WO2024092498A1 - 无线通信的方法及设备 - Google Patents

无线通信的方法及设备 Download PDF

Info

Publication number
WO2024092498A1
WO2024092498A1 PCT/CN2022/128935 CN2022128935W WO2024092498A1 WO 2024092498 A1 WO2024092498 A1 WO 2024092498A1 CN 2022128935 W CN2022128935 W CN 2022128935W WO 2024092498 A1 WO2024092498 A1 WO 2024092498A1
Authority
WO
WIPO (PCT)
Prior art keywords
instances
prediction
measurement
information
spatial filter
Prior art date
Application number
PCT/CN2022/128935
Other languages
English (en)
French (fr)
Inventor
曹建飞
刘文东
史志华
Original Assignee
Oppo广东移动通信有限公司
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 Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to PCT/CN2022/128935 priority Critical patent/WO2024092498A1/zh
Publication of WO2024092498A1 publication Critical patent/WO2024092498A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L27/00—Modulated-carrier systems

Definitions

  • the embodiments of the present application relate to the field of communications, and more specifically, to a method and device for wireless communications.
  • downlink beam management may include: downlink beam scanning, optimal beam reporting on the terminal side, downlink beam indication on the network side and other processes.
  • the network device scans all transmit beam directions through the downlink reference signal.
  • the terminal device can use different receive beams for measurement, so that all beam pairs can be traversed.
  • the terminal device needs to traverse all combinations of transmit beams and receive beams to select the optimal beam, which will bring a lot of overhead and delay.
  • the embodiments of the present application provide a method and device for wireless communication, which are conducive to reducing the overhead and delay caused by the beam scanning process.
  • a wireless communication method comprising:
  • the first communication device obtains a first measurement data set; wherein the first measurement data set includes at least one of the following: identification information of the spatial filter in M measurement instances, link quality information corresponding to the spatial filter in the M measurement instances; wherein M is a positive integer;
  • the first communication device inputs the first measurement data set into a first network model, and outputs a first prediction data set; wherein the first prediction data set includes at least one of the following: identification information of K spatial filters predicted in each of F prediction instances, link quality information corresponding to the K spatial filters predicted in each of the F prediction instances, and duration of the K spatial filters predicted in each of the F prediction instances; wherein F and K are both positive integers.
  • a communication device for executing the method in the first aspect.
  • the communication device includes a functional module for executing the method in the above-mentioned first aspect.
  • a communication device comprising a processor and a memory; the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory, so that the communication device executes the method in the above-mentioned first aspect.
  • a device for implementing the method in the first aspect.
  • the apparatus includes: a processor, configured to call and run a computer program from a memory, so that a device equipped with the apparatus executes the method in the first aspect described above.
  • a computer-readable storage medium for storing a computer program, wherein the computer program enables a computer to execute the method in the first aspect.
  • a computer program product comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method in the first aspect.
  • a computer program which, when executed on a computer, enables the computer to execute the method in the first aspect.
  • the first communication device can realize spatial filter prediction in the time domain based on the first network model, and the first communication device does not need to scan all deployed spatial filters, which is beneficial to reducing the overhead and delay caused by spatial filter scanning.
  • FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application.
  • FIG. 2 is a schematic diagram showing the connections of neurons in a neural network.
  • FIG. 3 is a schematic structural diagram of a neural network.
  • FIG4 is a schematic diagram of a convolutional neural network.
  • FIG5 is a schematic structural diagram of an LSTM unit.
  • FIG6 is a schematic diagram of an LSTM model provided in an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a downlink beam scanning process.
  • FIG8 is a schematic diagram of another downlink beam scanning process.
  • FIG9 is a schematic diagram of yet another downlink beam scanning process.
  • FIG10 is a schematic diagram of a wireless communication method provided according to an embodiment of the present application.
  • FIG. 11 is a schematic diagram of a data set B provided according to an embodiment of the present application.
  • FIG. 12 is a schematic diagram of a data set A provided according to an embodiment of the present application.
  • FIG13 is a flowchart of a beam prediction provided according to an embodiment of the present application.
  • FIG. 14 is a flowchart of another beam prediction method provided according to an embodiment of the present application.
  • Figure 15 shows that Set B provided according to an embodiment of the present application has different Tx beam configurations in different measurement instances.
  • Figure 16 is a schematic diagram of a DCI triggering multiple Set B measurements provided according to an embodiment of the present application.
  • Figure 17 is a schematic diagram of Set A with different Tx beam configurations in different prediction instances according to an embodiment of the present application.
  • Figure 18 is a schematic diagram of the Tx beam configurations X and Y of Set A appearing alternately according to an embodiment of the present application.
  • FIG19 is a schematic diagram of beam duration in time domain beam prediction according to an embodiment of the present application.
  • Figure 20 is a schematic block diagram of a communication device provided according to an embodiment of the present application.
  • Figure 21 is a schematic block diagram of a communication device provided according to an embodiment of the present application.
  • FIG. 22 is a schematic block diagram of a device provided according to an embodiment of the present application.
  • Figure 23 is a schematic block diagram of a communication system provided according to an embodiment of the present application.
  • GSM Global System of Mobile communication
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • LTE-A Advanced long term evolution
  • NR New Radio
  • LTE on unlicensed spectrum LTE-based ac
  • LTE-U LTE-based access to unlicensed spectrum
  • NR-U NR-based access to unlicensed spectrum
  • NTN Universal Mobile Telecommunication System
  • UMTS Universal Mobile Telecommunication System
  • WLAN Wireless Local Area Networks
  • IoT Wireless Fidelity
  • WiFi fifth-generation (5G) systems
  • 6G sixth-generation
  • D2D device to device
  • M2M machine to machine
  • MTC machine type communication
  • V2V vehicle to vehicle
  • SL sidelink
  • V2X vehicle to everything
  • the communication system in the embodiments of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, a standalone (SA) networking scenario, or a non-standalone (NSA) networking scenario.
  • CA carrier aggregation
  • DC dual connectivity
  • SA standalone
  • NSA non-standalone
  • the communication system in the embodiments of the present application can be applied to unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiments of the present application can also be applied to licensed spectrum, where the licensed spectrum can also be considered as an unshared spectrum.
  • the communication system in the embodiments of the present application can be applied to the FR1 frequency band (corresponding to the frequency band range of 410 MHz to 7.125 GHz), or to the FR2 frequency band (corresponding to the frequency band range of 24.25 GHz to 52.6 GHz), or to new frequency bands such as high-frequency frequency bands corresponding to the frequency band range of 52.6 GHz to 71 GHz or the frequency band range of 71 GHz to 114.25 GHz.
  • the embodiments of the present application describe various embodiments in conjunction with network equipment and terminal equipment, wherein the terminal equipment may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent or user device, etc.
  • UE user equipment
  • the terminal device can be a station (STATION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in the next generation communication system such as the NR network, or a terminal device in the future evolved Public Land Mobile Network (PLMN) network, etc.
  • STATION, ST in a WLAN
  • a cellular phone a cordless phone
  • Session Initiation Protocol (SIP) phone Session Initiation Protocol
  • WLL Wireless Local Loop
  • PDA Personal Digital Assistant
  • the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (for example, on airplanes, balloons and satellites, etc.).
  • the terminal device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city or a wireless terminal device in a smart home, an on-board communication device, a wireless communication chip/application specific integrated circuit (ASIC)/system on chip (SoC), etc.
  • VR virtual reality
  • AR augmented reality
  • a wireless terminal device in industrial control a wireless terminal device in self-driving
  • a wireless terminal device in remote medical a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city or a wireless terminal device in a smart home, an on-board communication device, a wireless communication chip/application specific integrated circuit (ASIC)
  • the terminal device may also be a wearable device.
  • Wearable devices may also be referred to as wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-sized, and fully or partially independent of smartphones, such as smart watches or smart glasses, as well as devices that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.
  • the network device may be a device for communicating with a mobile device.
  • the network device may be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a network device or a base station (gNB) or a transmission reception point (TRP) in a vehicle-mounted device, a wearable device, and an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.
  • AP access point
  • BTS base station
  • NodeB NodeB
  • NB base station
  • gNB base station
  • TRP transmission reception point
  • the network device may have a mobile feature, for example, the network device may be a mobile device.
  • the network device may be a satellite or a balloon station.
  • the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc.
  • the network device may also be a base station set up in a location such as land or water.
  • a network device can provide services for a cell, and a terminal device communicates with the network device through transmission resources used by the cell (for example, frequency domain resources, or spectrum resources).
  • the cell can be a cell corresponding to a network device (for example, a base station), and the cell can belong to a macro base station or a base station corresponding to a small cell.
  • the small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
  • the communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or referred to as a communication terminal or terminal).
  • the network device 110 may provide communication coverage for a specific geographic area and may communicate with terminal devices located in the coverage area.
  • FIG1 exemplarily shows a network device and two terminal devices.
  • the communication system 100 may include multiple network devices and each network device may include other number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.
  • the communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.
  • the device with communication function in the network/system in the embodiment of the present application can be called a communication device.
  • the communication device may include a network device 110 and a terminal device 120 with communication function, and the network device 110 and the terminal device 120 may be the specific devices described above, which will not be repeated here; the communication device may also include other devices in the communication system 100, such as other network entities such as a network controller and a mobile management entity, which is not limited in the embodiment of the present application.
  • the first communication device may be a terminal device, such as a mobile phone, a machine facility, a customer premises equipment (Customer Premise Equipment, CPE), industrial equipment, a vehicle, etc.; the second communication device may be a counterpart communication device of the first communication device, such as a network device, a mobile phone, an industrial equipment, a vehicle, etc.
  • the first communication device may be a terminal device, and the second communication device may be a network device (i.e., uplink communication or downlink communication); or, the first communication device may be a first terminal, and the second communication device may be a second terminal (i.e., sideline communication).
  • the "indication" mentioned in the embodiments 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, and B can be obtained through C; it can also mean that A and B have an association relationship.
  • corresponding may indicate a direct or indirect correspondence between two items, or an association relationship between the two items, or a relationship of indication and being indicated, configuration and being configured, etc.
  • pre-definition or “pre-configuration” can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device), and the present application does not limit the specific implementation method.
  • pre-definition can refer to what is defined in the protocol.
  • the “protocol” may refer to a standard protocol in the communication field, for example, it may be an evolution of an existing LTE protocol, NR protocol, Wi-Fi protocol, or a protocol related to other communication systems.
  • the present application does not limit the protocol type.
  • a neural network is a computational model consisting of multiple interconnected neuron nodes, where the connection between nodes represents the weighted value from input signal to output signal, called weight; each node performs weighted summation (SUM) on different input signals and outputs them through a specific activation function (f).
  • Figure 2 is a schematic diagram of a neuron structure, where a1, a2, ..., an represent input signals, w1, w2, ..., wn represent weights, f represents activation function, and t represents output.
  • a simple neural network is shown in Figure 3, which includes an input layer, a hidden layer, and an output layer. Through different connection methods, weights, and activation functions of multiple neurons, different outputs can be generated, thereby fitting the mapping relationship from input to output. Among them, each upper-level node is connected to all its lower-level nodes.
  • This neural network is a fully connected neural network, which can also be called a deep neural network (DNN).
  • DNN deep neural network
  • CNN convolutional neural network
  • input layer multiple convolutional layers
  • pooling layers fully connected layer and output layer, as shown in Figure 4.
  • Each neuron of the convolution kernel in the convolutional layer is locally connected to its input, and the maximum or average value of a certain layer is extracted by introducing the pooling layer, which effectively reduces the parameters of the network and mines the local features, so that the convolutional neural network can converge quickly and obtain excellent performance.
  • Deep learning uses a deep neural network with multiple hidden layers, which greatly improves the network's ability to learn features and fits complex nonlinear mappings from input to output. Therefore, it is widely used in speech and image processing.
  • deep learning also includes common basic structures such as convolutional neural networks (CNN) and recurrent neural networks (RNN) for different tasks.
  • CNN convolutional neural networks
  • RNN recurrent neural networks
  • the basic structure of a convolutional neural network includes: input layer, multiple convolutional layers, multiple pooling layers, fully connected layer and output layer, as shown in Figure 4.
  • Each neuron of the convolution kernel in the convolutional layer is locally connected to its input, and the maximum or average value of a certain layer is extracted by introducing the pooling layer, which effectively reduces the parameters of the network and mines the local features, so that the convolutional neural network can converge quickly and obtain excellent performance.
  • RNN is a neural network that models sequential data and has achieved remarkable results in the field of natural language processing, such as machine translation and speech recognition. Specifically, the network device memorizes the information of the past moment and uses it in the calculation of the current output, that is, the nodes between the hidden layers are no longer disconnected but connected, and the input of the hidden layer includes not only the input layer but also the output of the hidden layer at the previous moment.
  • Commonly used RNNs include structures such as Long Short-Term Memory (LSTM) and gated recurrent unit (GRU).
  • Figure 5 shows a basic LSTM unit structure, which can include a tanh activation function. Unlike RNN, which only considers the most recent state, the cell state of LSTM determines which states should be retained and which states should be forgotten, solving the defects of traditional RNN in long-term memory.
  • millimeter wave frequency band communication is introduced, and the corresponding beam management mechanism is also introduced, including uplink and downlink beam management.
  • Downlink beam management includes downlink beam scanning, optimal beam reporting on the UE side, and downlink beam indication on the network side.
  • the downlink beam scanning process may refer to: the network device scans different transmit beam directions through the downlink reference signal.
  • the UE may use different receive beams for measurement, so that all beam pairs can be traversed, and the UE calculates the Layer 1 Reference Signal Receiving Power (L1-RSRP) value corresponding to each beam pair.
  • L1-RSRP Layer 1 Reference Signal Receiving Power
  • the downlink reference signal includes a synchronization signal block (Synchronization Signal Block, SSB) and/or a channel state information reference signal (Channel State Information Reference Signal, CSI-RS).
  • SSB Synchronization Signal Block
  • CSI-RS Channel State Information Reference Signal
  • AI/ML-based beam management can predict downlink beams in both spatial and temporal domains.
  • Beam prediction in the spatial domain also called beam management example 1 (BM-Case1):
  • the downlink beam in data set A (Set A) is predicted in the spatial domain by measuring the beams in data set B (Set B).
  • Set B is either a subset of Set A, or Set B and Set A are two different beam sets.
  • Set B can be understood as a partial subset of beams (pairs);
  • Set A can be understood as the full set of beams (pairs).
  • Beam prediction in the time domain also called beam management example 2 (BM-Case2):
  • the downlink beam in the data set A (Set A) is predicted in the time domain by using the beams in the historical measurement data set B (Set B).
  • Set B is either a subset of Set A, the same as Set A, or a subset of Set A.
  • Set B can be understood as a partial subset of the beam (pair);
  • Set A can be understood as the full set of beams (pairs).
  • a neural network (NN) model can be trained and obtained through the processes of data set construction, training, verification and testing. This application assumes that the NN models have been trained in advance through offline training or online training. It should be noted that offline training and online training are not mutually exclusive.
  • the network (NW) can obtain a static training result through offline training of the data set, which can be referred to as offline training here.
  • the NN model can continue to collect more data and perform real-time online training to optimize the parameters of the NN model to achieve better inference and prediction results.
  • This application takes the prediction of time-domain beams (pairs) and their performance as an example, and selects the LSTM model, as shown in Figure 6.
  • the LSTM model can be understood as extending M instances (instance) as input in time sequence, which is equivalent to the cascade of M LSTM units.
  • the input of each LSTM unit is the L1-RSRP of the beam (pair) of instance m (Set Bm) in data set B, where 1 ⁇ m ⁇ M.
  • the index of the beam (pair) of Set Bm can be implicitly input through the fixed order of L1-RSRP.
  • the LSTM model can predict the optimal beam (pair) of the next F instances, the performance of the optimal beam (pair) (i.e., link quality information), and the duration (dwelling time) of the optimal beam (pair).
  • millimeter wave frequency band communication is introduced, that is, the beam management mechanism is introduced.
  • the beam management mechanism includes uplink beam management and downlink beam management.
  • the downlink beam management mechanism includes downlink beam scanning (beam sweeping), UE beam measurement and reporting (measurement&reporting), network equipment for downlink beam indication (beam indication) and other processes.
  • the downlink beam scanning process may include three processes, namely P1, P2 and P3 processes.
  • the P1 process refers to the network device scanning different transmit beams and the UE scanning different receive beams;
  • the P2 process refers to the network device scanning different transmit beams and the UE using the same receive beam;
  • the P3 process refers to the network device using the same transmit beam and the UE scanning different receive beams.
  • the network device completes the above beam scanning process by sending a downlink reference signal.
  • the downlink reference signal may include but is not limited to a synchronization signal block (Synchronization Signal Block, SSB) and/or a channel state information reference signal (Channel State Information Reference Signal, CSI-RS).
  • FIG. 7 is a schematic diagram of the P1 process (or the downlink full scan process)
  • FIG. 8 is a schematic diagram of the P2 process
  • FIG. 9 is a schematic diagram of the P3 process.
  • the network device traverses all transmit beams to send downlink reference signals, and the UE side traverses all receive beams to perform measurements and determine corresponding measurement results.
  • the network device traverses all transmit beams to send downlink reference signals, and the UE side uses a specific receive beam to perform measurements to determine the corresponding measurement results.
  • the network device may use a specific transmit beam to send a downlink reference signal, and the UE side traverses all receive beams to perform measurements and determine corresponding measurement results.
  • L1-RSRP can also be replaced by other beam link indicators, such as Layer 1 Signal to Interference plus Noise Ratio (L1-SINR), Layer 1 Reference Signal Received Quality (L1-RSRQ), etc.
  • L1-SINR Layer 1 Signal to Interference plus Noise Ratio
  • L1-RSRQ Layer 1 Reference Signal Received Quality
  • the network device After the network device learns the optimal beam reported by the terminal device, it can carry the Transmission Configuration Indicator (TCI) status (which contains the transmit beam using the downlink reference signal as a reference) through Media Access Control (MAC) or Downlink Control Information (DCI) signaling to complete the beam indication to the UE.
  • TCI Transmission Configuration Indicator
  • MAC Media Access Control
  • DCI Downlink Control Information
  • the UE uses the receive beam corresponding to the transmit beam for downlink reception.
  • the UE For the beam scanning process of NR, if it is a periodic full-beam scanning process of the downlink, that is, the periodic P1 process, the UE needs to periodically traverse all the combinations of transmit beams and receive beams, which will bring a lot of overhead and delay. For example, suppose NW deploys 64 different downlink transmission directions in FR2 (carried by up to 64 SSBs), and the UE uses multiple antenna panels (including only one receive beam panel) to perform receive beam scanning simultaneously when receiving, and each antenna panel has 4 receive beams. From a time perspective, each SSB period is about 20ms, so it takes 4 SSB periods to complete the measurement of 4 receive beams (assuming that multiple receive antenna panels can be used for beam scanning), then it will take at least 80ms.
  • the above process is repeated every 80 milliseconds.
  • this application proposes a time domain beam prediction solution based on AI/ML model, which is beneficial to reduce the overhead and delay caused by the beam scanning process.
  • FIG. 10 is a schematic flow chart of a wireless communication method 200 according to an embodiment of the present application. As shown in FIG. 10 , the wireless communication method 200 may include at least part of the following contents:
  • the first communication device acquires a first measurement data set; wherein the first measurement data set includes at least one of the following: identification information of the spatial filter in M measurement instances, link quality information corresponding to the spatial filter in the M measurement instances; wherein M is a positive integer;
  • the first communication device inputs the first measurement data set into the first network model, and outputs a first prediction data set; wherein, the first prediction data set includes at least one of the following: identification information of K spatial filters predicted in each of F prediction instances, link quality information corresponding to the K spatial filters predicted in each of the F prediction instances, and duration of the K spatial filters predicted in each of the F prediction instances; wherein F and K are both positive integers.
  • a spatial filter may also be referred to as a beam, a beam pair, a spatial relation, a spatial setting, a spatial domain filter, or a reference signal.
  • the spatial filter includes a transmit spatial filter.
  • the transmit spatial filter may also be referred to as a transmit beam (Tx beam) or a transmitter spatial filter, and the above terms may be interchangeable.
  • the spatial filter includes a receive spatial filter.
  • the receive spatial filter may also be referred to as a transmit beam (Rx beam) or a receive-end spatial filter, and the above terms may be interchangeable.
  • the spatial filter includes a transmit spatial filter and a receive spatial filter.
  • the combination of the transmit spatial filter and the receive spatial filter can also be called a beam pair, a spatial filter pair, or a spatial filter group, and the above terms can be interchangeable.
  • the identification information of the spatial filter may be an index or an identification of the spatial filter.
  • the identification information of the transmit spatial filter may be an index or an identification of the transmit spatial filter.
  • the identification information of the receiving spatial filter may be an index or an identification of the receiving spatial filter.
  • the identification information of the combination of the transmit spatial filter and the receive spatial filter may be a combination index.
  • the link quality information may include but is not limited to at least one of the following:
  • L1-RSRP Layer 1 Reference Signal Receiving Power
  • L1-RSRQ Layer 1 Reference Signal Receiving Quality
  • L1-SINR Layer 1 Signal to Interference plus Noise Ratio
  • a measurement instance may correspond to one or more time units, wherein the time unit may include but is not limited to one of the following: a time slot, a mini-time slot, a frame, a subframe, a symbol, a millisecond, and a microsecond.
  • a prediction instance may correspond to one or more time units, wherein the time unit may include but is not limited to one of the following: a time slot, a mini-time slot, a frame, a subframe, a symbol, a millisecond, and a microsecond.
  • the K spatial filters are determined based on link quality information in each prediction instance.
  • K spatial filters are obtained based on the order of link quality information in each prediction instance from high to low.
  • the spatial filters corresponding to the first K link quality information in the order of link quality information in each prediction instance from high to low are the K spatial filters in the prediction instance.
  • the K spatial filters are spatial filters corresponding to link quality information in each prediction instance whose link quality information is greater than or equal to a first threshold.
  • the first threshold is agreed upon by a protocol, or configured by a network device.
  • the value of K includes but is not limited to one of the following: 1, 2, 4, 8.
  • the dwelling time of the K spatial filters may be the time during which the link quality information corresponding to the K spatial filters remains stable.
  • the identification information of the spatial filters in the M measurement instances can be implicitly indicated by the link quality information corresponding to the spatial filters in the M measurement instances.
  • the first communication device is a terminal device, or the first communication device is a network device.
  • the first network model may be an LSTM model, as shown in FIG6 , which can be understood as extending M measurement instances (instance) as input in time sequence, which is equivalent to a cascade of M LSTM units.
  • the input of each LSTM unit is the link quality information (such as L1-RSRP) of the beam (pair) of the measurement instance m (Set B m) in the data set B (i.e., the first measurement data set), where 1 ⁇ m ⁇ M.
  • the spatial filters in each of the M measurement instances are part of all the spatial filters. Specifically, all the spatial filters are all the deployed spatial filters. That is, in each measurement instance, all the deployed spatial filters will not be traversed. For example, assuming that the network device (NW) deploys 64 different downlink transmission beams (transmission beam, Tx beam) in FR2, the number of downlink transmission beams in each of the M measurement instances is less than 64.
  • the configuration of the spatial filter in each of the M measurement instances is the same. That is, the spatial filter in each of the M measurement instances is the same.
  • the identifier and number of the spatial filter in each of the M measurement instances are the same.
  • the M measurement instances are recorded as Set B#1, Set B#2, ..., Set B#M-1, and Set B#M.
  • the indexes of the transmission-receiving (Tx-Rx) beam pairs in Set B#1 are from index#0 to index#15
  • the indexes of the transmission-receiving (Tx-Rx) beam pairs in Set B#2 are also from index#0 to index#15
  • the indexes of the transmission-receiving (Tx-Rx) beam pairs in Set B#M-1 are also from index#0 to index#15
  • the indexes of the transmission-receiving (Tx-Rx) beam pairs in Set B#M are also from index#0 to index#15.
  • the configuration of the spatial filters in at least some of the M measurement instances is different. That is, the spatial filters in at least some of the M measurement instances are different.
  • the identifiers of the spatial filters in at least some of the M measurement instances are different.
  • the number of spatial filters in at least some of the M measurement instances is different.
  • the identifiers and numbers of the spatial filters in at least some of the M measurement instances are different.
  • the M measurement instances are recorded as Set B#1, Set B#2, ..., Set B#M-1, and Set B#M.
  • the transmit-receive (Tx-Rx) beam pairs in Set B#1 are indexed from index#0 to index#15
  • the transmit-receive (Tx-Rx) beam pairs in Set B#2 are indexed from index#16 to index#19, ...
  • the transmit-receive (Tx-Rx) beam pairs in Set B#M are indexed from index#48 to index#63.
  • some of the spatial filters in different measurement instances in the M measurement instances are the same. That is, the spatial filters in different measurement instances in the M measurement instances may overlap to a certain extent.
  • the overlapping spatial filters may be spatial filters that are easy to select. Thus, the measurement quality may be improved.
  • the possibility of being selected is not exactly the same (generally speaking, the transmitting beam with a more moderate downtilt angle on the NW side is easy to be selected). Therefore, for beam pairs that are easy to be selected by UE, more measurements can be performed; for beam pairs that are not easily selected, fewer measurements can be performed, or even no measurement can be performed.
  • the M measurement instances are recorded as Set B#1, Set B#2, ..., Set B#M-1, and Set B#M.
  • the Tx-Rx beam pairs in Set B#1 are indexed from index#0 to index#15
  • the Tx-Rx beam pairs in Set B#2 are indexed from index#14 to index#19. That is, the Tx-Rx beam pairs in Set B#1 and Set B#2 both contain index#14 and index#15.
  • the M measurement instances are arranged at equal intervals in the time domain. That is, the M measurement instances may be periodic measurement instances.
  • period information corresponding to the measurement instance may be configured through RRC signaling.
  • the M measurement instances correspond to periodic spatial filter measurements within a first duration.
  • periodic information corresponding to the spatial filter measurements may be configured via RRC signaling.
  • the first duration is agreed upon by a protocol, or the first duration is configured by a network device.
  • the M measurement instances are arranged at unequal intervals in the time domain. For example, as shown in FIG. 11 , the time intervals (time gaps) between different measurement instances in the M measurement instances are different. Thus, it is possible to more flexibly adapt to changes in the channel.
  • the intervals of the M measurement instances in the time domain are determined based on the moving speed of the terminal device. For example, when the moving speed of the UE is fast, the frequency of measurement can be increased (i.e., the time interval between different measurement instances is small); when the moving speed of the UE is slow, the frequency of measurement can be reduced (i.e., the time interval between different measurement instances is large). Thus, the UE measures approximately the same number of times over the same moving distance.
  • different measurement instances in the M measurement instances correspond to the same period and different offsets.
  • the network can configure the same period (periodicity) and different offsets (offset) for different measurement instances.
  • the M measurement instances are measurement instances activated by downlink control information (DCI) or media access control layer control element (MAC CE) among multiple measurement instances of semi-persistent scheduling (SPS).
  • DCI downlink control information
  • MAC CE media access control layer control element
  • the M measurement instances are measurement instances dynamically triggered by DCI in a plurality of pre-configured measurement instances. That is, in this embodiment, one DCI can trigger the non-periodic CSI-RS of M measurement instances.
  • one DCI can trigger the non-periodic CSI-RS of M measurement instances. The advantage of this is that only one DCI (minimum signaling overhead) can be used to trigger the measurement of M measurement instances.
  • the M measurement instances are measurement instances corresponding to a set of measurement configurations activated by DCI or MAC CE in multiple measurement configurations, or the M measurement instances are measurement instances corresponding to a current measurement configuration in multiple measurement configurations activated by DCI or MAC CE and used in turn.
  • the multiple measurement configurations are configured in advance or semi-statically by the network device.
  • the network device may configure the M measurement instances in the first measurement data set, or the network device may activate the M measurement instances in the first measurement data set, or the network device may update the M measurement instances in the first measurement data set.
  • the network device may configure multiple measurement instances through RRC signaling, and activate the M measurement instances in the first measurement data set through MAC CE signaling.
  • the first communication device may measure M measurement instances to obtain the first measurement data set.
  • the first communication device may obtain measurement results of the terminal device for M measurement instances to obtain the first measurement data set.
  • the spatial filter in each measurement instance in the F prediction instances is a partial spatial filter in all spatial filters.
  • the all spatial filters are all deployed spatial filters. That is, in each prediction instance, all deployed spatial filters will not be traversed. For example, assuming that the network equipment (NW) deploys 64 different downlink transmit beams in FR2, the number of downlink transmit beams in each prediction instance in the F prediction instances is less than 64.
  • NW network equipment
  • the range of the predicted spatial filter can be limited, thereby controlling the range of the spatial filters that the model can select, focusing only on some key spatial filters, and improving the accuracy of the predicted spatial filters.
  • the configuration of the spatial filter in each of the F prediction instances is the same. That is, the spatial filter in each of the F prediction instances is the same. For example, the identification and quantity of the spatial filter in each of the F prediction instances are the same.
  • the F prediction instances are recorded as Set A#1, Set A#2, ..., Set A#F-1, and Set A#F.
  • the transmit-receive (Tx-Rx) beam pair indexes in Set A#1 are from index#0 to index#20
  • the transmit-receive (Tx-Rx) beam pair indexes in Set A#2 are also from index#0 to index#20
  • the transmit-receive (Tx-Rx) beam pair indexes in Set A#F-1 are also from index#0 to index#20
  • the transmit-receive (Tx-Rx) beam pair indexes in Set A#F are also from index#0 to index#20.
  • the configuration of the spatial filters in at least some of the prediction instances in the F prediction instances is different. That is, the spatial filters in at least some of the prediction instances in the F prediction instances are different.
  • the identification of the spatial filters in at least some of the prediction instances in the F prediction instances is different.
  • the number of spatial filters in at least some of the prediction instances in the F prediction instances is different.
  • the identification and number of spatial filters in at least some of the prediction instances in the F prediction instances are different.
  • the F prediction instances are recorded as Set A#1, Set A#2, ..., Set A#F-1, and Set A#F.
  • the transmit-receive (Tx-Rx) beam pair indexes (index) in Set A#1 are from index#0 to index#35
  • the transmit-receive (Tx-Rx) beam pair indexes (index) in Set A#2 are from index#0 to index#15, ...
  • the transmit-receive (Tx-Rx) beam pair indexes (index) in Set A#F are from index#0 to index#27.
  • some or all of the spatial filters in different prediction instances in the F prediction instances are the same. That is, the spatial filters in different prediction instances in the F prediction instances may overlap to a certain extent.
  • the overlapping spatial filters may be spatial filters that are easy to select. Thus, the prediction quality can be improved.
  • the possibility of being selected is not exactly the same (generally speaking, the transmitting beam with a more moderate downtilt angle on the NW side is easy to be selected). Therefore, for beam pairs that are easy to be selected by UE, more measurements can be performed; for beam pairs that are not easily selected, fewer measurements can be performed, or even no measurement can be performed.
  • the F prediction instances are arranged at equal intervals in the time domain. That is, the F prediction instances may be periodic prediction instances.
  • periodic information corresponding to the prediction instance may be configured through RRC signaling.
  • the F prediction instances correspond to periodic spatial filter predictions within the second duration.
  • periodic information corresponding to the spatial filter predictions may be configured via RRC signaling.
  • the second duration is agreed upon by a protocol, or the second duration is configured by a network device.
  • the F prediction instances are arranged at unequal intervals in the time domain. For example, as shown in FIG. 12 , the time intervals (time gaps) between different prediction instances in the F prediction instances are different. Thus, it is possible to adapt to channel changes more flexibly.
  • the intervals of the F prediction instances in the time domain are determined based on the moving speed of the terminal device. For example, when the moving speed of the UE is fast, the prediction frequency can be increased (i.e., the time intervals between different prediction instances are small); when the moving speed of the UE is slow, the prediction frequency can be reduced (i.e., the time intervals between different prediction instances are large). This achieves approximately the same number of predictions over the same moving distance.
  • different prediction instances in the F prediction instances correspond to the same period and different offsets.
  • the network can configure the same period (periodicity) and different offsets (offset) for different prediction instances.
  • the F prediction instances are prediction instances activated by DCI or MAC CE among multiple prediction instances of SPS.
  • the F prediction instances are prediction instances dynamically triggered by DCI from among multiple pre-configured prediction instances. That is, in this embodiment, one DCI can trigger F prediction instances from multiple pre-configured prediction instances.
  • DCI minimum signaling overhead
  • the F prediction instances are prediction instances corresponding to a set of prediction configurations activated by DCI or MAC CE in multiple sets of prediction configurations, or the F prediction instances are prediction instances corresponding to a current prediction configuration in multiple sets of prediction configurations activated by DCI or MAC CE and used in turn.
  • the multiple sets of prediction configurations are configured in advance or semi-statically by the network device.
  • the first network model may infer identification information of the K spatial filters and link quality information corresponding to the K spatial filters.
  • the first network model may infer identification information of the K spatial filters, link quality information corresponding to the K spatial filters, and durations of the K spatial filters.
  • the first network model can also infer the duration (dwelling time) of the optimal beam pair. For example, as shown in Figure 12, there is a period of time between Set A#1 and Set A#2, which can be defined as time gap #1.
  • the first network model infers the optimal K beam pairs for the prediction instance (instance) of Set A#1, and the first network model can also predict the time for the L1-RSRP of the K beam pairs to remain stable.
  • the stability here can be defined from the relative quality, that is, the beam quality ranking, such as the time for the top-1 beam pair to remain first.
  • L1-RSRP L1-RSRP
  • a certain threshold such as 3dB.
  • the advantage is that the duration of the effective beam pair can be more carefully characterized, thereby providing more beam information to the network (NW), so that the NW can adjust the beam in advance or delay the adjustment in the subsequent beam indication.
  • the network device may configure F prediction instances in the first prediction data set, or the network device may activate F prediction instances in the first prediction data set, or the network device may update F prediction instances in the first prediction data set.
  • the network device may configure multiple prediction instances through RRC signaling, and activate F prediction instances in the first prediction data set through MAC CE signaling.
  • the first communication device sends first information
  • the first information includes at least one of the following: identification information of the K spatial filters predicted in each of the F prediction instances, link quality information corresponding to the K spatial filters predicted in each of the F prediction instances, and duration of the K spatial filters predicted in each of the F prediction instances.
  • the first communication device may report prediction information in F prediction instances.
  • the first communication device sends the first information to the second communication device, wherein the first communication device is a terminal device and the second communication device is a network device. That is, after the first network model completes the prediction of the time-domain spatial filter, the terminal device needs to report the prediction results of the first network model in F prediction instances to the network device.
  • the first information is carried by one of the following:
  • Uplink Control Information UCI
  • MAC CE MAC CE signaling
  • RRC Radio Resource Control
  • the link quality information corresponding to the K spatial filters is sent in a differential manner.
  • the terminal device can send the prediction results of the F prediction instances to the network device through a channel state information (CSI) report, wherein the prediction results of the F prediction instances include 4 Tx-Rx beam pairs and L1-RSRPs corresponding to the 4 Tx-Rx beam pairs.
  • CSI channel state information
  • the terminal device may report the prediction results of F prediction instances through one CSI report. That is, the terminal device may report all the contents in Table 1 or Table 2 through one CSI report.
  • the terminal device may report the prediction results of F prediction instances through multiple CSI reports. For example, the terminal device reports the prediction result of one prediction instance in each CSI report. That is, the terminal device may report the prediction results of F prediction instances in Table 1 through F CSI reports, or the terminal device may report the prediction results of F prediction instances in Table 2 through F CSI reports.
  • Differential L1-RSRP#2 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#3 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#4 is the difference relative to L1-RSRP#1
  • L1-RSRP#1 is the L1-RSRP corresponding to Tx-Rx beam pair#1
  • Differential L1-RSRP#2 is the L1-RSRP corresponding to Tx-Rx beam pair#2
  • Differential L1-RSRP#3 is the L1-RSRP corresponding to Tx-Rx beam pair#3
  • Differential L1-RSRP#4 is the L1-RSRP corresponding to Tx-Rx beam pair#4.
  • Differential L1-RSRP#2 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#3 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#4 is the difference relative to L1-RSRP#1
  • L1-RSRP#1 is the L1-RSRP corresponding to Tx-Rx beam pair#1
  • Differential L1-RSRP#2 is the L1-RSRP corresponding to Tx-Rx beam pair#2
  • Differential L1-RSRP#3 is the L1-RSRP corresponding to Tx-Rx beam pair#4.
  • Beam dwelling time#1 is the beam duration of Tx-Rx beam pair#1
  • Beam dwelling time#2 is the beam duration of Tx-Rx beam pair#2
  • Beam dwelling time#3 is the beam duration of Tx-Rx beam pair#3
  • Beam dwelling time#4 is the beam duration of Tx-Rx beam pair#4.
  • the first communication device receives second information determined based on the first information
  • the second information is used to indicate the identification information of the spatial filter used in each of the F prediction instances, or the second information is used to indicate the identification information of the spatial filter used in the i-th prediction instance; or the second information is used to indicate the identification information and duration of the spatial filter used in each of the F prediction instances, or the second information is used to indicate the identification information and duration of the spatial filter used in the i-th prediction instance;
  • i is a positive integer, and 1 ⁇ i ⁇ F.
  • the first communication device may acquire the identification information of the spatial filter used in the prediction instance through the second information, or the first communication device may acquire the identification information and duration of the spatial filter used in the prediction instance through the second information.
  • the second information is used to indicate the identification information and duration of the spatial filter used in each of the F prediction instances, or the second information is used to indicate the identification information and duration of the spatial filter used in the i-th prediction instance.
  • a first communication device receives the second information sent by a second communication device, wherein the first communication device is a terminal device and the second communication device is a network device. That is, the network device can perform beam indication based on the prediction result of the first network model reported by the terminal device.
  • the second information is carried by one of the following:
  • DCI Downlink Control Information
  • the network device based on the prediction results in the F prediction instances reported by the terminal device, there are at least two ways for the network device to indicate the beam.
  • the first way is that the network device performs beam indication in batches according to the report of the terminal device, such as performing F beam information indications under the beam prediction of F prediction instances, that is, indicating the beam used in each of the F prediction instances respectively; wherein the beam information can be the index of the beam pair or the index of the transmitting beam in the beam pair (in NR, it is generally referred to by the resource index of SSB or CSI-RS).
  • Another way is to perform a one-time beam indication, that is, the network device indicates the beam information of F prediction instances to the terminal device at one time, that is, indicates the beam used in each of the F prediction instances at one time.
  • the advantage of a one-time beam indication is that the signaling overhead of the beam indication can be greatly reduced.
  • the NW indicates the beam information used in each of the F prediction instances at one time. If the beam information is a Tx-Rx beam pair index, then the MAC CE or DCI should include Tx-Rx beam pair index#1, Tx-Rx beam pair index#2, ..., Tx-Rx beam pair index#F. If the beam information is a Tx beam index, then the MAC CE or DCI should include Tx beam index(CSI-RS/SSB)#1, Tx beam index(CSI-RS/SSB)#2, ..., Tx beam index(CSI-RS/SSB)#F.
  • the meaning in the time domain is that whenever a prediction instance arrives, the NW will change to the indicated transmit beam, and the UE should also change the corresponding receive beam.
  • the NW may choose to indicate the beam information and beam duration used in each of the F prediction instances to the UE at one time.
  • the beam information is a Tx-Rx beam pair index
  • the MAC CE or DCI i.e., the second information
  • the MAC CE or DCI should include (Tx beam index (CSI-RS/SSB) #1, Application time #1), (Tx beam index (CSI-RS/SSB) #2, Application time #2), ..., (Tx beam index (CSI-RS/SSB) #F, Application time #F).
  • Tx beam index (CSI-RS/SSB) #1, Application time #1 (Tx beam index (CSI-RS/SSB) #2, Application time #2), ..., (Tx beam index (CSI-RS/SSB) #F, Application time #F).
  • Tx beam index (CSI-RS/SSB) #2 #2
  • Application time #2 Application time #2
  • Tx beam index (CSI-RS/SSB) #F Application time #F.
  • each indicated beam pair takes effect from the predicted instance, and its effective duration is the beam duration (beam dwelling time) indicated by the application time (application time).
  • the first communication device sends first capability information
  • the first capability information includes at least one of the following: the maximum number of spatial filters supported by the first measurement data set, the maximum number of measurement instances supported by the first measurement data set, the maximum number of spatial filters supported by the first prediction data set, the maximum number of prediction instances supported by the first prediction data set, whether the prediction and reporting of the duration of the spatial filter are supported, and whether the identification information of indicating the spatial filters in multiple prediction instances at one time is supported.
  • a first communication device sends the first capability information to a second communication device, wherein the first communication device is a terminal device and the second communication device is a network device.
  • the terminal device can report the first capability information, and the network device can configure, activate or update M measurement instances and/or F prediction instances based on the first capability information, and/or the network device can indicate the identification information of the spatial filter used in each of the F prediction instances based on the first capability information.
  • the first capability information can be carried by one of the following: UCI, MAC CE signaling, RRC signaling.
  • the first measurement data set is Set B
  • the first prediction data set is Set A
  • the terminal device can report the following capability information:
  • the spatial domain capacity of Set B the maximum number of beam pairs that can be measured (at one time);
  • Time domain capacity of Set B the maximum number of measurement instances supported
  • the spatial domain capacity of Set A the maximum number of beam pair predictions supported (at one time);
  • the time domain capacity of Set A the maximum number of prediction instances supported
  • the signaling interaction process between the network device (NW) and the terminal device (UE) to complete the time domain beam prediction can be as shown in Figure 13, which includes the UE's capability reporting, the NW's configuration and activation of the beam measurement set (Set B) and the beam prediction set (Set A), the UE's measurement of the beam measurement set, the UE's inference of the beam prediction set using the first network model, the UE's reporting of the prediction result, the NW's indication of the beam used in the prediction instance, etc.
  • the beam measurement set (Set B) is the above-mentioned first measurement data set
  • the beam prediction set (Set A) is the above-mentioned first prediction data set.
  • the first communication device sends third information
  • the third information is used to indicate the identification information of the spatial filter used in each of the F prediction instances, or the third information is used to indicate the identification information of the spatial filter used in the i-th prediction instance; or the third information is used to indicate the identification information and duration of the spatial filter used in each of the F prediction instances, or the third information is used to indicate the identification information and duration of the spatial filter used in the i-th prediction instance;
  • i is a positive integer, and 1 ⁇ i ⁇ F.
  • the first communication device may indicate the identification information of the spatial filter used in the prediction instance through the third information.
  • the third information is used to indicate the identification information and duration of the spatial filter used in each of the F prediction instances, or the third information is used to indicate the identification information and duration of the spatial filter used in the i-th prediction instance.
  • the first communication device sends the third information to the second communication device, wherein the first communication device is a network device and the second communication device is a terminal device. That is, the network device can perform beam indication based on the prediction result of the first network model.
  • the third information is carried via one of: DCI, MAC CE signaling.
  • the network device based on the prediction results of the F prediction instances predicted by the network device, there are at least two ways for the network device to indicate the beam.
  • the first way is that the network device performs beam indication in batches according to the prediction results, such as performing F beam information indications under the beam prediction of F prediction instances, that is, indicating the beam used in each of the F prediction instances respectively; wherein the beam information can be the index of the beam pair, or the index of the transmitting beam in the beam pair (in NR, it is generally referred to by the resource index of SSB or CSI-RS).
  • Another way is to perform a one-time beam indication, that is, the network device indicates the beam information of F prediction instances to the terminal device at one time, that is, indicates the beam used in each of the F prediction instances at one time.
  • the advantage of a one-time beam indication is that the signaling overhead of the beam indication can be greatly reduced.
  • the network device indicates the beam information used in each of the F prediction instances at one time. If the beam information is a Tx-Rx beam pair index, then the MAC CE or DCI (i.e., the third information) should include Tx-Rx beam pair index#1, Tx-Rx beam pair index#2, ..., Tx-Rx beam pair index#F. If the beam information is a Tx beam index, then the MAC CE or DCI (i.e., the third information) should include Tx beam index(CSI-RS/SSB)#1, Tx beam index(CSI-RS/SSB)#2, ..., Tx beam index(CSI-RS/SSB)#F.
  • the meaning in the time domain is that whenever a prediction instance arrives, the NW will change to the indicated transmit beam, and the UE should also change the corresponding receive beam.
  • the network device may choose to indicate the beam information and beam duration used in each of the F prediction instances to the UE at one time.
  • the beam information is a Tx-Rx beam pair index
  • the MAC CE or DCI i.e., the third information
  • the MAC CE or DCI should include (Tx beam index (CSI-RS/SSB) #1, Application time #1), (Tx beam index (CSI-RS/SSB) #2, Application time #2), ..., (Tx beam index (CSI-RS/SSB) #F, Application time #F).
  • Tx beam index (CSI-RS/SSB) #1, Application time #1 (Tx beam index (CSI-RS/SSB) #2, Application time #2), ..., (Tx beam index (CSI-RS/SSB) #F, Application time #F).
  • Tx beam index (CSI-RS/SSB) #2 #2
  • Application time #2 Application time #2
  • Tx beam index (CSI-RS/SSB) #F Application time #F.
  • each indicated beam pair takes effect from the predicted instance, and its effective duration is the beam duration (beam dwelling time) indicated by the application time (application time).
  • the first communication device receives first capability information
  • the first capability information includes at least one of the following: the maximum number of spatial filters supported by the first measurement data set, the maximum number of measurement instances supported by the first measurement data set, the maximum number of spatial filters supported by the first prediction data set, the maximum number of prediction instances supported by the first prediction data set, whether the prediction and reporting of the duration of the spatial filter are supported, and whether the identification information of indicating the spatial filters in multiple prediction instances at one time is supported.
  • a first communication device receives the first capability information sent by a second communication device, wherein the first communication device is a network device and the second communication device is a terminal device.
  • the terminal device can report the first capability information, and the network device can configure, activate or update M measurement instances and/or F prediction instances based on the first capability information, and/or the network device can indicate the identification information of the spatial filter used in each of the F prediction instances based on the first capability information.
  • the first capability information can be carried by one of the following: UCI, MAC CE signaling, RRC signaling.
  • the first measurement data set is Set B
  • the first prediction data set is Set A
  • the terminal device can report the following capability information:
  • the spatial domain capacity of Set B the maximum number of beam pairs that can be measured (at one time);
  • Time domain capacity of Set B the maximum number of measurement instances supported
  • the spatial domain capacity of Set A the maximum number of beam pair predictions supported (at one time);
  • the time domain capacity of Set A the maximum number of prediction instances supported
  • the UE when the first communication device is a network device (NW), assuming that the first measurement data set is Set B, the UE needs to measure M measurement instances of Set B. Then, all measurement results are reported to the model on the NW side.
  • NW network device
  • Tx-Rx beam pair the transmit-receive beam pair
  • Table 3 UE reports L1-RSRP values according to the time domain order of Set B
  • Example 2 Sorting by the performance (such as L1-RSRP) of each transmit-receive beam pair (Tx-Rx beam pair) in Set B, generally sorting by performance from high to low. As shown in Table 4, first is the Tx-Rx beam pair ID in Set B, then the absolute value of the performance of the highest beam pair, such as the absolute value quantification of L1-RSRP. For the performance of the beam pair with non-highest performance, it can be quantified by differential means, that is, reporting the difference in performance compared to the highest performance.
  • L1-RSRP L1-RSRP
  • Table 4 UE reports L1-RSRP values according to the time domain order of Set B
  • Differential L1-RSRP#2 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#3 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#4 is the difference relative to L1-RSRP#1.
  • the signaling interaction process between the network device (NW) and the terminal device (UE) to complete the time domain beam prediction can be as shown in Figure 14, which includes the UE's capability reporting, the NW's configuration and activation of the beam measurement set (Set B) and the beam prediction set (Set A), the UE's measurement of the beam measurement set, the UE's reporting of the measurement results for the beam measurement set, the network device's inference of the beam prediction set using the first network model, the NW's indication of the beam used in the prediction instance, etc.
  • the beam measurement set (Set B) is the above-mentioned first measurement data set
  • the beam prediction set (Set A) is the above-mentioned first prediction data set.
  • Example 1 The technical solution of the present application is described in detail below through Example 1 and Example 2.
  • Example 1 the model is deployed on the UE side, and the transmission (Tx) beam is predicted.
  • the first measurement data set is Set B, and the M measurement instances are respectively recorded as Set B#1, Set B#2, ..., Set B#M-1, and Set B#M.
  • the first prediction data set is Set A, and the F prediction instances are respectively recorded as Set A#1, Set A#2, ..., Set A#F-1, and Set A#F.
  • Tx beam prediction and P2 process are the same, that is, in the process of transmitting beam scanning, the optimal receiving beam or fixed receiving beam is used to find a suitable transmitting beam.
  • NW scans the transmitting beam and UE uses a fixed receiving beam.
  • the UE needs to report at least one of the following information:
  • Spatial domain capacity of Set B the maximum number of Tx beams that can be measured (at one time);
  • Time domain capacity of Set B the maximum number of measurement instances supported
  • the time domain capacity of Set A the maximum number of prediction instances supported
  • Set B For the configuration of Set B, it can be fixed or non-fixed in M measurement instances.
  • Set B#1 contains Tx beams from index#0 to index#3
  • Set B#2 contains Tx beams from index#4 to index#5
  • Set B#M contains Tx beams from index#6 to index#9.
  • Tx beams do not overlap.
  • the Tx beams contained in different measurement instances measured by the UE may also overlap to a certain extent, or even completely overlap.
  • Set B#1 and Set B#M may contain the same Tx beam index#0 to #3.
  • the time domain intervals between different measurement instances in Set B can be equal intervals, such as periodic measurements configured by RRC, or non-equal intervals, as shown in Figure 15 for different time gaps.
  • the NW can configure the same period (periodicity) and different offsets (offset) for different measurement instances.
  • non-periodic Set B measurements another method is for the NW to configure some non-periodic Set B measurements in advance, and then use DCI to dynamically trigger non-periodic measurements, thereby achieving the purpose of non-uniform interval measurements.
  • M a sequence non-periodic CSI-RS
  • Set A#1 includes Tx beams from index#0 to index#5
  • Set A#2 includes Tx beams from index#0 to index#3
  • Set A#F includes Tx beams from index#0 to index#6. It should be noted that the above multiple Set A may overlap or may not overlap.
  • the time domain intervals between different predictions of Set A can be equally spaced, such as periodic predictions configured by RRC, or non-equally spaced, as shown in the different time gaps in Figure 17.
  • NW can configure the same periodicity and different offsets for different prediction instances.
  • the K best Tx beams are sorted from high to low according to the L1-RSRP of the Tx beams.
  • the value of K is generally 1, 2, 4 or 8.
  • the model can infer several Tx beams as long as their performance (such as L1-RSRP) is above a pre-set threshold.
  • the model can also infer the duration of the optimal Tx beam (beam dwelling time). For example, there is a period of time between Set A#1 and Set A#2, which we define as time gap#1.
  • the model can also predict the time for the L1-RSRP of the K Tx beams to remain stable.
  • the stability here can be defined from the relative quality, that is, the beam quality ranking, such as the time for the Top-1 Tx beam to remain first. It can also be defined from the absolute quality of L1-RSRP, such as the time for the L1-RSRP of the Top-1 Tx beam to drop less than a certain threshold (such as 3dB).
  • the beam duration (beam dwelling time) in the time domain beam prediction can be shown in Figure 19.
  • the UE After the model completes the prediction of the time domain beam pair, the UE needs to report the prediction results of the F prediction instances of the model to the NW.
  • the specific format is shown in Table 5 or Table 6 below.
  • Differential L1-RSRP#2 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#3 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#4 is the difference relative to L1-RSRP#1
  • L1-RSRP#1 is the L1-RSRP corresponding to Tx beam pair#1
  • Differential L1-RSRP#2 is the L1-RSRP corresponding to Tx beam pair#2
  • Differential L1-RSRP#3 is the L1-RSRP corresponding to Tx beam pair#3
  • Differential L1-RSRP#4 is the L1-RSRP corresponding to Tx beam pair#4.
  • Table 6 UE reports Tx beam ID, L1-RSRP performance and Tx beam duration for F prediction instances
  • Differential L1-RSRP#2 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#3 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#4 is the difference relative to L1-RSRP#1
  • L1-RSRP#1 is the L1-RSRP corresponding to Tx beam pair#1
  • Differential L1-RSRP#2 is the L1-RSRP corresponding to Tx beam pair#2
  • Differential L1-RSRP#3 is the difference relative to L1-RSRP#4.
  • Beam dwelling time#1 is the beam duration of Tx beam pair#1
  • Beam dwelling time#2 is the beam duration of Tx beam pair#2
  • Beam dwelling time#3 is the beam duration of Tx beam pair#3
  • Beam dwelling time#4 is the beam duration of Tx beam pair#4.
  • differential reporting can also be considered, that is, Beam dwelling time#1 is the absolute time, and Beam dwelling time#2 to Beam dwelling time#4 are the time differences relative to Beam dwelling time#1.
  • the network device based on the prediction results in F prediction instances reported by the terminal device, there are at least two ways for the network device to indicate the beam.
  • the first way is that the network device performs beam indication in batches according to the report of the terminal device, such as performing F beam information indications under the beam prediction of F prediction instances, that is, indicating the beam used in each of the F prediction instances respectively; wherein the beam information can be the index of the transmitting beam (in NR, it is generally referred to by the resource index of SSB or CSI-RS).
  • Another way is to perform a one-time beam indication, that is, the network device indicates the beam information of F prediction instances to the terminal device at one time, that is, indicates the beam used in each of the F prediction instances at one time.
  • the advantage of a one-time beam indication is that the signaling overhead of the beam indication can be greatly reduced.
  • the NW indicates the beam information used in each of the F prediction instances at one time.
  • the MAC CE or DCI should include Tx beam index (CSI-RS/SSB) #1, Tx beam index (CSI-RS/SSB) #2, ..., Tx beam index (CSI-RS/SSB) #F.
  • Tx beam index CSI-RS/SSB
  • the NW will change to the indicated transmit beam, and the UE should also change the corresponding receive beam.
  • the NW can choose to indicate the beam information and beam duration used in each of the F prediction instances to the UE at one time.
  • the MAC CE or DCI i.e., the second information
  • the meaning in the time domain is that each indicated beam pair takes effect from the predicted instance, and its effective duration is the beam duration (beam dwelling time) indicated by the application time (application time).
  • Example 2 the model is deployed on the network (NW) side, and the transmission (Tx) beam is predicted.
  • the first measurement data set is Set B, and the M measurement instances are respectively recorded as Set B#1, Set B#2, ..., Set B#M-1, and Set B#M.
  • the first prediction data set is Set A, and the F prediction instances are respectively recorded as Set A#1, Set A#2, ..., Set A#F-1, and Set A#F.
  • Tx beam prediction and P2 process are the same, that is, in the process of transmitting beam scanning, the optimal receiving beam or fixed receiving beam is used to find a suitable transmitting beam.
  • NW scans the transmitting beam and UE uses a fixed receiving beam.
  • the UE needs to report at least one of the following information:
  • Spatial domain capacity of Set B the maximum number of Tx beams that can be measured (at one time);
  • Time domain capacity of Set B the maximum number of measurement instances supported
  • the time domain capacity of Set A the maximum number of prediction instances supported
  • Set B For the configuration of Set B, it can be fixed or non-fixed in M measurement instances.
  • Set B#1 contains Tx beams from index#0 to index#3
  • Set B#2 contains Tx beams from index#4 to index#5
  • Set B#M contains Tx beams from index#6 to index#9.
  • Tx beams do not overlap.
  • the Tx beams contained in different measurement instances measured by the UE may also overlap to a certain extent, or even completely overlap.
  • Set B#1 and Set B#M may contain the same Tx beam index#0 to #3.
  • the time domain intervals between different measurement instances in Set B can be equally spaced, such as periodic measurements configured by RRC, or non-equally spaced, as shown in the different time gaps in Figure 15.
  • the NW can configure the same period (periodicity) and different offsets (offset) for different measurement instances.
  • non-periodic Set B measurements another method is for the NW to configure some non-periodic Set B measurements in advance, and then use DCI to dynamically trigger non-periodic measurements, thereby achieving the purpose of non-uniform interval measurements.
  • M a sequence non-periodic CSI-RS
  • Set A#1 includes Tx beams from index#0 to index#5
  • Set A#2 includes Tx beams from index#0 to index#3
  • Set A#F includes Tx beams from index#0 to index#6. It should be noted that the above multiple Set A may overlap or may not overlap.
  • the time domain intervals between different predictions of Set A can be equally spaced, such as periodic predictions configured by RRC, or non-equally spaced, as shown in the different time gaps in Figure 17.
  • NW can configure the same periodicity and different offsets for different prediction instances.
  • the UE When the model is deployed on the NW side, the UE needs to measure M measurement instances of Set B. Then report all measurement results to the model on the NW side.
  • Tx beam transmit beam
  • Table 7 UE reports L1-RSRP values according to the time domain order of Set B
  • Example 4 Sorting by the performance (such as L1-RSRP) of each transmit beam (Tx beam) in Set B, generally sorting by performance from high to low. As shown in Table 8, first the Tx beam ID in Set B, then the absolute value of the performance of the highest Tx beam, such as the absolute value quantification of L1-RSRP, for the performance of the beam pair that is not the highest performance, it can be quantified by differential means, that is, reporting the difference in performance compared to the highest performance.
  • the performance such as L1-RSRP
  • Table 8 UE reports Set B Tx beam ID and L1-RSRP value in time domain order
  • Differential L1-RSRP#2 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#3 is the difference relative to L1-RSRP#1
  • Differential L1-RSRP#4 is the difference relative to L1-RSRP#1.
  • the K best Tx beams are sorted from high to low according to the L1-RSRP of the Tx beams.
  • the value of K is generally 1, 2, 4 or 8.
  • the model can infer several Tx beams as long as their performance (such as L1-RSRP) is above a pre-set threshold.
  • the model can also infer the duration of the optimal Tx beam (beam dwelling time). For example, there is a period of time between Set A#1 and Set A#2, which we define as time gap#1.
  • the model can also predict the time for the L1-RSRP of the K Tx beams to remain stable.
  • the stability here can be defined from the relative quality, that is, the beam quality ranking, such as the time for the Top-1 Tx beam to remain in the first place. It can also be defined from the absolute quality of L1-RSRP, such as the time for the L1-RSRP of the Top-1 Tx beam to drop less than a certain threshold (such as 3dB).
  • the network device based on the prediction results of the F prediction instances predicted by the network device, there are at least two ways for the network device to indicate the beam.
  • the first way is that the network device performs beam indication in batches according to the prediction results, such as performing F beam information indications under the beam prediction of F prediction instances, that is, indicating the beam used in each of the F prediction instances respectively; wherein the beam information can be the index of the transmit beam (in NR, it is generally referred to by the resource index of SSB or CSI-RS).
  • Another way is to perform a one-time beam indication, that is, the network device indicates the beam information of F prediction instances to the terminal device at one time, that is, indicates the beam used in each of the F prediction instances at one time.
  • the advantage of a one-time beam indication is that the signaling overhead of the beam indication can be greatly reduced.
  • the network device indicates the beam information used in each of the F prediction instances at one time.
  • Tx beam index (CSI-RS/SSB) #1, Tx beam index (CSI-RS/SSB) #2, ..., Tx beam index (CSI-RS/SSB) #F should be included in the MAC CE or DCI.
  • the NW will change to the indicated transmit beam, and the UE should also change the corresponding receive beam.
  • the network device can choose to indicate the beam information and beam duration used in each of the F prediction instances to the UE at one time.
  • the MAC CE or DCI should include (Tx beam index (CSI-RS/SSB) #1, Application time #1), (Tx beam index (CSI-RS/SSB) #2, Application time #2), ..., (Tx beam index (CSI-RS/SSB) #F, Application time #F).
  • the meaning in the time domain is that each indicated beam pair takes effect from the predicted instance, and its effective duration is the beam duration (beam dwelling time) indicated by the application time (application time).
  • the first communication device can implement spatial filter prediction in the time domain based on the first network model, and the first communication device does not need to scan all deployed spatial filters, which is beneficial to reducing the overhead and delay caused by spatial filter scanning.
  • FIG20 shows a schematic block diagram of a communication device 300 according to an embodiment of the present application.
  • the communication device 300 is a first communication device. As shown in FIG20 , the communication device 300 includes:
  • the processing unit 310 is configured to obtain a first measurement data set; wherein the first measurement data set includes at least one of the following: identification information of the spatial filter in M measurement instances, and link quality information corresponding to the spatial filter in the M measurement instances; wherein M is a positive integer;
  • the processing unit 310 is also used to input the first measurement data set into the first network model and output a first prediction data set; wherein the first prediction data set includes at least one of the following: identification information of K spatial filters predicted in each of F prediction instances, link quality information corresponding to the K spatial filters predicted in each of the F prediction instances, and duration of the K spatial filters predicted in each of the F prediction instances; wherein F and K are both positive integers.
  • the spatial filter in each measurement instance in the M measurement instances is a partial spatial filter in all spatial filters.
  • the configuration of the spatial filter in each of the M measurement instances is the same; or,
  • Configurations of spatial filters in at least some of the M measurement instances are different.
  • some spatial filters in different measurement instances in the M measurement instances are the same.
  • the M measurement instances are arranged at equal intervals in the time domain.
  • the M measurement instances correspond to periodic spatial filter measurements within a first duration.
  • the M measurement instances are arranged at unequal intervals in the time domain.
  • the intervals between the M measurement instances in the time domain are determined based on the moving speed of the terminal device.
  • different measurement instances in the M measurement instances correspond to the same period and different offsets.
  • the M measurement instances are measurement instances activated by downlink control information DCI or media access control layer control element MAC CE among multiple measurement instances of semi-persistent scheduling SPS; or,
  • the M measurement instances are measurement instances dynamically triggered by DCI among multiple pre-configured measurement instances.
  • the M measurement instances are measurement instances corresponding to a set of measurement configurations activated by DCI or MAC CE among multiple measurement configurations, or, the M measurement instances are measurement instances corresponding to a current measurement configuration among multiple measurement configurations activated by DCI or MAC CE and used in turn.
  • the spatial filter in each measurement instance in the F prediction instances is a partial spatial filter in all spatial filters.
  • the configuration of the spatial filter in each of the F prediction instances is the same; or,
  • Configurations of spatial filters in at least some of the F prediction instances are different.
  • some or all of the spatial filters in different prediction instances among the F prediction instances are the same.
  • the F prediction instances are arranged at equal intervals in the time domain.
  • the F prediction instances correspond to periodic spatial filter predictions within a second duration.
  • the F prediction instances are arranged at unequal intervals in the time domain.
  • the intervals between the F prediction instances in the time domain are determined based on the moving speed of the terminal device.
  • different prediction instances among the F prediction instances correspond to the same period and different offsets.
  • the F prediction instances are prediction instances activated by DCI or MAC CE among multiple prediction instances of SPS; or, the F prediction instances are prediction instances dynamically triggered by DCI among multiple pre-configured prediction instances.
  • the F prediction instances are prediction instances corresponding to a set of prediction configurations activated by DCI or MAC CE among multiple sets of prediction configurations, or, the F prediction instances are prediction instances corresponding to the current prediction configuration among multiple sets of prediction configurations activated by DCI or MAC CE and used in turn.
  • the value of K includes one of the following: 1, 2, 4, 8.
  • the communication device 300 further includes: a communication unit 320;
  • the communication unit 320 is used to send first information
  • the first information includes at least one of the following: identification information of the K spatial filters predicted in each of the F prediction instances, link quality information corresponding to the K spatial filters predicted in each of the F prediction instances, and duration of the K spatial filters predicted in each of the F prediction instances.
  • the link quality information corresponding to the K spatial filters is sent in a differential manner.
  • the communication unit 320 is further configured to receive second information determined based on the first information
  • the second information is used to indicate the identification information of the spatial filter used in each of the F prediction instances, or the second information is used to indicate the identification information of the spatial filter used in the i-th prediction instance; or the second information is used to indicate the identification information and duration of the spatial filter used in each of the F prediction instances, or the second information is used to indicate the identification information and duration of the spatial filter used in the i-th prediction instance;
  • i is a positive integer, and 1 ⁇ i ⁇ F.
  • the communication unit 320 is further configured to send the first capability information
  • the first capability information includes at least one of the following: the maximum number of spatial filters supported by the first measurement data set, the maximum number of measurement instances supported by the first measurement data set, the maximum number of spatial filters supported by the first prediction data set, the maximum number of prediction instances supported by the first prediction data set, whether the prediction and reporting of the duration of the spatial filter are supported, and whether the identification information of indicating the spatial filters in multiple prediction instances at one time is supported.
  • the first communication device is a terminal device.
  • the communication unit 320 is further used to send third information
  • the third information is used to indicate the identification information of the spatial filter used in each of the F prediction instances, or the third information is used to indicate the identification information of the spatial filter used in the i-th prediction instance; or the third information is used to indicate the identification information and duration of the spatial filter used in each of the F prediction instances, or the third information is used to indicate the identification information and duration of the spatial filter used in the i-th prediction instance;
  • i is a positive integer, and 1 ⁇ i ⁇ F.
  • the communication unit 320 is further configured to receive first capability information
  • the first capability information includes at least one of the following: the maximum number of spatial filters supported by the first measurement data set, the maximum number of measurement instances supported by the first measurement data set, the maximum number of spatial filters supported by the first prediction data set, the maximum number of prediction instances supported by the first prediction data set, whether the prediction and reporting of the duration of the spatial filter are supported, and whether the identification information of indicating the spatial filters in multiple prediction instances at one time is supported.
  • the first communication device is a network device.
  • the spatial filter comprises a transmit spatial filter
  • the spatial filter includes a transmitting spatial filter and a receiving spatial filter.
  • the communication unit may be a communication interface or a transceiver, or an input/output interface of a communication chip or a system on chip.
  • the processing unit may be one or more processors.
  • the communication device 300 may correspond to the first communication device in the method embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the communication device 300 are respectively for implementing the corresponding process of the first communication device in the method 200 shown in Figure 10, which will not be repeated here for the sake of brevity.
  • Fig. 21 is a schematic structural diagram of a communication device 400 provided in an embodiment of the present application.
  • the communication device 400 shown in Fig. 21 includes a processor 410, and the processor 410 can call and run a computer program from a memory to implement the method in the embodiment of the present application.
  • the communication device 400 may further include a memory 420.
  • the processor 410 may call and run a computer program from the memory 420 to implement the method in the embodiment of the present application.
  • the memory 420 may be a separate device independent of the processor 410 , or may be integrated into the processor 410 .
  • the communication device 400 may further include a transceiver 430 , and the processor 410 may control the transceiver 430 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 430 may include a transmitter and a receiver.
  • the transceiver 430 may further include an antenna, and the number of the antennas may be one or more.
  • the processor 410 may implement the functions of a processing unit in the communication device 300 , which will not be described in detail here for the sake of brevity.
  • the transceiver 430 may implement the function of a communication unit in the communication device 300 , which will not be described in detail here for the sake of brevity.
  • the communication device 400 may specifically be the communication device of the embodiment of the present application, and the communication device 400 may implement the corresponding processes implemented by the first communication device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.
  • Fig. 22 is a schematic structural diagram of a device according to an embodiment of the present application.
  • the device 500 shown in Fig. 22 includes a processor 510, and the processor 510 can call and run a computer program from a memory to implement the method according to the embodiment of the present application.
  • the apparatus 500 may further include a memory 520.
  • the processor 510 may call and run a computer program from the memory 520 to implement the method in the embodiment of the present application.
  • the memory 520 may be a separate device independent of the processor 510 , or may be integrated into the processor 510 .
  • the apparatus 500 may further include an input interface 530.
  • the processor 510 may control the input interface 530 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.
  • the processor 510 may be located inside or outside the chip.
  • the processor 510 may implement the functions of a processing unit in the communication device 300 , which will not be described in detail here for the sake of brevity.
  • the input interface 530 may implement the functionality of a communication unit in the communication device 300 .
  • the apparatus 500 may further include an output interface 540.
  • the processor 510 may control the output interface 540 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.
  • the processor 510 may be located inside or outside the chip.
  • the output interface 540 may implement the functionality of a communication unit in the communication device 300 .
  • the apparatus may be applied to the communication device in the embodiments of the present application, and the apparatus may implement the corresponding processes implemented by the first communication device in the various methods in the embodiments of the present application, which will not be described in detail here for the sake of brevity.
  • the device mentioned in the embodiments of the present application may also be a chip, for example, a system-on-chip, a system-on-chip, a chip system, or a system-on-chip chip.
  • FIG23 is a schematic block diagram of a communication system 600 provided in an embodiment of the present application. As shown in FIG23 , the communication system 600 includes a first communication device 610 and a second communication device 620 .
  • the first communication device 610 can be used to implement the corresponding functions implemented by the first communication device in the above method
  • the second communication device 620 can be used to implement the corresponding functions implemented by the second communication device in the above method.
  • the sake of brevity they are not repeated here.
  • 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 perform, or the hardware and software modules in the decoding processor can be combined to perform.
  • 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 embodiment 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 embodiments of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.
  • 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 communication device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the first communication device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be 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 communication device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the first communication device 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 communication device in the embodiments of the present application.
  • the computer program runs on a computer, the computer executes the corresponding processes implemented by the first communication device 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 functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

Landscapes

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

Abstract

本申请实施例提供了一种无线通信的方法及设备，有利于降低波束扫描过程带来的开销和时延。该无线通信的方法，包括：第一通信设备获取第一测量数据集；该第一测量数据集包括以下至少之一：M个测量实例中空间滤波器的标识信息，M个测量实例中空间滤波器对应的链路质量信息；M为正整数；该第一通信设备将该第一测量数据集输入第一网络模型，输出第一预测数据集；其中，该第一预测数据集包括以下至少之一：F个预测实例中的每个预测实例中预测的K个空间滤波器的标识信息，F个预测实例中的每个预测实例中预测的K个空间滤波器对应的链路质量信息，F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间；其中，F和K均为正整数。

Description

无线通信的方法及设备 技术领域
本申请实施例涉及通信领域，并且更具体地，涉及一种无线通信的方法及设备。
背景技术
在新无线(New Radio，NR)系统中，引入了毫米波频段的通信，也引入了相应的波束管理机制，具体可以分为上行和下行的波束管理。其中，下行的波束管理可以包括：下行的波束扫描，终端侧的最优波束上报，网络侧的下行波束指示等过程。具体地，网络设备通过下行参考信号来扫描所有的发射波束方向。终端设备可以使用不同的接收波束来进行测量，从而可以遍历全部的波束对。
由此可见，终端设备需要遍历全部的发射波束和接收波束的组合来选择最优波束，因此会带来大量的开销和时延。
发明内容
本申请实施例提供了一种无线通信的方法及设备，有利于降低波束扫描过程带来的开销和时延。
第一方面，提供了一种无线通信的方法，该方法包括：
第一通信设备获取第一测量数据集；其中，该第一测量数据集包括以下至少之一：M个测量实例中空间滤波器的标识信息，M个测量实例中空间滤波器对应的链路质量信息；其中，M为正整数；
该第一通信设备将该第一测量数据集输入第一网络模型，输出第一预测数据集；其中，该第一预测数据集包括以下至少之一：F个预测实例中的每个预测实例中预测的K个空间滤波器的标识信息，F个预测实例中的每个预测实例中预测的K个空间滤波器对应的链路质量信息，F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间；其中，F和K均为正整数。
第二方面，提供了一种通信设备，用于执行上述第一方面中的方法。
具体地，该通信设备包括用于执行上述第一方面中的方法的功能模块。
第三方面，提供了一种通信设备，包括处理器和存储器；该存储器用于存储计算机程序，该处理器用于调用并运行该存储器中存储的计算机程序，使得该通信设备执行上述第一方面中的方法。
第四方面，提供了一种装置，用于实现上述第一方面中的方法。
具体地，该装置包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有该装置的设备执行如上述第一方面中的方法。
第五方面，提供了一种计算机可读存储介质，用于存储计算机程序，该计算机程序使得计算机执行上述第一方面中的方法。
第六方面，提供了一种计算机程序产品，包括计算机程序指令，所述计算机程序指令使得计算机执行上述第一方面中的方法。
第七方面，提供了一种计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面中的方法。
通过上述技术方案，第一通信设备可以基于第一网络模型实现时域上的空间滤波器预测，并且，第一通信设备可以不必对部署的所有空间滤波器均进行扫描，有利于降低空间滤波器扫描带来的开销和时延。
附图说明
图1是本申请实施例提供的一种通信系统架构的示意性图。
图2是一种神经网络的神经元的连接示意图。
图3是一种神经网络的示意性结构图。
图4是一种卷积神经网络的示意性图。
图5是一种LSTM单元的示意性结构图。
图6是本申请实施例提供一种LSTM模型的示意性图。
图7是一种下行的波束扫描过程的示意性图。
图8是另一种下行的波束扫描过程的示意性图。
图9是又一种下行的波束扫描过程的示意性图。
图10是根据本申请实施例提供的一种无线通信的方法的示意性图。
图11是根据本申请实施例提供的一种数据集B的示意性图。
图12是根据本申请实施例提供的一种数据集A的示意性图。
图13是根据本申请实施例提供的一种波束预测的流程图。
图14是根据本申请实施例提供的另一种波束预测的流程图。
图15是根据本申请实施例提供的Set B在不同的测量实例上有不同的Tx波束配置。
图16是根据本申请实施例提供的一个DCI触发多个Set B测量的示意图。
图17是根据本申请实施例提供的Set A在不同的预测实例上有不同的Tx波束配置的示意性图。
图18是根据本申请实施例提供的Set A的Tx波束配置X和Y轮流出现的示意图。
图19是根据本申请实施例提供的时域波束预测中波束持续时间示意图。
图20是根据本申请实施例提供的一种通信设备的示意性框图。
图21是根据本申请实施例提供的一种通信设备的示意性框图。
图22是根据本申请实施例提供的一种装置的示意性框图。
图23是根据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。针对本申请中的实施例，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。
本申请实施例的技术方案可以应用于各种通信系统，例如：全球移动通讯(Global System of Mobile communication，GSM)系统、码分多址(Code Division Multiple Access，CDMA)系统、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)系统、通用分组无线业务(General Packet Radio Service，GPRS)、长期演进(Long Term Evolution，LTE)系统、先进的长期演进(Advanced long term evolution，LTE-A)系统、新无线(New Radio，NR)系统、NR系统的演进系统、非授权频谱上的LTE(LTE-based access to unlicensed spectrum，LTE-U)系统、非授权频谱上的NR(NR-based access to unlicensed spectrum，NR-U)系统、非地面通信网络(Non-Terrestrial Networks，NTN)系统、通用移动通信系统(Universal Mobile Telecommunication System，UMTS)、无线局域网(Wireless Local Area Networks，WLAN)、物联网(internet of things，IoT)、无线保真(Wireless Fidelity，WiFi)、第五代通信(5th-Generation，5G)系统、第六代通信(6th-Generation，6G)系统或其他通信系统等。
通常来说，传统的通信系统支持的连接数有限，也易于实现，然而，随着通信技术的发展，移动通信系统将不仅支持传统的通信，还将支持例如，设备到设备(Device to Device，D2D)通信，机器到机器(Machine to Machine，M2M)通信，机器类型通信(Machine Type Communication，MTC)，车辆间(Vehicle to Vehicle，V2V)通信，侧行(sidelink，SL)通信，车联网(Vehicle to everything，V2X)通信等，本申请实施例也可以应用于这些通信系统。
在一些实施例中，本申请实施例中的通信系统可以应用于载波聚合(Carrier Aggregation，CA)场景，也可以应用于双连接(Dual Connectivity，DC)场景，还可以应用于独立(Standalone，SA)布网场景，或者应用于非独立(Non-Standalone，NSA)布网场景。
在一些实施例中，本申请实施例中的通信系统可以应用于非授权频谱，其中，非授权频谱也可以认为是共享频谱；或者，本申请实施例中的通信系统也可以应用于授权频谱，其中，授权频谱也可以认为是非共享频谱。
在一些实施例中，本申请实施例中的通信系统可以应用于FR1频段(对应频段范围410MHz到7.125GHz)，也可以应用于FR2频段(对应频段范围24.25GHz到52.6GHz)，还可以应用于新的频段例如对应52.6GHz到71GHz频段范围或对应71GHz到114.25GHz频段范围的高频频段。
本申请实施例结合网络设备和终端设备描述了各个实施例，其中，终端设备也可以称为用户设备(User Equipment，UE)、接入终端、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等。
终端设备可以是WLAN中的站点(STATION，ST)，可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol，SIP)电话、无线本地环路(Wireless Local Loop，WLL)站、个人数字助理(Personal Digital Assistant，PDA)设备、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、下一代通信系统例如NR网络中的终端设备，或者未来演进的公共陆地移动网络(Public Land Mobile Network，PLMN)网络中的终端设备等。
在本申请实施例中，终端设备可以部署在陆地上，包括室内或室外、手持、穿戴或车载；也可以部署在水面上(如轮船等)；还可以部署在空中(例如飞机、气球和卫星上等)。
在本申请实施例中，终端设备可以是手机(Mobile Phone)、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(Virtual Reality，VR)终端设备、增强现实(Augmented Reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self driving)中的无线终端设备、远程医疗(remote medical)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全 (transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备或智慧家庭(smart home)中的无线终端设备、车载通信设备、无线通信芯片/专用集成电路(application specific integrated circuit，ASIC)/系统级芯片(System on Chip，SoC)等。
作为示例而非限定，在本申请实施例中，该终端设备还可以是可穿戴设备。可穿戴设备也可以称为穿戴式智能设备，是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能，例如：智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能首饰等。
在本申请实施例中，网络设备可以是用于与移动设备通信的设备，网络设备可以是WLAN中的接入点(Access Point，AP)，GSM或CDMA中的基站(Base Transceiver Station，BTS)，也可以是WCDMA中的基站(NodeB，NB)，还可以是LTE中的演进型基站(Evolutional Node B，eNB或eNodeB)，或者中继站或接入点，或者车载设备、可穿戴设备以及NR网络中的网络设备或者基站(gNB)或者发射接收点(Transmission Reception Point，TRP)，或者未来演进的PLMN网络中的网络设备或者NTN网络中的网络设备等。
作为示例而非限定，在本申请实施例中，网络设备可以具有移动特性，例如网络设备可以为移动的设备。在一些实施例中，网络设备可以为卫星、气球站。例如，卫星可以为低地球轨道(low earth orbit，LEO)卫星、中地球轨道(medium earth orbit，MEO)卫星、地球同步轨道(geostationary earth orbit，GEO)卫星、高椭圆轨道(High Elliptical Orbit，HEO)卫星等。在一些实施例中，网络设备还可以为设置在陆地、水域等位置的基站。
在本申请实施例中，网络设备可以为小区提供服务，终端设备通过该小区使用的传输资源(例如，频域资源，或者说，频谱资源)与网络设备进行通信，该小区可以是网络设备(例如基站)对应的小区，小区可以属于宏基站，也可以属于小小区(Small cell)对应的基站，这里的小小区可以包括：城市小区(Metro cell)、微小区(Micro cell)、微微小区(Pico cell)、毫微微小区(Femto cell)等，这些小小区具有覆盖范围小、发射功率低的特点，适用于提供高速率的数据传输服务。
示例性的，本申请实施例应用的通信系统100如图1所示。该通信系统100可以包括网络设备110，网络设备110可以是与终端设备120(或称为通信终端、终端)通信的设备。网络设备110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设备进行通信。
图1示例性地示出了一个网络设备和两个终端设备，在一些实施例中，该通信系统100可以包括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设备，本申请实施例对此不做限定。
在一些实施例中，该通信系统100还可以包括网络控制器、移动管理实体等其他网络实体，本申请实施例对此不作限定。
应理解，本申请实施例中网络/系统中具有通信功能的设备可称为通信设备。以图1示出的通信系统100为例，通信设备可包括具有通信功能的网络设备110和终端设备120，网络设备110和终端设备120可以为上文所述的具体设备，此处不再赘述；通信设备还可包括通信系统100中的其他设备，例如网络控制器、移动管理实体等其他网络实体，本申请实施例中对此不做限定。
应理解，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。
应理解，本文涉及第一通信设备和第二通信设备，第一通信设备可以是终端设备，例如手机，机器设施，用户前端设备(Customer Premise Equipment，CPE)，工业设备，车辆等；第二通信设备可以是第一通信设备的对端通信设备，例如网络设备，手机，工业设备，车辆等。在本申请实施例中，第一通信设备可以是终端设备，且第二通信设备可以网络设备(即上行通信或下行通信)；或者，第一通信设备可以是第一终端，且第二通信设备可以第二终端(即侧行通信)。
本申请的实施方式部分使用的术语仅用于对本申请的具体实施例进行解释，而非旨在限定本申请。本申请的说明书和权利要求书及所述附图中的术语“第一”、“第二”、“第三”和“第四”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。
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。
在本申请实施例的描述中，术语“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。
本申请实施例中，“预定义”或“预配置”可以通过在设备(例如，包括终端设备和网络设备)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。
本申请实施例中，所述“协议”可以指通信领域的标准协议，例如可以是对现有LTE协议、NR协议、Wi-Fi协议或者与之相关的其它通信系统相关的协议的演进，本申请不对协议类型进行限定。
为便于更好的理解本申请实施例，对本申请相关的神经网络和机器学习进行说明。
神经网络(Neural Network，NN)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(summation，SUM)，并通过特定的激活函数(f)输出，图2是一种神经元结构的示意图，其中，a1，a2，…，an表示输入信号，w1，w2，…，wn表示权重，f表示激励函数，t表示输出。
一个简单的神经网络如图3所示，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，权重和激活函数，可以产生不同的输出，进而拟合从输入到输出的映射关系。其中，每一个上一级节点都与其全部的下一级节点相连，该神经网络是一种全连接神经网络，也可以称为深度神经网络(Deep Neural Network，DNN)。
一个卷积神经网络(Convolutional Neural Network，CNN)的基本结构包括：输入层、多个卷积层、多个池化层、全连接层及输出层，如图4所示。卷积层中卷积核的每个神经元与其输入进行局部连接，并通过引入池化层提取某一层局部的最大值或者平均值特征，有效减少了网络的参数，并挖掘了局部特征，使得卷积神经网络能够快速收敛，获得优异的性能。
深度学习采用多隐藏层的深度神经网络，极大提升了网络学习特征的能力，能够拟合从输入到输出的复杂的非线性映射，因而语音和图像处理领域得到广泛的应用。除了深度神经网络，面对不同任务，深度学习还包括卷积神经网络(Convolutional Neural Network，CNN)、循环神经网络(Recurrent Neural Network，RNN)等常用基本结构。
一个卷积神经网络的基本结构包括：输入层、多个卷积层、多个池化层、全连接层及输出层，如图4所示。卷积层中卷积核的每个神经元与其输入进行局部连接，并通过引入池化层提取某一层局部的最大值或者平均值特征，有效减少了网络的参数，并挖掘了局部特征，使得卷积神经网络能够快速收敛，获得优异的性能。
RNN是一种对序列数据建模的神经网络，在自然语言处理领域，如机器翻译、语音识别等应用取得显著成绩。具体表现为，网络设备对过去时刻的信息进行记忆，并用于当前输出的计算中，即隐藏层之间的节点不再是无连接的而是有连接的，并且隐藏层的输入不仅包括输入层还包括上一时刻隐藏层的输出。常用的RNN包括长短期记忆网络(Long Short-Term Memory，LSTM)和门控循环单元(gated recurrent unit，GRU)等结构。图5所示为一个基本的LSTM单元结构，其可以包含tanh激活函数，不同于RNN只考虑最近的状态，LSTM的细胞状态会决定哪些状态应该被留下来，哪些状态应该被遗忘，解决了传统RNN在长期记忆上存在的缺陷。
为便于更好的理解本申请实施例，对本申请相关的波束管理进行说明。
在NR系统中，引入了毫米波频段的通信，也引入了相应的波束管理机制，包括可以分为上行和下行的波束管理。对于下行的波束管理包括下行的波束扫描，UE侧的最优波束上报，网络侧的下行波束指示等过程。
下行的波束扫描过程可以指：网络设备通过下行参考信号来扫描不同的发射波束方向。UE可以使用不同的接收波束来进行测量，从而可以遍历全部的波束对，UE计算每个波束对对应的层1参考信号接收功率(Layer1 Reference Signal Receiving Power，L1-RSRP)值。
其中，下行参考信号包括同步信号块(Synchronization Signal Block，SSB)和/或信道状态信息参考信号(Channel State Information Reference Signal，CSI-RS)。
为便于更好的理解本申请实施例，对本申请相关的基于人工智能(Artificial Intelligence，AI)/机器学习(machine learning，ML)的波束管理进行说明。
基于AI/ML的波束管理可以为空间和时间域的下行波束预测。
空间域的波束预测(也可以称之为波束管理示例1(BM-Case1))：通过测量数据集B(Set B)中的波束来进行数据集A(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(也可以称之为波束管理示例2(BM-Case2))：通过历史测量数据集B(Set B)中的波束来进行数据集A(Set A)中下行波束时间域预测。Set B要么是Set A的一个子集，要么和Set A相同，要么是Set A的一个子集。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。
为便于更好的理解本申请实施例，对本申请相关的神经网络模型进行说明。
通过数据集的构建，训练，验证和测试等过程可以训练并得到一个神经网络(Neural Network，NN)模型。本申请假设NN模型都已经是提前通过离线训练或者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。首先网络(network，NW)可以通过数据集离线训练的方式得到一个静态的训练结果，这里可以称之为离线训练。在网络(NW)或终端(UE)对NN模型的使用过程中，随着UE的进一步测量和/或上报，NN模型可以继续收集更多的数据，进行实时的在线训练来优化NN模型的参数，达到更好的推断和预测结果。
本申请以时间域波束(对)及其性能的预测为例，选用LSTM模型，如图6所示。该LSTM模型在时序上可以理解为延展了M个实例(instance)作为输入，等效为M个LSTM单元的级联。每一个LSTM单元的输入是数据集B中的实例m(Set Bm)的波束(对)的L1-RSRP，其中，1≤m≤M。
需要说明的是，Set Bm的波束(对)的索引可以通过L1-RSRP的固定排序方式隐含地输入。在完成了M个实例的性能输入后，LSTM模型可以预测接下来的F个实例的最优波束(对)，最优波束(对)的性能(即链路质量信息)，以及最优波束(对)的持续时间(dwelling time)。
为便于更好的理解本申请实施例，对本申请相关的NR的波束管理进行说明。
在NR系统中，引入了毫米波频段的通信，也即引入了波束管理机制。例如包括上行的波束管理、下行的波束管理。其中，下行波束管理机制包括下行的波束扫描(beam sweeping)，UE波束测量和上报(measurement&reporting)，网络设备对于下行波束指示(beam indication)等过程。
下行波束扫描过程可包括3个过程，即P1、P2和P3过程。P1过程指网络设备扫描不同发射波束，UE扫描不同的接收波束；P2过程指网络设备扫描不同发射波束，UE使用相同的接收波束；P3过程指网络设备使用相同的发射波束，UE扫描不同的接收波束。一般情况下，网络设备通过发送下行参考信号来完成上述波束扫描过程。可选地，该下行参考信号可以包括但不限于同步信号块(Synchronization Signal Block，SSB)和/或信道状态信息参考信号(Channel State Information Reference Signal，CSI-RS)。
图7所示是P1过程(或称下行的全扫描过程)的示意性图，图8所示是P2过程的示意性图，图9所示是P3过程的示意性图。
如图7所示，在P1过程中，网络设备遍历所有的发射波束发送下行参考信号，UE侧遍历所有的接收波束进行测量，确定对应的测量结果。
如图8所示，在P2过程中，网络设备遍历所有的发射波束发送下行参考信号，UE侧使用特定接收波束进行测量，确定对应的测量结果。
如图9所示，在P3过程中，网络设备可以使用特定发射波束发送下行参考信号，UE侧遍历所有的接收波束进行测量，确定对应的测量结果。
NR中的传统波束上报指UE通过测量不同波束(对)的L1-RSRP值，选择L1-RSRP最高的K个发射波束，以上行控制信息(Uplink Control Information，UCI)的形式上报给NW。这里L1-RSRP也可以替换为其他波束链路指标，如层1信号干扰噪声比(Layer1 Signal to Interference plus Noise Ratio，L1-SINR)，层1参考信号接收质量(Layer1 Reference Signal Received Quality，L1-RSRQ)等。
在网络设备获知终端设备上报的最优波束后，可以通过媒体接入控制(Media Access Control，MAC)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(其中包含下行参考信号作为参考的发射波束)，来完成对UE的波束指示，UE使用该发射波束对应的接收波束来进行下行接收。
为便于更好的理解本申请实施例，对本申请所解决的问题进行说明。
对于NR的波束扫描过程来说，如果是下行的周期性的全波束扫描过程，即周期性的P1过程，UE需要周期性地遍历全部的发射波束和接收波束的组合，因此会带来大量的开销和时延。举例来说，假设NW在FR2部署了64个不同的下行发射方向(通过最多64个SSB来承载)，UE接收时使用多个天线面板(包括仅有一个接收波束面板)来同时进行接收波束扫描，且每一个天线面板有4个接收波束。从时间的角度说，每个SSB周期大概是20ms，那么需要4个SSB周期才可以完成对4个接收波束的测量(假设多个接收天线面板可以通过进行波束扫描)，那么则至少需要80ms的时间。
上述过程每80毫秒就要重复一次，在每个80毫秒的周期内，UE至少需要测量64*4＝256个波 束对，对应的就是需要256个资源的下行资源开销。
因此，如何降低波束扫描的开销和时延是一项亟需解决的问题，基于此问题，本申请提出了一种基于AI/ML模型的时间域波束预测方案，有利于降低波束扫描过程带来的开销和时延。
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。本申请实施例包括以下内容中的至少部分内容。
图10是根据本申请实施例的无线通信的方法200的示意性流程图，如图10所示，该无线通信的方法200可以包括如下内容中的至少部分内容：
S210，第一通信设备获取第一测量数据集；其中，该第一测量数据集包括以下至少之一：M个测量实例中空间滤波器的标识信息，M个测量实例中空间滤波器对应的链路质量信息；其中，M为正整数；
S220，该第一通信设备将该第一测量数据集输入第一网络模型，输出第一预测数据集；其中，该第一预测数据集包括以下至少之一：F个预测实例中的每个预测实例中预测的K个空间滤波器的标识信息，F个预测实例中的每个预测实例中预测的K个空间滤波器对应的链路质量信息，F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间；其中，F和K均为正整数。
在本申请一些实施例中，空间滤波器(spatial filter)也可以称为波束(beam)、波束对(beam pair)、空间关系(Spatial relation)、空间配置(spatial setting)、空域滤波器(spatial domain filter)，或者，参考信号。
在一些实施例中，该空间滤波器包括一个发射空间滤波器。可选地，发射空间滤波器也可以称为发射波束(Tx beam)或发送端空域滤波器，上述术语可以相互替换。
在一些实施例中，该空间滤波器包括一个接收空间滤波器。可选地，接收空间滤波器也可以称为发射波束(Rx beam)或接收端空域滤波器，上述术语可以相互替换。
在一些实施例中，该空间滤波器包括一个发射空间滤波器和一个接收空间滤波器。可选地，发射空间滤波器和接收空间滤波器的组合也可以称为波束对，空间滤波器对，空间滤波器组，上述术语可以相互替换。
在一些实施例中，空间滤波器的标识信息可以为空间滤波器的索引或标识。
例如，发射空间滤波器的标识信息可以为发射空间滤波器的索引或标识。
又例如，接收空间滤波器的标识信息可以为接收空间滤波器的索引或标识。
再例如，发射空间滤波器和接收空间滤波器的组合的标识信息可以为组合索引。
在一些实施例中，链路质量信息可以包括但不限于如下至少之一：
层1参考信号接收功率(Layer1 Reference Signal Receiving Power，L1-RSRP)、层1参考信号接收质量(Reference Signal Receiving Quality，L1-RSRQ)、层1信号干扰噪声比(Layer1 Signal to Interference plus Noise Ratio，L1-SINR)。
在一些实施例中，一个测量实例可以对应一个或多个时间单元，其中，该时间单元可以包括但不限于以下之一：时隙，迷你时隙，帧，子帧，符号，毫秒，微秒。
在一些实施例中，一个预测实例可以对应一个或多个时间单元，其中，该时间单元可以包括但不限于以下之一：时隙，迷你时隙，帧，子帧，符号，毫秒，微秒。
在一些实施例中，K个空间滤波器基于每个预测实例中链路质量信息确定。
具体例如，K个空间滤波器基于每个预测实例中链路质量信息从高到低的排序得到。例如，每个预测实例中链路质量信息从高到低的排序中的前K个链路质量信息对应的空间滤波器即为该预测实例中的K个空间滤波器。
具体又例如，K个空间滤波器为每个预测实例中链路质量信息大于或等于第一阈值的链路质量信息对应的空间滤波器。可选地，该第一阈值由协议约定，或者，该第一阈值由网络设备配置。
在一些实施例中，K的取值包括但不限于以下之一：1，2，4，8。
在一些实施例中，K个空间滤波器的持续时间(dwelling time)，可以是该K个空间滤波器对应的链路质量信息保持稳定的时间。
在一些实施例中，在第一测量数据集仅包括M个测量实例中空间滤波器对应的链路质量信息的情况下，可以通过M个测量实例中空间滤波器对应的链路质量信息隐式指示M个测量实例中空间滤波器的标识信息。
在一些实施例中，该第一通信设备为终端设备，或者，该第一通信设备为网络设备。
在一些实施例中，该第一网络模型可以是LSTM模型，如图6所示，该LSTM模型在时序上可以理解为延展了M个测量实例(instance)作为输入，等效为M个LSTM单元的级联。每一个LSTM 单元的输入是数据集B(即第一测量数据集)中的测量实例m(Set B m)的波束(对)的链路质量信息(如L1-RSRP)，其中，1≤m≤M。
在一些实施例中，该M个测量实例中每个测量实例中的空间滤波器为全部空间滤波器中的部分空间滤波器。具体的，该全部空间滤波器为部署的所有空间滤波器。也即，在每个测量实例中，不会遍历部署的所有空间滤波器。例如，假设网络设备(NW)在FR2部署了64个不同的下行发射波束(transmission beam，Tx beam)，M个测量实例中的每个测量实例中的下行发射波束的数量小于64。
因此，在本实施例中，在每次测量中仅测量部分的空间滤波器信息，合并M次测量之后可以得到更多空间滤波器信息，甚至是全部的空间滤波器信息来进行后续的预测，减少每次测量的开销。
在一些实施例中，该M个测量实例中每个测量实例中的空间滤波器的配置相同。也即，M个测量实例中每个测量实例中的空间滤波器相同。例如，M个测量实例中每个测量实例中的空间滤波器的标识和数量均相同。
具体例如，假设第一测量数据集为Set B，M个测量实例分别记为Set B#1、Set B#2、…、Set B#M-1、Set B#M。其中，Set B#1中的发射接收(transmission-receiving，Tx-Rx)波束对索引(index)从index#0到index#15，Set B#2中的发射接收(Tx-Rx)波束对索引(index)也从index#0到index#15，…，Set B#M-1中的发射接收(Tx-Rx)波束对索引(index)也从index#0到index#15，Set B#M中的发射接收(Tx-Rx)波束对索引(index)也从index#0到index#15。
在一些实施例中，该M个测量实例中至少部分测量实例中的空间滤波器的配置不同。也即，M个测量实例中至少部分测量实例中的空间滤波器不同。例如，M个测量实例中至少部分测量实例中的空间滤波器的标识不同。又例如，M个测量实例中至少部分测量实例中的空间滤波器的数量不同。再例如，M个测量实例中至少部分测量实例中的空间滤波器的标识和数量不同。
具体例如，假设第一测量数据集为Set B，M个测量实例分别记为Set B#1、Set B#2、…、Set B#M-1、Set B#M。如图11所示，Set B#1中的发射接收(Tx-Rx)波束对索引(index)从index#0到index#15，Set B#2中的发射接收(Tx-Rx)波束对索引(index)从index#16到index#19，…，Set B#M中的发射接收(Tx-Rx)波束对索引(index)从index#48到index#63。
在一些实施例中，该M个测量实例中不同的测量实例中的部分空间滤波器相同。也即，M个测量实例中不同的测量实例中的空间滤波器可以有一定程度的重叠。可选地，重叠的空间滤波器可以是容易被选取的空间滤波器。从而，可以提升测量质量。
具体的，对于不同的波束对，被选择的可能性并不完全相同(一般情况下，在NW侧下倾角比较适中的发射波束容易被选择到)，因此对于容易被UE选择的波束对，可以测量较多的次数；对于不易被选择的波束对，可以测量较少，甚至不去测量。
具体例如，假设第一测量数据集为Set B，M个测量实例分别记为Set B#1、Set B#2、…、Set B#M-1、Set B#M。其中，Set B#1中的Tx-Rx波束对索引(index)从index#0到index#15，Set B#2中的Tx-Rx波束对索引(index)从index#14到index#19。也即，Set B#1和Set B#2中的Tx-Rx波束对均包含index#14和index#15。
在一些实施例中，该M个测量实例在时域上等间隔设置。也即，该M个测量实例可以是周期性的测量实例。可选地，可以通过RRC信令配置测量实例对应的周期信息。
在一些实施例中，该M个测量实例对应第一时长内的周期性空间滤波器测量。可选地，可以通过RRC信令配置空间滤波器测量对应的周期信息。
在一些实施例中，该第一时长由协议约定，或者，该第一时长由网络设备配置。
在一些实施例中，该M个测量实例在时域上非等间隔设置。例如，如图11所示，M个测量实例中不同的测量实例之间的时间间隔(time gap)不同。从而，可以更灵活地适应信道的变化。
在一些实施例中，该M个测量实例在时域上的间隔基于终端设备的移动速度确定。例如，当UE的移动速度较快时，可以增加测量的频次(即不同测量实例之间时间间隔较小)；当UE的移动速度较慢时，可以减少测量的频次(即不同测量实例之间时间间隔较大)。从而达到在相同的移动距离上，UE测量大致相同的次数。
在一些实施例中，该M个测量实例中不同的测量实例对应相同的周期和不同的偏移量。具体例如，对于时域上非均匀间隔的测量实例，从网络配置的角度来说，对于周期性的测量，网络可以给不同的测量实例配置相同的周期(periodicity)和不同的偏移量(offset)。
在一些实施例中，该M个测量实例为半持续调度(Semi-Persistent Scheduling，SPS)的多个测量实例中由下行控制信息(Downlink Control Information，DCI)或媒体接入控制层控制单元(Media Access Control Control Element，MAC CE)激活的测量实例。
在一些实施例中，该M个测量实例为预先配置的多个测量实例中由DCI动态触发的测量实例。 也即，本实施例中，一个DCI可以触发M个测量实例的非周期CSI-RS。这样做的好处是可以仅使用一个DCI(最小的信令开销)来触发M个测量实例的测量。
在一些实施例中，该M个测量实例为多套测量配置中由DCI或MAC CE激活的一套测量配置对应的测量实例，或者，该M个测量实例为由DCI或MAC CE激活的轮流使用的多套测量配置中当前的测量配置对应的测量实例。可选地，该多套测量配置由网络设备提前配置或半静态配置。
在一些实施例中，网络设备可以配置第一测量数据集中的M个测量实例，或者，网络设备可以激活第一测量数据集中的M个测量实例，或者，网络设备可以更新第一测量数据集中的M个测量实例。例如，网络设备可以通过RRC信令配置多个测量实例，以及通过MAC CE信令激活第一测量数据集中的M个测量实例。
在一些实施例中，假设第一通信设备为终端设备，第一通信设备可以测量M个测量实例，以得到该第一测量数据集。
在一些实施例中，假设第一通信设备为网络设备，第一通信设备可以获取终端设备针对M个测量实例的测量结果，以得到该第一测量数据集。
在一些实施例中，该F个预测实例中的每个测量实例中的空间滤波器为全部空间滤波器中的部分空间滤波器。具体的，该全部空间滤波器为部署的所有空间滤波器。也即，在每个预测实例中，不会遍历部署的所有空间滤波器。例如，假设网络设备(NW)在FR2部署了64个不同的下行发射波束，F个预测实例中的每个预测实例中的下行发射波束的数量小于64。
具体的，在每个预测实例中都可以限定预测的空间滤波器的范围，从而控制模型可以选择的空间滤波器的范围，只关注一些重点的空间滤波器，提升了预测的空间滤波器的准确性。
在一些实施例中，该F个预测实例中每个预测实例中的空间滤波器的配置相同。也即，F个预测实例中每个预测实例中的空间滤波器相同。例如，F个预测实例中每个预测实例中的空间滤波器的标识和数量均相同。
具体例如，假设第一预测数据集为Set A，F个预测实例分别记为Set A#1、Set A#2、…、Set A#F-1、Set A#F。其中，Set A#1中的发射接收(Tx-Rx)波束对索引(index)从index#0到index#20，Set A#2中的发射接收(Tx-Rx)波束对索引(index)也从index#0到index#20，…，Set A#F-1中的发射接收(Tx-Rx)波束对索引(index)也从index#0到index#20，Set A#F中的发射接收(Tx-Rx)波束对索引(index)也从index#0到index#20。
在一些实施例中，该F个预测实例中至少部分预测实例中的空间滤波器的配置不同。也即，F个预测实例中至少部分预测实例中的空间滤波器不同。例如，F个预测实例中至少部分预测实例中的空间滤波器的标识不同。又例如，F个预测实例中至少部分预测实例中的空间滤波器的数量不同。再例如，F个预测实例中至少部分预测实例中的空间滤波器的标识和数量不同。
具体例如，假设第一预测数据集为Set A，F个预测实例分别记为Set A#1、Set A#2、…、Set A#F-1、Set A#F。如图12所示，Set A#1中的发射接收(Tx-Rx)波束对索引(index)从index#0到index#35，Set A#2中的发射接收(Tx-Rx)波束对索引(index)从index#0到index#15，…，Set A#F中的发射接收(Tx-Rx)波束对索引(index)从index#0到index#27。
在一些实施例中，该F个预测实例中不同的预测实例中的部分或者全部空间滤波器相同。也即，F个预测实例中不同的预测实例中的空间滤波器可以有一定程度的重叠。可选地，重叠的空间滤波器可以是容易被选取的空间滤波器。从而，可以提升预测质量。
具体的，对于不同的波束对，被选择的可能性并不完全相同(一般情况下，在NW侧下倾角比较适中的发射波束容易被选择到)，因此对于容易被UE选择的波束对，可以测量较多的次数；对于不易被选择的波束对，可以测量较少，甚至不去测量。
在一些实施例中，该F个预测实例在时域上等间隔设置。也即，该F个预测实例可以是周期性的预测实例。可选地，可以通过RRC信令配置预测实例对应的周期信息。
在一些实施例中，该F个预测实例对应第二时长内的周期性空间滤波器预测。可选地，可以通过RRC信令配置空间滤波器预测对应的周期信息。
在一些实施例中，该第二时长由协议约定，或者，该第二时长由网络设备配置。
在一些实施例中，该F个预测实例在时域上非等间隔设置。例如，如图12所示，F个预测实例中不同的预测实例之间的时间间隔(time gap)不同。从而，可以更灵活地适应信道的变化。
在一些实施例中，该F个预测实例在时域上的间隔基于终端设备的移动速度确定。例如，当UE的移动速度较快时，可以增加预测的频次(即不同预测实例之间时间间隔较小)；当UE的移动速度较慢时，可以减少预测的频次(即不同预测实例之间时间间隔较大)。从而达到在相同的移动距离上，预测大致相同的次数。
在一些实施例中，该F个预测实例中不同的预测实例对应相同的周期和不同的偏移量。具体例如，对于时域上非均匀间隔的预测实例，从网络配置的角度来说，对于周期性的预测，网络可以给不同的预测实例配置相同的周期(periodicity)和不同的偏移量(offset)。
在一些实施例中，该F个预测实例为SPS的多个预测实例中由DCI或MAC CE激活的预测实例。
在一些实施例中，该F个预测实例为预先配置的多个预测实例中由DCI动态触发的预测实例。也即，本实施例中，一个DCI可以从预先配置的多个预测实例触发F个预测实例。这样做的好处是可以仅使用一个DCI(最小的信令开销)来触发F个预测实例的预测。
在一些实施例中，该F个预测实例为多套预测配置中由DCI或MAC CE激活的一套预测配置对应的预测实例，或者，该F个预测实例为由DCI或MAC CE激活的轮流使用的多套预测配置中当前的预测配置对应的预测实例。可选地，该多套预测配置由网络设备提前配置或半静态配置。
在一些实施例中，对于每一个预测实例，第一网络模型可以推断出K个空间滤波器的标识信息和K个空间滤波器对应的链路质量信息。
在一些实施例中，对于每一个预测实例，第一网络模型可以推断出K个空间滤波器的标识信息、K个空间滤波器对应的链路质量信息和K个空间滤波器的持续时间。
具体例如，假设空间滤波器为波束对，对于每一个预测实例，第一网络模型还可以推断出最优的波束对的持续时间(dwelling time)。举例来说，如图12所示，在Set A#1和Set A#2之间，有一段时间，可以定义为时间间隔(time gap)#1。第一网络模型为Set A#1的预测实例(instance)推测出最优的K个波束对，第一网络模型还可以预测出该K个波束对的L1-RSRP保持稳定的时间。这里的保持稳定可以从相对质量来定义，即波束质量排名，如Top-1的波束对保持第一的时间。也可以从L1-RSRP的绝对质量来定义，如Top-1的波束对的L1-RSRP下降小于一定门限(如3dB)的时间。好处是可以更仔细地刻画有效波束对的持续时间，从而给网络(NW)提供更多的波束信息，使得NW可以在后续的波束指示中提前调整或延后调整波束。
在一些实施例中，网络设备可以配置第一预测数据集中的F个预测实例，或者，网络设备可以激活第一预测数据集中的F个预测实例，或者，网络设备可以更新第一预测数据集中的F个预测实例。例如，网络设备可以通过RRC信令配置多个预测实例，以及通过MAC CE信令激活第一预测数据集中的F个预测实例。
在一些实施例中，该第一通信设备发送第一信息；
其中，该第一信息包括以下至少之一：该F个预测实例中的每个预测实例中预测的该K个空间滤波器的标识信息，该F个预测实例中的每个预测实例中预测的该K个空间滤波器对应的链路质量信息，该F个预测实例中的每个预测实例中预测的该K个空间滤波器的持续时间。
也即，第一通信设备可以上报F个预测实例中的预测信息。
具体例如，该第一通信设备向第二通信设备发送该第一信息，其中，该第一通信设备为终端设备，该第二通信设备为网络设备。也即，在第一网络模型完成时域空间滤波器的预测后，终端设备需要将第一网络模型在F个预测实例的预测结果上报给网络设备。
在一些实施例中，该第一信息通过以下之一承载：
上行控制信息(Uplink Control Information，UCI)，MAC CE信令，无线资源控制(Radio Resource Control，RRC)信令。
在一些实施例中，该K个空间滤波器对应的链路质量信息通过差分方式发送。
具体例如，假设第一预测数据集为Set A，F个预测实例分别记为Set A#1、Set A#2、…、Set A#F-1、Set A#F，且假设空间滤波器为发射接收波束对(Tx-Rx beam pair)、链路质量信息为L1-RSRP。可选地，如表1所示，终端设备可以通过信道状态信息(Channel State Information，CSI)报告向网络设备发送F个预测实例的预测结果，其中，该F个预测实例的预测结果包括4个Tx-Rx beam pair，及4个Tx-Rx beam pair分别对应的L1-RSRP。可选地，如表2所示，终端设备可以通过CSI报告向网络设备发送F个预测实例的预测结果，其中，该F个预测实例的预测结果包括4个Tx-Rx beam pair、4个Tx-Rx beam pair分别对应的L1-RSRP，及4个Tx-Rx beam pair的持续时间(Beam dwelling time)。也即，在表1和表2中，K＝4。应理解，表1和表2仅为示例，并不对本申请实施例构成限定。
可选地，终端设备可以通过一个CSI报告上报F个预测实例的预测结果。也即，终端设备可以通过一个CSI报告上报表1或表2中的全部内容。
可选地，终端设备可以通过多个CSI报告上报F个预测实例的预测结果。例如，终端设备在每个CSI报告中上报一个预测实例的预测结果。也即，终端设备可以通过F个CSI报告分别上报表1中的F个预测实例的预测结果，或者，终端设备可以通过F个CSI报告分别上报表2中的F个预测实例的预测结果。
表1 UE上报F个预测实例的波束对ID和L1-RSRP性能
Figure PCTCN2022128935-appb-000001
需要说明的是，在上述表1中，在一个预测实例中，Differential L1-RSRP#2为相对于L1-RSRP#1的差值，Differential L1-RSRP#3为相对于L1-RSRP#1的差值，Differential L1-RSRP#4为相对于L1-RSRP#1的差值，L1-RSRP#1为Tx-Rx beam pair#1对应的L1-RSRP，Differential L1-RSRP#2为Tx-Rx beam pair#2对应的L1-RSRP，Differential L1-RSRP#3为Tx-Rx beam pair#3对应的L1-RSRP，Differential L1-RSRP#4为Tx-Rx beam pair#4对应的L1-RSRP。
表2 UE上报F个预测实例的波束对ID、L1-RSRP性能以及波束持续时间
Figure PCTCN2022128935-appb-000002
需要说明的是，在上述表2中，在一个预测实例中，Differential L1-RSRP#2为相对于L1-RSRP#1的差值，Differential L1-RSRP#3为相对于L1-RSRP#1的差值，Differential L1-RSRP#4为相对于L1-RSRP#1的差值；L1-RSRP#1为Tx-Rx beam pair#1对应的L1-RSRP，Differential L1-RSRP#2为Tx-Rx beam pair#2对应的L1-RSRP，Differential L1-RSRP#3为Tx-Rx beam pair#3对应的L1-RSRP，Differential L1-RSRP#4为Tx-Rx beam pair#4对应的L1-RSRP；Beam dwelling time#1为Tx-Rx beam pair#1的波束持续时间，Beam dwelling time#2为Tx-Rx beam pair#2的波束持续时间，Beam dwelling time#3为Tx-Rx beam pair#3的波束持续时间，Beam dwelling time#4为Tx-Rx beam pair#4的波束持续时间。
在一些实施例中，该第一通信设备接收基于该第一信息确定的第二信息；
其中，该第二信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息，或者，该第二信息用于指示第i个预测实例中使用的空间滤波器的标识信息；或者，该第二信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，该第二信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间；
其中，i为正整数，且1≤i≤F。
也即，第一通信设备可以通过第二信息获取预测实例中使用的空间滤波器的标识信息，或者，第一通信设备可以通过第二信息获取预测实例中使用的空间滤波器的标识信息和持续时间。
具体的，在该第一预测数据集包括F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间的情况下，该第二信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，该第二信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间。
具体例如，第一通信设备接收第二通信设备发送的该第二信息，其中，该第一通信设备为终端设备，该第二通信设备为网络设备。也即，网络设备可以基于终端设备上报的第一网络模型的预测结果进行波束指示。
在一些实施例中，该第二信息通过以下之一承载：
下行控制信息(Downlink Control Information，DCI)，MAC CE信令。
具体的，在终端设备上报的F个预测实例中的预测结果的基础上，网络设备的波束指示有至少两种方式。第一种方式为，网络设备按照终端设备的上报分批次进行波束指示，如在F个预测实例的波束预测下，进行F次波束信息指示，即分别指示F个预测实例中的每个预测实例中使用的波束；其中，该波束信息可以是波束对的索引，也可以是波束对中发射波束的索引(在NR中，一般使用SSB或CSI-RS的资源索引来指代)。另一种方式是进行一次性的波束指示，即网络设备一次指示F个预测实例的波束信息给终端设备，即一次指示F个预测实例中的每个预测实例中使用的波束。一次性的波束指示的好处是可以大量地减少波束指示的信令开销。
具体例如，如果UE的波束上报不包含波束持续时间，NW一次性的指示F个预测实例中的每个预测实例中使用的波束信息。如果该波束信息是Tx-Rx波束对索引，那么在MAC CE或DCI中应该包含Tx-Rx beam pair index#1，Tx-Rx beam pair index#2，…，Tx-Rx beam pair index#F。如果该波束信息是Tx波束索引，那么在MAC CE或DCI中应该包含Tx beam index(CSI-RS/SSB)#1，Tx beam index(CSI-RS/SSB)#2，…，Tx beam index(CSI-RS/SSB)#F。在时间域的含义是每当预测实例到来时，NW会更换为所指示的发射波束，UE也应该更换对应的接收波束。
具体例如，如果UE的波束上报包含波束持续时间，那么NW可以选择一次性地将F个预测实例中的每个预测实例中使用的波束信息和波束持续时间指示给UE。如果该波束信息是Tx-Rx波束对索引，那么在MAC CE或DCI(即第二信息)中应该包含(Tx-Rx beam pair index#1，Application time#1)，(Tx-Rx beam pair index#2，Application time#2)，…，(Tx-Rx beam pair index#F，Application time#F)。如果该波束信息是Tx波束索引，那么在MAC CE或DCI(即第二信息)中应该包含(Tx beam index(CSI-RS/SSB)#1，Application time#1)，(Tx beam index(CSI-RS/SSB)#2，Application time#2)，…，(Tx beam index(CSI-RS/SSB)#F，Application time#F)。在时间域的含义是每个指示的波束对从预测的instance开始生效，其生效的时长是应用时间(application time)所指示的波束持续时间(beam dwelling time)。
在一些实施例中，该第一通信设备发送第一能力信息；
其中，该第一能力信息包括以下至少之一：该第一测量数据集最多支持的空间滤波器的数量，该第一测量数据集最多支持的测量实例的数量，该第一预测数据集最多支持的空间滤波器的数量，该第一预测数据集最多支持的预测实例的数量，是否支持空间滤波器的持续时间的预测和上报，是否支持一次性的指示多个预测实例中的空间滤波器的标识信息。
具体例如，第一通信设备向第二通信设备发送该第一能力信息，其中，该第一通信设备为终端设备，该第二通信设备为网络设备。
也即，终端设备可以上报第一能力信息，以及，网络设备可以基于第一能力信息配置或激活或更新M个测量实例和/或F个预测实例，和/或，网络设备可以基于第一能力信息指示F个预测实例中的每个预测实例中使用的空间滤波器的标识信息。
在一些实施例中，该第一能力信息可以通过以下之一承载：UCI，MAC CE信令，RRC信令。
具体例如，第一测量数据集为Set B，第一预测数据集为Set A，终端设备可以上报如下能力信息：
Set B的空间域容量：最多支持多少个波束对的测量(一次)；
Set B的时间域容量：最多支持多少个测量实例；
Set A的空间域容量：最多支持多少个波束对的预测(一次)；
Set A的时间域容量：最多支持多少个预测实例；
是否支持波束持续时间的预测和上报；
是否支持一次性的波束信息指示。
在一些实施例中，在第一通信设备为终端设备(UE)的情况下，网络设备(NW)和终端设备(UE) 之间为了完成时间域波束预测的信令交互过程可以如图13所示，其中包括UE的能力上报，NW对于波束测量集(Set B)和波束预测集(Set A)的配置和激活，UE对波束测量集的测量，UE使用第一网络模型对波束预测集的推断，UE上报预测结果，NW对于预测实例中使用的波束的指示等过程。需要说明的是，波束测量集(Set B)即为上述第一测量数据集，波束预测集(Set A)即为上述第一预测数据集。
在一些实施例中，该第一通信设备发送第三信息；
其中，该第三信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息，或者，该第三信息用于指示第i个预测实例中使用的空间滤波器的标识信息；或者，该第三信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，该第三信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间；
其中，i为正整数，且1≤i≤F。
也即，第一通信设备可以通过第三信息指示预测实例中使用的空间滤波器的标识信息。
具体的，在该第一预测数据集包括F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间的情况下，该第三信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，该第三信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间。
具体例如，第一通信设备向第二通信设备发送该第三信息，其中，该第一通信设备为网络设备，该第二通信设备为终端设备。也即，网络设备可以基于第一网络模型的预测结果进行波束指示。
在一些实施例中，该第三信息通过以下之一承载：DCI，MAC CE信令。
具体的，在网络设备预测的F个预测实例中的预测结果的基础上，网络设备的波束指示有至少两种方式。第一种方式为，网络设备按照预测结果分批次进行波束指示，如在F个预测实例的波束预测下，进行F次波束信息指示，即分别指示F个预测实例中的每个预测实例中使用的波束；其中，该波束信息可以是波束对的索引，也可以是波束对中发射波束的索引(在NR中，一般使用SSB或CSI-RS的资源索引来指代)。另一种方式是进行一次性的波束指示，即网络设备一次指示F个预测实例的波束信息给终端设备，即一次指示F个预测实例中的每个预测实例中使用的波束。一次性的波束指示的好处是可以大量地减少波束指示的信令开销。
具体例如，如果网络设备预测的预测实例中预测结果不包含波束持续时间，网络设备一次性的指示F个预测实例中的每个预测实例中使用的波束信息。如果该波束信息是Tx-Rx波束对索引，那么在MAC CE或DCI(即第三信息)中应该包含Tx-Rx beam pair index#1，Tx-Rx beam pair index#2，…，Tx-Rx beam pair index#F。如果该波束信息是Tx波束索引，那么在MAC CE或DCI(即第三信息)中应该包含Tx beam index(CSI-RS/SSB)#1，Tx beam index(CSI-RS/SSB)#2，…，Tx beam index(CSI-RS/SSB)#F。在时间域的含义是每当预测实例到来时，NW会更换为所指示的发射波束，UE也应该更换对应的接收波束。
具体例如，如果网络设备预测的预测实例中预测结果包含波束持续时间，那么网络设备可以选择一次性地将F个预测实例中的每个预测实例中使用的波束信息和波束持续时间指示给UE。如果该波束信息是Tx-Rx波束对索引，那么在MAC CE或DCI(即第三信息)中应该包含(Tx-Rx beam pair index#1，Application time#1)，(Tx-Rx beam pair index#2，Application time#2)，…，(Tx-Rx beam pair index#F，Application time#F)。如果该波束信息是Tx波束索引，那么在MAC CE或DCI(即第三信息)中应该包含(Tx beam index(CSI-RS/SSB)#1，Application time#1)，(Tx beam index(CSI-RS/SSB)#2，Application time#2)，…，(Tx beam index(CSI-RS/SSB)#F，Application time#F)。在时间域的含义是每个指示的波束对从预测的instance开始生效，其生效的时长是应用时间(application time)所指示的波束持续时间(beam dwelling time)。
在一些实施例中，该第一通信设备接收第一能力信息；
其中，该第一能力信息包括以下至少之一：该第一测量数据集最多支持的空间滤波器的数量，该第一测量数据集最多支持的测量实例的数量，该第一预测数据集最多支持的空间滤波器的数量，该第一预测数据集最多支持的预测实例的数量，是否支持空间滤波器的持续时间的预测和上报，是否支持一次性的指示多个预测实例中的空间滤波器的标识信息。
具体例如，第一通信设备接收第二通信设备发送的该第一能力信息，其中，该第一通信设备为网络设备，该第二通信设备为终端设备。
也即，终端设备可以上报第一能力信息，以及，网络设备可以基于第一能力信息配置或激活或更新M个测量实例和/或F个预测实例，和/或，网络设备可以基于第一能力信息指示F个预测实例中的每个预测实例中使用的空间滤波器的标识信息。
在一些实施例中，该第一能力信息可以通过以下之一承载：UCI，MAC CE信令，RRC信令。
具体例如，第一测量数据集为Set B，第一预测数据集为Set A，终端设备可以上报如下能力信息：
Set B的空间域容量：最多支持多少个波束对的测量(一次)；
Set B的时间域容量：最多支持多少个测量实例；
Set A的空间域容量：最多支持多少个波束对的预测(一次)；
Set A的时间域容量：最多支持多少个预测实例；
是否支持波束持续时间的预测和上报；
是否支持一次性的波束信息指示。
在一些实施例中，在第一通信设备为网络设备(NW)的情况下，假设第一测量数据集为Set B，UE需要测量Set B的M个测量实例。然后上报全部测量结果给NW侧的模型。具体上报方式如示例1和示例2所述。
示例1，按照Set B m，1<＝m<＝M中的时域顺序就行上报。在每一个测量实例中，按照配置的发射接收波束对(Tx-Rx beam pair)顺序来上报，如表3所示，这里仅需要上报相应的L1-RSRP或其他性能指标即可。
表3 UE按照Set B的时域顺序上报L1-RSRP值
Figure PCTCN2022128935-appb-000003
示例2，按照Set B中各个发射接收波束对(Tx-Rx beam pair)的性能(如L1-RSRP)来进行排序，一般是按照性能从高到低进行排序。如表4所示，首先是Set B中的Tx-Rx beam pair ID，然后是最高的波束对的性能绝对值，如L1-RSRP的绝对值量化，对于非最高性能的波束对的性能，可以采用差分的方式进行量化，即上报相较于最高性能其性能的差值是多少。
表4 UE按照Set B的时域顺序上报L1-RSRP值
Figure PCTCN2022128935-appb-000004
需要说明的是，在上述表4中，在一个预测实例中，Differential L1-RSRP#2为相对于L1-RSRP#1的差值，Differential L1-RSRP#3为相对于L1-RSRP#1的差值，Differential L1-RSRP#4为相对于L1-RSRP#1的差值。
在一些实施例中，在第一通信设备为网络设备(NW)的情况下，网络设备(NW)和终端设备(UE)之间为了完成时间域波束预测的信令交互过程可以如图14所示，其中包括UE的能力上报，NW对于波束测量集(Set B)和波束预测集(Set A)的配置和激活，UE对波束测量集的测量，UE上报针对波束测量集的测量结果，网络设备使用第一网络模型对波束预测集的推断，NW对于预测实例中使用的波束的指示等过程。需要说明的是，波束测量集(Set B)即为上述第一测量数据集，波束预测集(Set A)即为上述第一预测数据集。
以下通过实施例1和实施例2详述本申请技术方案。
实施例1，模型部署在UE侧，发射(transmission，Tx)波束预测，第一测量数据集为Set B，M个测量实例分别记为Set B#1、Set B#2、…、Set B#M-1、Set B#M。第一预测数据集为Set A，F个预测实例分别记为Set A#1、Set A#2、…、Set A#F-1、Set A#F。
总体上来看，Tx波束预测和P2过程的目的是一致的，即在发射波束扫描的过程中，以最优的接收波束或固定接收波束找到合适的发射波束。在波束扫描的过程中，NW扫描发射波束，UE使用固定的接收波束。
UE波束能力上报
可选地，UE需要上报以下信息中的至少一种：
Set B的空间域容量：最多支持多少个Tx波束的测量(一次)；
Set B的时间域容量：最多支持多少个测量实例；
Set A的空间域容量：最多支持多少个Tx波束的预测(一次)；
Set A的时间域容量：最多支持多少个预测实例；
是否支持Tx波束持续时间的预测和上报；
是否支持NW一次性的Tx波束信息指示。
NW对于Set A和Set B的配置，激活与更新
对于Set B的配置，在M个测量实例可以是固定的，也可以是不固定的。对于不固定情况，Set B m，1<＝m<＝M可以以一个特定的模式(pattern)出现，如图15所示，Set B在不同的测量实例上有不同的Tx波束配置。
举例来说，Set B#1包含Tx波束从index#0到index#3，Set B#2包含Tx波束从index#4到index#5，…，Set B#M包含Tx波束从index#6到index#9。上述是Tx波束没有重合的例子。需要说明的是，UE测量的不同测量实例所包含的Tx波束也可以有一定程度的重叠，甚至是完全的重叠。举例来说，Set B#1和Set B#M可以包含同样的Tx beam index#0到#3。
在Set B的不同测量实例之间的时域间隔可以是等间隔的，如通过RRC配置的周期性测量；也可以是非等间隔的，如图15中不同的time gap所示。对于时域非均匀间隔的Set B测量，从NW配置的角度来说，对于周期性和半静态的测量，NW可以给不同的测量实例配置相同的周期(periodicity)和不同的偏移量(offset)。
对于非周期的Set B测量，另外一个办法就是NW提前配置一些非周期的Set B测量，然后使用DCI动态地触发非周期的测量，从而实现非均匀间隔测量的目的。在时间域波束预测的用例中，本案设计一个DCI可以触发M个(一个序列)的非周期CSI-RS，它可以包含Set B m，1<＝m<＝M，如图16所示。这样做的好处是可以仅使用一个DCI(最小的信令开销)来完成Set B的测量。
对于Set A的配置，在F个预测实例上，Set A可以是固定的，也可以是不固定的。对于不固定情况，Set A f,1<＝f<＝F可以按照预先配置好的模式(pattern)出现，如图17所示，Set A在不同的预测实例上有不同的Tx波束配置。
举例来说，Set A#1包含Tx波束从index#0到index#5，Set A#2包含Tx波束从index#0到index#3，…，Set A#F包含Tx波束从index#0到index#6。需要说明上述的多个Set A可以重叠，也可以不重叠。
在Set A的不同预测之间，它们的时域间隔可以是等间隔的，如通过RRC配置的周期性预测；也可以是非等间隔的，如图17中不同的time gap所示。对于非均匀间隔的Set A预测，从NW配置的角度来说，NW可以给不同的预测实例配置相同的周期(periodicity)和不同的偏移量(offset)。
除了上述NW对于Set B和Set A在多个实例上的配置外，可以考虑NW进行多套Set B和Set A的配置，然后使用MAC CE来激活一套配置来使用。也可以考虑使用MAC CE来激活多套配置来轮流使用。举例来说，使用Set A的配置X，接下来使用Set A的配置Y，然后轮流出现配置X和配置Y，如图18所示。
UE的测量和推断
NW的Set B和Set A配置并激活后，UE进行M个测量实例的Set B的测量。用来作为模型的输入，测量集合Set Bm，其中1<＝m<＝M。
接下来，模型从Set Af,1<＝f<＝F推断F个预测实例中的最优K个Tx波束及其性能(如L1-RSRP)。K个最优的Tx波束是按照该Tx波束的L1-RSRP从高到低排序得到的。K的取值一般为1，2，4或8。或者模型可以推断出若干个Tx波束，只要其性能(如L1-RSRP)在某个预先设定好的门限之上便可。
对于每一个预测实例，模型还可以推断出最优的Tx波束的持续时间(beam dwelling time)。举例来说，在Set A#1和Set A#2中间，有一段时间，我们定义为time gap#1。当模型为Set A#1的预测实例推测出最优的K个Tx波束，还可以预测出K个Tx波束的L1-RSRP保持稳定的时间。这里的保持稳定可以从相对质量来定义，即波束质量排名，如Top-1的Tx波束保持第一的时间。也可以从L1-RSRP的绝对质量来定义，如Top-1的Tx波束的L1-RSRP下降小于一定门限(如3dB)的时间。具体的，时域波束预测中波束持续时间(beam dwelling time)可以如图19所示。
UE的波束信息上报
在模型完成时域波束对的预测后，UE需要将模型的F个预测实例的预测结果上报给NW。具体格式参考如下表5或表6。
表5 UE上报F个预测实例的Tx波束ID以及其L1-RSRP性能
Figure PCTCN2022128935-appb-000005
需要说明的是，在上述表5中，在一个预测实例中，Differential L1-RSRP#2为相对于L1-RSRP#1的差值，Differential L1-RSRP#3为相对于L1-RSRP#1的差值，Differential L1-RSRP#4为相对于L1-RSRP#1的差值；L1-RSRP#1为Tx beam pair#1对应的L1-RSRP，Differential L1-RSRP#2为Tx beam pair#2对应的L1-RSRP，Differential L1-RSRP#3为Tx beam pair#3对应的L1-RSRP，Differential L1-RSRP#4为Tx beam pair#4对应的L1-RSRP。
表6 UE上报F个预测实例的Tx波束ID，L1-RSRP性能以及Tx波束持续时间
Figure PCTCN2022128935-appb-000006
需要说明的是，在上述表6中，在一个预测实例中，Differential L1-RSRP#2为相对于L1-RSRP#1的差值，Differential L1-RSRP#3为相对于L1-RSRP#1的差值，Differential L1-RSRP#4为相对于L1-RSRP#1的差值；L1-RSRP#1为Tx beam pair#1对应的L1-RSRP，Differential L1-RSRP#2为Tx beam pair#2对应的L1-RSRP，Differential L1-RSRP#3为Tx beam pair#3对应的L1-RSRP，Differential L1-RSRP#4为Tx beam pair#4对应的L1-RSRP；Beam dwelling time#1为Tx beam pair#1的波束持续时间，Beam dwelling time#2为Tx beam pair#2的波束持续时间，Beam dwelling time#3为Tx beam pair#3的波束持续时间，Beam dwelling time#4为Tx beam pair#4的波束持续时间。
另外，考虑在上报波束持续时间的格式中，也可以考虑差分式的上报，即Beam dwelling time#1是绝对时间，Beam dwelling time#2到Beam dwelling time#4是相对于Beam dwelling time#1的时间差。
NW的波束指示
具体的，在终端设备上报的F个预测实例中的预测结果的基础上，网络设备的波束指示有至少两种方式。第一种方式为，网络设备按照终端设备的上报分批次进行波束指示，如在F个预测实例的波束预测下，进行F次波束信息指示，即分别指示F个预测实例中的每个预测实例中使用的波束；其中，该波束信息可以是发射波束的索引(在NR中，一般使用SSB或CSI-RS的资源索引来指代)。另一种方式是进行一次性的波束指示，即网络设备一次指示F个预测实例的波束信息给终端设备，即一次指示F个预测实例中的每个预测实例中使用的波束。一次性的波束指示的好处是可以大量地减少波束指示的信令开销。
具体例如，如果UE的波束上报不包含波束持续时间，NW一次性的指示F个预测实例中的每个预测实例中使用的波束信息。在MAC CE或DCI中应该包含Tx beam index(CSI-RS/SSB)#1，Tx beam index(CSI-RS/SSB)#2，…，Tx beam index(CSI-RS/SSB)#F。在时间域的含义是每当预测实例到来时，NW会更换为所指示的发射波束，UE也应该更换对应的接收波束。
具体例如，如果UE的波束上报包含波束持续时间，那么NW可以选择一次性地将F个预测实例中的每个预测实例中使用的波束信息和波束持续时间指示给UE。在MAC CE或DCI(即第二信息)中应该包含(Tx beam index(CSI-RS/SSB)#1，Application time#1)，(Tx beam index(CSI-RS/SSB)#2，Application time#2)，…，(Tx beam index(CSI-RS/SSB)#F，Application time#F)。在时间域的含义是每个指示的波束对从预测的instance开始生效，其生效的时长是应用时间(application time)所指示的波束持续时间(beam dwelling time)。
实施例2，模型部署在网络(NW)侧，发射(transmission，Tx)波束预测，第一测量数据集为Set B，M个测量实例分别记为Set B#1、Set B#2、…、Set B#M-1、Set B#M。第一预测数据集为Set A，F个预测实例分别记为Set A#1、Set A#2、…、Set A#F-1、Set A#F。
总体上来看，Tx波束预测和P2过程的目的是一致的，即在发射波束扫描的过程中，以最优的接收波束或固定接收波束找到合适的发射波束。在波束扫描的过程中，NW扫描发射波束，UE使用固定的接收波束。
UE波束能力上报
可选地，UE需要上报以下信息中的至少一种：
Set B的空间域容量：最多支持多少个Tx波束的测量(一次)；
Set B的时间域容量：最多支持多少个测量实例；
Set A的空间域容量：最多支持多少个Tx波束的预测(一次)；
Set A的时间域容量：最多支持多少个预测实例；
是否支持Tx波束持续时间的预测和上报；
是否支持NW一次性的Tx波束信息指示。
NW对于Set A和Set B的配置，激活与更新
对于Set B的配置，在M个测量实例可以是固定的，也可以是不固定的。对于不固定情况，Set B m，1<＝m<＝M可以以一个特定的模式(pattern)出现，如图15所示，Set B在不同的测量实例上有不同的Tx波束配置。
举例来说，Set B#1包含Tx波束从index#0到index#3，Set B#2包含Tx波束从index#4到index#5，…，Set B#M包含Tx波束从index#6到index#9。上述是Tx波束没有重合的例子。需要说明的是，UE测量的不同测量实例所包含的Tx波束也可以有一定程度的重叠，甚至是完全的重叠。举例来说，Set B#1和Set B#M可以包含同样的Tx beam index#0到#3。
在Set B的不同测量实例之间的时域间隔可以是等间隔的，如通过RRC配置的周期性测量；也可以是非等间隔的，如图15中不同的time gap所示。对于时域非均匀间隔的Set B测量，从NW配置的角度来说，对于周期性和半静态的测量，NW可以给不同的测量实例配置相同的周期(periodicity)和不同的偏移量(offset)。
对于非周期的Set B测量，另外一个办法就是NW提前配置一些非周期的Set B测量，然后使用DCI动态地触发非周期的测量，从而实现非均匀间隔测量的目的。在时间域波束预测的用例中，本案设计一个DCI可以触发M个(一个序列)的非周期CSI-RS，它可以包含Set B m，1<＝m<＝M，如图16所示。这样做的好处是可以仅使用一个DCI(最小的信令开销)来完成Set B的测量。
对于Set A的配置，在F个预测实例上，Set A可以是固定的，也可以是不固定的。对于不固定情况，Set A f,1<＝f<＝F可以按照预先配置好的模式(pattern)出现，如图17所示，Set A在不同的预测实例上有不同的Tx波束配置。
举例来说，Set A#1包含Tx波束从index#0到index#5，Set A#2包含Tx波束从index#0到index#3，…，Set A#F包含Tx波束从index#0到index#6。需要说明上述的多个Set A可以重叠，也可以 不重叠。
在Set A的不同预测之间，它们的时域间隔可以是等间隔的，如通过RRC配置的周期性预测；也可以是非等间隔的，如图17中不同的time gap所示。对于非均匀间隔的Set A预测，从NW配置的角度来说，NW可以给不同的预测实例配置相同的周期(periodicity)和不同的偏移量(offset)。
除了上述NW对于Set B和Set A在多个实例上的配置外，可以考虑NW进行多套Set B和Set A的配置，然后使用MAC CE来激活一套配置来使用。也可以考虑使用MAC CE来激活多套配置来轮流使用。举例来说，使用Set A的配置X，接下来使用Set A的配置Y，然后轮流出现配置X和配置Y，如图18所示。
UE测量并上报Set B
对于模型部署在NW侧的情况，UE需要测量Set B的M个测量实例。然后上报全部测量结果给NW侧的模型。这里可以考虑重新设计波束上报的格式。具体上报方式如示例3和示例4所述。
示例3，按照Set B m，1<＝m<＝M中的时域顺序就行上报。在每一个测量实例中，按照配置的发射波束(Tx beam)顺序上报，如表7所示，这里仅需要上报相应的L1-RSRP或其他性能指标即可。
表7 UE按照Set B的时域顺序上报L1-RSRP值
Figure PCTCN2022128935-appb-000007
示例4，按照Set B中各个发射波束(Tx beam)的性能(如L1-RSRP)来进行排序，一般是按照性能从高到低进行排序。如表8所示，首先是Set B中的Tx beam ID，然后是最高的Tx波束的性能绝对值，如L1-RSRP的绝对值量化，对于非最高性能的波束对的性能，可以采用差分的方式进行量化，即上报相较于最高性能其性能的差值是多少。
表8 UE按照时域顺序上报Set B Tx波束ID以及L1-RSRP值
Figure PCTCN2022128935-appb-000008
需要说明的是，在上述表8中，在一个预测实例中，Differential L1-RSRP#2为相对于L1-RSRP#1的差值，Differential L1-RSRP#3为相对于L1-RSRP#1的差值，Differential L1-RSRP#4为相对于L1-RSRP#1的差值。
NW执行波束预测
NW使用模型从Set Af,1<＝f<＝F推断F个预测实例中的最优K个Tx波束及其性能(如L1-RSRP)。K个最优的Tx波束是按照该Tx波束的L1-RSRP从高到低排序得到的。K的取值一般为1，2，4或8。或者模型可以推断出若干个Tx波束，只要其性能(如L1-RSRP)在某个预先设定好的门限之上便可。
对于每一个预测实例，模型还可以推断出最优的Tx波束的持续时间(beam dwelling time)。举例来说，在Set A#1和Set A#2中间，有一段时间，我们定义为time gap#1。当模型为Set A#1的预测实例推测出最优的K个Tx波束，还可以预测出K个Tx波束的L1-RSRP保持稳定的时间。这里的保持稳定可以从相对质量来定义，即波束质量排名，如Top-1的Tx波束保持第一的时间。也可以从L1-RSRP的绝对质量来定义，如Top-1的Tx波束的L1-RSRP下降小于一定门限(如3dB)的时间。
NW的波束指示
具体的，在网络设备预测的F个预测实例中的预测结果的基础上，网络设备的波束指示有至少两种方式。第一种方式为，网络设备按照预测结果分批次进行波束指示，如在F个预测实例的波束预测下，进行F次波束信息指示，即分别指示F个预测实例中的每个预测实例中使用的波束；其中，该波束信息可以是发射波束的索引(在NR中，一般使用SSB或CSI-RS的资源索引来指代)。另一种方式是进行一次性的波束指示，即网络设备一次指示F个预测实例的波束信息给终端设备，即一次指示F个预测实例中的每个预测实例中使用的波束。一次性的波束指示的好处是可以大量地减少波束指示的信令开销。
具体例如，如果网络设备预测的预测实例中预测结果不包含波束持续时间，网络设备一次性的指示F个预测实例中的每个预测实例中使用的波束信息。在MAC CE或DCI中应该包含Tx beam index(CSI-RS/SSB)#1，Tx beam index(CSI-RS/SSB)#2，…，Tx beam index(CSI-RS/SSB)#F。在时间域的含义是每当预测实例到来时，NW会更换为所指示的发射波束，UE也应该更换对应的接收波束。
具体例如，如果网络设备预测的预测实例中预测结果包含波束持续时间，那么网络设备可以选择 一次性地将F个预测实例中的每个预测实例中使用的波束信息和波束持续时间指示给UE。在MAC CE或DCI中应该包含(Tx beam index(CSI-RS/SSB)#1，Application time#1)，(Tx beam index(CSI-RS/SSB)#2，Application time#2)，…，(Tx beam index(CSI-RS/SSB)#F，Application time#F)。在时间域的含义是每个指示的波束对从预测的instance开始生效，其生效的时长是应用时间(application time)所指示的波束持续时间(beam dwelling time)。
因此，在本申请实施例中，第一通信设备可以基于第一网络模型实现时域上的空间滤波器预测，并且，第一通信设备可以不必对部署的所有空间滤波器均进行扫描，有利于降低空间滤波器扫描带来的开销和时延。
上文结合图10至图19，详细描述了本申请的方法实施例，下文结合图20至图23，详细描述本申请的装置实施例，应理解，装置实施例与方法实施例相互对应，类似的描述可以参照方法实施例。
图20示出了根据本申请实施例的通信设备300的示意性框图。该通信设备300为第一通信设备，如图20所示，该通信设备300包括：
处理单元310，用于获取第一测量数据集；其中，该第一测量数据集包括以下至少之一：M个测量实例中空间滤波器的标识信息，M个测量实例中空间滤波器对应的链路质量信息；其中，M为正整数；
该处理单元310还用于将该第一测量数据集输入第一网络模型，输出第一预测数据集；其中，该第一预测数据集包括以下至少之一：F个预测实例中的每个预测实例中预测的K个空间滤波器的标识信息，F个预测实例中的每个预测实例中预测的K个空间滤波器对应的链路质量信息，F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间；其中，F和K均为正整数。
在一些实施例中，该M个测量实例中每个测量实例中的空间滤波器为全部空间滤波器中的部分空间滤波器。
在一些实施例中，该M个测量实例中每个测量实例中的空间滤波器的配置相同；或者，
该M个测量实例中至少部分测量实例中的空间滤波器的配置不同。
在一些实施例中，该M个测量实例中不同的测量实例中的部分空间滤波器相同。
在一些实施例中，该M个测量实例在时域上等间隔设置。
在一些实施例中，该M个测量实例对应第一时长内的周期性空间滤波器测量。
在一些实施例中，该M个测量实例在时域上非等间隔设置。
在一些实施例中，该M个测量实例在时域上的间隔基于终端设备的移动速度确定。
在一些实施例中，该M个测量实例中不同的测量实例对应相同的周期和不同的偏移量。
在一些实施例中，该M个测量实例为半持续调度SPS的多个测量实例中由下行控制信息DCI或媒体接入控制层控制单元MAC CE激活的测量实例；或者，
该M个测量实例为预先配置的多个测量实例中由DCI动态触发的测量实例。
在一些实施例中，该M个测量实例为多套测量配置中由DCI或MAC CE激活的一套测量配置对应的测量实例，或者，该M个测量实例为由DCI或MAC CE激活的轮流使用的多套测量配置中当前的测量配置对应的测量实例。
在一些实施例中，该F个预测实例中的每个测量实例中的空间滤波器为全部空间滤波器中的部分空间滤波器。
在一些实施例中，该F个预测实例中每个预测实例中的空间滤波器的配置相同；或者，
该F个预测实例中至少部分预测实例中的空间滤波器的配置不同。
在一些实施例中，该F个预测实例中不同的预测实例中的部分或者全部空间滤波器相同。
在一些实施例中，该F个预测实例在时域上等间隔设置。
在一些实施例中，该F个预测实例对应第二时长内的周期性空间滤波器预测。
在一些实施例中，该F个预测实例在时域上非等间隔设置。
在一些实施例中，该F个预测实例在时域上的间隔基于终端设备的移动速度确定。
在一些实施例中，该F个预测实例中不同的预测实例对应相同的周期和不同的偏移量。
在一些实施例中，该F个预测实例为SPS的多个预测实例中由DCI或MAC CE激活的预测实例；或者，该F个预测实例为预先配置的多个预测实例中由DCI动态触发的预测实例。
在一些实施例中，该F个预测实例为多套预测配置中由DCI或MAC CE激活的一套预测配置对应的预测实例，或者，该F个预测实例为由DCI或MAC CE激活的轮流使用的多套预测配置中当前的预测配置对应的预测实例。
在一些实施例中，K的取值包括以下之一：1，2，4，8。
在一些实施例中，该通信设备300还包括：通信单元320；
该通信单元320用于发送第一信息；
其中，该第一信息包括以下至少之一：该F个预测实例中的每个预测实例中预测的该K个空间滤波器的标识信息，该F个预测实例中的每个预测实例中预测的该K个空间滤波器对应的链路质量信息，该F个预测实例中的每个预测实例中预测的该K个空间滤波器的持续时间。
在一些实施例中，该K个空间滤波器对应的链路质量信息通过差分方式发送。
在一些实施例中，该通信单元320还用于接收基于该第一信息确定的第二信息；
其中，该第二信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息，或者，该第二信息用于指示第i个预测实例中使用的空间滤波器的标识信息；或者，该第二信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，该第二信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间；
其中，i为正整数，且1≤i≤F。
在一些实施例中，该通信单元320还用于发送第一能力信息；
其中，该第一能力信息包括以下至少之一：该第一测量数据集最多支持的空间滤波器的数量，该第一测量数据集最多支持的测量实例的数量，该第一预测数据集最多支持的空间滤波器的数量，该第一预测数据集最多支持的预测实例的数量，是否支持空间滤波器的持续时间的预测和上报，是否支持一次性的指示多个预测实例中的空间滤波器的标识信息。
在一些实施例中，该第一通信设备为终端设备。
在一些实施例中，该通信单元320还用于发送第三信息；
其中，该第三信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息，或者，该第三信息用于指示第i个预测实例中使用的空间滤波器的标识信息；或者，该第三信息用于指示该F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，该第三信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间；
其中，i为正整数，且1≤i≤F。
在一些实施例中，该通信单元320还用于接收第一能力信息；
其中，该第一能力信息包括以下至少之一：该第一测量数据集最多支持的空间滤波器的数量，该第一测量数据集最多支持的测量实例的数量，该第一预测数据集最多支持的空间滤波器的数量，该第一预测数据集最多支持的预测实例的数量，是否支持空间滤波器的持续时间的预测和上报，是否支持一次性的指示多个预测实例中的空间滤波器的标识信息。
在一些实施例中，该第一通信设备为网络设备。
在一些实施例中，该空间滤波器包括一个发射空间滤波器；或者，
该空间滤波器包括一个发射空间滤波器和一个接收空间滤波器。
在一些实施例中，上述通信单元可以是通信接口或收发器，或者是通信芯片或者片上系统的输入输出接口。上述处理单元可以是一个或多个处理器。
应理解，根据本申请实施例的通信设备300可对应于本申请方法实施例中的第一通信设备，并且通信设备300中的各个单元的上述和其它操作和/或功能分别为了实现图10所示方法200中第一通信设备的相应流程，为了简洁，在此不再赘述。
图21是本申请实施例提供的一种通信设备400示意性结构图。图21所示的通信设备400包括处理器410，处理器410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。
在一些实施例中，如图21所示，通信设备400还可以包括存储器420。其中，处理器410可以从存储器420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420可以是独立于处理器410的一个单独的器件，也可以集成在处理器410中。
在一些实施例中，如图21所示，通信设备400还可以包括收发器430，处理器410可以控制该收发器430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430可以包括发射机和接收机。收发器430还可以进一步包括天线，天线的数量可以为一个或多个。
在一些实施例中，处理器410可以实现通信设备300中的处理单元的功能，为了简洁，在此不再赘述。
在一些实施例中，收发器430可以实现通信设备300中的通信单元的功能，为了简洁，在此不再赘述。
在一些实施例中，该通信设备400具体可为本申请实施例的通信设备，并且该通信设备400可以 实现本申请实施例的各个方法中由第一通信设备实现的相应流程，为了简洁，在此不再赘述。
图22是本申请实施例的装置的示意性结构图。图22所示的装置500包括处理器510，处理器510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。
在一些实施例中，如图22所示，装置500还可以包括存储器520。其中，处理器510可以从存储器520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520可以是独立于处理器510的一个单独的器件，也可以集成在处理器510中。
在一些实施例中，该装置500还可以包括输入接口530。其中，处理器510可以控制该输入接口530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，处理器510可以位于芯片内或芯片外。
在一些实施例中，处理器510可以实现通信设备300中的处理单元的功能，为了简洁，在此不再赘述。
在一些实施例中，输入接口530可以实现通信设备300中的通信单元的功能。
在一些实施例中，该装置500还可以包括输出接口540。其中，处理器510可以控制该输出接口540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，处理器510可以位于芯片内或芯片外。
在一些实施例中，输出接口540可以实现通信设备300中的通信单元的功能。
在一些实施例中，该装置可应用于本申请实施例中的通信设备，并且该装置可以实现本申请实施例的各个方法中由第一通信设备实现的相应流程，为了简洁，在此不再赘述。
在一些实施例中，本申请实施例提到的装置也可以是芯片。例如可以是系统级芯片，系统芯片，芯片系统或片上系统芯片等。
图23是本申请实施例提供的一种通信系统600的示意性框图。如图23所示，该通信系统600包括第一通信设备610和第二通信设备620。
其中，该第一通信设备610可以用于实现上述方法中由第一通信设备实现的相应的功能，以及该第二通信设备620可以用于实现上述方法中由第二通信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。
在一些实施例中，该计算机可读存储介质可应用于本申请实施例中的通信设备，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第一通信设备实现的相应流程，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。
在一些实施例中，该计算机程序产品可应用于本申请实施例中的通信设备，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第一通信设备实现的相应流程，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。
在一些实施例中，该计算机程序可应用于本申请实施例中的通信设备，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第一通信设备实现的相应流程，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。针对这样的理解，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。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应所述以权利要求的保护范围为准。

Claims (37)

  1. 一种无线通信的方法，其特征在于，包括：
    第一通信设备获取第一测量数据集；其中，所述第一测量数据集包括以下至少之一：M个测量实例中空间滤波器的标识信息，M个测量实例中空间滤波器对应的链路质量信息；其中，M为正整数；
    所述第一通信设备将所述第一测量数据集输入第一网络模型，输出第一预测数据集；其中，所述第一预测数据集包括以下至少之一：F个预测实例中的每个预测实例中预测的K个空间滤波器的标识信息，F个预测实例中的每个预测实例中预测的K个空间滤波器对应的链路质量信息，F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间；其中，F和K均为正整数。
  2. 如权利要求1所述的方法，其特征在于，
    所述M个测量实例中每个测量实例中的空间滤波器为全部空间滤波器中的部分空间滤波器。
  3. 如权利要求2所述的方法，其特征在于，
    所述M个测量实例中每个测量实例中的空间滤波器的配置相同；或者，
    所述M个测量实例中至少部分测量实例中的空间滤波器的配置不同。
  4. 如权利要求2或3所述的方法，其特征在于，
    所述M个测量实例中不同的测量实例中的部分空间滤波器相同。
  5. 如权利要求1至4中任一项所述的方法，其特征在于，
    所述M个测量实例在时域上等间隔设置。
  6. 如权利要求5所述的方法，其特征在于，
    所述M个测量实例对应第一时长内的周期性空间滤波器测量。
  7. 如权利要求1至4中任一项所述的方法，其特征在于，
    所述M个测量实例在时域上非等间隔设置。
  8. 如权利要求7所述的方法，其特征在于，
    所述M个测量实例在时域上的间隔基于终端设备的移动速度确定。
  9. 如权利要求7或8所述的方法，其特征在于，
    所述M个测量实例中不同的测量实例对应相同的周期和不同的偏移量。
  10. 如权利要求7至9中任一项所述的方法，其特征在于，
    所述M个测量实例为半持续调度SPS的多个测量实例中由下行控制信息DCI或媒体接入控制层控制单元MAC CE激活的测量实例；或者，
    所述M个测量实例为预先配置的多个测量实例中由DCI动态触发的测量实例。
  11. 如权利要求1至9中任一项所述的方法，其特征在于，所述M个测量实例为多套测量配置中由DCI或MAC CE激活的一套测量配置对应的测量实例，或者，所述M个测量实例为由DCI或MAC CE激活的轮流使用的多套测量配置中当前的测量配置对应的测量实例。
  12. 如权利要求1至11中任一项所述的方法，其特征在于，
    所述F个预测实例中的每个测量实例中的空间滤波器为全部空间滤波器中的部分空间滤波器。
  13. 如权利要求12所述的方法，其特征在于，
    所述F个预测实例中每个预测实例中的空间滤波器的配置相同；或者，
    所述F个预测实例中至少部分预测实例中的空间滤波器的配置不同。
  14. 如权利要求12或13所述的方法，其特征在于，
    所述F个预测实例中不同的预测实例中的部分或者全部空间滤波器相同。
  15. 如权利要求1至14中任一项所述的方法，其特征在于，
    所述F个预测实例在时域上等间隔设置。
  16. 如权利要求15所述的方法，其特征在于，
    所述F个预测实例对应第二时长内的周期性空间滤波器预测。
  17. 如权利要求1至14中任一项所述的方法，其特征在于，
    所述F个预测实例在时域上非等间隔设置。
  18. 如权利要求17所述的方法，其特征在于，
    所述F个预测实例在时域上的间隔基于终端设备的移动速度确定。
  19. 如权利要求17或18所述的方法，其特征在于，
    所述F个预测实例中不同的预测实例对应相同的周期和不同的偏移量。
  20. 如权利要求17至19中任一项所述的方法，其特征在于，
    所述F个预测实例为SPS的多个预测实例中由DCI或MAC CE激活的预测实例；或者，
    所述F个预测实例为预先配置的多个预测实例中由DCI动态触发的预测实例。
  21. 如权利要求1至19中任一项所述的方法，其特征在于，所述F个预测实例为多套预测配置中由DCI或MAC CE激活的一套预测配置对应的预测实例，或者，所述F个预测实例为由DCI或MAC CE激活的轮流使用的多套预测配置中当前的预测配置对应的预测实例。
  22. 如权利要求1至21中任一项所述的方法，其特征在于，
    K的取值包括以下之一：1，2，4，8。
  23. 如权利要求1至22中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一通信设备发送第一信息；
    其中，所述第一信息包括以下至少之一：所述F个预测实例中的每个预测实例中预测的所述K个空间滤波器的标识信息，所述F个预测实例中的每个预测实例中预测的所述K个空间滤波器对应的链路质量信息，所述F个预测实例中的每个预测实例中预测的所述K个空间滤波器的持续时间。
  24. 如权利要求23所述的方法，其特征在于，
    所述K个空间滤波器对应的链路质量信息通过差分方式发送。
  25. 如权利要求23或24所述的方法，其特征在于，所述方法还包括：
    所述第一通信设备接收基于所述第一信息确定的第二信息；
    其中，所述第二信息用于指示所述F个预测实例中的每个预测实例中使用的空间滤波器的标识信息，或者，所述第二信息用于指示第i个预测实例中使用的空间滤波器的标识信息；或者，所述第二信息用于指示所述F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，所述第二信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间；
    其中，i为正整数，且1≤i≤F。
  26. 如权利要求1至25中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一通信设备发送第一能力信息；
    其中，所述第一能力信息包括以下至少之一：所述第一测量数据集最多支持的空间滤波器的数量，所述第一测量数据集最多支持的测量实例的数量，所述第一预测数据集最多支持的空间滤波器的数量，所述第一预测数据集最多支持的预测实例的数量，是否支持空间滤波器的持续时间的预测和上报，是否支持一次性的指示多个预测实例中的空间滤波器的标识信息。
  27. 如权利要求1至26中任一项所述的方法，其特征在于，所述第一通信设备为终端设备。
  28. 如权利要求1至22中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一通信设备发送第三信息；
    其中，所述第三信息用于指示所述F个预测实例中的每个预测实例中使用的空间滤波器的标识信息，或者，所述第三信息用于指示第i个预测实例中使用的空间滤波器的标识信息；或者，所述第三信息用于指示所述F个预测实例中的每个预测实例中使用的空间滤波器的标识信息和持续时间，或者，所述第三信息用于指示第i个预测实例中使用的空间滤波器的标识信息和持续时间；
    其中，i为正整数，且1≤i≤F。
  29. 如权利要求1至22、28中任一项所述的方法，其特征在于，所述方法还包括：
    所述第一通信设备接收第一能力信息；
    其中，所述第一能力信息包括以下至少之一：所述第一测量数据集最多支持的空间滤波器的数量，所述第一测量数据集最多支持的测量实例的数量，所述第一预测数据集最多支持的空间滤波器的数量，所述第一预测数据集最多支持的预测实例的数量，是否支持空间滤波器的持续时间的预测和上报，是否支持一次性的指示多个预测实例中的空间滤波器的标识信息。
  30. 如权利要求1至22、28、29中任一项所述的方法，其特征在于，
    所述第一通信设备为网络设备。
  31. 如权利要求1至30中任一项所述的方法，其特征在于，
    所述空间滤波器包括一个发射空间滤波器；或者，
    所述空间滤波器包括一个发射空间滤波器和一个接收空间滤波器。
  32. 一种通信设备，其特征在于，所述通信设备为第一通信设备，所述通信设备包括：
    处理单元，用于获取第一测量数据集；其中，所述第一测量数据集包括以下至少之一：M个测量实例中空间滤波器的标识信息，M个测量实例中空间滤波器对应的链路质量信息；其中，M为正整数；
    所述处理单元还用于将所述第一测量数据集输入第一网络模型，输出第一预测数据集；其中，所述第一预测数据集包括以下至少之一：F个预测实例中的每个预测实例中预测的K个空间滤波器的标识信息，F个预测实例中的每个预测实例中预测的K个空间滤波器对应的链路质量信息，F个预测实例中的每个预测实例中预测的K个空间滤波器的持续时间；其中，F和K均为正整数。
  33. 一种通信设备，其特征在于，包括：处理器和存储器，所述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，使得所述通信设备执行如权利要求1至31中任一项所述的方法。
  34. 一种芯片，其特征在于，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31中任一项所述的方法。
  35. 一种计算机可读存储介质，其特征在于，用于存储计算机程序，当所述计算机程序被执行时，如权利要求1至31中任一项所述的方法被实现。
  36. 一种计算机程序产品，其特征在于，包括计算机程序指令，当所述计算机程序指令被执行时，如权利要求1至31中任一项所述的方法被实现。
  37. 一种计算机程序，其特征在于，当所述计算机程序被执行时，如权利要求1至31中任一项所述的方法被实现。
PCT/CN2022/128935 2022-11-01 2022-11-01 无线通信的方法及设备 WO2024092498A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/128935 WO2024092498A1 (zh) 2022-11-01 2022-11-01 无线通信的方法及设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/128935 WO2024092498A1 (zh) 2022-11-01 2022-11-01 无线通信的方法及设备

Publications (1)

Publication Number Publication Date
WO2024092498A1 true WO2024092498A1 (zh) 2024-05-10

Family

ID=90929106

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/128935 WO2024092498A1 (zh) 2022-11-01 2022-11-01 无线通信的方法及设备

Country Status (1)

Country Link
WO (1) WO2024092498A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110971359A (zh) * 2018-09-28 2020-04-07 华为技术有限公司 一种无线通信网络中的指示波束信息的方法和设备
CN113785621A (zh) * 2019-05-03 2021-12-10 Lg 电子株式会社 在无线通信系统中监测物理下行链路控制信道
US20220190883A1 (en) * 2019-04-17 2022-06-16 Nokia Technologies Oy Beam prediction for wireless networks
US20220210781A1 (en) * 2020-12-28 2022-06-30 Samsung Electronics Co., Ltd. Method and apparatus for predictive beam management
CN114938712A (zh) * 2022-04-13 2022-08-23 北京小米移动软件有限公司 波束选择方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110971359A (zh) * 2018-09-28 2020-04-07 华为技术有限公司 一种无线通信网络中的指示波束信息的方法和设备
US20220190883A1 (en) * 2019-04-17 2022-06-16 Nokia Technologies Oy Beam prediction for wireless networks
CN113785621A (zh) * 2019-05-03 2021-12-10 Lg 电子株式会社 在无线通信系统中监测物理下行链路控制信道
US20220210781A1 (en) * 2020-12-28 2022-06-30 Samsung Electronics Co., Ltd. Method and apparatus for predictive beam management
CN114938712A (zh) * 2022-04-13 2022-08-23 北京小米移动软件有限公司 波束选择方法和装置

Similar Documents

Publication Publication Date Title
CN109890078A (zh) 一种资源配置方法及其装置
US11510159B2 (en) Signal transmission method, network device, and terminal device
US20220287104A1 (en) Method and apparatus for support of machine learning or artificial intelligence techniques in communication systems
WO2020133163A1 (zh) 无线通信方法、终端设备和网络设备
CN113645657B (zh) 无线通信方法、终端设备和网络设备
US20230308141A1 (en) Communication Method, Device, and System
WO2021138866A1 (zh) 信息确定方法、信息指示方法、终端设备和网络设备
US11792831B2 (en) Method and device for signal transmission
WO2024092498A1 (zh) 无线通信的方法及设备
US20230319750A1 (en) Signal synchronization for over-the-air aggregation in a federated learning framework
WO2022126455A1 (zh) 测量参数的确定方法、终端设备、芯片和存储介质
WO2024130573A1 (zh) 无线通信的方法、终端设备和网络设备
WO2024130739A1 (zh) 无线通信的方法及设备
WO2024065696A1 (zh) 无线通信的方法、终端设备和网络设备
WO2021072602A1 (zh) 链路失败检测的方法和装置
WO2024065697A1 (zh) 模型监测的方法、终端设备和网络设备
WO2022182330A1 (en) Signalling support for split ml-assistance between next generation random access networks and user equipment
CN116941271A (zh) 测量方法、终端设备和网络设备
CN114071667A (zh) 通信的方法、通信装置及系统
CN113938907A (zh) 通信的方法及通信装置
WO2024119492A1 (zh) 无线通信的方法及设备
WO2023206163A1 (zh) 无线通信的方法、网络设备和终端设备
WO2023283889A1 (zh) 无线通信的方法、终端设备和网络设备
WO2023108556A1 (zh) 无线通信的方法、终端设备和网络设备
CN114451005B (zh) 链路失败检测的方法和装置

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: 22963817

Country of ref document: EP

Kind code of ref document: A1