group information has a corresponding relationship with the K measurement instance indexes; each group of information in the K group information includes: X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the format of the X2 link qualities in the report adopts a differential reporting format or a non-differential reporting format.
  • the reporting granularity is one measurement instance
  • the differential reporting format in the differential reporting format
  • the X2 link qualities are represented by a reference link quality and X2-1 differential values; or,
  • the X2 link qualities are divided into N groups of link qualities, and each group of link qualities is represented by a reference link quality and M-1 differential values.
  • K ⁇ X2 link qualities are represented by a reference link quality and K ⁇ X2-1 differential values; or,
  • the K ⁇ X2 link qualities are divided into K ⁇ N groups of link qualities, and each group of link qualities is represented by a reference link quality and M-1 differential values.
  • the X2 link qualities are represented by X2 link qualities.
  • the reporting granularity of the K measurement instances is the measurement result of one cell in one measurement instance.
  • the report has a sixth format, the sixth format including: a measurement time index, a cell index, and M link qualities;
  • the M link qualities include link qualities of M downlink reference signals of the cell corresponding to the cell index, and M is a positive integer.
  • the format of the M link qualities in the report adopts a differential reporting format or a non-differential reporting format.
  • the M link qualities are represented by a reference link quality and M-1 differential values.
  • the M link qualities are represented by M link qualities.
  • the receiving unit 1802 is used to receive a cell switching command sent by the network device, where the cell switching command is used to instruct the terminal to switch to a target cell, where the target cell is determined based on some or all of the F prediction instances.
  • the sending unit 1803 is configured to send a cell switching request to the network device, where the cell switching request carries a target prediction instance, and the target prediction instance is determined based on the F prediction instances.
  • the measurement times corresponding to the K measurement instances and the prediction times corresponding to the F prediction instances satisfy the following timing relationship:
  • the measurement moments corresponding to the K measurement instances are within a first time period, and the prediction moments corresponding to the F prediction instances are within a second time period, and the second time period does not overlap with the first time period;
  • the measurement moments corresponding to the K measurement instances are located within the K first time periods, and the prediction moments corresponding to the F prediction instances are located within the last first time period of the K first time periods.
  • FIG. 19 is a second schematic diagram of the structure of a mobility prediction device provided in an embodiment of the present application, which is applied to a network device. As shown in FIG. 19 , the device includes:
  • the receiving unit 1901 is used to receive K measurement instances corresponding to a first downlink reference signal set sent by a terminal, where the K measurement instances are obtained based on the terminal measuring the downlink reference signal in the first downlink reference signal set at K measurement times, and the first downlink reference signal set includes a first downlink reference signal subset of N cells; wherein the K measurement instances are used to obtain F prediction instances corresponding to a second downlink reference signal set based on a first model, different prediction instances correspond to different prediction times, and the second downlink reference signal set includes a second downlink reference signal subset of P cells; K, N, F and P are integers greater than or equal to 1.
  • the apparatus further includes: a sending unit 1902, configured to send the first configuration information and/or the second configuration information to the terminal;
  • the first configuration information is used to configure the first downlink reference signal set; the second configuration information is used to configure the second downlink reference signal set.
  • the first configuration information is further used to configure first time domain information corresponding to the first downlink reference signal set, and the first time domain information is used to determine K measurement times corresponding to the K measurement instances; and/or,
  • the second configuration information is further used to configure second time domain information corresponding to the second downlink reference signal set, and the second time domain information is used to determine F prediction moments corresponding to the F prediction instances.
  • the first time domain information includes at least one of the following: a measurement period, a first offset, a number K of measurement moments; and/or,
  • the second time domain information includes at least one of the following: a prediction period, a second offset, and the number F of prediction moments.
  • the first configuration information and/or the second configuration information is related to capability information of the terminal.
  • the receiving unit 1901 is configured to receive capability information of the terminal sent by the terminal, where the capability information of the terminal includes at least one of the following:
  • first information where the first information is used to indicate whether the terminal supports measurement and/or prediction of time domain mobility
  • the second information is used to indicate at least one of the following: the maximum number of cells supported for measurement by the terminal on all downlink CCs or BWPs; the maximum number of configured first downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs; the maximum number of first downlink reference signal subsets supported for measurement by the terminal on all downlink CCs or BWPs;
  • the third information is used to indicate at least one of the following: the maximum number of predicted cells supported by the terminal on all downlink CCs or BWPs; the maximum number of configured second downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs; the maximum number of predicted first downlink reference signal subsets supported by the terminal on all downlink CCs or BWPs;
  • the fourth information is used to indicate at least one of the following: the maximum number of cells supported for measurement by the terminal on each downlink CC or BWP; the maximum number of configured first downlink reference signal subsets supported by the terminal on each downlink CC or BWP; the maximum number of first downlink reference signal subsets supported for measurement by the terminal on each downlink CC or BWP;
  • the fifth information is used to indicate at least one of the following: the number of predicted cells supported by the terminal on each downlink CC or BWP at most; the number of configured second downlink reference signal subsets supported by the terminal on each downlink CC or BWP at most; the number of predicted second downlink reference signal subsets supported by the terminal on each downlink CC or BWP;
  • sixth information is used to indicate a maximum number of downlink reference signals that the terminal supports measuring in each first downlink reference signal subset
  • the seventh information is used to indicate a maximum number of predicted downlink reference signals supported by the terminal in each second downlink reference signal subset;
  • Eighth information where the eighth information is used to indicate the number of measurement moments supported by the terminal;
  • the ninth information is used to indicate the number of prediction moments supported by the terminal.
  • the K measurement instances include:
  • N ⁇ K indexes and N ⁇ K groups of link qualities the N ⁇ K indexes and the N ⁇ K link qualities have a corresponding relationship; each of the N ⁇ K indexes corresponds to a cell index and a measurement time index.
  • each of the F prediction instances includes at least one of the following:
  • the best J downlink reference signal resource indexes in each best cell
  • each prediction instance further includes: a prediction time index corresponding to the prediction instance.
  • the reporting manner of the K measurement instances includes at least one of the following: periodic reporting, semi-continuous reporting, and non-periodic reporting.
  • the sending unit 1902 is configured to send fourth configuration information to the terminal, where the fourth configuration information is used to configure a reporting period and a reporting offset corresponding to the periodic reporting or the semi-persistent reporting.
  • the sending unit 1902 is configured to send a third DCI to the terminal, where the third DCI is used to trigger the non-periodic reporting.
  • the reporting granularity of the K measurement instances is one measurement instance.
  • the reporting has a third format, the third format including: a measurement time index and X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the report has a fourth format, the fourth format including: a measurement time index, N cell indexes, and X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the reporting granularity of the K measurement instances is K measurement instances.
  • the report has a fifth format, the fifth format including: K groups of information, the K groups of information corresponding to the K measurement instances; each group of information in the K groups of information includes: X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the report has a sixth format, the sixth format includes: N cell indexes and K group information, or the sixth format includes: N cell indexes, K measurement instance indexes and K group information; the K group information has a corresponding relationship with the K measurement instance indexes; each group of information in the K group information includes: X2 link qualities;
  • the X2 link qualities include link qualities of M downlink reference signals of each cell in the N cells, where M is a positive integer.
  • the format of the X2 link qualities in the report adopts a differential reporting format or a non-differential reporting format.
  • the reporting granularity is one measurement instance
  • the differential reporting format in the differential reporting format
  • the X2 link qualities are represented by a reference link quality and X2-1 differential values; or,
  • the X2 link qualities are divided into N groups of link qualities, and each group of link qualities is represented by a reference link quality and M-1 differential values.
  • K ⁇ X2 link qualities are represented by a reference link quality and K ⁇ X2-1 differential values; or,
  • the K ⁇ X2 link qualities are divided into K ⁇ N groups of link qualities, and each group of link qualities is represented by a reference link quality and M-1 differential values.
  • the X2 link qualities are represented by X2 link qualities.
  • the reporting granularity of the K measurement instances is the measurement result of one cell in one measurement instance.
  • the report has a sixth format, the sixth format including: a measurement time index, a cell index, and M link qualities;
  • the M link qualities include link qualities of M downlink reference signals of the cell corresponding to the cell index, and M is a positive integer.
  • the format of the M link qualities in the report adopts a differential reporting format or a non-differential reporting format.
  • the M link qualities are represented by a reference link quality and M-1 differential values.
  • the M link qualities are represented by M link qualities.
  • the sending unit 1902 is configured to send a cell switching command to the terminal, where the cell switching command is used to instruct the terminal to switch to a target cell, where the target cell is determined based on some or all of the F prediction instances.
  • the measurement times corresponding to the K measurement instances and the prediction times corresponding to the F prediction instances satisfy the following timing relationship:
  • the measurement moments corresponding to the K measurement instances are within a first time period, and the prediction moments corresponding to the F prediction instances are within a second time period, and the second time period does not overlap with the first time period;
  • the measurement moments corresponding to the K measurement instances are located within the K first time periods, and the prediction moments corresponding to the F prediction instances are located within the last first time period of the K first time periods.
  • FIG20 is a schematic structural diagram of a communication device 2000 provided in an embodiment of the present application.
  • the communication device can be a terminal or a network device.
  • the communication device 2000 shown in FIG20 includes a processor 2010, and the processor 2010 can call and run a computer program from a memory to implement the method in the embodiment of the present application.
  • the communication device 2000 may further include a memory 2020.
  • the processor 2010 may call and run a computer program from the memory 2020 to implement the method in the embodiment of the present application.
  • the memory 2020 may be a separate device independent of the processor 2010 , or may be integrated into the processor 2010 .
  • the communication device 2000 may further include a transceiver 2030 , and the processor 2010 may control the transceiver 2030 to communicate with other devices, specifically, may send information or data to other devices, or receive information or data sent by other devices.
  • the transceiver 2030 may include a transmitter and a receiver.
  • the transceiver 2030 may further include an antenna, and the number of antennas may be one or more.
  • the communication device 2000 may specifically be a network device of an embodiment of the present application, and the communication device 2000 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.
  • the communication device 2000 may specifically be a mobile terminal/terminal of an embodiment of the present application, and the communication device 2000 may implement the corresponding processes implemented by the mobile terminal/terminal in each method of the embodiment of the present application, which will not be described again for the sake of brevity.
  • Fig. 21 is a schematic structural diagram of a chip according to an embodiment of the present application.
  • the chip 2100 shown in Fig. 21 includes a processor 2110, and the processor 2110 can call and run a computer program from a memory to implement the method according to the embodiment of the present application.
  • the memory 2120 may be a separate device independent of the processor 2110 , or may be integrated into the processor 2110 .
  • the chip 2100 may further include an input interface 2130.
  • the processor 2110 may control the input interface 2130 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.
  • the chip 2100 may further include an output interface 2140.
  • the processor 2110 may control the output interface 2140 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.
  • the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
  • the chip can be applied to the mobile terminal/terminal in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal/terminal in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
  • 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.
  • FIG22 is a schematic block diagram of a communication system 2200 provided in an embodiment of the present application. As shown in FIG22 , the communication system 2200 includes a terminal 2210 and a network device 2220 .
  • the terminal 2210 can be used to implement the corresponding functions implemented by the terminal in the above method
  • the network device 2220 can be used to implement the corresponding functions implemented by the network device in the above method.
  • the terminal 2210 can be used to implement the corresponding functions implemented by the terminal in the above method
  • the network device 2220 can be used to implement the corresponding functions implemented by the network device in the above method.
  • the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities.
  • each step of the above method embodiment can be completed by the hardware integrated logic circuit in the processor or the instruction in the form of software.
  • the above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • the methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed.
  • the general processor can be a microprocessor or the processor can also be any conventional processor, etc.
  • the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor can be executed.
  • the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
  • the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.
  • the non-volatile memory can 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 can be a random access memory (RAM), which is used as an external cache.
  • RAM Direct Rambus RAM
  • SRAM Static RAM
  • DRAM Dynamic RAM
  • SDRAM Synchronous DRAM
  • DDR SDRAM Double Data Rate SDRAM
  • ESDRAM Enhanced SDRAM
  • SLDRAM Synchlink DRAM
  • DR RAM Direct Rambus RAM
  • the memory in the embodiment of the present application may also be static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM) and direct RAM RAM (DR RAM), etc. That is to say, the memory in the embodiment of the present application is intended to include but not limited to these and any other suitable types of memory.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDR SDRAM double data rate synchronous DRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchronous link DRAM
  • DR RAM direct RAM
  • An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.
  • the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the computer-readable storage medium can be applied to the mobile terminal/terminal in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal/terminal in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • An embodiment of the present application also provides a computer program product, including computer program instructions.
  • the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the computer program product can be applied to the mobile terminal/terminal in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the mobile terminal/terminal in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the embodiment of the present application also provides a computer program.
  • the computer program can be applied to the network device in the embodiments of the present application.
  • the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods in the embodiments of the present application. For the sake of brevity, they are not described here.
  • the computer program can be applied to the mobile terminal/terminal in the embodiments of the present application.
  • the computer program runs on the computer, the computer executes the corresponding processes implemented by the mobile terminal/terminal in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application.
  • the aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请实施例提供一种时域移动性预测方法及装置、通信设备、芯片、存储介质，该方法包括：终端获取第一下行参考信号集对应的K个测量实例，所述K个测量实例基于所述终端在K个测量时刻对所述第一下行参考信号集中的下行参考信号进行测量得到，所述第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，所述K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的所述预测实例对应不同的预测时刻，所述第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。

Description

一种时域移动性预测方法及装置、设备、芯片和存储介质 技术领域
本申请实施例涉及通信技术领域，具体涉及一种时域移动性预测方法及装置、设备、芯片和存储介质。
背景技术
传统的移动性方案是基于测量的，属于被动(reactive)的方案，即链路质量下降到一定程度之后才会被发现，从而触发后续的移动性管理流程，如小区切换。然而，这种方案往往具有一定的滞后性，导致小区切换的时延较长(或者说小区切换不及时)，进而导致通信性能下降。
发明内容
本申请实施例提供一种时域移动性预测方法及装置、设备、芯片和存储介质。
第一方面，本申请实施例提供了一种移动性预测方法，该方法包括：
终端获取第一下行参考信号集对应的K个测量实例，K个测量实例基于终端在K个测量时刻对第一下行参考信号集中的下行参考信号进行测量得到，第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的预测实例对应不同的预测时刻，第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
第二方面，本申请实施例提供了一种移动性预测方法，该方法包括：
网络设备接收终端发送的第一下行参考信号集对应的K个测量实例，K个测量实例基于终端在K个测量时刻对第一下行参考信号集中的下行参考信号进行测量得到，第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的预测实例对应不同的预测时刻，第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
第三方面，本申请实施例提供了一种移动性预测装置，应用于终端，该装置包括：
获取单元，用于获取第一下行参考信号集对应的K个测量实例，K个测量实例基于终端在K个测量时刻对第一下行参考信号集中的下行参考信号进行测量得到，第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的预测实例对应不同的预测时刻，第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
第四方面，本申请实施例提供了一种移动性预测装置，应用于网络设备，该装置包括：
接收单元，用于接收终端发送的第一下行参考信号集对应的K个测量实例，K个测量实例基于终端在K个测量时刻对第一下行参考信号集中的下行参考信号进行测量得到，第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的预测实例对应不同的预测时刻，第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
第五方面，本申请实施例提供了一种通信设备，该通信设备包括存储器和处理器；其中，存储器，用于存储计算机可执行指令；处理器，与该存储器连接，用于通过执行该计算机可执行指令，实现如上述任一方面的方法。
第六方面，本申请实施例提供了一种芯片。该芯片包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有该芯片的设备执行如上述任一方面的方法。
第七方面，本申请实施例提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，计算机程序被至少一个处理器执行时实现如上述任一方面的方法。
本申请实施例的技术的方案，K个测量实例是终端在K个测量时刻对第一下行参考信号集中的下行参考信号进行测量得到的历史测量结果，基于第一模型根据历史测量结果可以预测得到未来的F个预测实例，这种移动性方案属于主动(pro-active)的方案，具有很强的前瞻性，通过F个预测实例可以及时触发移动性管理流程，从而避免因移动性管理流程的滞后导致的通信性能下降。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是本申请实施例的一个应用场景的示意图；
图2是NR系统中下行波束管理的一例示意图；
图3是神经元结构的一例示意图；
图4是神经网络的一例示意图；
图5是LSTM网络的示意图；
图6是适用于本申请实施例的神经网络模型的一例示意图；
图7是适用于本申请实施例的神经网络模型的另一例示意图；
图8是适用于本申请实施例的神经网络模型的另一例示意图；
图9是本申请实施例提供的一种时域移动性测量和预测的示意图；
图10是本申请实施例提供的测量实例和预测实例的一种时序关系示意图；
图11是本申请实施例提供的测量实例和预测实例的另一种时序关系示意图；
图12是本申请实施例提供的一种时域移动性预测方法的流程示意图一；
图13是本申请实施例提供的时域移动性预测模型的输入输出关系示意图一；
图14是本申请实施例提供的时域移动性预测模型的输入输出关系示意图二；
图15是本申请实施例提供的时域移动性预测模型的输入输出关系示意图三；
图16是本申请实施例提供的一种时域移动性预测方法的流程示意图二；
图17是本申请实施例提供的一种时域移动性预测方法的流程示意图三；
图18是本申请实施例提供的移动性预测装置的结构组成示意图一；
图19是本申请实施例提供的移动性预测装置的结构组成示意图二；
图20是本申请实施例提供的一种通信设备示意性结构图；
图21是本申请实施例的芯片的示意性结构图；
图22是本申请实施例提供的一种通信系统的示意性框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
图1是本申请实施例的一个应用场景的示意图。
如图1所示，通信系统100可以包括终端(如图1中的终端110)和网络设备(如图1中的网络设备120、网络设备130和网络设备140)。网络设备可以通过空口与终端通信。示例性地，网络设备120、网络设备130和网络设备140例如可位于不同的小区中，或者说，可服务于不同的小区。例如在通信系统100中，网络设备120位于小区#1，网络设备130位于小区#2，网络设备130位于小区#3。其中，终端110可位于一个或多个小区中，例如在通信系统100中，终端110位于小区#1。在该场景下，小区#1为终端110的服务小区，小区#2和小区#3为终端110的非服务小区。
在图1中，实线与虚线所表示的波束(对)的并集为各小区与终端之间的波束(对)的全集，实线表示的波束(对)为终端或网络设备需进行测量的波束(对)，虚线表示的波束(对)为终端或网络设备无需进行测量，但属于波束(对)全集中的波束(对)。
应理解，本申请实施例仅以通信系统100进行示例性说明，但本申请实施例不限定于此。也就是说，本申请实施例的技术方案可以应用于各种通信系统，例如：长期演进(Long Term Evolution，LTE)系统、LTE时分双工(Time Division Duplex，TDD)、通用移动通信系统(Universal Mobile Telecommunication System，UMTS)、物联网(Internet of Things，IoT)系统、窄带物联网(Narrow Band Internet of Things，NB-IoT)系统、增强的机器类型通信(enhanced Machine-Type Communications，eMTC)系统、5G通信系统(也称为新无线(New Radio，NR)通信系统)，或未来的通信系统等。
在图1所示的通信系统100中，网络设备(如网络设备120、网络设备130、网络设备140)可以是与终端(如终端110)通信的接入网设备。接入网设备可以为特定的地理区域提供通信覆盖，并且可以与位于该覆盖区域内的终端(例如UE)进行通信。
网络设备可以是长期演进(Long Term Evolution，LTE)系统中的演进型基站(Evolutional Node B，eNB或eNodeB)，或者是下一代无线接入网(Next Generation Radio Access Network，NG RAN)设备，或者是NR系统中的基站(gNB)，或者是云无线接入网络(Cloud Radio Access Network，CRAN)中的无线控制器，或者该网络设备可以为宏基站、微基站(也称为小站)、卫星、无线网络控制器(Radio Network Controller，RNC)、节点B(Node B，NB)、基站控制器(Base Station Controller，BSC)、基站收发台(Base Transceiver Station，BTS)、家庭基站(例如，Home Evolved NodeB，或Home Node B，HNB)、基带单元(Baseband Unit，BBU)，无线保真(Wireless Fidelity，WiFi)系统中的接入点(Access Point，AP)、无线中继节点、无线回传节点、传输点(Transmission Point，TP)或者发送接收点(Transmission and Reception Point，TRP)等。该网络设备还可以为中继站、接入点、车载设备、可穿戴设备、集线器、交换机、网桥、路由器，或者未来演进的公共陆地移动网络(Public Land Mobile Network，PLMN)中的网络设备等。
终端可以是任意终端，其包括但不限于与网络设备或其它终端采用有线或者无线连接的终端。
例如，所述终端可以指接入终端、用户设备(User Equipment，UE)、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、终端、无线通信设备、用户代理或用户装置。接入终端可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol，SIP)电话、IoT设备、卫星手持终端、无线本地环路(Wireless Local Loop，WLL)站、个人数字处理(Personal Digital Assistant，PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备、5G网络中的终端或者未来演进网络中的终端等。
终端可以用于设备到设备(Device to Device，D2D)的通信。
应理解，本申请实施例中对于终端和网络设备的具体形式不做特殊限制，在此仅是示例性说明。
无线通信系统100还可以包括与网络设备进行通信的核心网设备(图1中未予以画出)，该核心网设备可以是5G核心网(5G Core，5GC)设备，例如，接入与移动性管理功能(Access and Mobility Management Function，AMF)，又例如，认证服务器功能(Authentication Server Function，AUSF)，又例如，用户面功能(User Plane Function，UPF)，又例如，会话管理功能(Session Management Function，SMF)。可选地，核心网络设备也可以是LTE网络的分组核心演进(Evolved Packet Core，EPC)设备，例如，会话管理功能+核心网络的数据网关(Session Management Function+Core Packet Gateway，SMF+PGW-C)设备。应理解，SMF+PGW-C可以同时实现SMF和PGW-C所能实现的功能。在网络演进过程中，上述核心网设备也有可能叫其它名字，或者通过对核心网的功能进行划分形成新的网络实体，对此本申请实施例不做限制。
通信系统100中的各个功能单元之间还可以通过下一代网络(next generation，NG)接口建立连接实现通信。
例如，终端通过NR接口与接入网设备建立空口连接，用于传输用户面数据和控制面信令；终端可以通过NG接口1(简称N1)与AMF建立控制面信令连接；接入网设备例如下一代无线接入基站(gNB)，可以通过NG接口3(简称N3)与UPF建立用户面数据连接；接入网设备可以通过NG接口2(简称N2)与AMF建立控制面信令连接；UPF可以通过NG接口4(简称N4)与SMF建立控制面信令连接；UPF可以通过NG接口6(简称N6)与数据网络交互用户面数据；AMF可以通过NG接口11(简称N11)与SMF建立控制面信令连接；SMF可以通过NG接口7(简称N7)与PCF建立控制面信令连接。
图1示例性地示出了三个网络设备和一个终端，可选地，该无线通信系统100可以包括一个或多个网络设备并且每个网络设备的覆盖范围内可以包括其它数量的终端，本申请实施例对此不做限定。
需要说明的是，图1只是以示例的形式示意本申请所适用的系统，当然，本申请实施例所示的方法还可以适用于其它系统。此外，本文中术语“系统”和“网络”在本文中常被可互换使用。本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。还应理解，在本申请的实施例中提到的“指示”可以是直接指示，也可以是间接指示，还可以是表示具有关联关系。举例说明，A指示B，可以表示A直接指示B，例如B可以通过A获取；也可以表示A间接指示B，例如A指示C，B可以通过C获取；还可以表示A和B之间具有关联关系。还应理解，在本申请的实施例中提到的“对应”可表示两者之间具有直接对应或间接对应的关系，也可以表示两者之间具有关联关系，也可以是指示与被指示、配置与被配置等关系。还应理解，在本申请的实施例中提到的“预定义”或“预定义规则”可以通过在设备(例如，包括终端和网络设备)中预先保存相应的代码、表格或其他可用于指示相关信息的方式来实现，本申请对于其具体的实现方式不做限定。比如预定义可以是指协议中定义的。还应理解，本申请实施例中，所述“协议”可以指通信领域的标准协议，例如可以包括LTE协议、NR协议以及应用于未来的通信系统中的相关协议，本申请对此不做限定。
传统的移动性方案是基于测量的，属于被动(reactive)的方案，即链路质量下降到一定程度之后才会被发现，从而触发后续的移动性管理流程，如小区切换，但往往具有一定的滞后性。为此，提出了本申请实施例的技术方案，本申请实施例的技术方案，基于模型预测的移动性方案是基于历史测量结果，对未来多个小区的链路性能进行预测，从而选择最优的小区，属于主动(pro-active)的方案，具有很强的前瞻性，因此也可以节省小区切换的时延，降低无线链路失败的风险。让终端从一个链路质量较好的小区直接过度到另外一个链路质量较好的小区，体验不到由于小区切换不及时带来的性能下降。
为便于理解本申请实施例的技术方案，以下对本申请实施例的相关技术进行说明，以下相关技术作为可选方案与本申请实施例的技术方案可以进行任意结合，其均属于本申请实施例的保护范围。
1、NR的波束管理
NR系统的第一个版本(即Rel.15)引入了毫米波频段的通信，也即引入了波束管理机制。波束管理可以分为上行和下行的波束管理。其中，下行波束管理包括：下行波束扫描(Beam Sweeping)、UE波束测量和上报(Measurement&Reporting)、网络(Network，NW)的下行波束指示(Beam Indication)等过程；上行波束管理包括：上行波束扫描(UE发送波束扫描SRS)、NW波束测量，以及对UE的上行波束指示和配置。
图2是NR系统中下行波束管理的一例示意图。以下行波束扫描过程为例，可分为3个过程，即P1、P2和P3过程。其中，P1过程指NW扫描不同的发射波束，UE扫描不同的接收波束；P2过程指NW扫描不同的发射波束，UE使用相同的接收波束；P3过程指NW使用相同的发射波束，UE扫描不同的接收波束。通常，P1过程可在P2和P3过程之前执行，例如在图2的例子中，执行顺序可以为P1、P2和P3。一般情况下，NW通过发送下行参考信号—同步信号块(Synchronization Signal and PBCH Block，SSB)和/或信道状态信息-参考信号(Channel State Information-Reference Signal，CSI-RS)来完成上述波束扫描过程。
NR Rel.15中的波束上报机制包括：UE通过测量多个发射波束(P2过程)或发射接收波束对(P1过程)，将层1参考信号接收功率(L1-Reference Signal Receiving Power，RSRP，L1-RSRP)最高的L个发射波束及其质量，以信道状态信息(Channel State Information，CSI)的形式上报给NW。NW在解码了UE上报的波束信息后，可考虑下行传输信道和信号，并通过介质访问控制(Media access control，MAC)和/或下行控制信息(Downlink Control Information，DCI)信令来携带传输配置指示(Transmission Configuration Indicator，TCI)状态(TCI State)(包含SSB或CSI-RS资源索引作为UE的参考)，从而对UE进行波束信息指示。UE使用该指示的SSB或CSI-RS的发射波束对应的接收波束来进行下行接收。
相应地，NR定义了三种上行波束扫描过程，即U1，U2和U3。其中，U1过程包括：UE扫描不同的发射波束，NW扫描不同的接收波束；U2过程包括：UE使用相同的发射波束，NW扫描不同的接收波束；U3过程包括：UE扫描不同发射波束，NW使用相同的接收波束。对于上行波束扫描过程，由于NW对来自UE的波束进行测量，因此不需要UE的波束上报。NW可从测量的上行波束中，选择合适的上行波束指示或配置给UE以进行上行发射。同时，NW可准备好对应的接收波束。
2、NR的小区间波束管理
NR的小区间波束管理仅适用于下行的场景。
在Rel.17的波束管理中，根据UE的能力上报，NW可为UE配置和/或激活对于非服务小区的波束管理功能，包括波束测量、波束上报和波束指示。
UE可测量除服务小区之外的非服务小区，非服务小区具有与服务小区不同的物理小区标识(Physical Cell Identifier，PCI)。其中，UE能力支持可测量的非服务小区的数量为1、2、3或7。UE通过测量非服务小区的SSB，可选择波束质量较好的下行波束。在一次波束上报中，UE仅能够上报来自一个非服务小区的最多4个下行发射波束，其中包括波束对应的资源索引以及链路质量， 如L1-RSRP。
对于来自非服务小区的波束指示，NW可通过统一TCI State实现。例如，NW可在TCI State中配置来自非服务小区(通过PCI辨别是否为非服务小区)的参考信号。若该TCI state被指示给UE，则说明UE将使用来自该小区的下行波束。
3、NR的层1/层2触发的移动性
在Rel.18的层1/层2(L1/L2)触发的移动性管理中，相对于Rel.17中的小区间波束管理，标准化在测量和上报方面给予了一定程度的增强。具体增强如下，UE可以在NW配置的服务小区和目标小区中进行测量，并在一次上报中给出最多M×L个下行参考信号的测量结果，M和L的最大值基于UE的能力确定。显然，对于大量候选小区(candidate cell)的测量，需要大量的下行参考信号的开销，以及UE测量这些下行参考信号所需的时延，毕竟UE往往不能同时测量多个候选小区的多个波束(对)。
4、神经网络(Neural Network，NN)
1)神经元结构
神经网络是一种由多个神经元节点相互连接构成的运算模型，其中节点间的连接代表从输入信号到输出信号的加权值，称为权重；每个节点对不同的输入信号进行加权求和，并通过特定的激活函数输出。神经元结构如图3所示，其中，a1、a2、……、an和1为神经元的输入，w1、w2、……、wn和b表示权重，Sum表示求和函数，f表示激活函数，t为输出结果。
2)深度神经网络
图4示出了一个简单的神经网络。该神经网络包含输入层、隐藏层和输出层，通过多个神经元不同的连接方式，结合不同的权重和激活函数，可产生不同的输出，进而拟合从输入到输出的映射关系。示例性地，每一个上一级节点可与其全部的下一级节点相连，构成全连接模型。该全连接模型也可以称为深度神经网络(Deep Neural Network，DNN)。该NN模型可用于进行空间域的下行波束预测(Spatial-domain DL beam prediction)或时间域的下行波束预测(Temporal DL beam prediction)。
3)长短期记忆网络(Long Short-Term Memory，LSTM)模型
图5示出了一种LSTM模型。该LSTM模型在时序上可以理解为延展了K个时刻作为输入，等效为K个LSTM单元的级联。每一个LSTM单元的输入是Set Bk(1≤k≤K)中波束(对)的L1-RSRP，Set Bk代表时刻k对应的Set B。
需要说明的是，Set Bk中波束(对)的索引可以通过L1-RSRP的固定排序方式隐含地输入。再完成了K个时刻的L1-RSRP输入后，LSTM模型可以预测接下来的F个时刻的波束预测实例，每个波束预测实例包含最优波束(对)索引，最优波束(对)索引对应的链路质量，以及最优波束(对)的持续时间。
5、模型的获得
通过数据集的构建、训练、验证和测试等过程可训练得到一个NN模型。在本申请的实施例中，假设NN模型都已提前通过离线训练或在线训练的方式训练完成。需要说明的是，离线训练和在线训练并非相互排斥。例如，NW可首先通过数据集离线训练的方式得到一个静态的训练结果，该过程可称为离线训练。在NW或UE对NN的使用过程中，随着UE的进一步测量和/或上报，NN模型可继续收集更多的数据，并进行实时的在线训练以优化NN模型的参数，从而达到更好的推断和预测结果。
6、基于人工智能(Artificial Intelligence，AI)/机器学习(Machine Learning，ML)的波束管理
基于AI/ML的波束管理作为R18AI项目的主要用例，定义了两种用例，分别是空间域的下行波束预测(Spatial-domain DL beam prediction)和时间域的下行波束预测(Temporal DL beam prediction)。
空间域的波束预测(BM-Case1)的定义：通过测量Set B中的波束(对)来进行Set A中下行波束空间域预测。Set B要么是Set A的一个子集，要么Set B和Set A是两个不同的波束(对)集合。Set B可以理解为波束(对)的部分子集；Set A可以理解为波束(对)的全集。
时间域的波束预测(BM-Case2)的定义：通过测量K次Set B中的波束(对)来进行未来F次Set A中最优波束(对)的预测。Set B可以是Set A的一个子集，也可以和Set A相同。对于Set B和Set A相同的情况，波束预测为单纯的时间域的波束预测；对于Set B是Set A的一个子集的情况，波束预测为空间域和时域的波束预测。
此外，Set B和Set A还可以是两个不同的集合，Set B是一组少量的宽波束，Set A是一组大量的窄波束，Set B内的少量宽波束在空间上可以大致覆盖Set A内的大量窄波束。
下面对适用于本申请实施例的神经网络模型做简单介绍。
本申请实施例的技术方案可以采用DNN模型进行时域移动性预测，或者，考虑到时域的因素也可以采用LSTM模型进行时域移动性预测。虽然本申请实例的技术方案都是以DNN模型作为示例进行说明的，但不局限于此，其他能够实现时域移动性预测的模型(如LSTM模型)均适用于本申请实施例的技术方案。以下以图6至图8所示的DNN模型作为示例，来说明模型的实现。
图6是适用于本申请实施例的神经网络模型的一例示意图，该模型为最优波束(对)预测模型，可认为该模型解决的是一个多分类问题。该模型可用于拟合Set B的测量结果(如Set B中参考信号/波束(对)的L1-RSRP)到Set A中最优的L个波束(对)之间的关系。其中，Set B的测量结果可作为该模型的输入，输出可以是从全集(Set A)中选取的最优的J个波束(对)索引，即Set A中L1-RSRP最高的J个波束(对)。在图6的例子中，Set B中的波束(对)的数量为M，Set A中的波束(对)的数量为M'，J＝1，波束(对)#2为L1-RSRP最高的波束(对)，也即最优波束(对)。该模型使用的标签为全集中测量的最优(即最高L1-RSRP)的波束(对)索引。
图7是适用于本申请实施例的神经网络模型的另一例示意图，该模型为最优波束质量预测模型，可理解为一个线性回归问题。该模型的输入和输出关系为：从部分子集输入L1-RSRP到最优的K个波束(对)的L1-RSRP的关系。该模型的输入部分与图6所示的模型的输入相同，不同的是，该模型的输出为J(J≥1)个最优的L1-RSRP。在图7的例子中，Set B中的波束(对)的数量为M。该模型使用的标签为全集中测量的最优的K个L1-RSRP，以及对应的K个波束(对)索引。
图8是适用于本申请实施例的神经网络模型的另一例示意图，该模型为最优波束质量和最优波束索引预测模型，可理解为一个线性回归问题。该模型的输入部分与图6所示的模型的输入相同，不同的是，该模型的输出为全集(Set A)中全部波束(对)的L1-RSRP。在全部波束(对)的L1-RSRP中进行从高到低排序，可以选择出最优J(即Top-J)个L1-RSRP，然后按照该最优J个L1-RSRP对应的输出位置，可以找到对应的最优的J个波束(对)索引。因此，图8所示的模型可以实现图6和图7两个模型的功能。
作为一种实现方式，对于DNN模型，可以理解为2个不同的模型，使用相同的输入(即Set B)，有两个不同的输出，即一个输出是最优J(即Top-J)个波束(对)索引，另一个是最优J(即Top-J)个波束(对)的链路质量，即L1-RSRP，参照图6和图7所示。作为另一种实现方式，对于DNN模型，通过1个模型可以实现图6和图7两个模型的功能，参照图8。
应理解，模型的输出，还可以理解为推断(Inference)或预测(Prediction)结果，也即，推断和预测可表示相同的含义，可相互替换。
为便于理解本申请实施例的技术方案，以下通过具体实施例详述本申请的技术方案。以上相关技术作为可选方案与本申请实施例的技术方案可以进行任意结合，其均属于本申请实施例的保护范围。本申请实施例包括以下内容中的至少部分内容。
需要说明的是，本申请实施例中的“波束(对)”可以指波束，包括发射波束或接收波束，也可以指波束对，如一对发射波束和接收波束。本申请实施例中的该“波束(对)”的含义适用于下行传输的情况。本申请的实施例中的“波束(对)”还可以称为空间滤波器，也即，波束(对)和空间滤波器可相互替换。
需要说明的是，本申请实施例中的“下行参考信号资源索引”还可以称为波束(对)索引或者下行参考信号索引或者空间滤波器索引，也即，下行参考信号资源索引、波束(对)索引、下行参考信号索引和空间滤波器索引可相互替换。示例性地，下行参考信号资源索引可以是CSI-RS资源指示(CRI)或SSB资源指示(SSBRI)。
需要说明的是，本申请实施例中的下行参考信号可包括：信道状态信息-参考信号(Channel State Information-Reference Signal，CSI-RS)和/或SSB。对下行参考信号进行测量得到的测量结果表征了链路质量。在一些实施方式中，链路质量可包括以下至少一项：参考信号接收功率(Reference Signal Receiving Power，RSRP)(如L1-RSRP)、信号与干扰加噪声比(Signal to Interference plus Noise Ratio，SINR)(如L1-SINR)、接收信号的强度指示(Received Signal Strength Indicator，RSSI)(如L1-RSSI)、参考信号接收质量(Reference Signal Receiving Quality，RSRQ)(如L1-RSRQ)。
首先，定义第一下行参考信号集和第二下行参考信号集。
第一下行参考信号集为Set B或者Set C(称为Set B/Set C)，第二下行参考信号集为Set A。“下行参考信号集”，可以理解为下行参考信号的集合，还可以理解为下行参考信号资源的集合，或者还可以理解为波束(对)的集合。因此，“下行参考信号集”还可以称为“下行参考信号资源集”或“波束(对)集”。
在一些场景中，Set B可以是Set A的一个子集，此时，Set B可以理解为波束(对)的部分子集，Set A可以理解为波束(对)的全集。在另一些场景中，Set B和Set A还可以是两个不同的波束(对)集合。示例性地，Set B可作为测量集，Set A可作为预测集。在本申请的实施例中，神经网络模型(简称模型)可通过测量Set B中的波束来进行Set A中的波束预测。
在一些场景中，Set B为测量集，也是模型的输入集。在另一些场景中，Set C为测量集，从Set C中选择最优的M个波束(对)作为Set B，Set B为模型的输入集，也即，Set B是Set C的一个子集。
在一些实施例中，第一下行参考信号集可包括N(N≥1)个第一下行参考信号子集，其中，每一第一下行参考信号子集可对应于一个小区，可以理解，第一下行参考信号集包括N个小区的第一下行参考信号子集。作为示例，Set B/Set C中的第n(1≤n≤N)个第一下行参考信号子集可记为Set Bn/Set Cn。例如，Set B/Set C中的第1个第一个下行参考信号子集可记为Set B1/Set C1，Set B1/Set C1的索引为1，Set B/Set C中的第2个第一下行参考信号子集可记为Set B2/Set C2，Set B2/Set C2的索引为2，以此类推。应理解，该N个第一下行参考信号子集在Set B/Set C中的顺序是示例性地，该顺序可变更，本申请实施例对此不予限定。
在一些实施例中，第二下行参考信号集可包括P(P≥1)个第二下行参考信号子集，其中，每一第二下行参考信号子集可对应于一个小区，可以理解，第二下行参考信号集包括P个小区的第二下行参考信号子集。作为示例，Set A中的第p(1≤p≤P)个第二下行参考信号子集可记为Set Ap。例如，Set A中的第1个第二下行参考信号子集可记为Set A1，Set A1的索引为1，Set A中的第2个第二下行参考信号子集可记为Set A2，Set A2的索引为2，以此类推。应理解，该P个第二下行参考信号子集在Set A中的顺序是示例性地，该顺序可变更，本申请实施例对此不予限定。
作为一种实现方式，N的值可以等于P的值。作为另一种实现方式，N的值可以与P的值不同。示例性地，N的值可远小P的值，这样，可大大减少需要实际测量的下行参考信号的数量，从而达到降低计算开销和时延的目的。
其次，定义第一模型。
第一模型用于移动性预测，第一模型可以是神经网络模型，如上述DNN模型，或者LSTM模型等。本申请实施例的技术方案可以采用DNN模型进行移动性预测，或者，考虑到时域的因素也可以采用LSTM模型进行移动性预测。虽然本申请实例的技术方案都是以DNN模型作为示例进行说明的，但不局限于此，其他能够实现时域移动性预测的模型(如LSTM模型)均适用于本申请实施例的技术方案。
第一模型为已训练好的模型，可以利用有限的历史波束(对)的测量结果，从全局(多个小区以及对应的全部波束(对))选择最优小区以及该最优小区内的最优波束(对)。
作为一种实现方式，第一模型为终端侧的模型(也可以称为UE侧的模型)，或者说，第一模型为部署在终端侧的模型。第一模型可以实现时间域的波束预测，该时间域的波束预测可以是纯时间域的波束预测，或者是时间域和空间域的波束预测。作为另一种实现方式，第一模型为网络设备侧的模型(也可以称为NW侧的模型)，或者说，第一模型为部署在网络设备侧的模型。第一模型可以实现时间域的波束预测，该时间域的波束预测可以是纯时间域的波束预测，或者是时间域和空间域的波束预测。
第一模型的输入为K(K≥1)个测量实例，不同的测量实例对应不同的测量时刻，其中每个测量实例均是由终端对第一下行参考信号集中的下行参考信号进行测量得到，即测量实例可以理解为是终端对Set B的测量结果或者Set C的部分测量结果(如Set C中最优的M个波束(对)的测量结果)。
第一模型的输出为F(F≥1)个预测实例，不同的预测实例对应不同的预测时刻，其中每个预测实例均包含P(P≥1)个小区中最优的L(L≥1)个小区索引、和/或每个最优区中最优的J(J≥1)个波束(对)索引、和/或每个最优波束(对)索引对应的链路质量。
本申请对第一模型的具体网络结构不做限定。神经网络模型还可以称为AI模型或ML模型。
示例性地，图9是本申请实施例提供的一种时域移动性测量和预测的示意图，在图9中，TRP1的覆盖范围为小区#1，TRP2的覆盖范围为小区#2，TRP3的覆盖范围为小区#3。假设UE以一定的速度在多个小区(小区#1，小区#2，小区#1)中漫游，UE移动的轨迹如虚线所示。UE在K(K≥1)个测量时刻进行测量，得到K个测量实例(measurement instance)，通过第一模型根据K个测量实例预测未来的F(F≥1)个预测实例(prediction instance)，每个预测实例包括最优的L(L≥1)个小区索引，和/或每个最优小区中最优的J(J≥1)个波束(对)索引，和/或每个最优波束(对)对应的链路质量，如L1-RSRP。图9示意出了2个测量实例(即K＝2)和2个预测实例(即F＝2)，在图9中，UE在小区#1中针对测量集(即Set B/Set C)进行两次测量，得到2个测量实例；通过第一模型根据这2个测量实例针对预测集(即Set A)预测得到2个预测实例；UE实际测量的参考信号以实线椭圆表示，未测量但在预测集(即Set A)中的参考信号以虚线椭圆表示。
本申请实施例中，测量实例对应的测量时刻和预测实例对应的预测时刻可以满足一定时序关系。
在一些实施方式中，K个测量实例对应的测量时刻位于第一时段内，F个预测实例对应的预测时刻位于第二时段内，第二时段与第一时段不重叠。
示例性地，图10示意出了测量实例和预测实例的一种时序关系(可以称为类型1的时序关系)，在T1时间内，终端对Set B/Set C进行K次测量，得到K个测量实例。基于K个测量实例预可以预测出T2时间内的F个预测实例。
在另一些实施方式中，K个测量实例对应的测量时刻位于K个第一时段内，F个预测实例对应的预测时刻位于K个第一时段的最后一个第一时段内。
示例性地，图11示意出了测量实例和预测实例的另一种时序关系(可以称为类型2的时序关系)，在K个T1时间内，终端对Set B/Set C进行K次测量，得到K个测量实例，其中每个T1时间内进行一次T1时间。基于K个测量实例预可以预测出K个T1时间中最后一个T1时间内的F个预测实例。
图12是本申请实施例提供的一种时域移动性预测方法的流程示意图，如图12所示，该方法包括以下步骤：
步骤1201：终端获取第一下行参考信号集对应的K个测量实例，K个测量实例基于终端在K个测量时刻对第一下行参考信号集中的下行参考信号进行测量得到，第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的预测实例对应不同的预测时刻，第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
这里，每个测量时刻可以对应一个索引，称为测量时刻索引；每个测量实例可以对应一个索引，称为测量实例索引。在一些描述中，可以将“测量时刻索引”和“测量实例索引”相互替换。
这里，每个预测时刻可以对应一个索引，称为预测时刻索引；每个预测实例可以对应一个索引，称为预测实例索引。在一些描述中，可以将“预测时刻索引”和“预测实例索引”相互替换。
为便于描述，下文中所涉及到的示例中，将第一下行参考信号集记为Set B/Set C，将第二下行参考信号集记为Set A，其中，第一下行参考信号集也可以称为测量集，第二下行参考信号集也可以称为预测集。关于Set A、Set B、Set C的相关理解可以参照前述相关描述。其中，下行参考信号(或者称为下行参考信号资源)例如可包括：CSI-RS(或者称为CSI-RS资源)和/或SSB(或者称为SSB资源)。
下行参考信号集的配置
网络设备可以为终端配置上述第一下行参考信号集和/或上述第二下行参考信号集。网络设备向终端发送第一配置信息和/或第二配置信息；终端接收网络设备发送的第一配置信息和/或第二配置信息；第一配置信息用于配置第一下行参考信号集；第二配置信息用于配置第二下行参考信号集。
作为一种实现方式，第一配置信息和/或第二配置信息承载在RRC信令中。
在一些实施方式中，第一配置信息还用于配置第一下行参考信号集对应的第一时域信息，第一时域信息用于确定K个测量实例对应的K个测量时刻。在一些实施方式中，第一时域信息包括以下至少之一：测量周期、第一偏移量、测量时刻的数目K。
示例性地，网络设备使用RRC信令为终端配置Set B/Set C，Set B/Set C包括N(N≥1)个第一下行参考信号子集，每一第一下行参考信号子集可对应于一个小区，作为示例，Set B/Set C中的第n(1≤n≤N)个第一下行参考信号子集可记为Set Bn/Set Cn。Set B/Set C中的下行参考信号(或者称为下行参考信号资源)例如可包括：用于移动的CSI-RS(或者称为CSI-RS资源)和/或SSB(或者称为SSB资源)。网络设备还可以使用RRC信令配置Set B/Set C的测量周期、偏移量以及测量时刻的数目K，使得终端可以知道在哪些时刻进行测量，然后测量得到的结果存储起来作为第一模型的输入。对于Set Bn/Set Cn来说，测量时刻k(1≤k≤K)对应的Set Bn/Set Cn可以记作Set Bn,k/Set Cn,k，例如，测量时刻1对应的Set Bn/Set Cn可以记作Set Bn,1/Set Cn,1，Set Bn,1/Set Cn,1的索引为{n,1}，测量时刻2对应的Set Bn/Set Cn可以记作Set Bn,2/Set Cn,2，Set Bn,2/Set Cn,2的索引为{n,2}，以此类推。
在一些实施方式中，第二配置信息还用于配置第二下行参考信号集对应的第二时域信息，第二时域信息用于确定F个预测实例对应的F个预测时刻。在一些实施方式中，第二时域信息包括以下至少之一：预测周期、第二偏移量、预测时刻的数目F。
示例性地，网络设备使用RRC信令为终端配置Set A，Set A包括P(P≥1)个第二下行参考信号子集，每一第二下行参考信号子集可对应于一个小区，作为示例，Set A中的第p(1≤p≤P)个第二下行参考信号子集可记为Set Ap。Set A中的下行参考信号(或者称为下行参考信号资源)例如可包括：用于移动的CSI-RS(或者称为CSI-RS资源)和/或SSB(或者称为SSB资源)。网络设备还可以使用RRC信令配置Set A的测量周期、偏移量以及测量时刻的数目F，使得终端可以知道在哪些时刻进行预测。对于Set Ap来说，预测时刻f(1≤f≤F)对应的Set Ap可以记作Set Ap,f，例如，预测时刻1对应的Set Ap可以记作Set Ap,1，Set Ap,1的索引为{p,1}，预测时刻2对应的Set Ap可以记作Set Ap,2，Set Ap,2的索引为{p,2}，以此类推。
在一些实施方式中，上述第一配置信息和/或第二配置信息与终端的能力信息相关。网络设备根据终端的能力信息，为终端配置第一下行参考信号集和/或第二下行参考信号集。
终端能力上报
不同的终端对于测量和/或预测的能力不同，因此终端需要上报其测量和/或预测的相关能力。
在一些实施方式中，终端向网络设备发送终端的能力信息，网络设备接收终端发送的终端的能力信息，终端的能力信息包括以下至少之一：
第一信息，第一信息用于指示终端是否支持时域移动性的测量和/或预测；
第二信息，第二信息用于指示以下至少之一：终端在全部的下行载波分量(Carrier Component，CC)或带宽部分(Bandwidth Part，BWP)上，最多支持测量的小区的数量；终端在全部的下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；终端在全部的下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
第三信息，第三信息用于指示以下至少之一：终端在全部的下行CC或BWP上，最多支持预测的小区的数量；终端在全部的下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；终端在全部的下行CC或BWP上，最多支持预测的第一下行参考信号子集的数量；
第四信息，第四信息用于指示以下至少之一：终端在每一个下行CC或BWP上，最多支持测量的小区的数量；终端在每一个下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；终端在每一个下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
第五信息，第五信息用于指示以下至少之一：终端在每一个下行CC或BWP上，最多支持预测的小区的数量；终端在每一个下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；终端在每一个下行CC或BWP上，最多支持预测的第二下行参考信号子集的数量；
第六信息，第六信息用于指示终端在每一个第一下行参考信号子集内，最多支持测量的下行参考信号的数量；
第七信息，第七信息用于指示终端在每一个第二下行参考信号子集内，最多支持预测的下行参考信号的数量；
第八信息，第八信息用于指示终端支持的测量时刻的数量；
第九信息，第九信息用于指示终端支持的预测时刻的数量。
上述第一信息指示能力可以记作能力1，类似地，第二信息指示能力可以记作能力2，第三信息指示能力可以记作能力3，第四信息指示能力可以记作能力4，第五信息指示能力可以记作能力5，第六信息指示能力可以记作能力6，第七信息指示能力可以记作能力7，第八信息指示能力可以记作能力8，第九信息指示能力可以记作能力9。
示例性地，能力1可以理解为终端是否支持终端侧模型的时域移动性的测量和/或预测。或者，能力1可以理解为终端是否支持网络侧模型的时域移动性的测量和/或预测。
示例性地，能力2可以理解为终端在全部的下行CC或BWP上最多支持多少个小区的测量，或者终端在全部的下行CC或BWP上最多支持被配置多少个第一下行参考信号子集，或者在全部的下行CC或BWP上最多支持可以同时测量多少个第一下行参考信号子集。
示例性地，能力3可以理解为终端在全部的下行CC或BWP上最多支持多少个小区的预测，或者终端在全部的下行CC或BWP上最多支持被配置多少个第二下行参考信号子集，或者在全部的下行CC或BWP上最多支持可以同时预测多少个第二下行参考信号子集。
示例性地，能力4可以理解为终端在每一个下行CC或BWP上最多支持多少个小区的测量，或者终端在每一个下行CC或BWP上最多支持被配置多少个第一下行参考信号子集，或者在每一个下行CC或BWP上最多支持可以同时测量多少个第一下行参考信号子集。
示例性地，能力5可以理解为终端在每一个下行CC或BWP上最多支持多少个小区的预测，或者终端在每一个下行CC或BWP上最多支持被配置多少个第二下行参考信号子集，或者在每一个下行CC或BWP上最多支持可以同时预测多少个第二下行参考信号子集。
示例性地，能力6可以理解终端在每一个第一下行参考信号子集内最多支持测量多少个下行参考信号。
示例性地，能力7可以理解终端在每一个第二下行参考信号子集内最多支持预测多少个下行参考信号。
示例性地，能力8可以理解终端支持测量多少个测量时刻，即K的值。
示例性地，能力9可以理解终端支持预测多少个预测时刻，即F的值。
在一些实施方式中，终端的能力信息包括上述第一信息，可选地，在第一信息指示终端支持时域移动性的测量和/或预测的情况下，终端的能力信息可以包括上述第二信息至第九信息中的至少一种信息。
在一些实施方式中，终端的能力信息包括上述第一信息至第九信息中的至少一种信息。
时域移动性测量
对于K个测量时刻的每个测量时刻，终端通过物理层测量第一下行参考信号集内的下行参考信号(或者说下行参考信号资源)，如SSB(或者说SSB资源)和/或CSI-RS(或者说用于移动的CSI-RS资源)。其中，第k(1≤k≤K)个测量时刻测量的第n(1≤n≤N)个第一下行参考信号子集可以记作Set Bn,k/Set Cn,k，Set Bn,k/Set Cn,k的索引为{n,k}，n代表第一下行参考信号子集索引，k代表测量时刻索引。N个第一下行参考信号子集可以对应N个小区，每一第一下行参考信号子集可对应于一个小区，因而，第一下行参考信号子集索引可对应一个小区索引，示例性地，小区索引可以是物理学小区标识(Physical Cell Identifier，PCI)、PCI索引、或者小区配置索引(configuration index of cell)。也就是说，第一下行参考信号子集索引、PCI、PCI索引、小区配置索引之间可以相互替换。
需要说明的是，N个小区可以包括1个当前服务小区(如SpCell)以及(N-1)个候选小区。其中，当前服务小区也可以理解为是一个候选小区，基于这样的理解，N个小区可以描述为N个候选小区。
模型的输入和输出
第一模型用于移动性预测，第一模型可以是神经网络模型，如上述DNN模型，或者LSTM模型等。本申请实施例的技术方案可以采用DNN模型进行移动性预测，或者，考虑到时域的因素也可以采用LSTM模型进行移动性预测。虽然本申请实例的技术方案都是以DNN模型作为示例进行说明的，但不局限于此，其他能够实现时域移动性预测的模型(如LSTM模型)均适用于本申请实施例的技术方案。
1)模型的输入
第一模型的输入包括K个测量实例，K个测量实例的输入可以有如下两种方式：
第一种方式：K个测量实例包括：K×N组链路质量。
第二种方式：K个测量实例包括：K×N个索引和K×N组链路质量，K×N个索引和K×N个链路质量具有对应关系；K×N个索引中的每个索引对应一个测量时刻索引和一个小区索引。
这里，对于一个测量实例来说，终端对第一下行参考信号集中的N个下行参考信号子集进行测量，得到N组链路质量，每一个下行参考信号子集对应一组链路质量。假设一个下行参考信号子集包括M(M≥1)个下行参考信号，那么，每组链路质量包括M个链路质量。对于K个测量实例来说，可以得到K×N组链路质量，其中每组链路质量包括M个链路质量。示例性地，终端测量全部的Set Bn,k/Set Cn,k(1≤n≤N，1≤k≤K)，得到K×N组链路质量，其中，第k(1≤k≤K)个测量时刻测量的第n(1≤n≤N)个第一下行参考信号子集记作Set Bn,k/Set Cn,k，Set Bn,k/Set Cn,k的索引为{n,k}，n代表第一下行参考信号子集索引，k代表测量时刻索引。
这里，每个链路质量对应一个下行参考信号资源索引(如CRI或者SSBRI)、一个第一下行参考信号子集索引(如n索引)、以及一个测量时刻索引(如k索引)。其中，第一下行参考信号子集索引也可以替换为小区索引(如PCI、PCI索引、小区配置索引等)，也就是说，第一下行参考信号子集索引和小区索引(如PCI、PCI索引、小区配置索引等)之间可以相互替换。
在上述第一种方式中，如图13至图15中的情况1所示，按照固定的顺序向第一模型输入K×N组链路质量(即全部的Set Bn,k/Set Cn,k中的下行参考信号的链路质量)，该顺序与链路质量对应的索引有关，链路质量对应的索引包括：一个下行参考信号资源索引、一个第一下行参考信号子集索引、以及一个测量时刻索引。对于上述第一种方式，由于不需要向第一模型输入链路质量对应的索引，因而可以节省模型输入数据量。
在上述第二种方式中，如图13至图15中的情况2所示，第一模型的输入包括K×N个索引对应的K×N组链路质量(即全部的Set Bn,k/Set Cn,k中的下行参考信号的链路质量)，K×N个索引中的每个索引对应一个测量时刻索引(如k索引)和一个小区索引(如PCI、PCI索引、小区配置索引等)，其中，小区索引也可以替换为第一下行参考信号子集索引(如n索引)。对于上述第二种方式，由于向第一模型输入了链路质量对应的索引，因而可以灵活地选择不同的Set Bn,k/Set Cn,k组合作为模型的输入。
1)模型的输出
第一模型的输出包括F个预测实例。在一些实施方式中，F个预测实例中的每个预测实例包括以下至少之一：P个小区中的最优L个小区索引；每一个最优小区中的最优J个下行参考信号资源索引；每一个最优下行参考信号资源索引对应的链路质量。在一些实施方式中，每个预测实例还包括：预测实例对应的预测时刻索引。
示例性地，每个预测实例包含预测时刻索引、以及P(P≥1)个小区中最优的L(L≥1)个小区索引、和/或每个最优区中最优的J(J≥1)个波束(对)索引、和/或每个最优波束(对)索引对应的链路质量。
F个预测实例的输出可以有如下两种方式：
第一种方式：第一模型包括两个模型，分别为模型1和模型2。其中，模型1的输出包括：F个预测实例中每个预测实例对应的P个小区中的最优L个小区索引，以及每一个最优小区中的最优J个下行参考信号资源索引；模型2的输出包括：F个预测实例中每个预测实例对应的每个最优波束(对)索引对应的链路质量。
第二种方式：第一模型为一个模型。该模型的输出包括：F个预测实例中每个预测实例对应的P个小区中的最优L个小区索引，每一个最优小区中的最优J个下行参考信号资源索引，以及每个最优波束(对)索引对应的链路质量。
在上述第一种方式中，如图13所示，模型1推断全部的预测时刻f(1≤f≤F)对应的最优L个小区索引以及每一个最优小区中的最优J个下行参考信号资源索引。如图14所示，模型2推断预测时刻f(1≤f≤F)对应的每一个最优小区中每个最优波束(对)索引对应的链路质量。
在上述第二种方式中，如图15所示，该模型预测全部的Set Ap,f(1≤p≤P，1≤f≤F)的链路质量。针对F个预测实例中每个预测实例，按照链路质量从高到低的排序选出最优L个小区索引，每一个最优小区中的最优J个下行参考信号资源索引，以及每个最优波束(对)索引对应的链路质量。
本申请实施例中，即负责移动性预测的第一模型可以部署在终端侧，或者部署在网络设备侧。以下结合这两种部署方式对本申请实施例的技术方案分别进行说明。
模型位于终端侧
在一些实施方式中，上述方案中的第一模型位于终端侧。这里，终端获取K个测量实例后，基于本地的第一模型预测得到F个预测实例。
在一些实施方式中，终端向网络设备发送F个预测实例。
在一些实施方式中，F个预测实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报、基于层1和/或层2的移动性事件上报。
1)周期性/半持续性/非周期上报
在一些实施方式中，对于周期性上报或半持续性上报，终端向网络设备发送F个预测实例之前，网络设备向终端发送第三配置信息，终端接收网络设备发送的第三配置信息，第三配置信息用于配置周期性上报或半持续性上报对应的上报周期和上报偏移量。
在一些实施方式中，第三配置信息承载在RRC信令中。
这里，终端根据网络设备配置的上报周期和上报偏移量以及预测时刻的数目F，周期性或半持续地上报F个预测时刻对应的预测实例。对于周期性上报来说，终端一旦获得网络设备发送的测量配置(如上述第一配置信息和/或第二配置信息)和上报配置(如上述第三配置信息)，就会周期性地进行预测实例的上报。对于半持续性上报来说，终端在获得测量配置和上报配置后，还需要获得激活该配置的指令，在获得激活该配置的指令后，周期性地进行预测实例的上报。
在一些实施方式中，对于非周期上报，终端向网络设备发送F个预测实例之前，终端接收网络设备发送的第一下行控制信息(Downlink Control Information，DCI)，第一DCI用于触发非周期上报。
这里，对于非周期上报，终端在获得测量配置(如上述第一配置信息和/或第二配置信息)和上报配置(如上述第三配置信息)后，还需要获得一个触发测量和上报的指令，网络设备可以通过DCI(即触发指令)来触发终端进行测量和上报，终端在获得该触发指令后，进行K个测量实例的测量以及F个预测实例的上报。
2)基于层1和/或层2的移动性事件上报
在一些实施方式中，终端向网络设备发送F个预测实例之前，终端确定层1和/或层2的移动性事件被触发，向网络设备发送上报请求；终端接收网络设备发送的第二DCI，第二DCI用于调度上报用的物理上行共享信道(Physical Uplink Shared Channel，PUSCH)。进一步，终端利用该PUSCH发送F个预测实例。
示例性地，在部分或全部预测时刻f(1≤f≤F)，终端侧的第一模型的输出触发基于层1和/或层2的移动性事件，终端向网络设备发送上报请求，该上报请求用于请求移动性上报的资源；网络设备同意终端的上报请求，发送DCI，通过该DCI调度PUSCH；终端通过该DCI调度的PUSCH来承载移动性相关的上报内容，即预测实例。
在一些实施方式中，上述层1和/或层2的移动性事件包括以下至少之一：
第一事件，第一事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能好于第一门限或弱于第二门限；
第二事件，第二事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能好于或弱于候选小区的预测的链路性能加上一个偏移量；
第三事件，第三事件为：在F个预测时刻中的部分或全部预测时刻，候选小区的预测的链路性能好于第三门限或弱于第四门限；
第四事件，第四事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能弱于第五门限，且候选小区的预测的链路性能好于第六门限。
上述方案中，当前小区为P个小区中的一个小区，候选小区为P个小区中除当前小区以外的一个小区。当前小区也可以称为当前服务小区，当前小区也可以理解为是移动性管理流程中的一个候选小区。
终端根据上述定义的层1和/或层2的移动性事件以及第一模型的预测结果，进行对比，判断层1和/或层2的移动性事件是否发生(或者说是否被触发)，从而自主地选择是否进行F个预测实例的上报。
示例性地，在某个预测时刻f，当第一模型输出的最优小区仍然是终端当前服务小区，那么终端无需进行预测实例的上报，也无需触发后续的移动性操作。
示例性地，在某个预测时刻f，当第一模型输出的最优小区是一个候选小区，且性能好于当前服务小区一个偏移量(如6dB)，则终端可以判断第二事件发生，触发终端进行上报请求，该上报请求可以通过上行控制信息(Uplink Control Information，UCI)来承载，网络设备通过DCI为该上报请求调度PUSCH，终端利用该PUSCH发送预测实例。
示例性地，在全部的预测时刻f内，当第一模型输出的最优小区是一个候选小区，且性能好于一个特定的门限(如L1-RSRP高于-50dBm)，则终端可以判断第三事件发生，触发终端进行上报请求，该上报请求可以通过UCI来承载，网络设备通过DCI为该上报请求调度PUSCH，终端利用该PUSCH发送预测实例。
本申请实施例中，对于第一模型的预测结果(即F个预测实例)，每个预测实例包含从全部的Set Ap,f(1≤p≤P，1≤f≤F)中选择的最优小区索引，和/或该最优小区的最优波束(对)索引，和/或该最优波束(对)索引对应的链路质量，终端在一个或多次上报中将该预测结果上报给网络设备。其中，对于最优小区索引，终端可以上报最优小区的小区索引或者最优小区对应的Set Ap，f的索引(即p索引)，其中，小区索引可以是PCI，PCI索引，或者候选小区的配置索引(configuration index of candidate cell)；对于最优小区的最优波束(对)索引，可以使用NR系统中的下行参考信号资源索引，如SSBRI或CRI；对于链路质量，在一些示例中以L1-RSRP为例，并不排除其他链路质量的指标，如L1-SINR，L1-RSSI，L1-RSRQ或CQI等。
为了承载移动性的时域预测上报，本申请实施例的技术方案提出了以下上报格式：
A)在一些实施方式中，F个预测实例的上报粒度为一个预测实例。
在一些实施方式中，上述上报具有第一格式，第一格式包括：预测时刻索引、L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；其中，L个小区索引为P个小区中的最优L个小区索引；X1个下行参考信号资源索引包括L个小区中每个小区中最优J个下行参考信号资源索引；X1个链路质量与X1个下行参考信号资源索引具有对应关系。
这里，小区索引可以是PCI，PCI索引，候选小区的配置索引，或者Set A的索引(即p索引)。
这里，下行参考信号资源索引也可以替换为者波束(对)索引，下行参考信号索引或者空间滤波器索引。
这里，X1个链路质量可以采用差分方式上报，或者也可以采用非差分方式上报。其中，采用差分方式上报的情况下，X1个链路质量通过一个参考链路质量和X1-1个差分值表示，示例性地，该参考链路质量可以是X1个链路质量中最好的一个链路质量，一个差分值和一个参考链路质量可以确定一个链路质量，X1-1个差分值和一个参考链路质量可以确定X1-1个链路质量。进一步，上述上报格式还可以包括参考链路质量对应的下行参考信号资源索引。采用非差分方式上报的情况下，X1个链路质量通过一X1个链路质量直接表示。
作为示例，以下给出预测实例采用的上报格式。需要说明的是，下行参考信号资源索引(CRI或SSBR)或者波束(对)索引也可以替换为下行参考信号索引或者空间滤波器索引。
在以下表1中，给出了第f个预测时刻对应的预测实例的上报格式，X1个链路质量采用差分方式上报。在表1中，上报格式包括预测时刻索引，即f值。另外，对于该预测时刻的L个最优小区索引，可以直接上报其PCI，或PCI索引，或候选小区的配置索引，或对应的Set A的索引(即p值)。对于最优波束(对)索引，如果针对的是下行发射波束，那么可以用常规的CRI或SSBRI来表示，如果针对的是下行发射接收波束对，那么可以用波束(对)索引来表示。
表1：第f个预测时刻的移动性预测的上报
B)在一些实施方式中，F个预测实例的上报粒度为F个预测实例。
这里，为了节省上报次数，终端可以将F个预测实例在一次上报中上报给网络设备。
在一些实施方式中，上述上报具有第二格式，第二格式包括F组信息，F组信息与F个预测实例具有对应关系；F组信息中的每组信息包括：预测时刻索引、L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；或者，F组信息中的每组信息包括：L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；其中，L个小区索引为P个小区中的最优L个小区索引；X1个下行参考信号资源索引包括L个小区中每个小区中最优J个下行参考信号资源索引；X1个链路质量与X1个下行参考信号资源索引具有对应关系。
这里，小区索引可以是PCI，PCI索引，候选小区的配置索引，或者Set A的索引(即p索引)。
这里，下行参考信号资源索引也可以替换为者波束(对)索引，下行参考信号索引或者空间滤波器索引。
这里，X1个链路质量可以采用差分方式上报，或者也可以采用非差分方式上报。其中，采用差分方式上报的情况下，X1个链路质量通过一个参考链路质量和X1-1个差分值表示，示例性地，该参考链路质量可以是X1个链路质量中最好的一个链路质量，一个差分值和一个参考链路质量可以确定一个链路质量，X1-1个差分值和一个参考链路质量可以确定X1-1个链路质量。进一步，上述上报格式还可以包括参考链路质量对应的下行参考信号资源索引。采用非差分方式上报的情况下，X1个链路质量通过一X1个链路质量直接表示。
作为示例，以下给出预测实例采用的上报格式。需要说明的是，下行参考信号资源索引(CRI或SSBR)或者波束(对)索引也可以替换为下行参考信号索引或者空间滤波器索引。
在以下表2中，给出了F个预测时刻对应的预测实例的上报格式，链路质量采用差分方式上报。其中，F个预测时刻对应的预测实例可以带有或不带有[预测时刻索引]地进行上报，并不影响网络设备对预测结果的理解。在表2中，上报格式包括F组信息，每组信息代表一个预测实例。对于每个预测实例，其内容可以包括[预测时刻索引](即f值)，也可以不包括[预测时刻索引]。每个预测实例的内容与上述表1类似。
表2：F个预测时刻的移动性预测的上报

模型位于网络设备侧
在一些实施方式中，上述方案中的第一模型位于网络设备侧。这里，终端获取K个测量实例后，终端向网络设备发送K个测量实例，网络设备接收终端发送K个测量实例。网络设备基于本地的第一模型预测得到F个预测实例。
在一些实施方式中，K个测量实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报。
1)周期性/半持续性上报
在一些实施方式中，对于周期性上报或半持续性上报，终端向网络设备发送K个测量实例之前，网络设备向终端发送第四配置信息，终端接收网络设备发送的第四配置信息，第四配置信息用于配置周期性上报或半持续性上报对应的上报周期和上报偏移量。
在一些实施方式中，第四配置信息承载在RRC信令中。
这里，终端根据网络设备配置的上报周期和上报偏移量以及测量时刻的数目K，周期性或半持续地上报K个测量时刻对应的测量实例。对于周期性上报来说，终端一旦获得网络设备发送的测量配置(如上述第一配置信息和/或第二配置信息)和上报配置(如上述第四配置信息)，就会周期性地进行测量实例的上报。对于半持续性上报来说，终端在获得测量配置和上报配置后，还需要获得激活该配置的指令，在获得激活该配置的指令后，周期性地进行测量实例的上报。
2)非周期上报
在一些实施方式中，对于非周期上报，终端向网络设备发送K个测量实例之前，网络设备向终端发送第三DCI，终端接收网络设备发送的第三DCI，第三DCI用于触发非周期上报。
这里，对于非周期上报，终端在获得测量配置(如上述第一配置信息和/或第二配置信息)和上报配置(如上述第四配置信息)后，还需要获得一个触发测量和上报的指令，网络设备可以通过DCI(即触发指令)来触发终端进行测量和上报，终端在获得该触发指令后，进行K个测量实例的测量以及上报。
本申请实施例中，对于第一模型的测量结果(即K个测量实例)，每个测量实例包含从全部的Set Bn,k/Set Cn,k(1≤n≤N，1≤k≤K)中测量到的链路质量，终端在一个或多次上报中将该测量结果上报给网络设备。对于链路质量，在一些示例中以L1-RSRP为例，并不排除其他链路质量的指标，如L1-SINR，L1-RSSI，L1-RSRQ或CQI等。
为了承载移动性的时域测量上报，本申请实施例的技术方案提出了以下上报格式：
I)在一些实施方式中，K个测量实例的上报粒度为一个测量实例。
这里，对于K个测量实例，网络设备可以配置终端在每次测量之后进行上报，这种上报方式使得每次上报的负荷较小，但需要进行K次上报。
在一些实施方式中，上述上报具有第三格式，第三格式包括：测量时刻索引以及X2个链路质量；其中，X2个链路质量包括N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。这里，上报的内容不包含N个小区索引。
在一些实施方式中，上述上报具有第四格式，第四格式包括：测量时刻索引、N个小区索引以及X2个链路质量；其中，X2个链路质量包括N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。这里，上报的内容包含N个小区索引。
上述X2个链路质量在上报中的格式采用差分上报格式或者非差分上报格式。
作为一种实现方式，在非差分上报格式中，X2个链路质量通过X2个链路质量表示，如下表3所示。
作为另一种实现方式，在差分上报格式中，X2个链路质量划分为N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示，如下表5和表9所示，示例性地，该参考链路质量可以是M个链路质量中最好的一个链路质量，一个差分值和一个参考链路质量可以确定一个链路质量，M-1个差分值和一个参考链路质量可以确定M-1个链路质量。进一步，上述上报格式还可以包括参考链路质量对应的下行参考信号资源索引。
作为另一种实现方式，在差分上报格式中，X2个链路质量通过一个参考链路质量和X2-1个差分值表示，如下表7所示，示例性地，该参考链路质量可以是X2个链路质量中最好的一个链路质量，一个差分值和一个参考链路质量可以确定一个链路质量，X2-1个差分值和一个参考链路质量可以确定X2-1个链路质量。进一步，上述上报格式还可以包括参考链路质量对应的下行参考信号资源索引。
II)在一些实施方式中，K个测量实例的上报粒度为K个测量实例。
这里，网络设可以配置终端在K次测量后，将K个测量实例一起上报，这种上报方式使得一次上报的负荷较大，但只需要一次上报。
在一些实施方式中，上述上报具有第五格式，第五格式包括：K组信息，K组信息与K个测量实例具有对应关系；K组信息中的每组信息包括：X2个链路质量；其中，X2个链路质量包括N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。这里，上报的内容不包含N个小区索引。
在一些实施方式中，上述上报具有第六格式，第六格式包括：N个小区索引和K组信息，或者，第六格式包括：N个小区索引、K个测量实例索引和K组信息；K组信息与K个测量实例索引具有对应关系；K组信息中的每组信息包括：X2个链路质量；其中，X2个链路质量包括N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。这里，上报的内容包含N个小区索引和/或K个测量实例索引。
上述X2个链路质量在上报中的格式采用差分上报格式或者非差分上报格式。
作为一种实现方式，在非差分上报格式中，X2个链路质量通过X2个链路质量表示，如下表4所示。
作为另一种实现方式，在差分上报格式中，K×X2个链路质量划分为K×N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示，如下表6和表10所示，示例性地，该参考链路质量可以是M个链路质量中最好的一个链路质量，一个差分值和一个参考链路质量可以确定一个链路质量，M-1个差分值和一个参考链路质量可以确定M-1个链路质量。进一步，上述上报格式还可以包括参考链路质量对应的下行参考信号资源索引。
作为另一种实现方式，在差分上报格式中，K×X2个链路质量通过一个参考链路质量和K×X2-1个差分值表示，如下表8所示，示例性地，该参考链路质量可以是K×X2个链路质量中最好的一个链路质量，一个差分值和一个参考链路质量可以确定一个链路质量，K×X2-1个差分值和一个参考链路质量可以确定K×X2-1个链路质量。进一步，上述上报格式还可以包括参考链路质量对应的下行参考信号资源索引。
III)在一些实施方式中，K个测量实例的上报粒度为一个测量实例中的一个小区的测量结果。
在一些实施方式中，上述上报具有第六格式，第六格式包括：测量时刻索引、小区索引以及M个链路质量；其中，M个链路质量包括小区索引对应的小区的M个下行参考信号的链路质量，M为正整数。
上述M个链路质量在上报中的格式采用差分上报格式或者非差分上报格式。
作为一种实现方式，在非差分上报格式，M个链路质量通过M个链路质量表示。
作为另一种实现方式，在差分上报格式中，M个链路质量通过一个参考链路质量和M-1个差分值表示，如下表11所示，示例性地，该参考链路质量可以是M个链路质量中最好的一个链路质量，一个差分值和一个参考链路质量可以确定一个链路质量，M-1个差分值和一个参考链路质量可以确定M-1个链路质量。进一步，上述上报格式还可以包括参考链路质量对应的下行参考信号资源索引。
作为示例，以下给出测量实例采用的上报格式。需要说明的是，下行参考信号资源索引(CRI或SSBR)或者波束(对)索引也可以替换为下行参考信号索引或者空间滤波器索引。
在以下表3中，给出了第k个测量时刻对应的测量实例的上报格式，链路质量采用无差分方式上报。在表3中，上报格式包括测量时刻索引(即k值)以及N×M个链路质量。在第k次的测量实例中，链路质量可以按照对应的下行参考信号资源索引(即SSBRI或CRI或波束(对)索引)从小到大地进行上报，因此可以省略下行参考信号资源索引，进一步，下行参考信号资源索引可以先按照n索引(即小区索引)从小到大进行上报，然后按照k索引(即测量时刻索引)从小到大进行上报。
表3：第k个测量实例的测量结果上报(无L1-RSRP差分)
在以下表4中，给出了K个测量时刻对应的测量实例(即全部K个测量实例)的上报格式，链路质量采用无差分方式上报。在表4中，每个测量实例需要包含N个小区的链路质量，每个小区的链路质量包含M个下行参考信号的链路质量，因此，终端总共需要上报K×N×M个链路质量。在表4中，可以不包含测量时刻索引，这种情况下，每个测量时刻对应的测量实例需要按序排布在上报格式中；或者，也可以包含测量时刻索引，这种情况下，每个测量时刻对应的测量实例可以灵活排布在上报格式中。
表4：全部K个测量实例的测量结果上报(无L1-RSRP差分)
在以下表5中，给出了第k个测量时刻对应的测量实例的上报格式，链路质量采用差分方式上报。表5相对于表3的区别在于，链路质量采用差分方式上报，对于每个小区的M个链路质量，将M个链路质量中的最高的链路质量作为参考链路质量，并将该参考链路质量对应的下行参考信号资源索引(如SSBRI或CRI)标记出来，其他的链路质量按照下行参考信号资源索引资源固定的顺序(如从小到大的)进行差分上报，这里的差分上报是指仅上报其他的链路质量与参考链路质量的差值。
表5：第k个测量实例的测量结果上报(有L1-RSRP差分)
在以下表6中，给出了K个测量时刻对应的测量实例(即全部K个测量实例)的上报格式，链路质量采用差分方式上报。表6相对于表5的区别在于，表6包含了K个测量实例的内容，而每个测量实例的内容与表5是类似的。此外，在表6中，可以不包含测量时刻索引，这种情况下，每个测量时刻对应的测量实例需要按序排布在上报格式中；或者，也可以包含测量时刻索引，这种情况下，每个测量时刻对应的测量实例可以灵活排布在上报格式中。
表6：全部K个测量实例的测量结果上报(有L1-RSRP差分)
在以下表7中，给出了第k个测量时刻对应的测量实例的上报格式，链路质量采用差分方式上报。表7相对于表5的区别在于，从全部小区的链路质量中选择最高的链路质量作为参考链路质量, 并将该参考链路质量对应的下行参考信号资源索引(如SSBRI或CRI)标记出来，此外还需要标记出该参考链路质量对应的小区索引，其他的链路质量按照下行参考信号资源索引资源固定的顺序(如从小到大的)进行差分上报，这里的差分上报是指仅上报其他的链路质量与参考链路质量的差值。
表7：第k个测量实例的测量结果上报(有L1-RSRP差分)
在以下表8中，给出了K个测量时刻对应的测量实例(即全部K个测量实例)的上报格式，链路质量采用差分方式上报。表8相对于表7的区别在于，表8包含了K个测量实例的内容，而每个测量实例的内容与表7是类似的。此外，在表8中，需要包含参考链路质量对应的测量时刻索引(即k值)。
表8：全部K个测量实例的测量结果上报(有L1-RSRP差分)
在以下表9中，给出了第k个测量时刻对应的测量实例的上报格式，链路质量采用差分方式上报。表9相对于表5的区别在于，表9包含了N个小区索引，而质量质量的内容与表5是类似的，表9没有给出测量时刻索引，当然，表9是可以包含测量时刻索引的。通过表9所示的上报格式，终端可以灵活地上报部分或全部测量结果，具体来说，终端可以上报部分小区索引以及该部分小区中每个小区对应的链路质量。
表9：第k个测量实例的测量结果上报(有L1-RSRP差分)

在以下表10中，给出了K个测量时刻对应的测量实例(即全部K个测量实例)的上报格式，链路质量采用差分方式上报。表10相对于表9的区别在于，表10包含了K个测量实例，每个测量实例的内容与表9是类似的。此外，表10还包含了测量时刻索引，这种情况下，每个测量时刻对应的测量实例可以灵活排布在上报格式中。当然，表10也可以不包含测量时刻索引，这种情况下，每个测量时刻对应的测量实例按序排布在上报格式中。
表10：全部K个测量实例的测量结果上报(有L1-RSRP差分)
在以下表11中，给出了1个测量时刻对应的测量实例中的一个小区的测量结果的的上报格式，链路质量采用差分方式上报。该上报格式包括小区索引、测量时刻索引以及对应的链路质量，M个链路质量采用差分方式上报。采用表11所示的上报格式，终端在每次上报中可以仅上报一个第一下行参考信号子集的测量结果，网络设备需要收集终端的多次上报来作为第一模型的输入。当然，考虑到网络设备侧模型使用的灵活性，网络设备侧未必需要等到收集到所有第一下行参考信号子集的测量结果再进行预测。
表11：单个下行参考信号子集的测量结果上报

在一些实施方式中，当网络设备获得F个预测实例后，网络设备向终端发送小区切换命令(Cell Switch Command，CSC)，终端接收网络设备发送的小区切换命令，小区切换命令用于指示终端切换到目标小区，目标小区基于F个预测实例中的部分或全部预测实例确定。
这里，网络设备获得的F个预测实例可以是上述方案中，由终端发送给网络设备的F个预测实例(参考上述模型位于终端侧的方案)，或者，也可以是网络设备基于获得的K个测量实例预测得到的F个预测实例(参考上述模型位于网络设备侧的方案)。
示例性地，网络设备可以使用基于统一TCI状态(unified TCI state)的小区切换命令，该小区切换命令由MAC CE承载。其中统一TCI状态可以是下行/联合TCI状态(DL/joint TCI state)，其包括一个小区索引(如PCI、PCI索引、小区配置索引等)，通过该小区索引可以指示终端切换到的目标小区。
在一些实施方式中，终端获得K个测量实例并预测出F个预测实例后，终端向网络设备发送小区切换请求(Cell Switch reQuest，CSQ)，小区切换请求携带目标预测实例，目标预测实例基于F个预测实例确定。
这里，终端获得K个测量实例并预测出F个预测实例后，可以不上报F个预测实例，而是根据F个预测实例发送一个小区切换请求给网络设备，该小区切换请求由MAC CE承载。示例性地，该小区切换请求可以包含以下至少一种信息：预测时刻索引(即f值)；目标小区的小区索引，如PCI，PCI索引，候选小区配置索引，或p索引；目标小区对应的下行参考信号资源索引，如CRI/SSBRI或波束(对)索引；下行参考信号资源索引对应的链路质量，如L1-RSRP。网络设备在收到小区切换请求后，只需要向终端发送一个确认命令，终端便可以完成后续的切换操作。
需要说明的是，对于波束移动性(beam-level mobility)，模型预测的最优波束的结果是按照该波束对应的链路质量来评估，即highest L1-RSRP。对于小区移动性即(cell-level mobility)，举例来说，一个小区单个波束最优(其他波束质量都较差)，并不能保证该小区对UE来说是个最优小区，一种普遍的选择最优小区的方法是，对于该小区内的多个波束的链路质量进行加权平均，从而得到最优小区(以均值L1-RSRP从高到低排名)。在本申请实施例的技术方案中，用来预测最优小区的模型也参考了最优小区的选择机制，即cell-level mobility。
本申请实施例的技术方案，提出了一种基于模型的移动性预测技术，将多个历史测量时刻对多个小区的测量结果作为模型的输入，通过模型预测(输出)未来多个预测时刻的最优小区，和/或该小区下的最优波束(对)，和/或该波束(对)对应的链路质量，从而实现从被动到主动的移动性管理，减少下行移动性测量的开销和时延。
以下结合具体应用实例对本申请实施例的技术进行举例说明，以下应用实例中，将终端称为UE，将网络设备称为NW。
需要提前说明的是，对于模型的输入集，可以是测量集Set B，也可以是从测量集Set C中产生。换句话说，Set B本身可以是一个测量集，或者Set B也可以从测量集Set C中产生，即Set B是Set C中测量得到的最优多个波束(对)以及其链路质量。以下应用实例中，以Set B可以是一个测量集或者是从测量集Set C中产生。
应用实例一
本应用实例中，模型部署在UE侧，便于UE将下行参考信号的测量结果作为模型的输入，进行推断。
图16给出了一种时域移动性预测方法的流程示意图，如图16所示，该方法包括以下步骤：
步骤1601：UE向NW上报该UE的能力信息。
这里，UE的能力信息可以参照前述相关方案。
步骤1602：NW为UE配置Set A和Set B。
这里，NW为UE配置Set A和Set B可以参照前述相关方案。
步骤1603：UE根据NW的配置进行测量，得到K个测量实例。
这里，K个测量实例的内容可以参照前述相关方案。在图16中，K个测量实例中的第k(1≤k≤K)个测量实例称为测量实例#k。其中，测量实例#k包含了Set B_1,k,Set B_2,k,...,Set B_N,k分别对应的测量结果。这里的Set B_n,k(1≤n≤N，1≤k≤K)与上述方案中的Set Bn,k代表一样的含义。
步骤1604：UE侧模型根据测量实例，预测：最优的L(L≥1)个小区索引、每个最优区中最优的J(J≥1)个波束(对)索引、以及每个最优波束(对)索引对应的链路质量。
这里，UE侧模型根据进行了F个预测时刻对应的预测。具体地，UE侧模型需要K次历史测量实例作为输入，从而预测出后续F个预测时刻的测量实例。
步骤1605：UE向NW上报预测实例或者小区切换请求。
这里，预测实例内容或者小区切换请求可以参照前述相关方案。在图16中，F个预测实例中的第f(1≤f≤F)个预测实例称为预测实例#f。其中，预测实例#f包含了Set A_1,f,Set A_2,f,...,Set A_P,f分别对应的预测结果。这里的Set A_p,f(1≤p≤P，1≤f≤F)与上述方案中的Set Ap,f代表一样的含义。
步骤1606：NW向UE发送小区切换命令或者确认命令。
这里，小区切换命令或者确认命令可以参照前述相关方案。
需要说明的是，在图16中，步骤1606使用虚线表示是因为模型预测的最优小区可能是当前服务小区，因此不需要进行小区切换，所以步骤1606为可选步骤。
需要说明的是，在图16中，椭圆形代表测量集Set Bn,k，其中n(1≤n≤N)表示第一下行参考信号子集(即测量子集)的索引，k(1≤k≤K)表示测量时刻索引。虚线椭圆表示UE未进行测量，但包含在预测集Set Ap，f中的下行参考信号，其中p(1≤p≤P)表示第二下行参考信号子集(即预测子集)的索引，f(1≤f≤F)表示预测时刻索引。
需要说明的是，预测子集的数量P，未必与测量子集的数量N相等，比如P＝16，N＝8的情况，UE只测量8个测量子集，但可以从16个预测子集中(如1个服务小区和15个候选小区的预测子集)推断最优小区，和/或该最优小区对应的最优波束(对)索引，和/或该最优最优波束(对)索引对应的链路质量。当然，一种典型的部署方式是P等于N，即预测子集的数量和测量子集的数量相同，且每个预测子集/测量子集都对应着一个小区。
需要说明的是，对于一个小区来说，Set B和Set A可以相同(即仅有时域预测)，也可以Set B和Set A不同(即空域和时域的预测)。
需要说明的是，对于波束移动性(beam-level mobility)，模型预测的最优波束的结果是按照该波束对应的链路质量来评估，即highest L1-RSRP。对于小区移动性即(cell-level mobility)，举例来说，一个小区单个波束最优(其他波束质量都较差)，并不能保证该小区对UE来说是个最优小区，一种普遍的选择最优小区的方法是，对于该小区内的多个波束的链路质量进行加权平均，从而得到最优小区(以均值L1-RSRP从高到低排名)。在本申请实施例的技术方案中，用来预测最优小区的模型也参考了最优小区的选择机制，即cell-level mobility。
应用实例二
本应用实例中，模型部署在NW侧，UE进行时域移动性的测量，即测量Set B，并将测量结果上报给NW。NW侧部署的模型便可以进行时域移动性的预测。
图17给出了一种时域移动性预测方法的流程示意图，如图17所示，该方法包括以下步骤：
步骤1701：UE向NW上报该UE的能力信息。
这里，UE的能力信息可以参照前述相关方案。
步骤1702：NW为UE配置Set A和Set B。
这里，NW为UE配置Set A和Set B可以参照前述相关方案。
步骤1703：UE根据NW的配置进行测量，得到K个测量实例。
这里，K个测量实例的内容可以参照前述相关方案。在图17中，K个测量实例中的第k(1≤k≤K)个测量实例称为测量实例#k。其中，测量实例#k包含了Set B_1,k,Set B_2,k,...,Set B_N,k分别对应的测量结果。这里的Set B_n,k(1≤n≤N，1≤k≤K)与上述方案中的Set Bn,k代表一样的含义。
步骤1704：UE可以每得到一个测量实例就向NW上报一个测量实例，或者UE也可以测量得到K个测量实例后向NW上报K个测量实例。
步骤1705：NW侧模型根据测量实例，预测：最优的L(L≥1)个小区索引、每个最优区中最优的J(J≥1)个波束(对)索引、以及每个最优波束(对)索引对应的链路质量。
这里，预测实例内容可以参照前述相关方案。在图17中，F个预测实例中的第f(1≤f≤F)个预测实例称为预测实例#f。其中，预测实例#f包含了Set A_1,f,Set A_2,f,...,Set A_P,f分别对应的预测结果。这里的Set A_p,f(1≤p≤P，1≤f≤F)与上述方案中的Set Ap,f代表一样的含义。
步骤1706：NW向UE发送小区切换命令。
这里，小区切换命令或者确认命令可以参照前述相关方案。
需要说明的是，在图17中，步骤1706使用虚线表示是因为模型预测的最优小区可能是当前服务小区，因此不需要进行小区切换，所以步骤1706为可选步骤。
需要说明的是，在图17中，椭圆形代表测量集Set Bn,k，其中n(1≤n≤N)表示第一下行参考信号子集(即测量子集)的索引，k(1≤k≤K)表示测量时刻索引。虚线椭圆表示UE未进行测量，但包含在预测集Set Ap，f中的下行参考信号，其中p(1≤p≤P)表示第二下行参考信号子集(即预测子集)的索引，f(1≤f≤F)表示预测时刻索引。
需要说明的是，预测子集的数量P，未必与测量子集的数量N相等，比如P＝16，N＝8的情况，UE只测量8个测量子集，但NW可以从16个预测子集中(如1个服务小区和15个候选小区的预测子集)推断最优小区，和/或该最优小区对应的最优波束(对)索引，和/或该最优最优波束(对)索引对应的链路质量。当然，一种典型的部署方式是P等于N，即预测子集的数量和测量子集的数量相同，且每个预测子集/测量子集都对应着一个小区。
需要说明的是，对于一个小区来说，Set B和Set A可以相同(即仅有时域预测)，也可以Set B和Set A不同(即空域和时域的预测)。
需要说明的是，对于波束移动性(beam-level mobility)，模型预测的最优波束的结果是按照该波束对应的链路质量来评估，即highest L1-RSRP。对于小区移动性即(cell-level mobility)，举例来说，一个小区单个波束最优(其他波束质量都较差)，并不能保证该小区对UE来说是个最优小区，一种普遍的选择最优小区的方法是，对于该小区内的多个波束的链路质量进行加权平均，从而得到最优小区(以均值L1-RSRP从高到低排名)。在本申请实施例的技术方案中，用来预测最优小区的模型也参考了最优小区的选择机制，即cell-level mobility。
以上结合附图详细描述了本申请的优选实施方式，但是，本申请并不限于上述实施方式中的具体细节，在本申请的技术构思范围内，可以对本申请的技术方案进行多种简单变型，这些简单变型均属于本申请的保护范围。例如，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合，为了避免不必要的重复，本申请对各种可能的组合方式不再另行说明。又例如，本申请的各种不同的实施方式之间也可以进行任意组合，只要其不违背本申请的思想，其同样应当视为本申请所公开的内容。又例如，在不冲突的前提下，本申请描述的各个实施例和/或各个实施例中的技术特征可以和现有技术任意的相互组合，组合之后得到的技术方案也应落入本申请的保护范围。
还应理解，在本申请的各种方法实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。此外，在本申请实施例中，术语“下行”、“上行”和“侧行”用于表示信号或数据的传输方向，其中，“下行”用于表示信号或数据的传输方向为从站点发送至小区的用户设备的第一方向，“上行”用于表示信号或数据的传输方向为从小区的用户设备发送至站点的第二方向，“侧行”用于表示信号或数据的传输方向为从用户设备1发送至用户设备2的第三方向。例如，“下行信号”表示该信号的传输方向为第一方向。另外，本申请实施例中，术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系。具体地，A和/或B可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
图18是本申请实施例提供的移动性预测装置的结构组成示意图一，应用于终端，如图18所示，该装置包括：
获取单元1801，用于获取第一下行参考信号集对应的K个测量实例，所述K个测量实例基于所述终端在K个测量时刻对所述第一下行参考信号集中的下行参考信号进行测量得到，所述第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，所述K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的所述预测实例对应不同的预测时刻，所述第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
在一些实施方式中，装置还包括：接收单元1802，用于接收网络设备发送的第一配置信息和/或第二配置信息；所述第一配置信息用于配置所述第一下行参考信号集；所述第二配置信息用于配置所述第二下行参考信号集。
在一些实施方式中，所述第一配置信息还用于配置所述第一下行参考信号集对应的第一时域信息，所述第一时域信息用于确定所述K个测量实例对应的K个测量时刻；和/或，所述第二配置信息还用于配置所述第二下行参考信号集对应的第二时域信息，所述第二时域信息用于确定所述F个预测实例对应的F个预测时刻。
在一些实施方式中，所述第一时域信息包括以下至少之一：测量周期、第一偏移量、测量时刻的数目K；和/或，所述第二时域信息包括以下至少之一：预测周期、第二偏移量、预测时刻的数目F。
在一些实施方式中，所述第一配置信息和/或所述第二配置信息与所述终端的能力信息相关。
在一些实施方式中，装置还包括：发送单元1803，用于向所述网络设备发送所述终端的能力信息，所述终端的能力信息包括以下至少之一：
第一信息，所述第一信息用于指示所述终端是否支持时域移动性的测量和/或预测；
第二信息，所述第二信息用于指示以下至少之一：所述终端在全部的CC或BWP上，最多支持测量的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
第三信息，所述第三信息用于指示以下至少之一：所述终端在全部的下行CC或BWP上，最多支持预测的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持预测的第一下行参考信号子集的数量；
第四信息，所述第四信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持测量的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
第五信息，所述第五信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持预测的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持预测的第二下行参考信号子集的数量；
第六信息，所述第六信息用于指示所述终端在每一个第一下行参考信号子集内，最多支持测量的下行参考信号的数量；
第七信息，所述第七信息用于指示所述终端在每一个第二下行参考信号子集内，最多支持预测的下行参考信号的数量；
第八信息，所述第八信息用于指示所述终端支持的测量时刻的数量；
第九信息，所述第九信息用于指示所述终端支持的预测时刻的数量。
在一些实施方式中，所述K个测量实例包括：
K×N组链路质量；或者，
K×N个索引和K×N组链路质量，所述K×N个索引和所述K×N个链路质量具有对应关系；所述K×N个索引中的每个索引对应一个测量时刻索引和一个小区索引。
在一些实施方式中，所述F个预测实例中的每个预测实例包括以下至少之一：
所述P个小区中的最优L个小区索引；
每一个最优小区中的最优J个下行参考信号资源索引；
每一个最优下行参考信号资源索引对应的链路质量；
L，J为正整数。
在一些实施方式中，所述每个预测实例还包括：所述预测实例对应的预测时刻索引。
在一些实施方式中，所述第一模型位于所述终端侧。
在一些实施方式中，发送单元1803，用于向网络设备发送所述F个预测实例。
在一些实施方式中，所述F个预测实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报、基于层1和/或层2的移动性事件上报。
在一些实施方式中，对于所述周期性上报或所述半持续性上报，接收单元1802，用于接收网络设备发送的第三配置信息，所述第三配置信息用于配置所述周期性上报或所述半持续性上报对应的上报周期和上报偏移量。
在一些实施方式中，对于所述非周期上报，接收单元1802，用于接收网络设备发送的第一DCI，所述第一DCI用于触发所述非周期上报。
在一些实施方式中，所述层1和/或层2的移动性事件包括以下至少之一：
第一事件，所述第一事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能好于第一门限或弱于第二门限；
第二事件，所述第二事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能好于或弱于候选小区的预测的链路性能加上一个偏移量；
第三事件，所述第三事件为：在F个预测时刻中的部分或全部预测时刻，候选小区的预测的链路性能好于第三门限或弱于第四门限；
第四事件，所述第四事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能弱于第五门限，且候选小区的预测的链路性能好于第六门限；
所述当前小区为所述P个小区中的一个小区，所述候选小区为所述P个小区中除当前小区以外的一个小区。
在一些实施方式中，对于所述基于层1和/或层2的移动性事件上报，发送单元1803，用于确定所述层1和/或层2的移动性事件被触发，向网络设备发送上报请求；接收单元1802，用于接收所述网络设备发送的第二DCI，所述第二DCI用于调度上报用的PUSCH。
在一些实施方式中，所述F个预测实例的上报粒度为一个预测实例。
在一些实施方式中，所述上报具有第一格式，所述第一格式包括：预测时刻索引、L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；
其中，所述L个小区索引为所述P个小区中的最优L个小区索引；所述X1个下行参考信号资源索引包括所述L个小区中每个小区中最优J个下行参考信号资源索引；所述X1个链路质量与所述X1个下行参考信号资源索引具有对应关系。
在一些实施方式中，所述F个预测实例的上报粒度为F个预测实例。
在一些实施方式中，所述上报具有第二格式，所述第二格式包括F组信息，所述F组信息与所述F个预测实例具有对应关系；
所述F组信息中的每组信息包括：预测时刻索引、L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；或者，
所述F组信息中的每组信息包括：L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；
其中，所述L个小区索引为所述P个小区中的最优L个小区索引；所述X1个下行参考信号资源索引包括所述L个小区中每个小区中最优J个下行参考信号资源索引；所述X1个链路质量与所述X1个下行参考信号资源索引具有对应关系。
在一些实施方式中，所述第一模型位于网络设备侧。
在一些实施方式中，发送单元1803，用于向网络设备发送所述K个测量实例。
在一些实施方式中，所述K个测量实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报。
在一些实施方式中，对于所述周期性上报或所述半持续性上报，接收单元1802，用于接收网络设备发送的第四配置信息，所述第四配置信息用于配置所述周期性上报或所述半持续性上报对应的上报周期和上报偏移量。
在一些实施方式中，对于所述非周期上报，接收单元1802，用于接收网络设备发送的第三DCI，所述第三DCI用于触发所述非周期上报。
在一些实施方式中，所述K个测量实例的上报粒度为一个测量实例。
在一些实施方式中，所述上报具有第三格式，所述第三格式包括：测量时刻索引以及X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述上报具有第四格式，所述第四格式包括：测量时刻索引、N个小区索引以及X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述K个测量实例的上报粒度为K个测量实例。
在一些实施方式中，所述上报具有第五格式，所述第五格式包括：K组信息，所述K组信息与所述K个测量实例具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述上报具有第六格式，所述第六格式包括：N个小区索引和K组信息，或者，所述第六格式包括：N个小区索引、K个测量实例索引和K组信息；所述K组信息与所述K个测量实例索引具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述X2个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
在一些实施方式中，对于上报粒度为一个测量实例的情况，在所述差分上报格式中，
所述X2个链路质量通过一个参考链路质量和X2-1个差分值表示；或者，
所述X2个链路质量划分为N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
在一些实施方式中，对于上报粒度为K个测量实例的情况，在所述差分上报格式中，
K×X2个链路质量通过一个参考链路质量和K×X2-1个差分值表示；或者，
K×X2个链路质量划分为K×N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
在一些实施方式中，在所述非差分上报格式中，所述X2个链路质量通过X2个链路质量表示。
在一些实施方式中，所述K个测量实例的上报粒度为一个测量实例中的一个小区的测量结果。
在一些实施方式中，所述上报具有第六格式，所述第六格式包括：测量时刻索引、小区索引以及M个链路质量；
其中，所述M个链路质量包括所述小区索引对应的小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述M个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
在一些实施方式中，在所述差分上报格式中，所述M个链路质量通过一个参考链路质量和M-1个差分值表示。
在一些实施方式中，在所述非差分上报格式，所述M个链路质量通过M个链路质量表示。
在一些实施方式中，接收单元1802，用于接收所述网络设备发送的小区切换命令，所述小区切换命令用于指示所述终端切换到目标小区，所述目标小区基于所述F个预测实例中的部分或全部预测实例确定。
在一些实施方式中，发送单元1803，用于向所述网络设备发送小区切换请求，所述小区切换请求携带目标预测实例，所述目标预测实例基于所述F个预测实例确定。
在一些实施方式中，所述K个测量实例对应的测量时刻和所述F个预测实例对应的预测时刻满足如下时序关系：
所述K个测量实例对应的测量时刻位于第一时段内，所述F个预测实例对应的预测时刻位于第二时段内，所述第二时段与所述第一时段不重叠；或者，
所述K个测量实例对应的测量时刻位于K个第一时段内，所述F个预测实例对应的预测时刻位于所述K个第一时段的最后一个第一时段内。
本领域技术人员应当理解，本申请实施例的上述移动性预测装置的相关描述可以参照本申请实施例的时域移动性预测方法的相关描述进行理解。
图19是本申请实施例提供的移动性预测装置的结构组成示意图二，应用于网络设备，如图19所示，该装置包括：
接收单元1901，用于接收终端发送的第一下行参考信号集对应的K个测量实例，所述K个测量实例基于所述终端在K个测量时刻对所述第一下行参考信号集中的下行参考信号进行测量得到，所述第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，所述K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的所述预测实例对应不同的预测时刻，所述第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
在一些实施方式中，装置还包括：发送单元1902，用于向所述终端发送第一配置信息和/或第二配置信息；
所述第一配置信息用于配置所述第一下行参考信号集；所述第二配置信息用于配置所述第二下行参考信号集。
在一些实施方式中，所述第一配置信息还用于配置所述第一下行参考信号集对应的第一时域信息，所述第一时域信息用于确定所述K个测量实例对应的K个测量时刻；和/或，
所述第二配置信息还用于配置所述第二下行参考信号集对应的第二时域信息，所述第二时域信息用于确定所述F个预测实例对应的F个预测时刻。
在一些实施方式中，所述第一时域信息包括以下至少之一：测量周期、第一偏移量、测量时刻的数目K；和/或，
所述第二时域信息包括以下至少之一：预测周期、第二偏移量、预测时刻的数目F。
在一些实施方式中，所述第一配置信息和/或所述第二配置信息与所述终端的能力信息相关。
在一些实施方式中，接收单元1901，用于接收所述终端发送的所述终端的能力信息，所述终端的能力信息包括以下至少之一：
第一信息，所述第一信息用于指示所述终端是否支持时域移动性的测量和/或预测；
第二信息，所述第二信息用于指示以下至少之一：所述终端在全部的下行CC或BWP上，最多支持测量的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
第三信息，所述第三信息用于指示以下至少之一：所述终端在全部的下行CC或BWP上，最多支持预测的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持预测的第一下行参考信号子集的数量；
第四信息，所述第四信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持测量的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
第五信息，所述第五信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持预测的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持预测的第二下行参考信号子集的数量；
第六信息，所述第六信息用于指示所述终端在每一个第一下行参考信号子集内，最多支持测量的下行参考信号的数量；
第七信息，所述第七信息用于指示所述终端在每一个第二下行参考信号子集内，最多支持预测的下行参考信号的数量；
第八信息，所述第八信息用于指示所述终端支持的测量时刻的数量；
第九信息，所述第九信息用于指示所述终端支持的预测时刻的数量。
在一些实施方式中，所述K个测量实例包括：
N×K组链路质量；或者，
N×K个索引和N×K组链路质量，所述N×K个索引和所述N×K个链路质量具有对应关系；所述N×K个索引中的每个索引对应一个小区索引和一个测量时刻索引。
在一些实施方式中，所述F个预测实例中的每个预测实例包括以下至少之一：
所述P个小区中的最优L个小区索引；
每一个最优小区中的最优J个下行参考信号资源索引；
每一个最优下行参考信号资源索引对应的链路质量；
L，J为正整数。
在一些实施方式中，所述每个预测实例还包括：所述预测实例对应的预测时刻索引。
在一些实施方式中，所述K个测量实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报。
在一些实施方式中，发送单元1902，用于向所述终端发送第四配置信息，所述第四配置信息用于配置所述周期性上报或所述半持续性上报对应的上报周期和上报偏移量。
在一些实施方式中，发送单元1902，用于向所述终端发送第三DCI，所述第三DCI用于触发所述非周期上报。
在一些实施方式中，所述K个测量实例的上报粒度为一个测量实例。
在一些实施方式中，所述上报具有第三格式，所述第三格式包括：测量时刻索引以及X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述上报具有第四格式，所述第四格式包括：测量时刻索引、N个小区索引以及X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述K个测量实例的上报粒度为K个测量实例。
在一些实施方式中，所述上报具有第五格式，所述第五格式包括：K组信息，所述K组信息与所述K个测量实例具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述上报具有第六格式，所述第六格式包括：N个小区索引和K组信息，或者，所述第六格式包括：N个小区索引、K个测量实例索引和K组信息；所述K组信息与所述K个测量实例索引具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述X2个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
在一些实施方式中，对于上报粒度为一个测量实例的情况，在所述差分上报格式中，
所述X2个链路质量通过一个参考链路质量和X2-1个差分值表示；或者，
所述X2个链路质量划分为N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
在一些实施方式中，对于上报粒度为K个测量实例的情况，在所述差分上报格式中，
K×X2个链路质量通过一个参考链路质量和K×X2-1个差分值表示；或者，
K×X2个链路质量划分为K×N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
在一些实施方式中，在所述非差分上报格式中，所述X2个链路质量通过X2个链路质量表示。
在一些实施方式中，所述K个测量实例的上报粒度为一个测量实例中的一个小区的测量结果。
在一些实施方式中，所述上报具有第六格式，所述第六格式包括：测量时刻索引、小区索引以及M个链路质量；
其中，所述M个链路质量包括所述小区索引对应的小区的M个下行参考信号的链路质量，M为正整数。
在一些实施方式中，所述M个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
在一些实施方式中，在所述差分上报格式中，所述M个链路质量通过一个参考链路质量和M-1个差分值表示。
在一些实施方式中，在所述非差分上报格式，所述M个链路质量通过M个链路质量表示。
在一些实施方式中，发送单元1902，用于向所述终端发送小区切换命令，所述小区切换命令用于指示所述终端切换到目标小区，所述目标小区基于所述F个预测实例中的部分或全部预测实例确定。
在一些实施方式中，所述K个测量实例对应的测量时刻和所述F个预测实例对应的预测时刻满足如下时序关系：
所述K个测量实例对应的测量时刻位于第一时段内，所述F个预测实例对应的预测时刻位于第二时段内，所述第二时段与所述第一时段不重叠；或者，
所述K个测量实例对应的测量时刻位于K个第一时段内，所述F个预测实例对应的预测时刻位于所述K个第一时段的最后一个第一时段内。
本领域技术人员应当理解，本申请实施例的上述移动性预测装置的相关描述可以参照本申请实施例的时域移动性预测方法的相关描述进行理解。
图20是本申请实施例提供的一种通信设备2000示意性结构图。该通信设备可以终端，也可以是网络设备。图20所示的通信设备2000包括处理器2010，处理器2010可以从存储器中调用并运行计算机程序，以实现本申请实施例中的方法。
可选地，如图20所示，通信设备2000还可以包括存储器2020。其中，处理器2010可以从存储器2020中调用并运行计算机程序，以实现本申请实施例中的方法。
其中，存储器2020可以是独立于处理器2010的一个单独的器件，也可以集成在处理器2010中。
可选地，如图20所示，通信设备2000还可以包括收发器2030，处理器2010可以控制该收发器2030与其他设备进行通信，具体地，可以向其他设备发送信息或数据，或接收其他设备发送的信息或数据。
其中，收发器2030可以包括发射机和接收机。收发器2030还可以进一步包括天线，天线的数量可以为一个或多个。
可选地，该通信设备2000具体可为本申请实施例的网络设备，并且该通信设备2000可以实现本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。
可选地，该通信设备2000具体可为本申请实施例的移动终端/终端，并且该通信设备2000可以实现本申请实施例的各个方法中由移动终端/终端实现的相应流程，为了简洁，在此不再赘述。
图21是本申请实施例的芯片的示意性结构图。图21所示的芯片2100包括处理器2110，处理器2110可以从存储器中调用并运行计算机程序，以实现本申请实施例中的方法。
可选地，如图21所示，芯片2100还可以包括存储器2120。其中，处理器2110可以从存储器2120中调用并运行计算机程序，以实现本申请实施例中的方法。
其中，存储器2120可以是独立于处理器2110的一个单独的器件，也可以集成在处理器2110中。
可选地，该芯片2100还可以包括输入接口2130。其中，处理器2110可以控制该输入接口2130与其他设备或芯片进行通信，具体地，可以获取其他设备或芯片发送的信息或数据。
可选地，该芯片2100还可以包括输出接口2140。其中，处理器2110可以控制该输出接口2140与其他设备或芯片进行通信，具体地，可以向其他设备或芯片输出信息或数据。
可选地，该芯片可应用于本申请实施例中的网络设备，并且该芯片可以实现本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。
可选地，该芯片可应用于本申请实施例中的移动终端/终端，并且该芯片可以实现本申请实施例的各个方法中由移动终端/终端实现的相应流程，为了简洁，在此不再赘述。
应理解，本申请实施例提到的芯片还可以称为系统级芯片，系统芯片，芯片系统或片上系统芯片等。
图22是本申请实施例提供的一种通信系统2200的示意性框图。如图22所示，该通信系统2200包括终端2210和网络设备2220。
其中，该终端2210可以用于实现上述方法中由终端实现的相应的功能，以及该网络设备2220可以用于实现上述方法中由网络设备实现的相应的功能为了简洁，在此不再赘述。
应理解，本申请实施例的处理器可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
应理解，上述存储器为示例性但不是限制性说明，例如，本申请实施例中的存储器还可以是静 态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synch link DRAM，SLDRAM)以及直接内存总线随机存取存储器(Direct Rambus RAM，DR RAM)等等。也就是说，本申请实施例中的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本申请实施例还提供了一种计算机可读存储介质，用于存储计算机程序。
可选的，该计算机可读存储介质可应用于本申请实施例中的网络设备，并且该计算机程序使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。
可选地，该计算机可读存储介质可应用于本申请实施例中的移动终端/终端，并且该计算机程序使得计算机执行本申请实施例的各个方法中由移动终端/终端实现的相应流程，为了简洁，在此不再赘述。
本申请实施例还提供了一种计算机程序产品，包括计算机程序指令。
可选的，该计算机程序产品可应用于本申请实施例中的网络设备，并且该计算机程序指令使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。
可选地，该计算机程序产品可应用于本申请实施例中的移动终端/终端，并且该计算机程序指令使得计算机执行本申请实施例的各个方法中由移动终端/终端实现的相应流程，为了简洁，在此不再赘述。
本申请实施例还提供了一种计算机程序。
可选的，该计算机程序可应用于本申请实施例中的网络设备，当该计算机程序在计算机上运行时，使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。
可选地，该计算机程序可应用于本申请实施例中的移动终端/终端，当该计算机程序在计算机上运行时，使得计算机执行本申请实施例的各个方法中由移动终端/终端实现的相应流程，为了简洁，在此不再赘述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，)ROM、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (79)

  1. 一种移动性预测方法，所述方法包括：
    终端获取第一下行参考信号集对应的K个测量实例，所述K个测量实例基于所述终端在K个测量时刻对所述第一下行参考信号集中的下行参考信号进行测量得到，所述第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，所述K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的所述预测实例对应不同的预测时刻，所述第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    所述终端接收网络设备发送的第一配置信息和/或第二配置信息；
    所述第一配置信息用于配置所述第一下行参考信号集；所述第二配置信息用于配置所述第二下行参考信号集。
  3. 根据权利要求2所述的方法，其中，
    所述第一配置信息还用于配置所述第一下行参考信号集对应的第一时域信息，所述第一时域信息用于确定所述K个测量实例对应的K个测量时刻；和/或，
    所述第二配置信息还用于配置所述第二下行参考信号集对应的第二时域信息，所述第二时域信息用于确定所述F个预测实例对应的F个预测时刻。
  4. 根据权利要求3所述的方法，其中，
    所述第一时域信息包括以下至少之一：测量周期、第一偏移量、测量时刻的数目K；和/或，
    所述第二时域信息包括以下至少之一：预测周期、第二偏移量、预测时刻的数目F。
  5. 根据权利要求2至4中任一项所述的方法，其中，所述第一配置信息和/或所述第二配置信息与所述终端的能力信息相关。
  6. 根据权利要求2至5中任一项所述的方法，其中，所述方法还包括：
    所述终端向所述网络设备发送所述终端的能力信息，所述终端的能力信息包括以下至少之一：
    第一信息，所述第一信息用于指示所述终端是否支持时域移动性的测量和/或预测；
    第二信息，所述第二信息用于指示以下至少之一：所述终端在全部的下行载波分量CC或带宽部分BWP上，最多支持测量的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
    第三信息，所述第三信息用于指示以下至少之一：所述终端在全部的下行CC或BWP上，最多支持预测的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持预测的第一下行参考信号子集的数量；
    第四信息，所述第四信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持测量的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
    第五信息，所述第五信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持预测的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持预测的第二下行参考信号子集的数量；
    第六信息，所述第六信息用于指示所述终端在每一个第一下行参考信号子集内，最多支持测量的下行参考信号的数量；
    第七信息，所述第七信息用于指示所述终端在每一个第二下行参考信号子集内，最多支持预测的下行参考信号的数量；
    第八信息，所述第八信息用于指示所述终端支持的测量时刻的数量；
    第九信息，所述第九信息用于指示所述终端支持的预测时刻的数量。
  7. 根据权利要求1至6中任一项所述的方法，其中，所述K个测量实例包括：
    K×N组链路质量；或者，
    K×N个索引和K×N组链路质量，所述K×N个索引和所述K×N个链路质量具有对应关系；所述K×N个索引中的每个索引对应一个测量时刻索引和一个小区索引。
  8. 根据权利要求1至7中任一项所述的方法，其中，所述F个预测实例中的每个预测实例包括以下至少之一：
    所述P个小区中的最优L个小区索引；
    每一个最优小区中的最优J个下行参考信号资源索引；
    每一个最优下行参考信号资源索引对应的链路质量；
    L，J为正整数。
  9. 根据权利要求8所述的方法，其中，所述每个预测实例还包括：所述预测实例对应的预测时刻索引。
  10. 根据权利要求1至8中任一项所述的方法，其中，所述第一模型位于所述终端侧。
  11. 根据权利要求10所述的方法，其中，所述方法还包括：
    所述终端向网络设备发送所述F个预测实例。
  12. 根据权利要求11所述的方法，所述F个预测实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报、基于层1和/或层2的移动性事件上报。
  13. 根据权利要求12所述的方法，其中，对于所述周期性上报或所述半持续性上报，所述终端向网络设备发送所述F个预测实例之前，所述方法还包括：
    所述终端接收网络设备发送的第三配置信息，所述第三配置信息用于配置所述周期性上报或所述半持续性上报对应的上报周期和上报偏移量。
  14. 根据权利要求12所述的方法，其中，对于所述非周期上报，所述终端向网络设备发送所述F个预测实例之前，所述方法还包括：
    所述终端接收网络设备发送的第一下行控制信息DCI，所述第一DCI用于触发所述非周期上报。
  15. 根据权利要求12所述的方法，其中，所述层1和/或层2的移动性事件包括以下至少之一：
    第一事件，所述第一事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能好于第一门限或弱于第二门限；
    第二事件，所述第二事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能好于或弱于候选小区的预测的链路性能加上一个偏移量；
    第三事件，所述第三事件为：在F个预测时刻中的部分或全部预测时刻，候选小区的预测的链路性能好于第三门限或弱于第四门限；
    第四事件，所述第四事件为：在F个预测时刻中的部分或全部预测时刻，当前服务小区的预测的链路性能弱于第五门限，且候选小区的预测的链路性能好于第六门限；
    所述当前小区为所述P个小区中的一个小区，所述候选小区为所述P个小区中除当前小区以外的一个小区。
  16. 根据权利要求12或15所述的方法，其中，对于所述基于层1和/或层2的移动性事件上报，所述终端向网络设备发送所述F个预测实例之前，所述方法还包括：
    所述终端确定所述层1和/或层2的移动性事件被触发，向网络设备发送上报请求；
    所述终端接收所述网络设备发送的第二DCI，所述第二DCI用于调度上报用的物理上行共享信道PUSCH。
  17. 根据权利要求11至16中任一项所述的方法，其中，所述F个预测实例的上报粒度为一个预测实例。
  18. 根据权利要求17所述的方法，其中，所述上报具有第一格式，所述第一格式包括：预测时刻索引、L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；
    其中，所述L个小区索引为所述P个小区中的最优L个小区索引；所述X1个下行参考信号资源索引包括所述L个小区中每个小区中最优J个下行参考信号资源索引；所述X1个链路质量与所述X1个下行参考信号资源索引具有对应关系。
  19. 根据权利要求11至16中任一项所述的方法，其中，所述F个预测实例的上报粒度为F个预测实例。
  20. 根据权利要求19所述的方法，其中，所述上报具有第二格式，所述第二格式包括F组信息，所述F组信息与所述F个预测实例具有对应关系；
    所述F组信息中的每组信息包括：预测时刻索引、L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；或者，
    所述F组信息中的每组信息包括：L个小区索引、X1个下行参考信号资源索引以及X1个链路质量；
    其中，所述L个小区索引为所述P个小区中的最优L个小区索引；所述X1个下行参考信号资源索引包括所述L个小区中每个小区中最优J个下行参考信号资源索引；所述X1个链路质量与所述X1个下行参考信号资源索引具有对应关系。
  21. 根据权利要求1至8中任一项所述的方法，其中，所述第一模型位于网络设备侧。
  22. 根据权利要求21所述的方法，其中，所述方法还包括：
    所述终端向网络设备发送所述K个测量实例。
  23. 根据权利要求22所述的方法，其中，所述K个测量实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报。
  24. 根据权利要求23所述的方法，其中，对于所述周期性上报或所述半持续性上报，所述终端向网络设备发送所述K个测量实例之前，所述方法还包括：
    所述终端接收网络设备发送的第四配置信息，所述第四配置信息用于配置所述周期性上报或所述半持续性上报对应的上报周期和上报偏移量。
  25. 根据权利要求23所述的方法，其中，对于所述非周期上报，所述终端向网络设备发送所述K个测量实例之前，所述方法还包括：
    所述终端接收网络设备发送的第三DCI，所述第三DCI用于触发所述非周期上报。
  26. 根据权利要求22至25中任一项所述的方法，其中，所述K个测量实例的上报粒度为一个测量实例。
  27. 根据权利要求26所述的方法，其中，所述上报具有第三格式，所述第三格式包括：测量时刻索引以及X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  28. 根据权利要求26所述的方法，其中，所述上报具有第四格式，所述第四格式包括：测量时刻索引、N个小区索引以及X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  29. 根据权利要求22至25中任一项所述的方法，其中，所述K个测量实例的上报粒度为K个测量实例。
  30. 根据权利要求29所述的方法，其中，所述上报具有第五格式，所述第五格式包括：K组信息，所述K组信息与所述K个测量实例具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  31. 根据权利要求29所述的方法，其中，所述上报具有第六格式，所述第六格式包括：N个小区索引和K组信息，或者，所述第六格式包括：N个小区索引、K个测量实例索引和K组信息；所述K组信息与所述K个测量实例索引具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  32. 根据权利要求27至31中任一项所述的方法，其中，所述X2个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
  33. 根据权利要求32所述的方法，其中，对于上报粒度为一个测量实例的情况，在所述差分上报格式中，
    所述X2个链路质量通过一个参考链路质量和X2-1个差分值表示；或者，
    所述X2个链路质量划分为N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
  34. 根据权利要求32所述的方法，其中，对于上报粒度为K个测量实例的情况，在所述差分上报格式中，
    K×X2个链路质量通过一个参考链路质量和K×X2-1个差分值表示；或者，
    K×X2个链路质量划分为K×N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
  35. 根据权利要求32所述的方法，其中，在所述非差分上报格式中，所述X2个链路质量通过X2个链路质量表示。
  36. 根据权利要求22至25中任一项所述的方法，其中，所述K个测量实例的上报粒度为一个测量实例中的一个小区的测量结果。
  37. 根据权利要求36所述的方法，其中，所述上报具有第六格式，所述第六格式包括：测量时刻索引、小区索引以及M个链路质量；
    其中，所述M个链路质量包括所述小区索引对应的小区的M个下行参考信号的链路质量，M为正整数。
  38. 根据权利要求37所述的方法，其中，所述M个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
  39. 根据权利要求38所述的方法，其中，在所述差分上报格式中，所述M个链路质量通过一个参考链路质量和M-1个差分值表示。
  40. 根据权利要求38所述的方法，其中，在所述非差分上报格式，所述M个链路质量通过M个链路质量表示。
  41. 根据权利要求1至40中任一项所述的方法，其中，所述方法还包括：
    所述终端接收所述网络设备发送的小区切换命令，所述小区切换命令用于指示所述终端切换到目标小区，所述目标小区基于所述F个预测实例中的部分或全部预测实例确定。
  42. 根据权利要求1至20中任一项所述的方法，其中，所述方法还包括：
    所述终端向所述网络设备发送小区切换请求，所述小区切换请求携带目标预测实例，所述目标预测实例基于所述F个预测实例确定。
  43. 根据权利要求1至42中任一项所述的方法，其中，所述K个测量实例对应的测量时刻和所述F个预测实例对应的预测时刻满足如下时序关系：
    所述K个测量实例对应的测量时刻位于第一时段内，所述F个预测实例对应的预测时刻位于第二时段内，所述第二时段与所述第一时段不重叠；或者，
    所述K个测量实例对应的测量时刻位于K个第一时段内，所述F个预测实例对应的预测时刻位于所述K个第一时段的最后一个第一时段内。
  44. 一种移动性预测方法，所述方法包括：
    网络设备接收终端发送的第一下行参考信号集对应的K个测量实例，所述K个测量实例基于所述终端在K个测量时刻对所述第一下行参考信号集中的下行参考信号进行测量得到，所述第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，所述K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的所述预测实例对应不同的预测时刻，所述第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
  45. 根据权利要求44所述的方法，其中，所述方法还包括：
    所述网络设备向所述终端发送第一配置信息和/或第二配置信息；
    所述第一配置信息用于配置所述第一下行参考信号集；所述第二配置信息用于配置所述第二下行参考信号集。
  46. 根据权利要求45所述的方法，其中，
    所述第一配置信息还用于配置所述第一下行参考信号集对应的第一时域信息，所述第一时域信息用于确定所述K个测量实例对应的K个测量时刻；和/或，
    所述第二配置信息还用于配置所述第二下行参考信号集对应的第二时域信息，所述第二时域信息用于确定所述F个预测实例对应的F个预测时刻。
  47. 根据权利要求46所述的方法，其中，
    所述第一时域信息包括以下至少之一：测量周期、第一偏移量、测量时刻的数目K；和/或，
    所述第二时域信息包括以下至少之一：预测周期、第二偏移量、预测时刻的数目F。
  48. 根据权利要求45至47中任一项所述的方法，其中，所述第一配置信息和/或所述第二配置信息与所述终端的能力信息相关。
  49. 根据权利要求45至48中任一项所述的方法，其中，所述方法还包括：
    所述网络设备接收所述终端发送的所述终端的能力信息，所述终端的能力信息包括以下至少之一：
    第一信息，所述第一信息用于指示所述终端是否支持时域移动性的测量和/或预测；
    第二信息，所述第二信息用于指示以下至少之一：所述终端在全部的下行CC或BWP上，最多支持测量的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
    第三信息，所述第三信息用于指示以下至少之一：所述终端在全部的下行CC或BWP上，最多支持预测的小区的数量；所述终端在全部的下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在全部的下行CC或BWP上，最多支持预测的第一下行参考信号子集的数量；
    第四信息，所述第四信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持测量的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第一下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持测量的第一下行参考信号子集的数量；
    第五信息，所述第五信息用于指示以下至少之一：所述终端在每一个下行CC或BWP上，最多支持预测的小区的数量；所述终端在每一个下行CC或BWP上，最多支持被配置的第二下行参考信号子集的数量；所述终端在每一个下行CC或BWP上，最多支持预测的第二下行参考信号子集的数量；
    第六信息，所述第六信息用于指示所述终端在每一个第一下行参考信号子集内，最多支持测量的下行参考信号的数量；
    第七信息，所述第七信息用于指示所述终端在每一个第二下行参考信号子集内，最多支持预测的下行参考信号的数量；
    第八信息，所述第八信息用于指示所述终端支持的测量时刻的数量；
    第九信息，所述第九信息用于指示所述终端支持的预测时刻的数量。
  50. 根据权利要求44至49中任一项所述的方法，其中，所述K个测量实例包括：
    N×K组链路质量；或者，
    N×K个索引和N×K组链路质量，所述N×K个索引和所述N×K个链路质量具有对应关系；所述N×K个索引中的每个索引对应一个小区索引和一个测量时刻索引。
  51. 根据权利要求44至50中任一项所述的方法，其中，所述F个预测实例中的每个预测实例包括以下至少之一：
    所述P个小区中的最优L个小区索引；
    每一个最优小区中的最优J个下行参考信号资源索引；
    每一个最优下行参考信号资源索引对应的链路质量；
    L，J为正整数。
  52. 根据权利要求51所述的方法，其中，所述每个预测实例还包括：所述预测实例对应的预测时刻索引。
  53. 根据权利要求44至52中任一项所述的方法，其中，所述K个测量实例的上报方式包括以下至少之一：周期性上报、半持续性上报、非周期上报。
  54. 根据权利要求53所述的方法，其中，所述方法还包括：
    所述网络设备向所述终端发送第四配置信息，所述第四配置信息用于配置所述周期性上报或所述半持续性上报对应的上报周期和上报偏移量。
  55. 根据权利要求53所述的方法，其中，所述方法还包括：
    所述网络设备向所述终端发送第三DCI，所述第三DCI用于触发所述非周期上报。
  56. 根据权利要求44至55中任一项所述的方法，其中，所述K个测量实例的上报粒度为一个测量实例。
  57. 根据权利要求56所述的方法，其中，所述上报具有第三格式，所述第三格式包括：测量时刻索引以及X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  58. 根据权利要求56所述的方法，其中，所述上报具有第四格式，所述第四格式包括：测量时刻索引、N个小区索引以及X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  59. 根据权利要求44至55中任一项所述的方法，其中，所述K个测量实例的上报粒度为K个测量实例。
  60. 根据权利要求59所述的方法，其中，所述上报具有第五格式，所述第五格式包括：K组信息，所述K组信息与所述K个测量实例具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  61. 根据权利要求59所述的方法，其中，所述上报具有第六格式，所述第六格式包括：N个小区索引和K组信息，或者，所述第六格式包括：N个小区索引、K个测量实例索引和K组信息；所述K组信息与所述K个测量实例索引具有对应关系；所述K组信息中的每组信息包括：X2个链路质量；
    其中，所述X2个链路质量包括所述N个小区中每个小区的M个下行参考信号的链路质量，M为正整数。
  62. 根据权利要求57至61中任一项所述的方法，其中，所述X2个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
  63. 根据权利要求62所述的方法，其中，对于上报粒度为一个测量实例的情况，在所述差分上报格式中，
    所述X2个链路质量通过一个参考链路质量和X2-1个差分值表示；或者，
    所述X2个链路质量划分为N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
  64. 根据权利要求62所述的方法，其中，对于上报粒度为K个测量实例的情况，在所述差分上报格式中，
    K×X2个链路质量通过一个参考链路质量和K×X2-1个差分值表示；或者，
    K×X2个链路质量划分为K×N组链路质量，每组链路质量通过一个参考链路质量和M-1个差分值表示。
  65. 根据权利要求62所述的方法，其中，在所述非差分上报格式中，所述X2个链路质量通过X2个链路质量表示。
  66. 根据权利要求44至55中任一项所述的方法，其中，所述K个测量实例的上报粒度为一个测量实例中的一个小区的测量结果。
  67. 根据权利要求66所述的方法，其中，所述上报具有第六格式，所述第六格式包括：测量时刻索引、小区索引以及M个链路质量；
    其中，所述M个链路质量包括所述小区索引对应的小区的M个下行参考信号的链路质量，M为正整数。
  68. 根据权利要求67所述的方法，其中，所述M个链路质量在所述上报中的格式采用差分上报格式或者非差分上报格式。
  69. 根据权利要求68所述的方法，其中，在所述差分上报格式中，所述M个链路质量通过一个参考链路质量和M-1个差分值表示。
  70. 根据权利要求68所述的方法，其中，在所述非差分上报格式，所述M个链路质量通过M个链路质量表示。
  71. 根据权利要求44至70中任一项所述的方法，其中，所述方法还包括：
    所述网络设备向所述终端发送小区切换命令，所述小区切换命令用于指示所述终端切换到目标小区，所述目标小区基于所述F个预测实例中的部分或全部预测实例确定。
  72. 根据权利要求44至71中任一项所述的方法，其中，所述K个测量实例对应的测量时刻和所述F个预测实例对应的预测时刻满足如下时序关系：
    所述K个测量实例对应的测量时刻位于第一时段内，所述F个预测实例对应的预测时刻位于第二时段内，所述第二时段与所述第一时段不重叠；或者，
    所述K个测量实例对应的测量时刻位于K个第一时段内，所述F个预测实例对应的预测时刻位于所述K个第一时段的最后一个第一时段内。
  73. 一种移动性预测装置，应用于终端，所述装置包括：
    获取单元，用于获取第一下行参考信号集对应的K个测量实例，所述K个测量实例基于所述终端在K个测量时刻对所述第一下行参考信号集中的下行参考信号进行测量得到，所述第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，所述K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的所述预测实例对应不同的预测时刻，所述第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
  74. 一种移动性预测装置，应用于网络设备，所述装置包括：
    接收单元，用于接收终端发送的第一下行参考信号集对应的K个测量实例，所述K个测量实例基于所述终端在K个测量时刻对所述第一下行参考信号集中的下行参考信号进行测量得到，所述第一下行参考信号集包括N个小区的第一下行参考信号子集；其中，所述K个测量实例用于基于第一模型获取第二下行参考信号集对应的F个预测实例，不同的所述预测实例对应不同的预测时刻，所述第二下行参考信号集包括P个小区的第二下行参考信号子集；K，N，F和P为大于等于1的整数。
  75. 一种通信设备，包括：处理器和存储器，该存储器用于存储计算机程序，所述处理器用于调用并运行所述存储器中存储的计算机程序，以使所述网络设备执行如权利要求1至43中任一项所述的方法，或者权利要求44至72中任一项所述的方法。
  76. 一种芯片，包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有所述芯片的设备执行如权利要求1至43中任一项所述的方法，或者权利要求44至72中任一项所述的方法。
  77. 一种计算机可读存储介质，用于存储计算机程序，所述计算机程序使得计算机执行如权利要求1至43中任一项所述的方法，或者权利要求44至72中任一项所述的方法。
  78. 一种计算机程序产品，包括计算机程序指令，该计算机程序指令使得计算机执行如权利要求1至43中任一项所述的方法，或者权利要求44至72中任一项所述的方法。
  79. 一种计算机程序，所述计算机程序使得计算机执行如权利要求1至43中任一项所述的方法，或者权利要求44至72中任一项所述的方法。
PCT/CN2023/107045 2023-07-12 2023-07-12 一种时域移动性预测方法及装置、设备、芯片和存储介质 Pending WO2025010664A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2023/107045 WO2025010664A1 (zh) 2023-07-12 2023-07-12 一种时域移动性预测方法及装置、设备、芯片和存储介质
CN202380100229.XA CN121533064A (zh) 2023-07-12 2023-07-12 一种时域移动性预测方法及装置、设备、芯片和存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/107045 WO2025010664A1 (zh) 2023-07-12 2023-07-12 一种时域移动性预测方法及装置、设备、芯片和存储介质

Publications (1)

Publication Number Publication Date
WO2025010664A1 true WO2025010664A1 (zh) 2025-01-16

Family

ID=94214409

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/107045 Pending WO2025010664A1 (zh) 2023-07-12 2023-07-12 一种时域移动性预测方法及装置、设备、芯片和存储介质

Country Status (2)

Country Link
CN (1) CN121533064A (zh)
WO (1) WO2025010664A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110017560A (ko) * 2009-08-14 2011-02-22 광운대학교 산학협력단 무선 인터넷에서 ａｒｉｍａ 모델을 이용한 핸드오버 지연 단축 방법 및 이를 위한 모바일 라우터
CN110034792A (zh) * 2018-01-11 2019-07-19 中国移动通信有限公司研究院 一种多入多出传输方法、设备及计算机可读存储介质
CN112449393A (zh) * 2020-12-23 2021-03-05 中国联合网络通信集团有限公司 小区切换方法及终端
CN113965291A (zh) * 2020-07-20 2022-01-21 中兴通讯股份有限公司 通信控制方法、基站、终端及存储介质
US20230131579A1 (en) * 2020-06-24 2023-04-27 Huawei Technologies Co., Ltd. Wireless signal propagation prediction method and apparatus

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110017560A (ko) * 2009-08-14 2011-02-22 광운대학교 산학협력단 무선 인터넷에서 ａｒｉｍａ 모델을 이용한 핸드오버 지연 단축 방법 및 이를 위한 모바일 라우터
CN110034792A (zh) * 2018-01-11 2019-07-19 中国移动通信有限公司研究院 一种多入多出传输方法、设备及计算机可读存储介质
US20230131579A1 (en) * 2020-06-24 2023-04-27 Huawei Technologies Co., Ltd. Wireless signal propagation prediction method and apparatus
CN113965291A (zh) * 2020-07-20 2022-01-21 中兴通讯股份有限公司 通信控制方法、基站、终端及存储介质
CN112449393A (zh) * 2020-12-23 2021-03-05 中国联合网络通信集团有限公司 小区切换方法及终端

Also Published As

Publication number Publication date
CN121533064A (zh) 2026-02-13

Similar Documents

Publication Publication Date Title
US20250133432A1 (en) Beam measurement method and apparatus, measurement configuration method and apparatus, terminal and network device
CN117676688A (zh) 测量上报方法、装置、终端及网络设备
EP4618609A1 (en) Model monitoring method and apparatus, terminal, and network side device
US20220216905A1 (en) Methods and devices for radio beam determination
WO2021016770A1 (zh) 一种信息处理方法、网络设备、用户设备
WO2021012166A1 (zh) 无线通信的方法和设备
CN116828605A (zh) 载波选择方法、设备、装置及存储介质
US20250097773A1 (en) Communication method and apparatus
WO2025044392A1 (zh) 性能监控方法和通信设备
WO2025010664A1 (zh) 一种时域移动性预测方法及装置、设备、芯片和存储介质
US20260089728A1 (en) Spatial filter determination method and apparatus, device, chip, and storage medium
US20220103269A1 (en) Methods and Devices for Inter-Cell Interference Estimation
CN118055467B (zh) 通信方法、设备、存储介质及产品
US20260113755A1 (en) Data set determination method and apparatus, device, chip and storage medium
WO2025166515A1 (zh) 一种无线通信方法及装置、设备、存储介质
WO2025152011A1 (zh) 通信方法、装置、设备、芯片及存储介质
WO2025160844A1 (zh) 一种无线通信方法及装置、设备、存储介质
WO2025160845A1 (zh) 一种无线通信方法及装置、设备、存储介质
WO2024255502A1 (zh) 信息传输方法、装置及存储介质
WO2024169462A1 (zh) 模型监控方法、装置、终端及网络侧设备
WO2026044515A1 (zh) 通信方法、终端、接入网设备、系统及存储介质
WO2026026897A1 (zh) 一种通信方法及相关装置
WO2025091466A1 (zh) 波束测量汇报的方法和装置
WO2025167428A1 (zh) 波束管理中ai/ml模型的数据请求方法及装置
WO2025010531A1 (zh) 信息收发方法与装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23944684

Country of ref document: EP

Kind code of ref document: A1

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112026000413

Country of ref document: BR

WWE Wipo information: entry into national phase

Ref document number: 2023944684

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE