WO2023206163A1 - 无线通信的方法、网络设备和终端设备 - Google Patents

无线通信的方法、网络设备和终端设备 Download PDF

Info

Publication number
WO2023206163A1
WO2023206163A1 PCT/CN2022/089649 CN2022089649W WO2023206163A1 WO 2023206163 A1 WO2023206163 A1 WO 2023206163A1 CN 2022089649 W CN2022089649 W CN 2022089649W WO 2023206163 A1 WO2023206163 A1 WO 2023206163A1
Authority
WO
WIPO (PCT)
Prior art keywords
spatial filters
terminal device
target
information
spatial
Prior art date
Application number
PCT/CN2022/089649
Other languages
English (en)
French (fr)
Inventor
曹建飞
刘文东
陈文洪
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/CN2022/089649 priority Critical patent/WO2023206163A1/zh
Publication of WO2023206163A1 publication Critical patent/WO2023206163A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0408Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas using two or more beams, i.e. beam diversity
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/08Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W72/00Local resource management
    • H04W72/04Wireless resource allocation

Definitions

  • Embodiments of the present application relate to the field of communications, and specifically relate to a wireless communication method, network equipment, and terminal equipment.
  • Downlink beam management includes processes such as downlink beam scanning, optimal beam reporting on the terminal side, and downlink beam indication on the network side.
  • the network device scans all transmit beam directions through the downlink reference signal.
  • the terminal device can use different receive beams to perform measurements, thereby traversing all beam pairs.
  • the terminal equipment 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.
  • This application provides a wireless communication method, network equipment and terminal equipment, which is beneficial to reducing the overhead and delay caused by the beam scanning process.
  • a wireless communication method including: a network device obtains a first data set, the first data set includes identification information of M1 spatial filters, and/or the M1 spatial filters The measurement result, the M1 is a positive integer;
  • the first data set is input into the target model, and target information is output.
  • the target information includes identification information of K spatial filters, and/or measurement results of the K spatial filters, where K is a positive integer.
  • a wireless communication method including: a terminal device acquiring a third data set, the third data set including identification information of M3 spatial filters, and/or the M3 spatial filters The measurement result, the M3 is a positive integer;
  • the target information includes the identification information of the K spatial filters, and/or the measurement results of the K spatial filters, where K is positive integer.
  • a wireless communication method including: the network device obtains a sixth data set, including measurement information of multiple spatial filters by the terminal device; training the target model according to the sixth data set to obtain the target model model parameters, wherein the target model is used to determine the target spatial filter among the plurality of spatial filters according to the measurement results of the plurality of spatial filters.
  • a wireless communication method including: a terminal device acquiring a seventh data set, including measurement information of a plurality of spatial filters by the terminal device; training a target model according to the seventh data set to obtain Model parameters of a target model, wherein the target model is used to determine a target spatial filter among the plurality of spatial filters according to measurement results of the plurality of spatial filters.
  • a fifth aspect provides a network device for executing the method in the above first aspect or its respective implementations.
  • the network device includes a functional module for executing the method in the above-mentioned first aspect or its respective implementations.
  • a sixth aspect provides a terminal device for executing the method in the above second aspect or its respective implementations.
  • the terminal device includes a functional module for executing the method in the above second aspect or its respective implementations.
  • a seventh aspect provides a network device for performing the method in the above third aspect or its respective implementations.
  • the network device includes a functional module for executing the method in the above third aspect or its respective implementations.
  • An eighth aspect provides a terminal device for executing the method in the above fourth aspect or its respective implementations.
  • the terminal device includes a functional module for executing the method in the above fourth aspect or its respective implementations.
  • a ninth aspect provides a network device, including a processor and a memory.
  • the memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory, and execute the methods in the above-mentioned first aspect or third aspect or respective implementations thereof.
  • a terminal device including a processor and a memory.
  • the memory is used to store computer programs
  • the processor is used to call and run the computer programs stored in the memory, and execute the methods in the above-mentioned second aspect or fourth aspect or respective implementations thereof.
  • An eleventh aspect provides a chip for implementing any one of the above-mentioned first to fourth aspects or the method in each implementation manner thereof.
  • the chip includes: a processor, configured to call and run a computer program from a memory, so that the device installed with the device executes any one of the above-mentioned first to fourth aspects or implementations thereof. method.
  • a computer-readable storage medium for storing a computer program, the computer program causing the computer to execute any one of the above-mentioned first to fourth aspects or the method in each implementation manner thereof.
  • a computer program product including computer program instructions, which cause a computer to execute any one of the above-mentioned first to fourth aspects or the method in each implementation thereof.
  • a fourteenth aspect provides a computer program that, when run on a computer, causes the computer to execute any one of the above-mentioned first to fourth aspects or the method in each implementation thereof.
  • the trained target model can be used to predict the optimal spatial filter. Therefore, the network device only needs to perform scanning of part of the spatial filter, and the terminal device only needs to measure part of the spatial filter, which is beneficial to Reduce the overhead and delay caused by downlink beam scanning.
  • Figure 1 is a schematic diagram of a communication system architecture provided by an embodiment of the present application.
  • Figure 2 is a schematic diagram of the connection of neurons in a neural network.
  • Figure 3 is a schematic structural diagram of a convolutional neural network.
  • Figure 4 is a schematic structural diagram of an LSTM unit.
  • Figure 5 is a schematic diagram of a downlink beam scanning process.
  • Figure 6 is a schematic diagram of another downlink beam scanning process.
  • Figure 7 is a schematic diagram of a wireless communication method provided according to an embodiment of the present application.
  • Figure 8 is a schematic composition diagram of the target model.
  • Figure 9 is an example diagram of the model structure and input and output relationships of the first target model provided by the embodiment of the present application.
  • Figure 10 is an example diagram of the model structure and input and output relationships of the second target model provided by the embodiment of the present application.
  • Figure 11 is a schematic diagram of another wireless communication method provided according to an embodiment of the present application.
  • Figure 12 is a schematic diagram of yet another wireless communication method provided according to an embodiment of the present application.
  • Figure 13 is a schematic diagram of yet another wireless communication method provided according to an embodiment of the present application.
  • Figure 14 is a schematic interaction diagram for performing model training and inference on the network device side.
  • Figure 15 is a schematic interaction diagram in which the network device side performs model training and the terminal device side performs inference.
  • Figure 16 is a schematic interaction diagram in which the network device side performs model training, and both the terminal device and the network device perform inference.
  • Figure 17 is a schematic interaction diagram for executing model training and inference on the terminal device side.
  • Figure 18 is a schematic interaction diagram in which the terminal device side performs model training, and both the terminal device and the network device perform inference.
  • Figure 19 is a schematic interaction diagram in which the terminal device side performs model training and the network device performs inference.
  • Figure 20 is a schematic block diagram of a network device provided according to an embodiment of the present application.
  • Figure 21 is a schematic block diagram of a terminal device provided according to an embodiment of the present application.
  • Figure 22 is a schematic block diagram of another network device provided according to an embodiment of the present application.
  • Figure 23 is a schematic block diagram of another terminal device provided according to an embodiment of the present application.
  • Figure 24 is a schematic block diagram of a communication device provided according to an embodiment of the present application.
  • Figure 25 is a schematic block diagram of a chip provided according to an embodiment of the present application.
  • Figure 26 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 broadband code division multiple access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • LTE-A Advanced long term evolution
  • NR New Radio
  • NTN Non-Terrestrial Networks
  • UMTS Universal Mobile Telecommunication System
  • WLAN Wireless Local Area Networks
  • WiFi wireless fidelity
  • 5G fifth-generation communication
  • the communication system in the embodiment of the present application can be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, a dual connectivity (Dual Connectivity, DC) scenario, or a standalone (Standalone, SA) deployment scenario.
  • CA Carrier Aggregation
  • DC Dual Connectivity
  • SA standalone deployment scenario.
  • the communication system in the embodiment of the present application can be applied to the unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or the communication system in the embodiment of the present application can also be applied to the licensed spectrum, where, Licensed spectrum can also be considered as unshared spectrum.
  • the embodiments of this application describe various embodiments in combination with network equipment and terminal equipment.
  • the terminal equipment may also be called user equipment (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.
  • User Equipment User Equipment
  • the terminal device can be a station (STATION, ST) in the WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, or a personal digital assistant.
  • PDA Personal Digital Assistant
  • handheld devices with wireless communication capabilities computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, next-generation communication systems such as terminal devices in NR networks, or in the future Terminal equipment in the evolved Public Land Mobile Network (PLMN) network, etc.
  • PLMN Public Land Mobile Network
  • the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as aircraft, balloons and satellites). superior).
  • the terminal device may be a mobile phone (Mobile Phone), a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (Virtual Reality, VR) terminal device, or an augmented reality (Augmented Reality, AR) terminal.
  • Equipment wireless terminal equipment in industrial control, wireless terminal equipment in self-driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid , wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, or wireless terminal equipment in smart home, etc.
  • the terminal device may also be a wearable device.
  • Wearable devices can also be called wearable smart devices. It is a general term for applying wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes, etc.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not just hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-sized devices that can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, and those that only focus on a certain type of application function and need to cooperate with other devices such as smartphones.
  • the network device may be a device used to communicate with mobile devices.
  • the network device may be an access point (Access Point, AP) in WLAN, or a base station (Base Transceiver Station, BTS) in GSM or CDMA.
  • BTS Base Transceiver Station
  • it can be a base station (NodeB, NB) in WCDMA, or an evolutionary base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and an NR network network equipment (gNB) or network equipment in the future evolved PLMN network or network equipment in the NTN network, etc.
  • AP Access Point
  • BTS Base Transceiver Station
  • NodeB, NB base station
  • Evolutional Node B, eNB or eNodeB evolution base station
  • gNB NR network network equipment
  • the network device may have mobile characteristics, for example, the network device may be a mobile device.
  • the network device can be a satellite or balloon station.
  • the satellite can be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geosynchronous orbit (geostationary earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite ) satellite, etc.
  • the network device may also be a base station installed on land, water, etc.
  • network equipment can provide services for a cell, and terminal equipment communicates with the network equipment through transmission resources (for example, frequency domain resources, or spectrum resources) used by the cell.
  • the cell can be a network equipment ( For example, the cell corresponding to the base station), the cell can belong to the macro base station, or it can belong to the base station corresponding to the small cell (Small cell).
  • the small cell here can include: urban cell (Metro cell), micro cell (Micro cell), pico cell ( Pico cell), femto cell (Femto cell), etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-rate 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 (also referred to as a communication terminal or terminal).
  • the network device 110 can provide communication coverage for a specific geographical area and can communicate with terminal devices located within the coverage area.
  • Figure 1 exemplarily shows one network device and two terminal devices.
  • the communication system 100 may include multiple network devices and the coverage of each network device may include other numbers of terminal devices. This application The embodiment does not limit this.
  • the communication system 100 may also include other network entities such as a network controller and a mobility management entity, which are not limited in this embodiment of the present application.
  • network entities such as a network controller and a mobility management entity, which are not limited in this embodiment of the present application.
  • the communication device may include a network device 110 and a terminal device 120 with communication functions.
  • the network device 110 and the terminal device 120 may be the specific devices described above, which will not be described again here.
  • the communication device may also include other devices in the communication system 100, such as network controllers, mobility management entities and other network entities, which are not limited in the embodiments of this application.
  • the "instruction” mentioned in the embodiments of this application may be a direct instruction, an indirect instruction, or 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 there is an association between A and B. relation.
  • correlate can mean that there is a direct correspondence or indirect correspondence between the two, it can also mean that there is an associated relationship between the two, or it can mean indicating and being instructed, configuration and being. Configuration and other relationships.
  • predefinition can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in devices (for example, including terminal devices and network devices).
  • devices for example, including terminal devices and network devices.
  • predefined can refer to what is defined in the protocol.
  • the "protocol” may refer to a standard protocol in the communication field, which may include, for example, LTE protocol, NR protocol, and related protocols applied in future communication systems. This application does not limit this.
  • Neural Network is a computing model composed of multiple neuron nodes connected to each other, as shown in Figure 2.
  • the connection between nodes represents the weighted value from the input signal to the output signal, called weight;
  • Each node performs a weighted summation of different input signals and outputs it through a specific activation function.
  • CNN Convolutional Neural Network
  • Figure 3 is a simple CNN structure diagram, including input layer, hidden layer and output layer, through multiple neurons with different connection methods and weights. and activation functions, which can produce different outputs and then fit the mapping relationship from input to output, in which each upper-level node is connected to all its lower-level nodes.
  • Recurrent Neural Network is a neural network that models sequence data. It has achieved remarkable results in the field of natural language processing, such as machine translation, speech recognition and other applications. The specific performance is that the network device remembers 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 unconnected but connected, and the input of the hidden layer not only includes the input layer Also includes 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 4 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 will determine which states should be kept and which states should be forgotten, solving the traditional problem of RNN has shortcomings in long-term memory.
  • Downlink beam management includes processes such as 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 can use different receiving beams for measurement, so that all beam pairs can be traversed.
  • 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 synchronization signal block (Synchronization Signal Block, SSB) and/or channel state information reference signal (Channel State Information Reference Signal, CSI-RS).
  • SSB Synchronization Signal Block
  • CSI-RS Channel State Information Reference Signal
  • the downlink beam scanning process may be the P1 process shown in FIG. 5 (or the downlink full scanning process) and the P3 process shown in FIG. 6 .
  • the network device can traverse all transmit beams to send downlink reference signals, and the UE side traverses all receive beams to perform measurements and determine the corresponding measurement results.
  • the network device can send a downlink reference signal in a specific transmit beam, and the UE side traverses all receive beams to perform measurements and determine the corresponding measurement results.
  • the network device After the network device learns the optimal beam reported by the terminal device, it can carry the Transmission Configuration Indicator (TCI) through Media Access Control (MAC) or Downlink Control Information (DCI) signaling. ) state (which contains the downlink reference signal as a reference transmit beam) to complete the beam indication to the UE, and the UE uses the receive beam corresponding to the transmit beam to perform downlink reception.
  • TCI Transmission Configuration Indicator
  • MAC Media Access Control
  • DCI Downlink Control Information
  • the UE For the downlink full scan process, that is, the P1 process, the UE needs to traverse all combinations of transmit beams and receive beams, which will bring a lot of overhead and delay.
  • the network equipment deploys 64 different downlink transmit beams in the FR2 band (carried by up to 64 SSBs), and the UE uses multiple antenna panels (including only one receive beam panel) to scan the receive beams simultaneously when receiving, and Each antenna panel has 4 receiving beams, so the UE needs to measure at least 256 beam pairs, which requires a downlink resource overhead of 256 resources.
  • each SSB cycle is about 20ms, so it takes 4 SSB cycles to complete the measurement of the 4 receiving beams (assuming that multiple receiving antenna panels can scan the beams through), then at least 80ms is required. .
  • Figure 7 is a schematic flowchart of a wireless communication method 200 according to an embodiment of the present application.
  • the method 200 can be executed by the network device in the communication system shown in Figure 1.
  • the method 200 includes at least the following: Part:
  • the network device obtains a first data set, where the first data set includes identification information of M1 spatial filters, and/or measurement results of the M1 spatial filters, where M1 is a positive integer;
  • the target information includes identification information of K spatial filters, and/or measurement results of the K spatial filters, K is positive. integer.
  • a spatial filter may also be called a beam, a spatial relation, a spatial setting, a spatial domain filter, or a reference signal.
  • the spatial filter may include a transmit spatial filter (Tx spatial filter, or Tx spatial domain filter) and/or a receive spatial filter (Rx spatial filter, or Rx spatial domain filter).
  • the spatial filter includes a transmit spatial filter.
  • the spatial filter includes a combination of a transmit spatial filter and a receive spatial filter.
  • the transmit spatial filter may also be called a transmit beam (Tx beam) or a transmitter spatial filter, and the above terms may be interchanged.
  • the receive spatial filter may also be called a receive beam (Rx beam) or a receive-side spatial filter, and the above terms may be interchanged.
  • the combination of a transmit spatial filter and a receive spatial filter may also be referred to as a beam pair, a spatial filter pair, or a spatial filter bank, and the above terms may be interchanged with each other.
  • the K spatial filters may include K transmit spatial filters, denoted as Case 1.
  • the target information inferred by the network device based on the target model is the information of K transmit beams.
  • the target information may include identification information of the K transmit beams and/or measurement results of the K transmit beams.
  • the K spatial filters may include a combination of K transmit spatial filters and receive spatial filters, denoted as case 2. That is, the target information inferred by the network device based on the target model is the information of K beam pairs.
  • the target information may include identification information of the K beam pairs and/or measurement results of the K beam pairs.
  • the identification information of the spatial filter may be an index of the spatial filter.
  • the identification information of the transmit spatial filter may be an index of the transmit spatial filter.
  • the identification information of the receive spatial filter may be the index of the receive spatial filter.
  • the identification information of the combination of the transmit spatial filter and the receive spatial filter may be a combination index.
  • the measurement results of the spatial filter may include but are not limited to at least one of the following:
  • L1-RSRP Layer1 Reference Signal Receiving Power
  • L1-RSRQ Layer1 Reference Signal Receiving Quality
  • L1-SINR Layer1 Signal to Interference plus Noise Ratio
  • the first data set may be obtained from a terminal device.
  • the first data set is obtained by the terminal device measuring some of the spatial filters in the candidate spatial filter set, wherein the candidate spatial filter set includes N spatial filters, where, N is a positive integer.
  • the first data set may include identification information of M1 transmit spatial filters, and/or measurement results of the M1 transmit spatial filters.
  • the first data set may include identification information of M1 combinations of transmit spatial filters and receive spatial filters, and/or measurement results of the M1 combinations.
  • the set of candidate spatial filters may be network device configured.
  • the set of candidate spatial filters may be considered a spatial filter ensemble.
  • the set of candidate spatial filters includes N transmit spatial filters.
  • the set of candidate spatial filters may include N transmit beams.
  • the set of candidate spatial filters includes N combinations of transmit spatial filters and receive spatial filters.
  • the set of candidate spatial filters may include N beam pairs, each beam pair including one transmit beam and one receive beam.
  • the M1 spatial filters may be spatial filters actually used in the downlink beam scanning process.
  • the M1 spatial filters are a subset of the complete set of spatial filters.
  • M1 spatial filters are also called a set of tested spatial filters.
  • M1 is less than N, that is, the network device can only use part of the spatial filters in the candidate spatial filter set to send downlink reference signals, instead of using all spatial filters to send downlink reference signals, which is beneficial to reducing the beam size. Choice of cost and latency.
  • the identification information of the K spatial filters and the measurement results of the K spatial filters may be output through the same model, or may be output through different models. This application provides This is not a limitation.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output the identification information of the K spatial filters, such as the optimal K beams or beams.
  • the second target model is used to output the measurement results of the K spatial filters, such as the measurement results of the optimal K beams or beam pairs.
  • the first target model and the second target model use the same input, that is, the first data set.
  • Figure 9 shows the model structure of the first target model and an example of the relationship between input and output.
  • the input of the first target model can be the index of the beam or beam pair and the corresponding measurement result
  • the label can be the K beams or beam pairs with the best measurement results (or, in other words, the best link quality)
  • the output can be the index of K beams or beam pairs with the best measurement results.
  • Figure 10 shows the model structure of the second target model and an example of the relationship between input and output.
  • the input of the second target model can be the index of the beam or beam pair and the corresponding measurement result
  • the label can be the K beams or beam pairs with the best measurement results (or, in other words, the best link quality)
  • the output can be the measurement results of the optimal K beams or beam pairs.
  • the number of beams or beam pairs output by using the target model to infer the optimal beam or beam pair may be the same as the number of beams or beam pairs marked when training the target model, or alternatively, Can be smaller than the number of beams or beam pairs labeled when training the target model.
  • K beams or beam pairs are marked when training the target model, when using the target model to infer the optimal beam or beam pair, K beams or beam pairs can be output, or less than K beams or beam pairs can be output. Yes, this application only takes outputting the same number of beams or beam pairs as an example for description, but this application is not limited to this.
  • the target model may be CNN, or it may be RNN, or it may be other neural network models, which is not limited in this application.
  • the target model is trained by the network device.
  • the method 200 further includes:
  • the network device obtains the second data set
  • the target model is trained according to the second data set to obtain model parameters of the target model.
  • the second data set is obtained from the terminal device.
  • the second data set includes: partial measurement information obtained by the terminal device during the downlink full scan process, and optimal spatial filtering determined based on all measurement information obtained by the terminal device during the downlink full scan process. device information.
  • the second data set includes at least one of the following:
  • the M2 spatial filters include some of the spatial filters in the candidate spatial filter set, and the P spatial filters are all spatial filters in the candidate spatial filter set that the terminal device Obtained by measurement.
  • the target model may be obtained by using offline training, or may be obtained by using online training, or may be obtained by combining offline training and online training.
  • the network device first obtains a static training result through offline training, and further uses the offline trained model to predict the optimal beam or beam pair. In subsequent measurements and/or reports of the terminal device, the network device can continue to collect more information. More measurement data is then used to continue training the target model to optimize model parameters to achieve better prediction results.
  • P may be equal to K, or P may be greater than K.
  • the number of optimal spatial filters inferred using the target model may be less than or equal to the number of optimal spatial filters labeled when training the target model.
  • the method 200 further includes:
  • the network device sends the model type and/or model parameters of the target model to the terminal device.
  • the network device may send the model type and/or model parameters of the target model to the terminal device.
  • the terminal device can construct a target model based on the above information, and then after performing the downlink scanning process to obtain the measurement results, the target model can be used to infer the optimal beam or beam pair.
  • the model type of the target model may be DNN or RNN, etc.
  • the model type and model parameters of the target model can be used by the terminal device to construct the target model.
  • the model parameters of the target model are used to indicate the network structure (for example, included layers) of the target model, the connection relationships between the various layers, and other parameters.
  • the target model is trained by the terminal device.
  • the terminal device can obtain a data set used for model training, and further train the target model based on the data set to obtain model parameters of the target model.
  • the network device can trigger a downlink full scan process (ie, P1 process), and the terminal device traverses all receiving spatial filters to receive the downlink reference signal to obtain a measurement result set.
  • a downlink full scan process ie, P1 process
  • the terminal device can select the K highest ones from the measurement result set, label the K measurement results as the optimal K measurement results, and label the spatial filters corresponding to the K measurement results as the optimal K ones. spatial filter.
  • the data set used for model training may include: partial measurement results in the measurement result set and identification information of the spatial filters corresponding to the partial measurement results, as well as the K highest labeled measurement results and the K highest labeled The identification information of the spatial filter corresponding to the measurement result.
  • the terminal device may send information about the trained target model to the network device.
  • the method 200 further includes:
  • the network device receives the model type and/or model parameter information of the target model sent by the terminal device.
  • the terminal device can send the model type and/or model parameters of the target model to the network device. Further, the network device can build the target model based on the model type and/or model parameters of the target model.
  • the method 200 further includes:
  • the network device sends first indication information to the terminal device, where the first indication information is used to indicate the K spatial filters.
  • the network device may indicate the K spatial filters to the terminal device.
  • the first indication information may be sent through MAC CE or DCI.
  • Case 1 The K spatial filters are K transmit spatial filters.
  • the first indication information is used to indicate K TCI states, and the K TCI states correspond to K transmit spatial filters. That is, network equipment can use TCI status to indicate the optimal transmit beam.
  • the K spatial filters are a combination of K transmit spatial filters and receive spatial filters.
  • the network device may indicate to the terminal device K transmit spatial filters out of a combination of K transmit spatial filters and receive spatial filters, or may also indicate a combination of K transmit spatial filters and receive spatial filters. combination.
  • Method 1 The first indication information is used to indicate K TCI states, and the K TCI states correspond to the K transmit spatial filters in the combination of the K transmit spatial filters and the receive spatial filters.
  • the network device may use the TCI status to indicate only the transmit spatial filter to the terminal device.
  • Method 2 The first indication information is used to indicate the identification information of the transmit spatial filter and the identification information of the receive spatial filter in each of the K combinations.
  • the network device when the network device infers K combinations of transmit spatial filters and receive spatial filters, the network device may indicate the identification information of the transmit spatial filter and the identification information of the receive spatial filter to the terminal device.
  • the transmit spatial filter can also be indicated by TCI status.
  • the first indication information may be sent through MAC CE or DCI.
  • Method 3 The first indication information is used to indicate K TCI states, and the K TCI states correspond to K combinations of transmit spatial filters and receive spatial filters.
  • the network device may use the TCI status to indicate the transmit spatial filter and the receive spatial filter to the terminal device.
  • the TCI status in this case can be thought of as an added spatial filter indication.
  • Method 4 The first indication information is the identification information of each of the K combinations.
  • the network device may indicate the combined identification information to the terminal device, and the combined identification information may be used to indicate one transmit spatial filter. receiver and receive spatial filter.
  • the network device when the K spatial filters belong to the M1 spatial filters, the network device sends the first indication information to the terminal device.
  • the network device may send the first indication information to the terminal device.
  • the terminal device can learn which receive spatial filter is used to receive the K transmit spatial filters used by the network device to send The downlink reference signal, therefore, does not need to further perform the downlink beam scanning process to determine the optimal receiving spatial filter.
  • the M1 spatial filters include M1 transmit spatial filters
  • the K spatial filters include a first transmit spatial filter
  • the combination of filters includes a combination of a first transmit spatial filter and a first receive spatial filter.
  • the method 200 further includes:
  • the network device sends first trigger information to the terminal device.
  • the first trigger information is used to trigger the terminal device to traverse all receive spatial filters to receive the downlink reference signal sent by the first transmit spatial filter to determine the optimal receive spatial filter.
  • the network device can trigger the P3 process. It should be understood that when the transmit spatial filter inferred by the network device does not belong to the measured transmit spatial filter set, the terminal device may not know which receive spatial filter to use to receive the downlink data sent by the network device using the transmit spatial filter. The reference signal, therefore, needs to be further determined based on the P3 process.
  • the network device For example, if the network device triggers an aperiodic P3 process, such as transmitting a CSI-RS resource set with its repetition type (Repetition) set to ON, the network device will transmit all CSI-RS resources in the CSI-RS resource set.
  • the first transmit spatial filter is used for transmission.
  • the UE receives CSI-RS resources by converting different receive spatial filters to determine the optimal receive spatial filter corresponding to the first transmit spatial filter.
  • the terminal device when both the terminal device and the network device predict the optimal spatial filter based on the target model, the terminal device can also infer the optimal spatial filter based on the target model. In this case, The network device may not send the first indication information to the terminal device. Alternatively, if the optimal transmit space filter inferred by the terminal device and the network device is not in the set of measured transmit space filters, the network device may trigger the P3 process to Determine the optimal receive spatial filter corresponding to the optimal transmit spatial filter.
  • the method 200 further includes:
  • the network device receives the first capability information sent by the terminal device, wherein the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal device uses the target model. The ability to predict (or infer) the target information.
  • the terminal device may indicate to the network device its training capabilities and/or inference capabilities for the model for spatial filter prediction.
  • the first capability information includes at least one of the following:
  • Whether the terminal device supports model-based prediction of the target information that is, whether the terminal device supports model-based prediction of optimal spatial filters
  • the size of the training data set supported by the terminal device such as the number of bytes supported
  • the type of model supported by the terminal device such as CNN or RNN, etc.;
  • the data type supported by the terminal device for predicting the target information is not limited to the data type supported by the terminal device for predicting the target information.
  • the configuration of the model supported by the terminal device includes at least one of the following:
  • the number of input parameters, the number of hidden layers, and the number of output parameters are the number of input parameters, the number of hidden layers, and the number of output parameters.
  • the method 200 further includes:
  • the network device sends first configuration information to the terminal device according to the first capability information.
  • the first configuration information is used to configure the terminal device to train the target model and/or use the target.
  • the model predicts the target information.
  • the network device can instruct the terminal device to be responsible for training the target model.
  • the network device may instruct the terminal device to be responsible for using the target model to predict the optimal spatial filter.
  • the network device can instruct the terminal device to be responsible for training the target model and using the target model to predict the optimal spatial filter.
  • the first configuration information is also used to configure the type of the target model used by the terminal device.
  • the first configuration information can be used to configure the target model to be implemented through CNN or RNN.
  • the first configuration information can be sent through any downlink signaling.
  • the first configuration information is sent through radio resource control RRC signaling.
  • the network device only needs to perform scanning of some spatial filters, and the terminal device only needs to measure some of the spatial filters to use the trained target model to predict the optimal spatial filter. , which is beneficial to reducing the overhead and delay caused by downlink beam scanning.
  • FIG 11 is a schematic flowchart of a wireless communication method 300 according to another embodiment of the present application.
  • the method 300 can be executed by the terminal device in the communication system shown in Figure 1.
  • the method 300 includes The following content:
  • the terminal device obtains a third data set, where the third data set includes identification information of M3 spatial filters, and/or measurement results of the M3 spatial filters, where M3 is a positive integer;
  • the target information includes identification information of K spatial filters and/or measurement results of the K spatial filters, where K is a positive integer.
  • the K spatial filters may include K transmit spatial filters, denoted as Case 1. That is, the target information inferred by the terminal device based on the target model is the information of K transmit beams.
  • the target information may include identification information of the K transmit beams and/or measurement results of the K transmit beams.
  • the K spatial filters may include a combination of K transmit spatial filters and receive spatial filters, denoted as case 2. That is, the target information inferred by the terminal device based on the target model is the information of K beam pairs.
  • the target information may include identification information of the K beam pairs and/or measurement results of the K beam pairs.
  • the third data set is obtained by the terminal device measuring some of the spatial filters in the candidate spatial filter set, wherein the candidate spatial filter set includes N spatial filters, where, N is a positive integer.
  • the third data set may include identification information of M3 transmit spatial filters, and/or measurement results of the M3 transmit spatial filters.
  • the third data set may include identification information of combinations of M3 transmit spatial filters and receive spatial filters, and/or measurement results of the M3 combinations.
  • candidate spatial filter set may refer to the relevant description in the method 200, and for the sake of brevity, it will not be described again here.
  • the M3 spatial filters may be spatial filters actually used in the downlink beam scanning process.
  • the M3 spatial filters are a subset of the complete set of spatial filters.
  • M3 spatial filters are also called measured spatial filter sets.
  • M3 is less than N, that is, the network device can only use part of the spatial filters in the candidate spatial filter set to send downlink reference signals, without using all spatial filters to send downlink reference signals, which is beneficial to reducing the beam size. Choice of cost and latency.
  • the identification information of the K spatial filters and the measurement results of the K spatial filters may be output through the same model, or may be output through different models. This application provides This is not a limitation.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output the identification information of the K spatial filters, such as the optimal K beams or beams.
  • the second target model is used to output the measurement results of the K spatial filters, such as the measurement results of the optimal K beams or beam pairs.
  • the first target model and the second target model use the same input, that is, the first data set.
  • Figure 9 shows the model structure of the first target model and an example of the relationship between input and output.
  • the input of the first target model can be the index of the beam or beam pair and the corresponding measurement result
  • the label can be the K beams or beam pairs with the best measurement results (or, in other words, the best link quality)
  • the output can be the index of K beams or beam pairs with the best measurement results.
  • Figure 10 shows the model structure of the second target model and an example of the relationship between input and output.
  • the input of the second target model can be the index of the beam or beam pair and the corresponding measurement result
  • the label can be the K beams or beam pairs with the best measurement results (or, in other words, the best link quality)
  • the output can be the measurement results of the optimal K beams or beam pairs.
  • the number of beams or beam pairs output by using the target model to infer the optimal beam or beam pair may be the same as the number of beams or beam pairs marked when training the target model, or alternatively, Can be smaller than the number of beams or beam pairs labeled when training the target model.
  • K beams or beam pairs are marked when training the target model, when using the target model to infer the optimal beam or beam pair, K beams or beam pairs can be output, or less than K beams or beam pairs can be output. Yes, this application only takes outputting the same number of beams or beam pairs as an example for description, but this application is not limited to this.
  • the target model may be CNN, or it may be RNN, or it may be other neural network models, which is not limited in this application.
  • the target model is trained by a network device.
  • the method 300 further includes:
  • the terminal device sends a fourth data set to the network device.
  • the fourth data set is used by the network device to train the target model and obtain model parameters of the target model.
  • the fourth data set includes: partial measurement information obtained by the terminal device during the downlink full scan process, and optimal spatial filtering determined based on all measurement information obtained by the terminal device during the downlink full scan process. device information.
  • the fourth data set includes at least one of the following:
  • the M4 spatial filters include some of the spatial filters in the candidate spatial filter set, and the Q spatial filters are all spatial filters in the candidate spatial filter set that the terminal device Obtained by measurement.
  • Q may be equal to K, or Q may be greater than K.
  • the number of optimal spatial filters inferred using the target model may be less than or equal to the number of optimal spatial filters labeled when training the target model.
  • the method 300 further includes:
  • the terminal device receives the model type and/or model parameter information of the target model sent by the network device.
  • the network device may send the model type and/or model parameter information of the target model to the terminal device.
  • the network device may send information about the trained target model to the terminal device.
  • the model type and model parameters of the target model can be used by the terminal device to construct the target model.
  • the model parameters of the target model are used to indicate the network structure (for example, included layers) of the target model, the connection relationships between the various layers, and other parameters.
  • the target model is trained by the terminal device.
  • the method 300 further includes:
  • the terminal device acquires the fifth data set
  • the terminal device trains the target model according to the fifth data set to obtain model parameters of the target model.
  • the fifth data set includes: partial measurement information obtained by the terminal device during the downlink full scan process, and optimal spatial filtering determined based on all measurement information obtained by the terminal device during the downlink full scan process. device information.
  • the fifth data set includes at least one of the following:
  • the M5 spatial filters include some of the spatial filters in the candidate spatial filter set, and the X spatial filters are all spatial filters in the candidate spatial filter set that the terminal device Obtained by measurement.
  • the method 300 further includes:
  • the terminal device sends the model type and/or model parameter information of the target model to the network device.
  • the network device can send the information of the target model to the terminal device.
  • the method 300 further includes:
  • the terminal device sends second indication information to the network device, where the second indication information is used to indicate the K spatial filters.
  • Case 1 The K spatial filters are K transmit spatial filters.
  • the second indication information is used to indicate the identification information of the K transmit spatial filters, such as the indices of the K transmit beams.
  • the K spatial filters are a combination of K transmit spatial filters and receive spatial filters.
  • the terminal device may indicate to the terminal device K transmit spatial filters from a combination of K transmit spatial filters and receive spatial filters, or may also indicate a combination of K transmit spatial filters and receive spatial filters. combination.
  • Method 1 The second indication information is used to indicate the identification information of the transmit spatial filter in each of the K combinations.
  • the terminal device may indicate to the network device the identification information of the transmit spatial filters in each combination, and the transmit spatial filter
  • the identification information can be used to indicate a transmit spatial filter.
  • Method 2 The second indication information is used to indicate the identification information of each of the K combinations.
  • the terminal device may indicate identification information of each combination to the network device, and the combined identification information may be used to indicate a transmit Combination of spatial filter and receive spatial filter.
  • Method 3 The second indication information is used to indicate the identification information of the transmit spatial filter and the identification information of the receive spatial filter in each of the K combinations.
  • the terminal device may indicate to the network device the identification information of the transmit spatial filter and the identity of the receive spatial filter in each combination.
  • Information the identification information of the transmit spatial filter may be used to indicate a transmit spatial filter
  • the identification information of the receive spatial filter may be used to indicate a receive spatial filter.
  • the terminal device when the K spatial filters belong to the M3 spatial filters, the terminal device sends the second indication information to the network device.
  • the terminal device may send the second indication information to the network device.
  • the terminal device can learn which receive spatial filter is used to receive the network device's transmission using the K transmit spatial filters.
  • the downlink reference signal therefore, does not need to further perform the downlink beam scanning process to determine the optimal receiving spatial filter.
  • the method 300 further includes:
  • the terminal device receives third indication information sent by the network device, where the third indication information is used to indicate the target spatial filter determined by the network device among the K spatial filters.
  • the network device can learn the identification information of K spatial filters. Further, the network device can determine the target spatial filter among the K spatial filters, and then notify the terminal through the third indication information. Device indicates the target space filter.
  • the indication manner of the third indication information may refer to the indication manner of the first indication information in method 200, and for the sake of brevity, details will not be described here.
  • the target filter includes a target transmit spatial filter
  • the third indication information is used to indicate at least one transmission configuration indication TCI state, and the at least one TCI state corresponds to the target transmit spatial filter.
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter
  • the third indication information is used to indicate at least one TCI state, and the at least one TCI state corresponds to the combination. target emission spatial filter.
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter
  • the third indication information is used to indicate at least one TCI state, and the at least one TCI state corresponds to the combination.
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter
  • the third indication information is used to indicate identification information of the target transmit spatial filter and the target receive space. Identification information of the filter.
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter, and the third indication information is used to indicate identification information of the combination.
  • the method 300 further includes:
  • the terminal device sends fourth indication information to the network device, and the fourth indication information is used to trigger the network device to use the second spatial filter to send a downlink reference signal.
  • the second spatial filter among the K spatial filters that does not belong to the M3 spatial filters may include:
  • the K spatial filters are K transmit spatial filters, including a second transmit spatial filter, and the second transmit spatial filter does not belong to the M3 transmit spatial filters;
  • the K spatial filters are a combination of K transmit spatial filters and receive spatial filters, including a combination of a second transmit spatial filter and a second receive spatial filter, a second transmit spatial filter and a second receive spatial filter.
  • the combination of filters does not belong to the combination of M3 transmit spatial filters and receive spatial filters.
  • the terminal device can trigger the network device P1 process. It should be understood that when the transmit spatial filter inferred by the terminal device does not belong to the measured transmit spatial filter set, the terminal device may not know which receive spatial filter to use to receive the downlink data sent by the network device using the transmit spatial filter. The reference signal, therefore, needs to be further determined based on the P3 process.
  • the network device triggers an aperiodic P3 process according to the fourth instruction information, such as transmitting a CSI-RS resource set with its repetition type (Repetition) set to ON.
  • CSI-RS resources are sent using the first transmit spatial filter.
  • the UE receives CSI-RS resources by converting different receive spatial filters to determine the optimal receive spatial filter corresponding to the first transmit spatial filter.
  • the network device when both the terminal device and the network device predict the optimal spatial filter based on the target model, the network device can also infer the optimal spatial filter based on the target model. In this case, The terminal device may not send the second indication information to the network device. Alternatively, if the optimal transmit space filter inferred by the terminal device and the network device is not in the set of measured transmit space filters, the terminal device may instruct the network device to trigger The P3 process determines the optimal receive spatial filter corresponding to the optimal transmit spatial filter.
  • the method 300 further includes:
  • the terminal device sends first capability information to the network device, where the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal device uses the target model to predict The ability to target information.
  • the terminal device may indicate to the network device its training capabilities and/or inference capabilities for the model for spatial filter prediction.
  • the first capability information includes at least one of the following:
  • Whether the terminal device supports model-based prediction of the target information that is, whether the terminal device supports model-based prediction of optimal spatial filters
  • the size of the training data set supported by the terminal device such as the number of bytes supported
  • the type of model supported by the terminal device such as CNN or RNN, etc.;
  • the data type supported by the terminal device for predicting the target information is not limited to the data type supported by the terminal device for predicting the target information.
  • the configuration of the model supported by the terminal device includes at least one of the following:
  • the number of input parameters, the number of hidden layers, and the number of output parameters are the number of input parameters, the number of hidden layers, and the number of output parameters.
  • the method 300 further includes:
  • the terminal device receives first configuration information of the network device, and the first configuration information is used to configure the terminal device to train the target model and/or use the target model to predict the target information.
  • the network device may instruct the terminal device to be responsible for training the target model.
  • the network device may instruct the terminal device to be responsible for using the target model to predict the optimal spatial filter.
  • the network device can instruct the terminal device to be responsible for training the target model and using the target model to predict the optimal spatial filter.
  • the first configuration information is also used to configure the type of the target model used by the terminal device.
  • the first configuration information can be used to configure the target model to be implemented through CNN or RNN.
  • the first configuration information can be sent through any downlink signaling.
  • the first configuration information is sent through radio resource control RRC signaling.
  • the network device only needs to perform scanning of some spatial filters, and the terminal device only needs to measure some of the spatial filters to use the trained target model to predict the optimal spatial filter. , which is beneficial to reducing the overhead and delay caused by downlink beam scanning.
  • Figure 12 is a schematic flowchart of a wireless communication method 1000 according to another embodiment of the present application.
  • the method 1000 can be executed by the network device in the communication system shown in Figure 1.
  • the method 1000 includes The following content:
  • the network device obtains a sixth data set, where the sixth data set includes measurement information of multiple spatial filters by the terminal device;
  • S1020 train the target model according to the sixth data set to obtain model parameters of the target model, wherein the target model is used to select the target model among the multiple spatial filters according to the measurement results of the multiple spatial filters. Determine the target space filter.
  • the sixth data set includes at least one of the following:
  • the sixth data set includes: partial measurement information obtained by the terminal device during the downlink full scan process, and optimal spatial filtering determined based on all measurement information obtained by the terminal device during the downlink full scan process. device information.
  • the target model may be obtained by using offline training, or may be obtained by using online training, or may be obtained by combining offline training and online training.
  • the network device first obtains a static training result through offline training, and further uses the offline trained model to predict the optimal beam or beam pair. In subsequent measurements and/or reports of the terminal device, the network device can continue to collect more information. More measurement data is then used to continue training the target model to optimize model parameters to achieve better prediction results.
  • the M6 spatial filters include some of the spatial filters in the candidate spatial filter set, and the Y spatial filters are measured by the terminal device on all spatial filters in the candidate spatial filter set. owned.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output identification information of K spatial filters
  • the second target model is used to output the Measurement results of K spatial filters, where K is a positive integer.
  • Y may be greater than or equal to K.
  • the method 1000 further includes:
  • the network device sends the model type and/or model parameter information of the target model to the terminal device.
  • the network device when the network device is responsible for training the target model and the terminal device predicts the optimal spatial filter based on the target model, the network device may send the model type and/or model parameters of the target model to the terminal device.
  • the network device when the network device is responsible for training the target model, and both the terminal device and the terminal device predict the optimal spatial filter based on the target model, the network device may send the model type and/or model parameters of the target model to the terminal device.
  • the method 1000 further includes:
  • the network device receives the first capability information sent by the terminal device, wherein the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal device uses the target model. The ability to predict said target information.
  • the terminal device may indicate to the network device its training capabilities and/or inference capabilities for the model for spatial filter prediction.
  • the first capability information includes at least one of the following:
  • Whether the terminal device supports model-based prediction of the target information that is, whether the terminal device supports model-based prediction of optimal spatial filters
  • the size of the training data set supported by the terminal device such as the number of bytes supported
  • the type of model supported by the terminal device such as CNN or RNN, etc.;
  • the data type supported by the terminal device for predicting the target information is not limited to the data type supported by the terminal device for predicting the target information.
  • the configuration of the model supported by the terminal device includes at least one of the following:
  • the number of input parameters, the number of hidden layers, and the number of output parameters are the number of input parameters, the number of hidden layers, and the number of output parameters.
  • the method 200 further includes:
  • the network device sends first configuration information to the terminal device according to the first capability information.
  • the first configuration information is used to configure the terminal device to train the target model and/or use the target.
  • the model predicts the target information.
  • the network device may instruct the terminal device to be responsible for training the target model.
  • the network device may instruct the terminal device to be responsible for using the target model to predict the optimal spatial filter.
  • the network device can instruct the terminal device to be responsible for training the target model and using the target model to predict the optimal spatial filter.
  • the first configuration information is also used to configure the type of the target model used by the terminal device.
  • the first configuration information can be used to configure the target model to be implemented through CNN or RNN.
  • the first configuration information can be sent through any downlink signaling.
  • the first configuration information is sent through radio resource control RRC signaling.
  • the network device may also use the target model to infer optimal spatial filters.
  • the network device may obtain the first data set from the terminal device, further input the first data set into the target model, and output the target information, where the target information may include identification information of K spatial filters, and/or the K The measurement results of a spatial filter, where K is a positive integer.
  • the network device may also indicate the inferred K spatial filters to the terminal device.
  • the network device may send first indication information to the terminal device, where the first indication information is used to indicate the K spatial filters.
  • first indication information is used to indicate the K spatial filters.
  • the first indication information please refer to the relevant description of the first indication information in the method 200. For the sake of brevity, details will not be described here.
  • Figure 13 is a schematic flowchart of a wireless communication method 1100 according to another embodiment of the present application.
  • the method 1100 can be executed by the terminal device in the communication system shown in Figure 1.
  • the method 1100 includes The following content:
  • the terminal device obtains a seventh data set, where the seventh data set includes measurement information of multiple spatial filters by the terminal device;
  • S1120 train the target model according to the seventh data set to obtain model parameters of the target model, wherein the target model is used to select the target model among the plurality of spatial filters according to the measurement results of the plurality of spatial filters. Determine the target space filter.
  • the seventh data set includes: partial measurement information obtained by the terminal device during the downlink full scan process, and optimal spatial filtering determined based on all measurement information obtained by the terminal device during the downlink full scan process. device information.
  • the seventh data set includes at least one of the following:
  • the M7 spatial filters include some of the spatial filters in the candidate spatial filter set, and the Z spatial filters are measured by the terminal device on all spatial filters in the candidate spatial filter set. owned.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output identification information of K spatial filters
  • the second target model is used to output the Measurement results of K spatial filters, where K is a positive integer.
  • the method 1100 further includes:
  • the terminal device sends the model type and/or model parameter information of the target model to the network device.
  • the terminal device when the terminal device is responsible for training the target model and the network device predicts the optimal spatial filter based on the target model, the terminal device may send the model type and/or model parameters of the target model to the network device.
  • the terminal device when the terminal device is responsible for training the target model, and both the terminal device and the terminal device predict the optimal spatial filter based on the target model, the terminal device may send the model type and/or model parameters of the target model to the network device.
  • the method 1100 further includes:
  • the terminal device sends first capability information to the network device, where the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal device uses the target model to predict The ability to target information.
  • the terminal device may indicate to the network device its training capabilities and/or inference capabilities for the model for spatial filter prediction.
  • the first capability information includes at least one of the following:
  • Whether the terminal device supports model-based prediction of the target information that is, whether the terminal device supports model-based prediction of optimal spatial filters
  • the size of the training data set supported by the terminal device such as the number of bytes supported
  • the type of model supported by the terminal device such as CNN or RNN, etc.;
  • the data type supported by the terminal device for predicting the target information is not limited to the data type supported by the terminal device for predicting the target information.
  • the configuration of the model supported by the terminal device includes at least one of the following:
  • the number of input parameters, the number of hidden layers, and the number of output parameters are the number of input parameters, the number of hidden layers, and the number of output parameters.
  • the method 1100 further includes:
  • the terminal device receives first configuration information of the network device, and the first configuration information is used to configure the terminal device to train the target model and/or use the target model to predict the target information.
  • the network device may instruct the terminal device to be responsible for training the target model.
  • the network device may instruct the terminal device to be responsible for using the target model to predict the optimal spatial filter.
  • the network device can instruct the terminal device to be responsible for training the target model and using the target model to predict the optimal spatial filter.
  • the first configuration information is also used to configure the type of the target model used by the terminal device.
  • the first configuration information can be used to configure the target model to be implemented through CNN or RNN.
  • the first configuration information can be sent through any downlink signaling.
  • the first configuration information is sent through radio resource control RRC signaling.
  • the terminal device may also use the target model to infer optimal spatial filters.
  • the terminal device may obtain the third data set, further input the third data set into the target model, and output the target information, where the target information may include identification information of K spatial filters, and/or the K spatial filters
  • the target information may include identification information of K spatial filters, and/or the K spatial filters
  • the terminal device may also indicate the inferred K spatial filters to the network device.
  • the terminal device may send second indication information to the network device, where the second indication information is used to indicate the K spatial filters.
  • the second indication information is used to indicate the K spatial filters.
  • the second instruction information please refer to the relevant description of the second instruction information in method 300. For the sake of brevity, details will not be described here.
  • Embodiment 1 The network device performs training of the model and infers optimal beams or pairs of beams.
  • This Embodiment 1 can be applied to UEs with weak computing power.
  • the neural network model is not deployed on the terminal device side. Therefore, after the network device has trained the target model, it does not need to send the model parameters to the UE.
  • the UE reports training data, such as the aforementioned second data set, to the network device.
  • network equipment scans all transmit beams, such as those used by 64 SSBs.
  • the UE measures beam quality through multiple receive beams of each receive antenna panel.
  • the training data reported by the UE may include the following two parts:
  • the first part is the input part of the model, that is, the partially measured M downlink beam indexes or beam pair indexes and the corresponding measurement results;
  • the second part is the annotation part of the model, the K optimal downlink beams or beam pairs, and the corresponding measurement results, such as L1-RSRP.
  • the network device constructs a data set through the training data reported by the UE, and trains the target model (for example, using a gradient descent algorithm) to obtain parameters on each node in the model.
  • S402 The UE reports measurement data used for inference.
  • the measurement data may include measurement data corresponding to partially measured beams or beam pairs. That is, the network device only needs to perform scanning of part of the transmitted beams, and the terminal device only needs to measure part of the transmitted beams or beam pairs, which is beneficial to reducing The overhead and delay caused by the beam scanning process.
  • the measurement data may include identification information and measurement results corresponding to some measured beams or beam pairs, for example, identification information and corresponding measurement results of M beams or beam pairs.
  • the network device can use the measurement data as input to the target model, for example, input the measurement data into the first target model and the second target model respectively, and run the first target model and the second target model,
  • the optimal K beams or beam pair indexes and their corresponding K measurement results are inferred respectively, such as the K optimal L1-RSRPs.
  • S403 The network device performs beam or beam pair instructions.
  • Case 1 The network device uses the target model to infer the optimal transmit beam.
  • the network device may indicate the transmit beam through the TCI status.
  • the network device can trigger an aperiodic P3 process, such as transmitting a CSI-RS resource set with Repetition set to ON, that is, all CSI-RS resources in the CSI-RS resource set are sent using the transmit beam direction.
  • the UE determines the optimal receiving beam corresponding to the transmitting beam by switching different receiving beams.
  • Case 2 The network device uses the target model to infer the optimal beam pair, including the optimal transmit beam and its corresponding receive beam.
  • Case 2-1 The optimal beam pair is among the measured subset of beam pairs.
  • Method 1 The network device can indicate the transmit beam through the TCI status, and the UE can find the optimal receive beam from the measured beam pair subset.
  • Method 2 The network device can separately instruct the UE to transmit the beam (for example, based on TCI status indication) and receive the beam.
  • the TCI status is carried in the MAC CE or DCI to indicate the transmit beam, and an information field is added to the MAC CE or DCI to indicate the index of the receive beam. .
  • Method 3 The network device can indicate the transmit beam and receive beam to the UE through the TCI status.
  • the receive beam index can be jointly encoded into the TCI state.
  • the UE For each TCI state, the UE has 4 possible receive beams, so only 2 extra bits are needed to indicate the 4 receive beams. That is, a total of 5 bits are needed to indicate the beam pair.
  • the advantage of joint coding is that different TCI states may correspond to different numbers of receiving beams. For example, some TCI states correspond to 2 receiving beams, and some TCI states correspond to 4 receiving beams. Compared with adding a new information domain, To indicate the receive beam, the length of the joint code can be made shorter.
  • the network device may indicate the beam pair index to the UE.
  • the network device can indicate the index of the receiving beam to the UE
  • the index of the receiving beam is carried in the DCI or MAC CE.
  • the network device Since the terminal device does not need the transmit beam of the terminal network device, the network device only instructs the receive beam, which is beneficial to reducing signaling overhead.
  • Case 2-2 The optimal beam pair is not in the measured beam pair subset.
  • the UE has not measured the beam pair in advance, so the UE does not know which receiving beam to use for reception.
  • the network device can trigger the P3 process for the terminal device to determine the optimal receiving beam.
  • Embodiment 2 The network device performs training of the model, and the terminal device infers the optimal beam or beam pair.
  • Embodiment 2 can maximize the use of existing standards, with few modifications to existing standards.
  • the UE reports training data, such as the aforementioned second data set, to the network device.
  • the network device sends the trained model information to the UE.
  • model type and model parameter information is sent to the UE.
  • the UE uses the downloaded model type and model parameters to build the target model for subsequent inference operations.
  • the network device can perform scanning of partial transmission beams (or, in other words, perform scanning of a subset of beams), and the UE can measure partial transmission beams or beam pairs, which is beneficial to reducing the overhead and delay of the downlink beam scanning process.
  • S414 The UE uses the target model to derive optimal K beams or beam pairs and corresponding measurement results.
  • the UE indicates K transmit beams or beam pairs to the network device.
  • the UE sends second indication information to the network device, where the second indication information is used to indicate the K transmit beams or beam pairs.
  • Case 1 The UE uses the target model to infer the optimal transmit beam.
  • the UE may indicate the downlink reference signal by transmitting the corresponding beam.
  • a transmit beam is represented by its corresponding downlink reference signal index, for example, by a CSI-RS Resource Indicator (CRI) or an SSB Resource Indicator (SSBRI).
  • CRI CSI-RS Resource Indicator
  • SSBRI SSB Resource Indicator
  • the UE may use a beam reporting mechanism to report the K transmit beams and their corresponding measurement results. For example, K transmit beams and their corresponding measurement results are reported through the CSI domain.
  • the UE can report 4 transmit beams and their corresponding measurement results.
  • the four transmit beams are indicated by their corresponding CRI or SSBRI.
  • the measurement results corresponding to the four transmit beams can be indicated in the form of reference measurement results and differential measurement results. For example, the absolute value of the measurement result of one transmit beam can be reported, and the measurement results of other transmit beams can be reported using the difference relative to the absolute value. Value mode indication.
  • Table 1 illustrates the reporting format for the UE to report four transmit beams and their corresponding measurement results.
  • RSRP#1 represents the absolute value of L1-RSRP corresponding to CRI or SSBRI#1
  • Differential RSRP#2 represents the differential value of L1-RSRP corresponding to CRI or SSBRI#2 relative to RSRP#1
  • Differential RSRP#3 represents CRI or SSBRI
  • Differential RSRP#4 represents the differential value of L1-RSRP corresponding to CRI or SSBRI#4 relative to RSRP#1.
  • the embodiments of the present application do not limit the specific reporting method of the terminal device reporting the measurement results.
  • the absolute value of each measurement result can be reported directly, or multiple measurements can be reported by adding the absolute value of the measurement result plus the differential value.
  • the present application is not limited to this.
  • Case 2 The UE uses the target model to infer the optimal beam pair.
  • Method 1 The UE only reports the transmit beam information in K beam pairs.
  • Method 2 The UE reports the identification information of K beam pairs, such as the beam pair index, that is, the identification information of the beam pair is used to identify a pair of transmitting beams and receiving beams. That is, the identification information of the beam pair may be a joint code of the transmitting beam and the receiving beam.
  • Method 3 The UE reports the identification information of each transmit beam and the identification information of the receive beam in the K beam pairs.
  • the identification information of the transmitting beam is used to identify a transmitting beam
  • the identification information of the receiving beam is used to identify a receiving beam
  • S416 The network device performs beam or beam pair instructions.
  • the network device can select a target beam or beam pair among them and further indicate it to the UE. For example, the network device may send third indication information to the UE for indicating the target beam or beam pair.
  • the indication method of the third indication information refers to the indication method of the first indication information, and for the sake of brevity, it will not be described again here.
  • Embodiment 3 The network device performs model training, and both the terminal device and the network device infer the optimal beam or beam pair.
  • the UE reports training data, such as the aforementioned second data set, to the network device.
  • the network device sends the trained model information to the UE.
  • model type and model parameter information is sent to the UE.
  • the UE uses the downloaded model type and model parameters to build the target model for subsequent inference operations.
  • the network device can perform scanning of partial transmit beams, and the UE can measure partial transmit beams or beam pairs, which is beneficial to reducing the overhead and delay of the downlink beam scanning process.
  • S424 The UE uses the target model to derive optimal K beams or beam pairs and corresponding measurement results.
  • the UE can input the measurement data obtained during the downlink beam scanning process into the target model to obtain the optimal K beams or beam pairs and the corresponding measurement results.
  • the measurement data may include measurement data corresponding to partially measured beams or beam pairs.
  • the measurement data may include identification information and measurement results corresponding to some measured beams or beam pairs, for example, identification information and corresponding measurement results of M beams or beam pairs.
  • S425 The UE reports measurement data used for inference to the network device.
  • the network device uses the target model to derive the optimal K beams or beam pairs, and the corresponding measurement results.
  • the network device can use the measurement data as input to the target model, for example, input the measurement data into the first target model and the second target model respectively, and run the first target model and the second target model.
  • model respectively infer the optimal K beams or beam pair indexes, and their corresponding K measurement results, such as K optimal L1-RSRPs.
  • the network device can trigger the P3 process and use the inferred transmit beam to scan to determine the The receive beam corresponding to the transmit beam.
  • Embodiment 4 The terminal device performs training of the model, and the terminal device infers the optimal beam or beam pair.
  • the UE determines the labeling information of the model based on all the measurement results obtained during the beam scanning process. For example, it labels K optimal beams or beam pairs, and uses some of the measurement results and their corresponding identification information of the beams or beam pairs as input to the model to construct training. Data set to train the model.
  • S432 Perform scanning of partially reflected beams (or perform scanning of a subset of beams).
  • the UE performs measurement of partially reflected beams or beam pairs to obtain measurement data.
  • the measurement data may include measurement data corresponding to partially measured beams or beam pairs.
  • the measurement data may include identification information and measurement results corresponding to some measured beams or beam pairs, for example, identification information and corresponding measurement results of M beams or beam pairs.
  • S433 The UE uses the target model to derive the optimal K beams or beam pairs, and the corresponding measurement results.
  • S434 The UE reports the inference result to the network device.
  • the UE sends second indication information to the network device, where the second indication information is used to indicate K beams or beam pairs.
  • the second indication information is used to indicate K beams or beam pairs.
  • S435 The network device performs beam or beam pair instructions.
  • the network device can select a target beam or beam pair among them and further indicate it to the UE. For example, the network device may send third indication information to the UE for indicating the target beam or beam pair.
  • the indication method of the third indication information refers to the indication method of the first indication information, and for the sake of brevity, it will not be described again here.
  • Embodiment 5 The terminal device performs training of the model, and the terminal device and the network device infer the optimal beam or beam pair.
  • the UE determines the labeling information of the model based on all the measurement results obtained during the beam scanning process. For example, it labels K optimal beams or beam pairs, and uses some of the measurement results and their corresponding identification information of the beams or beam pairs as input to the model to construct training. Data set to train the model.
  • S442 The UE sends the trained model information to the network device.
  • model type and model parameter information is sent to the UE.
  • the UE uses the downloaded model type and model parameters to build the target model for subsequent inference operations.
  • the UE performs measurement of partially reflected beams or beam pairs to obtain measurement data.
  • the measurement data may include measurement data corresponding to partially measured beams or beam pairs.
  • the measurement data may include identification information and measurement results corresponding to some measured beams or beam pairs, for example, identification information and corresponding measurement results of M beams or beam pairs.
  • S444 The UE uses the target model to determine the optimal K beams or beam pairs, and the corresponding measurement results.
  • S445 The UE reports measurement data used for inference to the network device.
  • the network device uses the target model to derive the optimal K beams or beam pairs, and the corresponding measurement results.
  • the network device can use the measurement data as input to the target model, for example, input the measurement data into the first target model and the second target model respectively, and run the first target model and the second target model.
  • model respectively infer the optimal K beams or beam pair indexes, and their corresponding K measurement results, such as K optimal L1-RSRPs.
  • the network device can trigger the P3 process and use the inferred transmit beam to scan to determine the The receive beam corresponding to the transmit beam.
  • Embodiment 6 The terminal device performs model training, and the network device infers the optimal beam or beam pair.
  • S451 Execute the downlink beam scanning process, that is, the P1 process.
  • the UE determines the labeling information of the model based on all the measurement results obtained during the beam scanning process. For example, it labels K optimal beams or beam pairs, and uses some of the measurement results and their corresponding identification information of the beams or beam pairs as input to the model to construct training. Data set to train the model.
  • S452 The UE sends the trained model information to the network device.
  • model type and model parameter information is sent to the UE.
  • the UE uses the downloaded model type and model parameters to build the target model for subsequent inference operations.
  • the UE performs measurement of partially reflected beams or beam pairs to obtain measurement data.
  • S454 The UE reports measurement data used for inference to the network device.
  • the network device uses the target model to determine the optimal K beams or beam pairs, and the corresponding measurement results.
  • the network device indicates the optimal beam or beam pair to the UE.
  • the network device only needs to perform scanning of some spatial filters, and the terminal device only needs to measure some of the spatial filters to use the trained target model to predict the optimal spatial filter. , which is beneficial to reducing the overhead and delay caused by downlink beam scanning.
  • Figure 20 shows a schematic block diagram of a network device 1200 according to an embodiment of the present application.
  • the network device 1200 includes: a communication unit 1210, used to obtain a first data set.
  • the first data set includes identification information of M1 spatial filters, and/or measurement results of M1 spatial filters.
  • M1 is a positive integer;
  • the processing unit 1220 is configured to input the first data set into the target model and output target information.
  • the target information includes the identification information of the K spatial filters and/or the measurement results of the K spatial filters, where K is a positive integer.
  • the spatial filter includes a transmit spatial filter
  • the spatial filter includes a transmit spatial filter and a receive spatial filter.
  • the first data set is obtained by the terminal device measuring some of the spatial filters in the candidate spatial filter set, where the candidate spatial filter set includes N spatial filters, where N is a positive integer. .
  • the set of candidate spatial filters includes N transmit spatial filters; or
  • the set of candidate spatial filters includes N combinations of transmit spatial filters and receive spatial filters.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output the identification information of the K spatial filters
  • the second target model is used to output the measurement results of the K spatial filters. .
  • the first data set is obtained from the terminal device.
  • the target model is trained by a network device.
  • the communication unit 1210 is also used to: obtain the second data set;
  • the processing unit 1220 is also configured to: train the target model according to the second data set to obtain model parameters of the target model.
  • the second data set includes at least one of the following:
  • the M2 spatial filters include some spatial filters in the candidate spatial filter set, and the P spatial filters are obtained by measuring all spatial filters in the candidate spatial filter set by the terminal device.
  • the target model is trained by the terminal device.
  • the communication unit 1210 is also configured to receive model type and/or model parameter information of the target model sent by the terminal device.
  • the communication unit 1210 is further configured to: send first indication information to the terminal device for indicating K spatial filters.
  • the K spatial filters are K transmit spatial filters
  • the first indication information is used to indicate K transmission configuration indication TCI states
  • the K TCI states correspond to the K transmit spatial filters.
  • the K spatial filters are a combination of K transmit spatial filters and receive spatial filters
  • the first indication information is used to indicate K TCI states
  • the K TCI states correspond to the K transmit spatial filters and K transmit spatial filters in a combination of receive spatial filters
  • K spatial filters are a combination of K transmit spatial filters and receive spatial filters.
  • the first indication information is used to indicate K TCI states.
  • the K TCI states correspond to a combination of K transmit spatial filters and receive spatial filters. ;or
  • the K spatial filters are combinations of K transmit spatial filters and receive spatial filters.
  • the first indication information is used to indicate the identification information of the transmit spatial filter and the receive spatial filter in each of the K combinations. identification information; or
  • the K spatial filters are combinations of K transmit spatial filters and receive spatial filters, and the first indication information is the identification information of each of the K combinations.
  • the network device when the K spatial filters belong to the M1 spatial filters, the network device sends the first indication information to the terminal device.
  • the K spatial filters include a first transmit spatial filter, or a combination of a first transmit spatial filter and a first receive spatial filter
  • the M1 spatial filters include M1 transmit spatial filters, or A combination of M1 transmit spatial filters and receive spatial filters.
  • the communication unit 1210 is also used to: send the first trigger information to the terminal device, the first The trigger information is used to trigger the terminal device to traverse all receive spatial filters to receive the downlink reference signal sent by the first transmit spatial filter to determine the optimal receive spatial filter.
  • the communication unit 1210 is further configured to: receive first capability information sent by the terminal device, used to indicate the terminal device's ability to train the target model and/or the terminal device's ability to predict the target information using the target model.
  • the first capability information includes at least one of the following:
  • the terminal device supports model-based prediction of target information, the size of the training data set supported by the terminal device, the type of model supported by the terminal device, the configuration of the model supported by the terminal device, and the data type used for predicting target information supported by the terminal device.
  • the communication unit 1210 is also configured to: send first configuration information to the terminal device for configuring the terminal device to perform target model training and/or use the target model to predict target information, where the first configuration information is based on the first capability. Information confirmed.
  • the first configuration information is also used to configure the type of target model used by the terminal device.
  • the first configuration information is sent through Radio Resource Control RRC signaling.
  • the above-mentioned communication unit may be a communication interface or transceiver, or an input/output interface of a communication chip or a system on a chip.
  • the above-mentioned processing unit may be one or more processors.
  • network device 1200 may correspond to the network device in the method embodiment of the present application, and the above and other operations and/or functions of each unit in the network device 1200 are respectively to implement Figures 7 to 19
  • Figures 7 to 19 For the sake of simplicity, the corresponding processes of the network equipment in the method embodiment shown will not be described again here.
  • Figure 21 is a schematic block diagram of a terminal device according to an embodiment of the present application.
  • the terminal device 1300 of Figure 21 includes:
  • the processing unit 1310 is configured to obtain a third data set.
  • the third data set includes identification information of M3 spatial filters, and/or measurement results of M3 spatial filters, where M3 is a positive integer;
  • the target information includes identification information of K spatial filters and/or measurement results of K spatial filters, where K is a positive integer.
  • the spatial filter includes a transmit spatial filter
  • the spatial filter includes a transmit spatial filter and a receive spatial filter.
  • the third data set is obtained by the terminal device measuring some of the spatial filters in the candidate spatial filter set, where the candidate spatial filter set includes N spatial filters, where N is a positive integer. .
  • the set of candidate spatial filters includes N transmit spatial filters; or
  • the set of candidate spatial filters includes N combinations of transmit spatial filters and receive spatial filters.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output the identification information of the K spatial filters
  • the second target model is used to output the measurement results of the K spatial filters. .
  • the target model is trained by a network device.
  • the terminal device further includes: a communication unit 1320, configured to send a fourth data set to the network device.
  • the fourth data set is used by the network device to train the target model and obtain model parameters of the target model.
  • the fourth data set includes at least one of the following:
  • the M4 spatial filters include some spatial filters in the candidate spatial filter set, and the Q spatial filters are obtained by measuring all spatial filters in the candidate spatial filter set by the terminal device.
  • the terminal device further includes: a communication unit 1320, configured to receive the model type and/or model parameter information of the target model sent by the network device.
  • the target model is trained by the terminal device.
  • the terminal device further includes: a communication unit 1320, used to obtain the fifth data set;
  • the processing unit 1310 is also configured to: train the target model according to the fifth data set to obtain model parameters of the target model.
  • the fifth data set includes at least one of the following:
  • the M5 spatial filters include some spatial filters in the candidate spatial filter set, and the X spatial filters are obtained by measuring all spatial filters in the candidate spatial filter set by the terminal device.
  • the terminal device further includes: a communication unit 1320, configured to send the model type and/or model parameters of the target model to the network device.
  • the terminal device further includes: a communication unit 1320, configured to send second indication information to the network device, where the second indication information is used to indicate K spatial filters.
  • the K spatial filters are K transmit spatial filters
  • the second indication information is used to indicate the identification information of the K transmit spatial filters.
  • the K spatial filters are combinations of K transmit spatial filters and receive spatial filters
  • the second indication information is used to indicate identification information of the transmit spatial filter in each of the K combinations.
  • the K spatial filters are combinations of K transmit spatial filters and receive spatial filters, and the second indication information is used to indicate the identification information of each of the K combinations;
  • the K spatial filters are combinations of K transmit spatial filters and receive spatial filters.
  • the second indication information is used to indicate the identification information of the transmit spatial filter and the receive spatial filter in each of the K combinations. Identification information.
  • the terminal device when the K spatial filters belong to M3 spatial filters, the terminal device sends the second indication information to the network device.
  • the terminal device further includes: a communication unit 1320, configured to receive third indication information sent by the network device.
  • the third indication information is used to instruct the network device to determine the target spatial filtering among the K spatial filters. device.
  • the target filter includes a target transmit spatial filter
  • the third indication information is used to indicate at least one transmission configuration indicating TCI state, and the at least one TCI state corresponds to the target transmit spatial filter.
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter
  • the third indication information is used to indicate at least one TCI state, and the at least one TCI state corresponds to the target transmit spatial filter in the combination
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter, and the third indication information is used to indicate at least one TCI state, and the at least one TCI state corresponds to the combination; or
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter, and the third indication information is used to indicate the identification information of the target transmit spatial filter and the identification information of the target receive spatial filter;
  • the target filter includes a combination of a target transmit spatial filter and a target receive filter, and the third indication information is used to indicate the identification information of the combination.
  • the terminal device further includes: a communication unit 1320, configured to send fourth indication information to the network device, where the fourth indication information is used to trigger the network device to use the second spatial filter to send the downlink reference signal.
  • the terminal device further includes: a communication unit 1320, configured to send first capability information to the network device, where the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal The ability of a device to predict target information using a target model.
  • a communication unit 1320 configured to send first capability information to the network device, where the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal The ability of a device to predict target information using a target model.
  • the first capability information includes at least one of the following:
  • the terminal device supports model-based prediction of target information, the size of the training data set supported by the terminal device, the type of model supported by the terminal device, the configuration of the model supported by the terminal device, and the data type used for predicting target information supported by the terminal device.
  • the terminal device further includes: a communication unit 1320, configured to receive first configuration information of the network device.
  • the first configuration information is used to configure the terminal device to train the target model and/or use the target model to predict the target. information.
  • the first configuration information is also used to configure the type of target model used by the terminal device.
  • the first configuration information is sent through Radio Resource Control RRC signaling.
  • the above-mentioned communication unit may be a communication interface or transceiver, or an input/output interface of a communication chip or a system on a chip.
  • the above-mentioned processing unit may be one or more processors.
  • terminal device 1300 may correspond to the terminal device in the method embodiment of the present application, and the above and other operations and/or functions of each unit in the terminal device 1300 are respectively to realize Figures 7 to 19
  • the corresponding process of the terminal device in the method embodiment shown is not repeated here for the sake of simplicity.
  • Figure 22 shows a schematic block diagram of a network device 1400 according to an embodiment of the present application.
  • the network device 1400 includes:
  • Communication unit 1410 configured to obtain a sixth data set, which includes measurement information of multiple spatial filters by the terminal device;
  • the processing unit 1420 is configured to train the target model according to the sixth data set to obtain model parameters of the target model, wherein the target model is used to determine the target spatial filter among the multiple spatial filters according to the measurement results of the multiple spatial filters. device.
  • the sixth data set includes at least one of the following:
  • the M6 spatial filters include some spatial filters in the candidate spatial filter set, and the Y spatial filters are obtained by measuring all spatial filters in the candidate spatial filter set by the terminal device.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output the identification information of the K spatial filters
  • the second target model is used to output the measurement results of the K spatial filters.
  • K is a positive integer.
  • the communication unit 1410 is also configured to: send model type and/or model parameter information of the target model to the terminal device.
  • the communication unit 1410 is further configured to: receive first capability information sent by the terminal device, where the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal device uses the target model to predict ability to target information.
  • the first capability information includes at least one of the following:
  • the terminal device supports model-based prediction of target information, the size of the training data set supported by the terminal device, the type of model supported by the terminal device, the configuration of the model supported by the terminal device, and the data type used for predicting target information supported by the terminal device.
  • the communication unit 1410 is further configured to: send first configuration information to the terminal device, where the first configuration information is used to configure the terminal device to perform target model training and/or use the target model to predict target information.
  • the first configuration information is also used to configure the type of target model used by the terminal device.
  • the first configuration information is sent through Radio Resource Control RRC signaling.
  • the above-mentioned communication unit may be a communication interface or transceiver, or an input/output interface of a communication chip or a system on a chip.
  • the above-mentioned processing unit may be one or more processors.
  • network device 1400 may correspond to the network device in the method embodiment of the present application, and the above and other operations and/or functions of each unit in the network device 1400 are respectively to implement Figures 7 to 19
  • the corresponding processes of the network equipment in the method embodiment shown will not be described again here.
  • Figure 23 is a schematic block diagram of a terminal device according to an embodiment of the present application.
  • the terminal device 1500 of Figure 23 includes:
  • the processing unit 1510 is configured to obtain a seventh data set, which includes measurement information of multiple spatial filters by the terminal device; and to train the target model according to the seventh data set to obtain model parameters of the target model, where, The target model is used to determine the target spatial filter among the plurality of spatial filters based on the measurement results of the plurality of spatial filters.
  • the seventh data set includes at least one of the following:
  • the M7 spatial filters include some spatial filters in the candidate spatial filter set, and the Z spatial filters are obtained by measuring all spatial filters in the candidate spatial filter set by the terminal device.
  • the target model includes a first target model and a second target model.
  • the first target model is used to output the identification information of the K spatial filters
  • the second target model is used to output the measurement results of the K spatial filters.
  • K is a positive integer.
  • the terminal device further includes: a communication unit 1520, configured to send the model type and/or model parameter information of the target model to the network device.
  • the terminal device further includes: a communication unit 1520, configured to send first capability information to the network device, where the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal The ability of a device to predict target information using a target model.
  • a communication unit 1520 configured to send first capability information to the network device, where the first capability information is used to indicate the terminal device's ability to train the target model and/or the terminal The ability of a device to predict target information using a target model.
  • the first capability information includes at least one of the following:
  • the terminal device supports model-based prediction of target information, the size of the training data set supported by the terminal device, the type of model supported by the terminal device, the configuration of the model supported by the terminal device, and the data type used for predicting target information supported by the terminal device.
  • the terminal device further includes: a communication unit 1520, configured to receive first configuration information of the network device.
  • the first configuration information is used to configure the terminal device to train the target model and/or use the target model to predict the target. information.
  • the first configuration information is also used to configure the type of target model used by the terminal device.
  • the first configuration information is sent through Radio Resource Control RRC signaling.
  • the above-mentioned communication unit may be a communication interface or transceiver, or an input/output interface of a communication chip or a system on a chip.
  • the above-mentioned processing unit may be one or more processors.
  • terminal device 1500 may correspond to the terminal device in the method embodiment of the present application, and the above and other operations and/or functions of each unit in the terminal device 1500 are to implement FIGS. 7 to 19 respectively.
  • the corresponding process of the terminal device in the method embodiment shown is not repeated here for the sake of simplicity.
  • Figure 24 is a schematic structural diagram of a communication device 600 provided by an embodiment of the present application.
  • the communication device 600 shown in Figure 24 includes a processor 610.
  • the processor 610 can call and run a computer program from the memory to implement the method in the embodiment of the present application.
  • the communication device 600 may further include a memory 620.
  • the processor 610 can call and run the computer program from the memory 620 to implement the method in the embodiment of the present application.
  • the memory 620 may be a separate device independent of the processor 610 , or may be integrated into the processor 610 .
  • the communication device 600 may also include a transceiver 630, and the processor 610 may control the transceiver 630 to communicate with other devices. Specifically, it may send information or data to other devices, or receive other devices. Information or data sent by the device.
  • the transceiver 630 may include a transmitter and a receiver.
  • the transceiver 630 may further include an antenna, and the number of antennas may be one or more.
  • the communication device 600 may specifically be a network device according to the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the network device in the various methods of the embodiment of the present application. For the sake of brevity, details will not be repeated here. .
  • the communication device 600 can be a mobile terminal/terminal device according to the embodiment of the present application, and the communication device 600 can implement the corresponding processes implemented by the mobile terminal/terminal device in each method of the embodiment of the present application. For the sake of simplicity, , which will not be described in detail here.
  • Figure 25 is a schematic structural diagram of a chip according to an embodiment of the present application.
  • the chip 700 shown in Figure 25 includes a processor 710.
  • the processor 710 can call and run a computer program from the memory to implement the method in the embodiment of the present application.
  • the chip 700 may also include a memory 720 .
  • the processor 710 can call and run the computer program from the memory 720 to implement the method in the embodiment of the present application.
  • the memory 720 may be a separate device independent of the processor 710 , or may be integrated into the processor 710 .
  • the chip 700 may also include an input interface 730.
  • the processor 710 can control the input interface 730 to communicate with other devices or chips. Specifically, it can obtain information or data sent by other devices or chips.
  • the chip 700 may also include an output interface 740.
  • the processor 710 can control the output interface 740 to communicate with other devices or chips. Specifically, it can output information or data to other devices or chips.
  • the chip can be applied to the network device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the network device in the various methods of the embodiment of the present application.
  • the details will not be described again.
  • the chip can be applied to the mobile terminal/terminal device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiment of the present application. For the sake of simplicity, here No longer.
  • chips mentioned in the embodiments of this application may also be called system-on-chip, system-on-a-chip, system-on-chip or system-on-chip, etc.
  • Figure 26 is a schematic block diagram of a communication system 900 provided by an embodiment of the present application. As shown in Figure 26, the communication system 900 includes a terminal device 910 and a network device 920.
  • the terminal device 910 can be used to implement the corresponding functions implemented by the terminal device in the above method
  • the network device 920 can be used to implement the corresponding functions implemented by the network device in the above method.
  • no further details will be given here. .
  • the processor in the embodiment of the present application may be an integrated circuit chip and has signal processing capabilities.
  • each step of the above method embodiment can be completed through an integrated logic circuit of hardware in the processor or instructions in the form of software.
  • the above-mentioned processor can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other available processors.
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the steps of the method disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • 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.
  • non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electrically removable memory. Erase programmable read-only memory (Electrically EPROM, EEPROM) or flash memory. Volatile memory may be Random Access Memory (RAM), which is used as an external cache.
  • RAM Random Access Memory
  • RAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM DDR SDRAM
  • enhanced SDRAM ESDRAM
  • Synchlink DRAM SLDRAM
  • Direct Rambus RAM Direct Rambus RAM
  • the memory in the embodiment of the present application can also be a static random access memory (static RAM, SRAM), a 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 connection Dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM) and so on. That is, memories in embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.
  • Embodiments of the present application also provide a computer-readable storage medium for storing computer programs.
  • the computer-readable storage medium can be applied to the network device in the embodiment of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiment of the present application. For the sake of simplicity, here No longer.
  • the computer-readable storage medium can be applied to the mobile terminal/terminal device in the embodiment of the present application, and the computer program causes the computer to execute the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiment of the present application. , for the sake of brevity, 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 network device in the embodiment of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiment of the present application. For the sake of brevity, they are not included here. Again.
  • the computer program product can be applied to the mobile terminal/terminal device in the embodiment of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the mobile terminal/terminal device in each method of the embodiment of the present application, For the sake of brevity, no further details will be given here.
  • An embodiment of the present application also provides a computer program.
  • the computer program can be applied to the network device in the embodiment of the present application.
  • the computer program When the computer program is run on the computer, it causes the computer to execute the corresponding processes implemented by the network device in each method of the embodiment of the present application.
  • the computer program For the sake of simplicity , which will not be described in detail here.
  • the computer program can be applied to the mobile terminal/terminal device in the embodiments of the present application.
  • the computer program When the computer program is run on the computer, it causes the computer to execute the various methods implemented by the mobile terminal/terminal device in the embodiments of the present application. The corresponding process, for the sake of brevity, will not be repeated here.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in 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 they may be distributed to multiple network units. Some or all of the units can 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 can be integrated into one processing unit, each unit can exist physically alone, or two or more units can 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 technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code. .

Landscapes

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

Abstract

一种无线通信的方法、网络设备和终端设备,该方法包括:网络设备获取第一数据集,所述第一数据集包括M1个空间滤波器的标识信息,和/或,所述M1个空间滤波器的测量结果,所述M1为正整数;将所述第一数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,K为正整数。

Description

无线通信的方法、网络设备和终端设备 技术领域
本申请实施例涉及通信领域,具体涉及一种无线通信的方法、网络设备和终端设备。
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,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,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
本申请提供了一种无线通信的方法、网络设备和终端设备,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,包括:网络设备获取第一数据集,所述第一数据集包括M1个空间滤波器的标识信息,和/或,所述M1个空间滤波器的测量结果,所述M1为正整数;
将所述第一数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,K为正整数。
第二方面,提供了一种无线通信的方法,包括:终端设备获取第三数据集,所述第三数据集包括M3个空间滤波器的标识信息,和/或,所述M3个空间滤波器的测量结果,所述M3为正整数;
将所述第三数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,其中,K为正整数。
第三方面,提供了一种无线通信的方法,包括:网络设备获取第六数据集,包括终端设备对多个空间滤波器的测量信息;根据第六数据集对目标模型进行训练,得到目标模型的模型参数,其中,目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
第四方面,提供了一种无线通信的方法,包括:终端设备获取第七数据集,包括所述终端设备对多个空间滤波器的测量信息;根据第七数据集对目标模型进行训练,得到目标模型的模型参数,其中,所述目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
第五方面,提供了一种网络设备,用于执行上述第一方面或其各实现方式中的方法。
具体地,该网络设备包括用于执行上述第一方面或其各实现方式中的方法的功能模块。
第六方面,提供了一种终端设备,用于执行上述第二方面或其各实现方式中的方法。
具体地,该终端设备包括用于执行上述第二方面或其各实现方式中的方法的功能模块。
第七方面,提供了一种网络设备,用于执行上述第三方面或其各实现方式中的方法。
具体地,该网络设备包括用于执行上述第三方面或其各实现方式中的方法的功能模块。
第八方面,提供了一种终端设备,用于执行上述第四方面或其各实现方式中的方法。
具体地,该终端设备包括用于执行上述第四方面或其各实现方式中的方法的功能模块。
第九方面,提供了一种网络设备,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,执行上述第一方面或第三方面或其各实现方式中的方法。
第十方面,提供了一种终端设备,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,执行上述第二方面或第四方面或其各实现方式中的方法。
第十一方面,提供了一种芯片,用于实现上述第一方面至第四方面中的任一方面或其各实现方式中的方法。具体地,该芯片包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有该装置的设备执行如上述第一方面至第四方面中的任一方面或其各实现方式中的方法。
第十二方面,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至第四方面中的任一方面或其各实现方式中的方法。
第十三方面,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至第四方面中的任一方面或其各实现方式中的方法。
第十四方面,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至第四方面中的任一方面或其各实现方式中的方法。
通过上述技术方案,可利用已训练好的目标模型进行最优空间滤波器的预测,因此,网络设备只需执行部分空间滤波器的扫描,终端设备只需对部分空间滤波器进行测量,有利于减少下行波束扫描产生的开销和时延。
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是一种卷积神经网络的示意性结构图。
图4是一种LSTM单元的示意性结构图。
图5是一种下行的波束扫描过程的示意性图。
图6是另一种下行的波束扫描过程的示意性图。
图7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8是目标模型的示意性组成图。
图9是本申请实施例提供的第一目标模型的模型结构以及输入和输出关系的示例图。
图10是本申请实施例提供的第二目标模型的模型结构以及输入和输出关系的示例图。
图11是根据本申请实施例提供的另一种无线通信的方法的示意性图。
图12是根据本申请实施例提供的又一种无线通信的方法的示意性图。
图13是根据本申请实施例提供的又一种无线通信的方法的示意性图。
图14是网络设备侧执行模型训练和推断的示意性交互图。
图15是网络设备侧执行模型训练,终端设备侧执行推断的示意性交互图。
图16是网络设备侧执行模型训练,终端设备和网络设备均执行推断的示意性交互图。
图17是终端设备侧执行模型训练以及推断的示意性交互图。
图18是终端设备侧执行模型训练,终端设备和网络设备均执行推断的示意性交互图。
图19是终端设备侧执行模型训练,网络设备执行推断的示意性交互图。
图20是根据本申请实施例提供的一种网络设备的示意性框图。
图21是根据本申请实施例提供的一种终端设备的示意性框图。
图22是根据本申请实施例提供的另一种网络设备的示意性框图。
图23是根据本申请实施例提供的另一种终端设备的示意性框图。
图24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25是根据本申请实施例提供的一种芯片的示意性框图。
图26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)、无线保真(Wireless Fidelity,WiFi)、第五代通信(5th-Generation,5G)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,或车联网(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。
可选地,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。
可选地,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。
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(gNB)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。可选地,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。可选地,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,可选地,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。
可选地,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,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"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,例如可以包括LTE协议、NR协议以及应用于未来的通信系统中的相关协议,本申请对此不做限定。
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,如图2所示,其中节点间的连接代表从输入信号到输出信号的加权值,称为权重;每个节点对不同的输入信号进行加权求和,并通过特定的激活函数输出。
卷积神经网络(Convolutional Neural Network,CNN)是一种典型的神经网络,图3是一个简单的CNN结构图,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。
循环神经网络(Recurrent Neural Network,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4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)。
下行的波束扫描过程可以为图5所示的P1过程(或称下行的全扫描过程)和图6所示的P3过程。
如图5所示,网络设备可以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6所示,网络设备可以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。
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。
对于下行的全扫描过程,即P1过程,UE需要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。例如网络设备在FR2频段部署了64个不同的下行发射波束(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,那么UE至少需要测量256个波束对,从而需要256个资源 的下行资源开销。
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),那么至少需要80ms的时间。
因此,如何降低波束选择的开销时延是一项亟需解决的问题。
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7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,该方法200可以由图1所示的通信系统中的网络设备执行,如图7所示,该方法200包括如下至少部分内容:
S210,网络设备获取第一数据集,所述第一数据集包括M1个空间滤波器的标识信息,和/或,所述M1个空间滤波器的测量结果,所述M1为正整数;
S220,将所述第一数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,K为正整数。
在一些实施例中,空间滤波器(spatial filter)也可以称为波束(beam)或者空间关系(Spatial relation)或者空间配置(spatial setting)或者,空域滤波器(spatial domain filter),或者,参考信号。在一些实施例中,空间滤波器可以包括发射空间滤波器(Tx spatial filter,或者Tx spatial domain filter)和/或接收空间滤波器(Rx spatial filter,或者,Rx spatial domain filter)。
例如,所述空间滤波器包括一个发射空间滤波器。
又例如,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的组合。
在一些实施例中,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,接收空间滤波器也可以称为接收波束(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,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,所述K个空间滤波器可以包括K个发射空间滤波器,记为情况1。
即,网络设备根据目标模型推断的目标信息是K个发射波束的信息。
此情况下,所述目标信息可以包括K个发射波束的标识信息和/或K个发射波束的测量结果。
在另一些实施例中,所述K个空间滤波器可以包括K个发射空间滤波器和接收空间滤波器的组合,记为情况2。即,网络设备根据目标模型推断的目标信息是K个波束对的信息。
此情况下,所述目标信息可以包括K个波束对的标识信息和/或K个波束对的测量结果。
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。
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。
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。
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,空间滤波器的测量结果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,所述第一数据集可以是从终端设备获取的。
在一些实施例中,所述第一数据集是终端设备对候选空间滤波器集合中的部分空间滤波器进行测量得到的,其中,所述候选空间滤波器集合包括N个空间滤波器,其中,N为正整数。
在一些实施例中,所述第一数据集可以包括M1个发射空间滤波器的标识信息,和/或,所述M1个发射空间滤波器的测量结果。
在一些实施例中,所述第一数据集可以包括M1个发射空间滤波器和接收空间滤波器的组合的标识信息,和/或,所述M1个组合的测量结果。
在一些实施例中,候选空间滤波器集合可以是网络设备配置的。
在一些实施例中,候选空间滤波器集合可以认为是空间滤波器全集。
在一些实施例中,所述候选空间滤波器集合包括N个发射空间滤波器。
即,候选空间滤波器集合可以包括N个发射波束。
在一些实施例中,所述候选空间滤波器集合包括N个发射空间滤波器和接收空间滤波器的组合。
即,候选空间滤波器集合可以包括N个波束对,每个波束对包括一个发射波束和一个接收波束。
在一些实施例中,所述M1个空间滤波器可以是下行的波束扫描过程中实际所使用的空间滤波器。
即,M1个空间滤波器为空间滤波器全集的子集。
在一些实施例中,M1个空间滤波器或称已测空间滤波器集合。
在一些实施例中,M1小于N,即网络设备可以仅使用候选空间滤波器集合中的部分空间滤波器发送下行参考信号,而不需要使用所有的空间滤波器发送下行参考信号,有利于降低波束选择的开销和时延。
在一些实施例中,所述K个空间滤波器的标识信息和所述K个空间滤波器的测量结果可以是通过同一模型输出的,或者,也可以是通过不同的模型输出的,本申请对此不作限定。
例如,如图8所示,目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出所述K个空间滤波器的标识信息,例如最优的K个波束或波束对索引,所述第二目标模型用于输出所述K个空间滤波器的测量结果,例如最优的K个波束或波束对的测量结果。其中,第一目标模型和第二目标模型采用相同的输入,即第一数据集。
图9所示是第一目标模型的模型结构,以及输入和输出关系的一个示例。
如图9所示,第一目标模型的输入可以是波束或波束对的索引以及对应的测量结果,标签可以是测量结果最优(或者说,链路质量最优)的K个波束或波束对的索引,输出可以是测量结果最优的K个波束或波束对的索引。
图10所示是第二目标模型的模型结构,以及输入和输出关系的一个示例。
如图10所示,第二目标模型的输入可以是波束或波束对的索引以及对应的测量结果,标签可以是测量结果最优(或者说,链路质量最优)的K个波束或波束对的测量结果,输出可以是最优的K个波束或波束对的测量结果。
可选地,在一些实施例中,使用目标模型推断最优波束或波束对所输出的波束或波束对的数量,可以和训练目标模型时所标注的波束或波束对的数量相同,或者,也可以小于训练目标模型时所标注的波束或波束对的数量。
也即,训练目标模型时标注了K个波束或波束对的话,使用该目标模型推断最优波束或波束对时,可以输出K个波束或波束对,或者,也可以输出小于K个波束或波束对,本申请仅以输出相同数量的波束或波束对为例进行说明,但本申请并不限于此。
在一些实施例中,所述目标模型可以是CNN,或者,也可以是RNN,或者也可以是其他神经网络模型,本申请对此不作限定。
在本申请一些实施例中,所述目标模型是所述网络设备训练得到的。
在一些实施例中,所述方法200还包括:
所述网络设备获取第二数据集;
根据所述第二数据集对所述目标模型进行训练,得到所述目标模型的模型参数。
其中,所述第二数据集是从终端设备获取的。
在一些实施例中,所述第二数据集包括:下行的全扫描过程中终端设备获取的部分测量信息,以及根据下行的全扫描过程中终端设备获取的全部测量信息确定的最优的空间滤波器信息。
在一些实施例中,所述第二数据集包括以下至少之一:
M2个空间滤波器的标识信息,其中M2为正整数;
M2个空间滤波器的测量结果;
标注的P个最优的空间滤波器的标识信息,其中,P为正整数;
标注的P个最优的空间滤波器的测量结果。
在一些实施例中,所述M2个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述P个空间滤波器是终端设备对所述候选空间滤波器集合中的所有空间滤波器进行测量得到的。
应理解,在本申请实施例中,所述目标模型可以是采用离线训练方式得到的,或者也可以是采用在线训练方式得到的,或者,也可以采用离线训练和在线训练结合的方式得到的。例如网络设备首先通过离线训练方式获得一个静态的训练结果,进一步使用该离线训练的模型进行最优波束或波束对预测,在后续的终端设备的测量和/或上报中,网络设备可以继续收集更多的测量数据,然后使用该测量结果继续训练该目标模型优化模型参数,以达到更好的预测结果。
在一些实施例中,P可以等于K,或者,P也可以大于K。
即,使用该目标模型推断的最优的最优空间滤波器的数量可以小于或等于训练目标模型时所标注的最优空间滤波器的个数。
在本申请一些实施例中,所述方法200还包括:
所述网络设备向所述终端设备发送所述目标模型的模型类型和/或模型参数。
例如,在终端设备和网络设备均根据目标模型预测最优空间滤波器的情况下,网络设备可以将目标模型的模型类型和/或模型参数发送给终端设备。
进一步地,终端设备可以根据上述信息构建目标模型,然后在执行下行的扫描过程获得测量结果之后,可以使用该目标模型推断最优的波束或波束对。
在一些实施例中,目标模型的模型类型可以为DNN或RNN等。
在一些实施例中,目标模型的模型类型和模型参数可以用于终端设备构建所述目标模型。
在一些实施例中,目标模型的模型参数用于指示目标模型的网络结构(例如,包括的层),各个层之间的连接关系等参数。
在本申请另一些实施例中,所述目标模型是所述终端设备训练得到的。
例如,终端设备可以获取用于模型训练的数据集,进一步基于该数据集对目标模型进行训练,得到目标模型的模型参数。
在一些实施例中,网络设备可以触发下行的全扫描过程(即P1过程),终端设备遍历所有的接收空间滤波器进行下行参考信号的接收,得到测量结果集。
进一步地,终端设备可以从测量结果集中选择最高的K个,将该K个测量结果标注为最优的K个测量结果,以及该K个测量结果对应的空间滤波器标注为最优的K个空间滤波器。
在一些实施例中,用于模型训练的数据集可以包括:测量结果集中的部分测量结果以及该部分测量结果对应的空间滤波器的标识信息,以及标注的K个最高的测量结果和K个最高的测量结果对应的空间滤波器的标识信息。
例如,在由终端设备执行目标模型的训练,由网络设备使用目标模型执行最优空间滤波器推断的情况下,终端设备可以将训练得到的目标模型的信息发送给网络设备。
在本申请一些实施例中,所述方法200还包括:
所述网络设备接收所述终端设备发送的所述目标模型的模型类型和/或模型参数信息。
在模型训练完成之后,终端设备可以向网络设备发送目标模型的模型类型和/或模型参数,进一步地,网络设备可以基于该目标模型的模型类型和/或模型参数构建所述目标模型。
在本申请一些实施例中,所述方法200还包括:
所述网络设备向所述终端设备发送第一指示信息,所述第一指示信息用于指示所述K个空间滤波器。
例如,在网络设备根据目标模型推断确定K个空间滤波器之后,网络设备可以向终端设备指示所述K个空间滤波器。
在一些实施例中,所述第一指示信息可以通过MAC CE或DCI发送。
情况1:所述K个空间滤波器为K个发射空间滤波器。
即网络设备推断得到的是K个发射空间滤波器。
可选地,此情况下,第一指示信息用于指示K个TCI状态,该K个TCI状态对应K个发射空间滤波器。即网络设备可以使用TCI状态来指示最优的发射波束。
情况2:所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合。
即网络设备推断得到的是K个发射空间滤波器和接收空间滤波器的组合。
此情况下,网络设备可以向终端设备指示K个发射空间滤波器和接收空间滤波器的组合中的K个发射空间滤波器,或者,也可以指示K个发射空间滤波器和接收空间滤波器的组合。
方式1:第一指示信息用于指示K个TCI状态,所述K个TCI状态对应所述K个发射空间滤波器和接收空间滤波器的组合中的K个发射空间滤波器。
即,在网络设备推断得到K个发射空间滤波器和接收空间滤波器的组合的情况下,网络设备可以使用TCI状态向终端设备仅指示发射空间滤波器。
方式2:第一指示信息用于指示所述K个组合中的每个组合中的发射空间滤波器的标识信息以及接收空间滤波器的标识信息。
即,在网络设备推断得到K个发射空间滤波器和接收空间滤波器的组合的情况下,网络设备可以向终端设备指示发射空间滤波器的标识信息和接收空间滤波器的标识信息。
可选地,所述发射空间滤波器也可以通过TCI状态指示。
在一些实施例中,所述第一指示信息可以通过MAC CE或DCI发送。
例如,在MAC CE或DCI中增加一个信息域,用于指示接收空间滤波器的标识信息。
方式3:第一指示信息用于指示K个TCI状态,所述K个TCI状态对应K个发射空间滤波器和接收空间滤波器的组合。
即,在网络设备推断得到K个发射空间滤波器和接收空间滤波器的组合的情况下,网络设备可以 使用TCI状态向终端设备指示发射空间滤波器和接收空间滤波器。此情况下的TCI状态可以认为是一种增加的空间滤波器指示方式。
方式4:所述第一指示信息为所述K个组合中的每个组合的标识信息。
即,在网络设备推断得到K个发射空间滤波器和接收空间滤波器的组合的情况下,网络设备可以向终端设备指示组合的标识信息,所述组合的标识信息可以用于指示一个发射空间滤波器和接收空间滤波器的组合。
在一些实施例中,在所述K个空间滤波器属于所述M1个空间滤波器的情况下,所述网络设备向所述终端设备发送所述第一指示信息。
例如,在网络设备推断得到的K个发射空间滤波器属于M1个发射空间滤波器(已测的发射空间滤波器集合)时,网络设备可以向终端设备发送第一指示信息。
应理解,在网络设备推断得到的K个发射空间滤波器属于已测的发射空间滤波器集合的情况下,终端设备可以获知使用哪个接收空间滤波器接收网络设备使用该K个发射空间滤波器发送的下行参考信号,因此,不需要进一步执行下行的波束扫描过程来确定最优的接收空间滤波器。
在一些实施例中,所述M1个空间滤波器包括M1个发射空间滤波器,所述K个空间滤波器包括第一发射空间滤波器,或者,所述M1个发射空间滤波器和接收空间滤波器的组合包括第一发射空间滤波器和第一接收空间滤波器的组合,在所述第一发射空间滤波器不属于所述M1个发射空间滤波器的情况下,所述方法200还包括:
所述网络设备向终端设备发送第一触发信息,所述第一触发信息用于触发所述终端设备遍历所有接收空间滤波器接收所述第一发射空间滤波器发送的下行参考信号以确定最优的接收空间滤波器。
即,在网络设备推断得到的发射空间滤波器不属于M1个发射空间滤波器(已测的发射空间滤波器集合)时,网络设备可以触发P3过程。应理解,在网络设备推断得到的发射空间滤波器不属于已测的发射空间滤波器集合的情况下,终端设备可以不知道使用哪个接收空间滤波器接收网络设备使用该发射空间滤波器发送的下行参考信号,因此,需要进一步基于P3过程确定。
例如,网络设备触发一个非周期的P3过程,比如发射一个CSI-RS资源集,其重复类型(Repetition)设置为开启(ON),网络设备对于该CSI-RS资源集中的全部CSI-RS资源都使用第一发射空间滤波器来发送,对应地,UE通过转换不同的接收空间滤波器来接收CSI-RS资源来判断第一发射空间滤波器对应的最优接收空间滤波器。
应理解,在本申请一些实施例中,在终端设备和网络设备均根据目标模型预测最优空间滤波器的情况下,终端设备也可以根据目标模型推断最优的空间滤波器,此情况下,网络设备也可以不向终端设备发送第一指示信息,可选地,如果终端设备和网络设备推断得到的最优发射空间滤波器不在已测发射空间滤波器集合中,网络设备可以触发P3过程以确定该最优发射空间滤波器对应的最优接收空间滤波器。
在本申请一些实施例中,所述方法200还包括:
所述网络设备接收终端设备发送的第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测(或者说,推断)所述目标信息的能力。
即,终端设备可以向网络设备指示其对于用于空间滤波器预测的模型的训练能力和/或推断能力。
在一些实施例中,所述第一能力信息包括以下至少之一:
所述终端设备是否支持基于模型预测所述目标信息,即终端设备是否支持基于模型预测最优空间滤波器;
所述终端设备是否支持对所述目标模型进行训练;
所述终端设备是否支持使用所述目标模型确定目标信息;
所述终端设备支持的训练数据集的大小,例如支持的字节量;
所述终端设备支持的模型的类型,例如支持CNN或RNN等;
所述终端设备支持的模型的配置;
所述终端设备支持的用于预测所述目标信息的数据类型。
在一些实施例中,所述终端设备支持的模型的配置包括以下至少之一:
输入参数的个数,隐藏层的数目,输出参数的个数。
在本申请一些实施例中,所述方法200还包括:
所述网络设备根据所述第一能力信息,向所述终端设备发送第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
例如,在终端设备支持训练得到目标模型的情况下,网络设备可以指示终端设备负责目标模型的 训练。
又例如,在终端设备支持使用目标模型进行最优空间滤波器预测的情况下,网络设备可以指示终端设备负责使用目标模型进行最优空间滤波器的预测。
再例如,在终端设备支持训练得到目标模型以及使用目标模型进行最优空间滤波器预测的情况下,网络设备可以指示终端设备负责目标模型的训练,以及使用目标模型进行最优空间滤波器的预测。
在一些实施例中,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
例如,第一配置信息可以用于配置目标模型通过CNN或RNN实现。
应理解,所述第一配置信息可以通过任一下行信令发送,作为示例而非限定,所述第一配置信息通过无线资源控制RRC信令发送。
综上,在本申请实施例中,网络设备只需执行部分空间滤波器的扫描,终端设备只需对部分空间滤波器进行测量即可利用已训练好的目标模型进行最优空间滤波器的预测,有利于减少下行波束扫描产生的开销和时延。
图11是根据本申请另一实施例的无线通信的方法300的示意性流程图,该方法300可以由图1所示的通信系统中的终端设备执行,如图11所示,该方法300包括如下内容:
S310,终端设备获取第三数据集,所述第三数据集包括M3个空间滤波器的标识信息,和/或,所述M3个空间滤波器的测量结果,所述M3为正整数;
S320,将所述第三数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,其中,K为正整数。
应理解,该方法300中的空间滤波器的相关说明参考方法200中的相关说明,为了简洁,这里不再赘述。
在一些实施例中,所述K个空间滤波器可以包括K个发射空间滤波器,记为情况1。即,终端设备根据目标模型推断的目标信息是K个发射波束的信息。
此情况下,所述目标信息可以包括K个发射波束的标识信息和/或K个发射波束的测量结果。
在另一些实施例中,所述K个空间滤波器可以包括K个发射空间滤波器和接收空间滤波器的组合,记为情况2。即,终端设备根据目标模型推断的目标信息是K个波束对的信息。
此情况下,所述目标信息可以包括K个波束对的标识信息和/或K个波束对的测量结果。
在一些实施例中,所述第三数据集是终端设备对候选空间滤波器集合中的部分空间滤波器进行测量得到的,其中,所述候选空间滤波器集合包括N个空间滤波器,其中,N为正整数。
在一些实施例中,所述第三数据集可以包括M3个发射空间滤波器的标识信息,和/或,所述M3个发射空间滤波器的测量结果。
在一些实施例中,所述第三数据集可以包括M3个发射空间滤波器和接收空间滤波器的组合的标识信息,和/或,所述M3个组合的测量结果。
应理解,候选空间滤波器集合可以参考方法200中的相关说明,为了简洁,这里不再赘述。
在一些实施例中,所述M3个空间滤波器可以是下行的波束扫描过程中实际所使用的空间滤波器。
即,M3个空间滤波器为空间滤波器全集的子集。
在一些实施例中,M3个空间滤波器或称已测空间滤波器集合。
在一些实施例中,M3小于N,即网络设备可以仅使用候选空间滤波器集合中的部分空间滤波器发送下行参考信号,而不需要使用所有的空间滤波器发送下行参考信号,有利于降低波束选择的开销和时延。
在一些实施例中,所述K个空间滤波器的标识信息和所述K个空间滤波器的测量结果可以是通过同一模型输出的,或者,也可以是通过不同的模型输出的,本申请对此不作限定。
例如,如图8所示,目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出所述K个空间滤波器的标识信息,例如最优的K个波束或波束对索引,所述第二目标模型用于输出所述K个空间滤波器的测量结果,例如最优的K个波束或波束对的测量结果。其中,第一目标模型和第二目标模型采用相同的输入,即第一数据集。
图9所示是第一目标模型的模型结构,以及输入和输出关系的一个示例。
如图9所示,第一目标模型的输入可以是波束或波束对的索引以及对应的测量结果,标签可以是测量结果最优(或者说,链路质量最优)的K个波束或波束对的索引,输出可以是测量结果最优的K个波束或波束对的索引。
图10所示是第二目标模型的模型结构,以及输入和输出关系的一个示例。
如图10所示,第二目标模型的输入可以是波束或波束对的索引以及对应的测量结果,标签可以是测量结果最优(或者说,链路质量最优)的K个波束或波束对的测量结果,输出可以是最优的K 个波束或波束对的测量结果。
可选地,在一些实施例中,使用目标模型推断最优波束或波束对所输出的波束或波束对的数量,可以和训练目标模型时所标注的波束或波束对的数量相同,或者,也可以小于训练目标模型时所标注的波束或波束对的数量。
也即,训练目标模型时标注了K个波束或波束对的话,使用该目标模型推断最优波束或波束对时,可以输出K个波束或波束对,或者,也可以输出小于K个波束或波束对,本申请仅以输出相同数量的波束或波束对为例进行说明,但本申请并不限于此。
在一些实施例中,所述目标模型可以是CNN,或者,也可以是RNN,或者也可以是其他神经网络模型,本申请对此不作限定。
在本申请一些实施例中,所述目标模型是网络设备训练得到的。
在一些实施例中,所述方法300还包括:
所述终端设备向所述网络设备发送第四数据集,所述第四数据集用于所述网络设备对所述目标模型进行训练,得到所述目标模型的模型参数。
在一些实施例中,所述第四数据集包括:下行的全扫描过程中终端设备获取的部分测量信息,以及根据下行的全扫描过程中终端设备获取的全部测量信息确定的最优的空间滤波器信息。
在一些实施例中,所述第四数据集包括以下至少之一:
M4个空间滤波器的标识信息,其中M4为正整数;
M4个空间滤波器的测量结果;
Q个最优的空间滤波器的标识信息,其中Q为正整数;
Q个最优的空间滤波器的测量结果。
在一些实施例中,所述M4个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述Q个空间滤波器是终端设备对所述候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,Q可以等于K,或者,Q也可以大于K。
即,使用该目标模型推断的最优的最优空间滤波器的数量可以小于或等于训练目标模型时所标注的最优空间滤波器的个数。
在本申请一些实施例中,所述方法300还包括:
所述终端设备接收所述网络设备发送的所述目标模型的模型类型和/或模型参数信息。
即,网络设备根据第四数据集进行训练得到目标模型之后,可以向终端设备发送目标模型的模型类型和/或模型参数信息。
例如,在由网络设备执行目标模型的训练,由终端设备使用目标模型执行最优空间滤波器推断的情况下,网络设备可以将训练得到的目标模型的信息发送给终端设备。
在一些实施例中,目标模型的模型类型和模型参数可以用于终端设备构建所述目标模型。
在一些实施例中,目标模型的模型参数用于指示目标模型的网络结构(例如,包括的层),各个层之间的连接关系等参数。
在本申请又一些实施例中,所述目标模型是所述终端设备训练得到的。
在一些实施例中,所述方法300还包括:
所述终端设备获取第五数据集;
所述终端设备根据所述第五数据集对所述目标模型进行训练,得到所述目标模型的模型参数。
在一些实施例中,所述第五数据集包括:下行的全扫描过程中终端设备获取的部分测量信息,以及根据下行的全扫描过程中终端设备获取的全部测量信息确定的最优的空间滤波器信息。
在一些实施例中,所述第五数据集包括以下至少之一:
M5个空间滤波器的标识信息,其中M5为正整数;
M5个空间滤波器的测量结果;
X个最优的空间滤波器的标识信息;
X个最优的空间滤波器的测量结果。
在一些实施例中,所述M5个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述X个空间滤波器是终端设备对所述候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,所述方法300还包括:
所述终端设备向所述网络设备发送所述目标模型的模型类型和/或模型参数信息。
例如,在终端设备和网络设备均根据目标模型预测最优空间滤波器的情况下,网络设备可以将目标模型的信息发送给终端设备。
在本申请一些实施例中,所述方法300还包括:
所述终端设备向所述网络设备发送第二指示信息,所述第二指示信息用于指示所述K个空间滤波器。
情况1:所述K个空间滤波器为K个发射空间滤波器。
即网络设备推断得到的是K个发射空间滤波器。
可选地,此情况下,所述第二指示信息用于指示所述K个发射空间滤波器的标识信息,例如K个发射波束的索引。
情况2:所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合。
即网络设备推断得到的是K个发射空间滤波器和接收空间滤波器的组合。
此情况下,终端设备可以向终端设备指示K个发射空间滤波器和接收空间滤波器的组合中的K个发射空间滤波器,或者,也可以指示K个发射空间滤波器和接收空间滤波器的组合。
方式1:第二指示信息用于指示所述K个组合中的每个组合中的发射空间滤波器的标识信息。
即,在终端设备推断得到K个发射空间滤波器和接收空间滤波器的组合的情况下,终端设备可以向网络设备指示每个组合中的发射空间滤波器的标识信息,所述发射空间滤波器的标识信息可以用于指示一个发射空间滤波器。
方式2:第二指示信息用于指示所述K个组合中的每个组合的标识信息。
即,在终端设备推断得到K个发射空间滤波器和接收空间滤波器的组合的情况下,终端设备可以向网络设备指示每个组合的标识信息,所述组合的标识信息可以用于指示一个发射空间滤波器和接收空间滤波器的组合。
方式3:第二指示信息用于指示所述K个组合中的每个组合中的发射空间滤波器的标识信息以及接收空间滤波器的标识信息。
即,在终端设备推断得到K个发射空间滤波器和接收空间滤波器的组合的情况下,终端设备可以向网络设备指示每个组合中的发射空间滤波器的标识信息和接收空间滤波器的标识信息,所述发射空间滤波器的标识信息可以用于指示一个发射空间滤波器,所述接收空间滤波器的标识信息用于指示一个接收空间滤波器。
在一些实施例中,在所述K个空间滤波器属于所述M3个空间滤波器的情况下,所述终端设备向所述网络设备发送所述第二指示信息。
例如,在终端设备推断得到的K个发射空间滤波器属于M3个发射空间滤波器(已测的发射空间滤波器集合)时,终端设备可以向网络设备发送第二指示信息。
应理解,在终端设备推断得到的K个发射空间滤波器属于已测的发射空间滤波器集合的情况下,终端设备可以获知使用哪个接收空间滤波器接收网络设备使用该K个发射空间滤波器发送的下行参考信号,因此,不需要进一步执行下行的波束扫描过程来确定最优的接收空间滤波器。
在本申请一些实施例中,所述方法300还包括:
所述终端设备接收所述网络设备发送的第三指示信息,所述第三指示信息用于指示所述网络设备在所述K个空间滤波器中确定的目标空间滤波器。
例如,网络设备接收到第二指示信息之后,可以获知K个空间滤波器的标识信息,进一步地,网络设备可以在K个空间滤波器中确定目标空间滤波器,然后通过第三指示信息向终端设备指示目标空间滤波器。
应理解,第三指示信息的指示方式可以参考方法200中第一指示信息的指示方式,为了简洁,这里不再赘述。
在一些实施例中,所述目标滤波器包括目标发射空间滤波器,所述第三指示信息用于指示至少一个传输配置指示TCI状态,所述至少一个TCI状态对应所述目标发射空间滤波器。
在一些实施例中,所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示至少一个TCI状态,所述至少一个TCI状态对应所述组合中的目标发射空间滤波器。
在一些实施例中,所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示至少一个TCI状态,所述至少一个TCI状态对应所述组合。
在一些实施例中,所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示所述目标发射空间滤波器的标识信息以及所述目标接收空间滤波器的标识信息。
在一些实施例中,所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示所述组合的标识信息。
在本申请另一些实施例中,在所述K个空间滤波器中的第二空间滤波器不属于所述M3个空间滤波器的情况下,所述方法300还包括:
所述终端设备向所述网络设备发送第四指示信息,所述第四指示信息用于触发所述网络设备使用 所述第二空间滤波器发送下行参考信号。
在一些实施例中,K个空间滤波器中的第二空间滤波器不属于所述M3个空间滤波器可以包括:
K个空间滤波器为K个发射空间滤波器,其中包括第二发射空间滤波器,第二发射空间滤波器不属于M3个发射空间滤波器;或者
K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,其中包括第二发射空间滤波器和第二接收空间滤波器的组合,第二发射空间滤波器和第二接收空间滤波器的组合不属于M3个发射空间滤波器和接收空间滤波器的组合。
例如,在终端设备推断得到的发射空间滤波器不属于M3个发射空间滤波器(已测的发射空间滤波器集合)时,终端设备可以触发网络设备P1过程。应理解,在终端设备推断得到的发射空间滤波器不属于已测的发射空间滤波器集合的情况下,终端设备可以不知道使用哪个接收空间滤波器接收网络设备使用该发射空间滤波器发送的下行参考信号,因此,需要进一步基于P3过程确定。
例如,网络设备根据第四指示信息触发一个非周期的P3过程,比如发射一个CSI-RS资源集,其重复类型(Repetition)设置为开启(ON),网络设备对于该CSI-RS资源集中的全部CSI-RS资源都使用第一发射空间滤波器来发送,对应地,UE通过转换不同的接收空间滤波器来接收CSI-RS资源来判断第一发射空间滤波器对应的最优接收空间滤波器。
应理解,在本申请一些实施例中,在终端设备和网络设备均根据目标模型预测最优空间滤波器的情况下,网络设备也可以根据目标模型推断最优的空间滤波器,此情况下,终端设备也可以不向网络设备发送第二指示信息,可选地,如果终端设备和网络设备推断得到的最优发射空间滤波器不在已测发射空间滤波器集合中,终端设备可以指示网络设备触发P3过程以确定该最优发射空间滤波器对应的最优接收空间滤波器。
在本申请一些实施例中,所述方法300还包括:
所述终端设备向网络设备发送第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测所述目标信息的能力。
即,终端设备可以向网络设备指示其对于用于空间滤波器预测的模型的训练能力和/或推断能力。
在一些实施例中,所述第一能力信息包括以下至少之一:
所述终端设备是否支持基于模型预测所述目标信息,即终端设备是否支持基于模型预测最优空间滤波器;
所述终端设备是否支持对所述目标模型进行训练;
所述终端设备是否支持使用所述目标模型确定目标信息;
所述终端设备支持的训练数据集的大小,例如支持的字节量;
所述终端设备支持的模型的类型,例如支持CNN或RNN等;
所述终端设备支持的模型的配置;
所述终端设备支持的用于预测所述目标信息的数据类型。
在一些实施例中,所述终端设备支持的模型的配置包括以下至少之一:
输入参数的个数,隐藏层的数目,输出参数的个数。
在本申请一些实施例中,所述方法300还包括:
所述终端设备接收网络设备的第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
例如,在终端设备支持训练得到目标模型的情况下,网络设备可以指示终端设备负责目标模型的训练。
又例如,在终端设备支持使用目标模型进行最优空间滤波器预测的情况下,网络设备可以指示终端设备负责使用目标模型进行最优空间滤波器的预测。
再例如,在终端设备支持训练得到目标模型以及使用目标模型进行最优空间滤波器预测的情况下,网络设备可以指示终端设备负责目标模型的训练,以及使用目标模型进行最优空间滤波器的预测。
在一些实施例中,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
例如,第一配置信息可以用于配置目标模型通过CNN或RNN实现。
应理解,所述第一配置信息可以通过任一下行信令发送,作为示例而非限定,所述第一配置信息通过无线资源控制RRC信令发送。
综上,在本申请实施例中,网络设备只需执行部分空间滤波器的扫描,终端设备只需对部分空间滤波器进行测量即可利用已训练好的目标模型进行最优空间滤波器的预测,有利于减少下行波束扫描产生的开销和时延。
图12是根据本申请又一实施例的无线通信的方法1000的示意性流程图,该方法1000可以由图 1所示的通信系统中的网络设备执行,如图12所示,该方法1000包括如下内容:
S1010,网络设备获取第六数据集,所述第六数据集包括终端设备对多个空间滤波器的测量信息;
S1020,根据所述第六数据集对目标模型进行训练,得到所述目标模型的模型参数,其中,所述目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
在一些实施例中,所述第六数据集包括以下至少之一:
M6个空间滤波器的标识信息,其中M6为正整数;
M6个空间滤波器的测量结果;
Y个最优的空间滤波器的标识信息,其中,Y为正整数;
Y个最优的空间滤波器的测量结果。
在一些实施例中,所述第六数据集包括:下行的全扫描过程中终端设备获取的部分测量信息,以及根据下行的全扫描过程中终端设备获取的全部测量信息确定的最优的空间滤波器信息。
应理解,在本申请实施例中,所述目标模型可以是采用离线训练方式得到的,或者也可以是采用在线训练方式得到的,或者,也可以采用离线训练和在线训练结合的方式得到的。例如网络设备首先通过离线训练方式获得一个静态的训练结果,进一步使用该离线训练的模型进行最优波束或波束对预测,在后续的终端设备的测量和/或上报中,网络设备可以继续收集更多的测量数据,然后使用该测量结果继续训练该目标模型优化模型参数,以达到更好的预测结果。
在一些实施例中,所述M6个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述Y个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,所述目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出K个空间滤波器的标识信息,所述第二目标模型用于输出所述K个空间滤波器的测量结果,其中K为正整数。
在一些实施例中,Y可以大于或等于K。
应理解,所述目标模型的相关实现参考方法200中的相关描述,为了简洁,这里不再赘述。
在一些实施例中,所述方法1000还包括:
所述网络设备向所述终端设备发送所述目标模型的模型类型和/或模型参数信息。
例如,在网络设备负责目标模型的训练,终端设备根据目标模型预测最优空间滤波器的情况下,网络设备可以将目标模型的模型类型和/或模型参数发送给终端设备。
又例如,在网络设备负责目标模型的训练,终端设备和终端设备均根据目标模型预测最优空间滤波器的情况下,网络设备可以将目标模型的模型类型和/或模型参数发送给终端设备。
在一些实施例中,所述方法1000还包括:
所述网络设备接收终端设备发送的第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测所述目标信息的能力。
即,终端设备可以向网络设备指示其对于用于空间滤波器预测的模型的训练能力和/或推断能力。
在一些实施例中,所述第一能力信息包括以下至少之一:
所述终端设备是否支持基于模型预测所述目标信息,即终端设备是否支持基于模型预测最优空间滤波器;
所述终端设备是否支持对所述目标模型进行训练;
所述终端设备是否支持使用所述目标模型确定目标信息;
所述终端设备支持的训练数据集的大小,例如支持的字节量;
所述终端设备支持的模型的类型,例如支持CNN或RNN等;
所述终端设备支持的模型的配置;
所述终端设备支持的用于预测所述目标信息的数据类型。
在一些实施例中,所述终端设备支持的模型的配置包括以下至少之一:
输入参数的个数,隐藏层的数目,输出参数的个数。
在本申请一些实施例中,所述方法200还包括:
所述网络设备根据所述第一能力信息,向所述终端设备发送第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
例如,在终端设备支持训练得到目标模型的情况下,网络设备可以指示终端设备负责目标模型的训练。
又例如,在终端设备支持使用目标模型进行最优空间滤波器预测的情况下,网络设备可以指示终端设备负责使用目标模型进行最优空间滤波器的预测。
再例如,在终端设备支持训练得到目标模型以及使用目标模型进行最优空间滤波器预测的情况 下,网络设备可以指示终端设备负责目标模型的训练,以及使用目标模型进行最优空间滤波器的预测。
在一些实施例中,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
例如,第一配置信息可以用于配置目标模型通过CNN或RNN实现。
应理解,所述第一配置信息可以通过任一下行信令发送,作为示例而非限定,所述第一配置信息通过无线资源控制RRC信令发送。
在一些实施例中,所述网络设备还可以使用所述目标模型推断最优的空间滤波器。
例如,网络设备可以从终端设备获取第一数据集,进一步将第一数据集输入目标模型,输出目标信息,其中,目标信息可以包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,其中,K为正整数。
应理解,网络设备根据目标模型推断最优空间滤波器的具体实现参考方法200中的相关说明,为了简洁,这里不再赘述。
可选地,在一些实施例中,所述网络设备还可以向终端设备指示推断得到的K个空间滤波器。
例如,网络设备可以向终端设备发送第一指示信息,所述第一指示信息用于指示所述K个空间滤波器。其中,第一指示信息的具体实现参考方法200中的第一指示信息的相关说明,为了简洁,这里不再赘述。
图13是根据本申请又一实施例的无线通信的方法1100的示意性流程图,该方法1100可以由图1所示的通信系统中的终端设备执行,如图13所示,该方法1100包括如下内容:
S1110,终端设备获取第七数据集,所述第七数据集包括所述终端设备对多个空间滤波器的测量信息;
S1120,根据所述第七数据集对目标模型进行训练,得到所述目标模型的模型参数,其中,所述目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
在一些实施例中,所述第七数据集包括:下行的全扫描过程中终端设备获取的部分测量信息,以及根据下行的全扫描过程中终端设备获取的全部测量信息确定的最优的空间滤波器信息。
在一些实施例中,所述第七数据集包括以下至少之一:
M7个空间滤波器的标识信息,其中M7为正整数;
M7个空间滤波器的测量结果;
Z个最优的空间滤波器的标识信息,其中,Z为正整数;
Z个最优的空间滤波器的测量结果。
在一些实施例中,所述M7个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述Z个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,所述目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出K个空间滤波器的标识信息,所述第二目标模型用于输出所述K个空间滤波器的测量结果,其中K为正整数。
应理解,所述目标模型的相关实现参考方法200中的相关描述,为了简洁,这里不再赘述。
在一些实施例中,所述方法1100还包括:
所述终端设备向所述网络设备发送所述目标模型的模型类型和/或模型参数信息。
例如,在终端设备负责目标模型的训练,网络设备根据目标模型预测最优空间滤波器的情况下,终端设备可以将目标模型的模型类型和/或模型参数发送给网络设备。
又例如,在终端设备负责目标模型的训练,终端设备和终端设备均根据目标模型预测最优空间滤波器的情况下,终端设备可以将目标模型的模型类型和/或模型参数发送给网络设备。
在一些实施例中,所述方法1100还包括:
所述终端设备向网络设备发送第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测所述目标信息的能力。
即,终端设备可以向网络设备指示其对于用于空间滤波器预测的模型的训练能力和/或推断能力。
在一些实施例中,所述第一能力信息包括以下至少之一:
所述终端设备是否支持基于模型预测所述目标信息,即终端设备是否支持基于模型预测最优空间滤波器;
所述终端设备是否支持对所述目标模型进行训练;
所述终端设备是否支持使用所述目标模型确定目标信息;
所述终端设备支持的训练数据集的大小,例如支持的字节量;
所述终端设备支持的模型的类型,例如支持CNN或RNN等;
所述终端设备支持的模型的配置;
所述终端设备支持的用于预测所述目标信息的数据类型。
在一些实施例中,所述终端设备支持的模型的配置包括以下至少之一:
输入参数的个数,隐藏层的数目,输出参数的个数。
在一些实施例中,所述方法1100还包括:
所述终端设备接收网络设备的第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
例如,在终端设备支持训练得到目标模型的情况下,网络设备可以指示终端设备负责目标模型的训练。
又例如,在终端设备支持使用目标模型进行最优空间滤波器预测的情况下,网络设备可以指示终端设备负责使用目标模型进行最优空间滤波器的预测。
再例如,在终端设备支持训练得到目标模型以及使用目标模型进行最优空间滤波器预测的情况下,网络设备可以指示终端设备负责目标模型的训练,以及使用目标模型进行最优空间滤波器的预测。
在一些实施例中,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
例如,第一配置信息可以用于配置目标模型通过CNN或RNN实现。
应理解,所述第一配置信息可以通过任一下行信令发送,作为示例而非限定,所述第一配置信息通过无线资源控制RRC信令发送。
在一些实施例中,所述终端设备还可以使用所述目标模型推断最优的空间滤波器。
例如,终端设备可以获取第三数据集,进一步将第三数据集输入目标模型,输出目标信息,其中,目标信息可以包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,其中,K为正整数。
应理解,终端设备根据目标模型推断最优空间滤波器的具体实现参考方法300中的相关说明,为了简洁,这里不再赘述。
可选地,在一些实施例中,所述终端设备还可以向网络设备指示推断得到的K个空间滤波器。
例如,终端设备可以向网络设备发送第二指示信息,所述第二指示信息用于指示所述K个空间滤波器。其中,第二指示信息的具体实现参考方法300中的第二指示信息的相关说明,为了简洁,这里不再赘述。
以下,结合实施例1至实施例6,以空间滤波器为波束或波束对为例,说明具体的实现过程。
实施例1:网络设备执行模型的训练,以及推断最优波束或波束对。
该实施例1可以适用于算力较弱的UE,该终端设备侧没有部署神经网络模型,因此,网络设备在训练好目标模型之后,不需要将模型参数发送给UE。
如图14所示,可以包括如下步骤:
S401,UE向网络设备上报训练数据,例如,前述第二数据集。
例如,网络设备扫描全部的发射波束,如64个SSB所用的波束。UE通过每一个接收天线面板的多个接收波束来进行波束质量的测量。
UE上报的训练数据可以包括如下两部分:
第一部分是模型的输入部分,即部分测量的M个下行波束索引或波束对索引以及对应的测量结果;
第二部分是模型的标注部分,K个最优的下行波束或波束对,以及对应的测量结果,例如L1-RSRP。
网络设备通过UE的上报的训练数据来构建数据集,训练目标模型(如使用梯度下降算法)得到模型中的各个节点上的参数。
S402,UE上报用于推断的测量数据。
其中,该测量数据可以包括部分测量的波束或波束对对应的测量数据,也即,网络设备只需执行部分发射波束的扫描,终端设备只需对部分发射波束或波束对进行测量,有利于降低波束扫描过程带来的开销和时延。
例如,测量数据可以包括测量的部分波束或波束对对应的标识信息以及测量结果,例如M个波束或波束对的标识信息以及对应的测量结果。
网络设备在获知UE上报的测量数据之后,可以将测量数据作为目标模型的输入,例如将测量数据分别输入至第一目标模型和第二目标模型,并运行第一目标模型和第二目标模型,分别推断最优的K个波束或波束对索引,以及其对应的K个测量结果,如K个最优的L1-RSRP。
S403,网络设备进行波束或波束对指示。
情况1:网络设备使用目标模型推断得到的是最优的发射波束。
如果该发射波束是在UE已测量的发射波束子集中,那么网络设备可以通过TCI状态指示该发射波束。
如果该发射波束不在UE已测量的发射波束子集中,那么UE需要对该发射波束进行测量来找到对应的最优接收波束。因此,网络设备可以触发一个非周期的P3过程,例如传输一个CSI-RS资源集,其Repetition设置为ON,即该CSI-RS资源集中的全部CSI-RS资源都使用该发射波束方向来发送,对应的,UE通过转换不同的接收波束来判断该发射波束对应的最优接收波束。
情况2:网络设备使用目标模型推断得到的是最优的波束对,包含最优的发射波束和其对应的接收波束。
情况2-1:该最优的波束对是在已测量的波束对子集中。
方式1:网络设备可以通过TCI状态指示该发射波束,UE可以从已测量的波束对子集中找到最优的接收波束。
方式2:网络设备可以向UE分别指示发射波束(例如基于TCI状态指示),以及接收波束。
例如,如MAC CE或DCI中携带TCI状态,用于指示发射波束,以及在MAC CE或DCI中增加一个信息域,专用于指示接收波束的索引。。
方式3:网络设备可以通过TCI状态向UE指示发射波束以及接收波束。
即可以将接收波束索引联合编码到TCI状态中。
例如,如果有8个处于激活状态的TCI状态,需要3bits来指示其中之一。
对于每一个TCI状态,UE有4个可能的接收波束,那么仅需要额外的2比特就可以指示该4个接收波束。即总共需要使用5比特来进行波束对的指示。
联合编码的好处在于:不同的TCI状态可能对应的接收波束个数不同,例如有的TCI状态对应2个接收波束,有的TCI状态对应4个接收波束,相比于增加一个新的信息域用于指示接收波束,联合编码的长度可以做到更短。
方式4:网络设备可以向UE指示波束对索引。
方式5:网络设备可以向UE指示接收波束的索引
例如,在DCI或MAC CE中携带接收波束的索引。
由于,终端设备不需要终端网络设备的发射波束,网络设备只指示接收波束,有利于降低信令开销。
情况2-2:该最优的波束对不在已测量的波束对子集中。UE没有提前测量过该波束对,那么UE不知道该使用哪个接收波束来进行接收。例如,网络设备可以触发P3过程用于终端设备确定最优的接收波束。
实施例2:网络设备执行模型的训练,以及终端设备推断最优波束或波束对。
该实施例2的执行过程可以最大化沿用已有标准,对已有标准的修改较少。
如图15所示,可以包括如下步骤:
S411,UE向网络设备上报训练数据,例如,前述第二数据集。
具体的实现过程参考图14中的S401的相关描述,这里不再赘述。
S412,网络设备将训练好的模型信息发送给UE。
例如,将模型类型和模型参数信息发送给UE。
UE使用下载的模型类型和模型参数构建目标模型以进行后续的推断操作。
S413,执行下行波束的扫描过程。
具体地,网络设备可以执行部分发射波束的扫描(或者说,执行波束子集的扫描),UE可以对部分发射波束或波束对进行测量,有利于降低下行波束扫描过程的开销和时延。
S414,UE使用目标模型推导最优的K个波束或波束对,以及对应的测量结果。
S415,UE向网络设备指示K个发射波束或波束对。
例如,UE向网络设备发送第二指示信息,所述第二指示信息用于指示所述K个发射波束或波束对。
情况1:UE使用目标模型推断得到的是最优的发射波束。
在一些实施例中,UE可以通过发射波束对应的下行参考信号指示。例如发射波束通过其对应的下行参考信号索引表示,例如,通过CSI-RS资源指示(CSI-RS Resource Indicator,CRI)或SSB资源指示(SSB Resource Indicator,SSBRI)指示。
在一些实施例中,UE可以使用波束上报机制上报所述K个发射波束及其对应的测量结果。例如,通过CSI域上报K个发射波束及其对应的测量结果。
以K等于4为例,UE可以上报4个发射波束及其对应的测量结果。其中,该4个发射波束通过 其对应的CRI或SSBRI指示。该4个发射波束对应的测量结果可以采用参考测量结果和差分测量结果的方式指示,例如,可以上报一个发射波束的测量结果的绝对值,其他发射波束的测量结果采用相对于该绝对值的差分值方式指示。
表1示例了UE上报4个发射波束及其对应的测量结果的上报格式。其中CRI or SSBRI#n表示UE上报的发射波束对应的CSI-RS资源或SSB资源的索引,n=1,2,3,4。RSRP#1表示CRI or SSBRI#1对应的L1-RSRP的绝对值,Differential RSRP#2表示CRI or SSBRI#2对应的L1-RSRP相对于RSRP#1的差分值,Differential RSRP#3表示CRI or SSBRI#3对应的L1-RSRP相对于RSRP#1的差分值,Differential RSRP#4表示CRI or SSBRI#4对应的L1-RSRP相对于RSRP#1的差分值。
表1
Figure PCTCN2022089649-appb-000001
应理解,本申请实施例并不限定终端设备上报测量结果的具体上报方式,例如,可以直接上报每个测量结果的绝对值,也可以采用测量结果的绝对值加差分值的方式上报多个测量结果,本申请并不限于此。
情况2:UE使用目标模型推断得到的是最优的波束对。
方式1:UE仅上报K个波束对中的发射波束信息。
方式2:UE上报K个波束对的标识信息,例如波束对索引,即波束对的标识信息用于标识一对发射波束和接收波束。即该波束对的标识信息可以是发射波束和接收波束的联合编码。
方式3:UE上报K个波束对中的每个发射波束的标识信息和接收波束的标识信息。
其中,该发射波束的标识信息用于标识一个发射波束,接收波束的标识信息用于标识一个接收波束。
S416,网络设备进行波束或波束对指示。
例如,网络设备在获知UE上报的K个波束或波束对之后,可以在其中选择目标波束或波束对,进一步指示给UE。例如,网络设备可以向UE发送第三指示信息,用于指示目标波束或波束对。
其中,第三指示信息的指示方式参考第一指示信息的指示方式,为了简洁,这里不再赘述。
实施例3:网络设备执行模型的训练,终端设备和网络设备均推断最优波束或波束对。
如图16所示,可以包括如下步骤:
S421,UE向网络设备上报训练数据,例如,前述第二数据集。
具体的实现过程参考图14中的S401的相关描述,这里不再赘述。
S422,网络设备将训练好的模型信息发送给UE。
例如,将模型类型和模型参数信息发送给UE。
UE使用下载的模型类型和模型参数构建目标模型以进行后续的推断操作。
S423,执行下行波束的扫描过程。
具体地,网络设备可以执行部分发射波束的扫描,UE可以对部分发射波束或波束对进行测量,有利于降低下行波束扫描过程的开销和时延。
S424,UE使用目标模型推导最优的K个波束或波束对,以及对应的测量结果。
例如,UE可以将下行波束扫描过程获得的测量数据输入目标模型,得到最优的K个波束或波束对,以及对应的测量结果。
其中,该测量数据可以包括部分测量的波束或波束对对应的测量数据。例如,测量数据可以包括测量的部分波束或波束对对应的标识信息以及测量结果,例如M个波束或波束对的标识信息以及对应的测量结果。
S425,UE向网络设备上报用于推断的测量数据。
应理解,本申请并不限定S424和S425的执行顺序,可替换地,也可以先执行S425后执行S424。
S426,网络设备使用目标模型推导最优的K个波束或波束对,以及对应的测量结果。
例如,网络设备在获知UE上报的测量数据之后,可以将测量数据作为目标模型的输入,例如将测量数据分别输入至第一目标模型和第二目标模型,并运行第一目标模型和第二目标模型,分别推断 最优的K个波束或波束对索引,以及其对应的K个测量结果,如K个最优的L1-RSRP。
此情况下,网络设备和UE之间可以不进行波束或波束对的指示。
在一些实施例中,若推断的发射波束不在已测发射波束集合中,或者,推断的波束对不在已测波束对集合中,网络设备可以触发P3过程,使用推断的发射波束进行扫描以确定该发射波束对应的接收波束。
实施例4:终端设备执行模型的训练,终端设备推断最优波束或波束对。
如图17所示,可以包括如下步骤:
S431,执行下行的波束扫描过程,即P1过程。
UE基于波束扫描过程获得的全部测量结果确定模型的标注信息,例如,标注K个最优的波束或波束对,将部分测量结果及其对应的波束或波束对的标识信息作为模型的输入构建训练数据集,对模型进行训练。
S432,执行部分反射波束的扫描(或者,执行波束子集的扫描)。
对应的,UE执行部分反射波束或波束对的测量,得到测量数据。
其中,该测量数据可以包括部分测量的波束或波束对对应的测量数据。
例如,测量数据可以包括测量的部分波束或波束对对应的标识信息以及测量结果,例如M个波束或波束对的标识信息以及对应的测量结果。
S433,UE使用目标模型推导最优的K个波束或波束对,以及对应的测量结果。
S434,UE向网络设备上报推断结果。
例如,UE向网络设备发送第二指示信息,所述第二指示信息用于指示K个波束或波束对。具体的指示方式参考前述实施例的相关描述,这里不再赘述。
S435,网络设备进行波束或波束对指示。
例如,网络设备在获知UE上报的K个波束或波束对之后,可以在其中选择目标波束或波束对,进一步指示给UE。例如,网络设备可以向UE发送第三指示信息,用于指示目标波束或波束对。
其中,第三指示信息的指示方式参考第一指示信息的指示方式,为了简洁,这里不再赘述。
实施例5:终端设备执行模型的训练,终端设备和网络设备推断最优波束或波束对。
如图18所示,可以包括如下步骤:
S441,执行下行的波束扫描过程,即P1过程。
UE基于波束扫描过程获得的全部测量结果确定模型的标注信息,例如,标注K个最优的波束或波束对,将部分测量结果及其对应的波束或波束对的标识信息作为模型的输入构建训练数据集,对模型进行训练。
S442,UE向网络设备发送训练好的模型信息。
例如,将模型类型和模型参数信息发送给UE。
UE使用下载的模型类型和模型参数构建目标模型以进行后续的推断操作。
S443,执行部分反射波束的扫描。
对应的,UE执行部分反射波束或波束对的测量,得到测量数据。
其中,该测量数据可以包括部分测量的波束或波束对对应的测量数据。
例如,测量数据可以包括测量的部分波束或波束对对应的标识信息以及测量结果,例如M个波束或波束对的标识信息以及对应的测量结果。
S444,UE使用目标模型断最优的K个波束或波束对,以及对应的测量结果。
S445,UE向网络设备上报用于推断的测量数据。
应理解,本申请并不限定S444和S445的执行顺序,可替换地,也可以先执行S445后执行S444。
S446,网络设备使用目标模型推导最优的K个波束或波束对,以及对应的测量结果。
例如,网络设备在获知UE上报的测量数据之后,可以将测量数据作为目标模型的输入,例如将测量数据分别输入至第一目标模型和第二目标模型,并运行第一目标模型和第二目标模型,分别推断最优的K个波束或波束对索引,以及其对应的K个测量结果,如K个最优的L1-RSRP。
此情况下,网络设备和UE之间可以不进行波束或波束对的指示。
在一些实施例中,若推断的发射波束不在已测发射波束集合中,或者,推断的波束对不在已测波束对集合中,网络设备可以触发P3过程,使用推断的发射波束进行扫描以确定该发射波束对应的接收波束。
实施例6:终端设备执行模型的训练,网络设备推断最优波束或波束对。
如图19所示,可以包括如下步骤:
S451,执行下行的波束扫描过程,即P1过程。
UE基于波束扫描过程获得的全部测量结果确定模型的标注信息,例如,标注K个最优的波束或波束对,将部分测量结果及其对应的波束或波束对的标识信息作为模型的输入构建训练数据集,对模型进行训练。
S452,UE向网络设备发送训练好的模型信息。
例如,将模型类型和模型参数信息发送给UE。
UE使用下载的模型类型和模型参数构建目标模型以进行后续的推断操作。
S453,执行部分反射波束的扫描。
对应的,UE执行部分反射波束或波束对的测量,得到测量数据。
S454,UE向网络设备上报用于推断的测量数据。
S455,网络设备使用目标模型断最优的K个波束或波束对,以及对应的测量结果。
应理解,本申请并不限定S444和S445的执行顺序,可替换地,也可以先执行S445后执行S444。
S456,网络设备向UE指示最优波束或波束对。
具体指示方式参考S403的相关说明,这里不再赘述。
综上,在本申请实施例中,网络设备只需执行部分空间滤波器的扫描,终端设备只需对部分空间滤波器进行测量即可利用已训练好的目标模型进行最优空间滤波器的预测,有利于减少下行波束扫描产生的开销和时延。
上文结合图7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26,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网络设备1200的示意性框图。如图20所示,该网络设备1200包括:通信单元1210,用于获取第一数据集,第一数据集包括M1个空间滤波器的标识信息,和/或,M1个空间滤波器的测量结果,M1为正整数;
处理单元1220,用于将第一数据集输入至目标模型,输出目标信息,目标信息包括K个空间滤波器的标识信息,和/或,K个空间滤波器的测量结果,K为正整数。
在一些实施例中,空间滤波器包括一个发射空间滤波器;或者
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,第一数据集是终端设备对候选空间滤波器集合中的部分空间滤波器进行测量得到的,其中,候选空间滤波器集合包括N个空间滤波器,其中,N为正整数。
在一些实施例中,候选空间滤波器集合包括N个发射空间滤波器;或者
候选空间滤波器集合包括N个发射空间滤波器和接收空间滤波器的组合。
在一些实施例中,目标模型包括第一目标模型和第二目标模型,第一目标模型用于输出K个空间滤波器的标识信息,第二目标模型用于输出K个空间滤波器的测量结果。
在一些实施例中,第一数据集是从终端设备获取的。
在一些实施例中,目标模型是网络设备训练得到的。
在一些实施例中,通信单元1210还用于:获取第二数据集;
处理单元1220还用于:根据第二数据集对目标模型进行训练,得到目标模型的模型参数。
在一些实施例中,第二数据集包括以下至少之一:
M2个空间滤波器的标识信息,其中M2为正整数;
M2个空间滤波器的测量结果;
P个最优的空间滤波器的标识信息,其中,P为正整数;
P个最优的空间滤波器的测量结果。
在一些实施例中,M2个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,P个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,目标模型是终端设备训练得到的。
在一些实施例中,通信单元1210还用于:接收终端设备发送的目标模型的模型类型和/或模型参数信息。
在一些实施例中,通信单元1210还用于:向终端设备发送第一指示信息,用于指示K个空间滤波器。
在一些实施例中,K个空间滤波器为K个发射空间滤波器,第一指示信息用于指示K个传输配置指示TCI状态,K个TCI状态对应K个发射空间滤波器。
在一些实施例中,K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,第一指示信息用于指示K个TCI状态,K个TCI状态对应K个发射空间滤波器和接收空间滤波器的组合中的K个发射空间滤波器;或者
K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,第一指示信息用于指示K个TCI状态,K个TCI状态对应K个发射空间滤波器和接收空间滤波器的组合;或者
K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,第一指示信息用于指示K个组合中的每个组合中的发射空间滤波器的标识信息以及接收空间滤波器的标识信息;或者
K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,第一指示信息为K个组合中的每个组合的标识信息。
在一些实施例中,在K个空间滤波器属于M1个空间滤波器的情况下,网络设备向终端设备发送第一指示信息。
在一些实施例中,K个空间滤波器包括第一发射空间滤波器,或第一发射空间滤波器和第一接收空间滤波器的组合,M1个空间滤波器包括M1个发射空间滤波器,或者M1个发射空间滤波器和接收空间滤波器的组合,在第一发射空间滤波器不属于M1个空间滤波器的情况下,通信单元1210还用于:向终端设备发送第一触发信息,第一触发信息用于触发终端设备遍历所有接收空间滤波器接收第一发射空间滤波器发送的下行参考信号以确定最优的接收空间滤波器。
在一些实施例中,通信单元1210还用于:接收终端设备发送的第一能力信息,用于指示终端设备对目标模型进行训练的能力和/或终端设备使用目标模型预测目标信息的能力。
在一些实施例中,第一能力信息包括以下至少之一:
终端设备是否支持基于模型预测目标信息,终端设备支持的训练数据集的大小,终端设备支持的模型的类型,终端设备支持的模型的配置,终端设备支持的用于预测目标信息的数据类型。
在一些实施例中,通信单元1210还用于:向终端设备发送第一配置信息,用于配置终端设备进行目标模型的训练和/或使用目标模型预测目标信息,第一配置信息根据第一能力信息确定。
在一些实施例中,第一配置信息还用于配置终端设备使用的目标模型的类型。
在一些实施例中,第一配置信息通过无线资源控制RRC信令发送。
可选地,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网络设备1200可对应于本申请方法实施例中的网络设备,并且网络设备1200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7至图19所示方法实施例中网络设备的相应流程,为了简洁,在此不再赘述。
图21是根据本申请实施例的终端设备的示意性框图。图21的终端设备1300包括:
处理单元1310,用于获取第三数据集,第三数据集包括M3个空间滤波器的标识信息,和/或,M3个空间滤波器的测量结果,M3为正整数;以及
将第三数据集输入至目标模型,输出目标信息,目标信息包括K个空间滤波器的标识信息,和/或,K个空间滤波器的测量结果,其中,K为正整数。
在一些实施例中,空间滤波器包括一个发射空间滤波器;或者
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,第三数据集是终端设备对候选空间滤波器集合中的部分空间滤波器进行测量得到的,其中,候选空间滤波器集合包括N个空间滤波器,其中,N为正整数。
在一些实施例中,候选空间滤波器集合包括N个发射空间滤波器;或者
候选空间滤波器集合包括N个发射空间滤波器和接收空间滤波器的组合。
在一些实施例中,目标模型包括第一目标模型和第二目标模型,第一目标模型用于输出K个空间滤波器的标识信息,第二目标模型用于输出K个空间滤波器的测量结果。
在一些实施例中,目标模型是网络设备训练得到的。
在一些实施例中,终端设备还包括:通信单元1320,用于向网络设备发送第四数据集,第四数据集用于网络设备对目标模型进行训练,得到目标模型的模型参数。
在一些实施例中,第四数据集包括以下至少之一:
M4个空间滤波器的标识信息,M4个空间滤波器的测量结果,Q个最优的空间滤波器的标识信息,Q个最优的空间滤波器的测量结果,其中Q为正整数。
在一些实施例中,M4个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,Q个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,终端设备还包括:通信单元1320,用于接收网络设备发送的目标模型的模型类型和/或模型参数信息。
在一些实施例中,目标模型是终端设备训练得到的。
在一些实施例中,所述终端设备还包括:通信单元1320,用于获取第五数据集;
处理单元1310还用于:根据第五数据集对目标模型进行训练,得到目标模型的模型参数。
在一些实施例中,第五数据集包括以下至少之一:
M5个空间滤波器的标识信息,M5个空间滤波器的测量结果,X个最优的空间滤波器的标识信息,X个最优的空间滤波器的测量结果,其中,M5为正整数,X为正整数。
在一些实施例中,M5个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,X个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,所述终端设备还包括:通信单元1320,用于向网络设备发送目标模型的模型类型和/或模型参数。
在一些实施例中,所述终端设备还包括:通信单元1320,用于向网络设备发送第二指示信息,第二指示信息用于指示K个空间滤波器。
在一些实施例中,K个空间滤波器为K个发射空间滤波器,第二指示信息用于指示K个发射空间滤波器的标识信息。
在一些实施例中,K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,第二指示信息用于指示K个组合中的每个组合中的发射空间滤波器的标识信息;或者
K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,第二指示信息用于指示K个组合中的每个组合的标识信息;或者
K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,第二指示信息用于指示K个组合中的每个组合中的发射空间滤波器的标识信息以及接收空间滤波器的标识信息。
在一些实施例中,在K个空间滤波器属于M3个空间滤波器的情况下,终端设备向网络设备发送第二指示信息。
在一些实施例中,所述终端设备还包括:通信单元1320,用于接收网络设备发送的第三指示信息,第三指示信息用于指示网络设备在K个空间滤波器中确定的目标空间滤波器。
在一些实施例中,目标滤波器包括目标发射空间滤波器,第三指示信息用于指示至少一个传输配置指示TCI状态,至少一个TCI状态对应目标发射空间滤波器。
在一些实施例中,目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,第三指示信息用于指示至少一个TCI状态,至少一个TCI状态对应组合中的目标发射空间滤波器;或者
目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,第三指示信息用于指示至少一个TCI状态,至少一个TCI状态对应组合;或者
目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,第三指示信息用于指示目标发射空间滤波器的标识信息以及目标接收空间滤波器的标识信息;或者
目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,第三指示信息用于指示组合的标识信息。
在一些实施例中,所述终端设备还包括:通信单元1320,用于向网络设备发送第四指示信息,第四指示信息用于触发网络设备使用第二空间滤波器发送下行参考信号。
在一些实施例中,所述终端设备还包括:通信单元1320,用于向网络设备发送第一能力信息,其中,第一能力信息用于指示终端设备对目标模型进行训练的能力和/或终端设备使用目标模型预测目标信息的能力。
在一些实施例中,第一能力信息包括以下至少之一:
终端设备是否支持基于模型预测目标信息,终端设备支持的训练数据集的大小,终端设备支持的模型的类型,终端设备支持的模型的配置,终端设备支持的用于预测目标信息的数据类型。
在一些实施例中,所述终端设备还包括:通信单元1320,用于接收网络设备的第一配置信息,第一配置信息用于配置终端设备进行目标模型的训练和/或使用目标模型预测目标信息。
在一些实施例中,第一配置信息还用于配置终端设备使用的目标模型的类型。
在一些实施例中,第一配置信息通过无线资源控制RRC信令发送。
可选地,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终端设备1300可对应于本申请方法实施例中的终端设备,并且终端设备1300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7至图19所示方法实施例中终端设备的相应流程,为了简洁,在此不再赘述。
图22示出了根据本申请实施例的网络设备1400的示意性框图。如图22所示,该网络设备1400包括:
通信单元1410,用于获取第六数据集,第六数据集包括终端设备对多个空间滤波器的测量信息;
处理单元1420,用于根据第六数据集对目标模型进行训练,得到目标模型的模型参数,其中,目标模型用于根据多个空间滤波器的测量结果在多个空间滤波器中确定目标空间滤波器。
在一些实施例中,第六数据集包括以下至少之一:
M6个空间滤波器的标识信息,其中M6为正整数;
M6个空间滤波器的测量结果;
Y个最优的空间滤波器的标识信息,其中,Y为正整数;
Y个最优的空间滤波器的测量结果。
在一些实施例中,M6个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,Y个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,目标模型包括第一目标模型和第二目标模型,第一目标模型用于输出K个空间滤波器的标识信息,第二目标模型用于输出K个空间滤波器的测量结果,其中K为正整数。
在一些实施例中,通信单元1410还用于:向终端设备发送目标模型的模型类型和/或模型参数信息。
在一些实施例中,通信单元1410还用于:接收终端设备发送的第一能力信息,其中,第一能力信息用于指示终端设备对目标模型进行训练的能力和/或终端设备使用目标模型预测目标信息的能力。
在一些实施例中,第一能力信息包括以下至少之一:
终端设备是否支持基于模型预测目标信息,终端设备支持的训练数据集的大小,终端设备支持的模型的类型,终端设备支持的模型的配置,终端设备支持的用于预测目标信息的数据类型。
在一些实施例中,通信单元1410还用于:向终端设备发送第一配置信息,第一配置信息用于配置终端设备进行目标模型的训练和/或使用目标模型预测目标信息。
在一些实施例中,第一配置信息还用于配置终端设备使用的目标模型的类型。
在一些实施例中,第一配置信息通过无线资源控制RRC信令发送。可选地,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网络设备1400可对应于本申请方法实施例中的网络设备,并且网络设备1400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7至图19所示方法实施例中网络设备的相应流程,为了简洁,在此不再赘述。
图23是根据本申请实施例的终端设备的示意性框图。图23的终端设备1500包括:
处理单元1510,用于获取第七数据集,第七数据集包括终端设备对多个空间滤波器的测量信息;以及根据第七数据集对目标模型进行训练,得到目标模型的模型参数,其中,目标模型用于根据多个空间滤波器的测量结果在多个空间滤波器中确定目标空间滤波器。
在一些实施例中,第七数据集包括以下至少之一:
M7个空间滤波器的标识信息,其中M7为正整数;
M7个空间滤波器的测量结果;
Z个最优的空间滤波器的标识信息,其中,Z为正整数;
Z个最优的空间滤波器的测量结果。
在一些实施例中,M7个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,Z个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
在一些实施例中,目标模型包括第一目标模型和第二目标模型,第一目标模型用于输出K个空间滤波器的标识信息,第二目标模型用于输出K个空间滤波器的测量结果,其中K为正整数。
在一些实施例中,所述终端设备还包括:通信单元1520,用于向网络设备发送目标模型的模型类型和/或模型参数信息。
在一些实施例中,所述终端设备还包括:通信单元1520,用于向网络设备发送第一能力信息,其中,第一能力信息用于指示终端设备对目标模型进行训练的能力和/或终端设备使用目标模型预测目标信息的能力。
在一些实施例中,第一能力信息包括以下至少之一:
终端设备是否支持基于模型预测目标信息,终端设备支持的训练数据集的大小,终端设备支持的模型的类型,终端设备支持的模型的配置,终端设备支持的用于预测目标信息的数据类型。
在一些实施例中,所述终端设备还包括:通信单元1520,用于接收网络设备的第一配置信息,第一配置信息用于配置终端设备进行目标模型的训练和/或使用目标模型预测目标信息。
在一些实施例中,第一配置信息还用于配置终端设备使用的目标模型的类型。
在一些实施例中,第一配置信息通过无线资源控制RRC信令发送。
可选地,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终端设备1500可对应于本申请方法实施例中的终端设备,并且终端设备1500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7至图19所示方法实施例中终端设备的相应流程,为了简洁,在此不再赘述。
图24是本申请实施例提供的一种通信设备600示意性结构图。图24所示的通信设备600包括处理器610,处理器610可以从存储器中调用并运行计算机程序,以实现本申请实施例中的方法。
可选地,如图24所示,通信设备600还可以包括存储器620。其中,处理器610可以从存储器620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620可以是独立于处理器610的一个单独的器件,也可以集成在处理器610中。
可选地,如图24所示,通信设备600还可以包括收发器630,处理器610可以控制该收发器630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630可以包括发射机和接收机。收发器630还可以进一步包括天线,天线的数量可以为一个或多个。
可选地,该通信设备600具体可为本申请实施例的网络设备,并且该通信设备600可以实现本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
可选地,该通信设备600具体可为本申请实施例的移动终端/终端设备,并且该通信设备600可以实现本申请实施例的各个方法中由移动终端/终端设备实现的相应流程,为了简洁,在此不再赘述。
图25是本申请实施例的芯片的示意性结构图。图25所示的芯片700包括处理器710,处理器710可以从存储器中调用并运行计算机程序,以实现本申请实施例中的方法。
可选地,如图25所示,芯片700还可以包括存储器720。其中,处理器710可以从存储器720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720可以是独立于处理器710的一个单独的器件,也可以集成在处理器710中。
可选地,该芯片700还可以包括输入接口730。其中,处理器710可以控制该输入接口730与其他设备或芯片进行通信,具体地,可以获取其他设备或芯片发送的信息或数据。
可选地,该芯片700还可以包括输出接口740。其中,处理器710可以控制该输出接口740与其他设备或芯片进行通信,具体地,可以向其他设备或芯片输出信息或数据。
可选地,该芯片可应用于本申请实施例中的网络设备,并且该芯片可以实现本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
可选地,该芯片可应用于本申请实施例中的移动终端/终端设备,并且该芯片可以实现本申请实施例的各个方法中由移动终端/终端设备实现的相应流程,为了简洁,在此不再赘述。
应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。
图26是本申请实施例提供的一种通信系统900的示意性框图。如图26所示,该通信系统900包括终端设备910和网络设备920。
其中,该终端设备910可以用于实现上述方法中由终端设备实现的相应的功能,以及该网络设备920可以用于实现上述方法中由网络设备实现的相应的功能为了简洁,在此不再赘述。
应理解,本申请实施例的处理器可能是一种集成电路芯片,具有信号的处理能力。在实现过程中,上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成,或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器,处理器读取存储器中的信息,结合其硬件完成上述方法的步骤。
可以理解,本申请实施例中的存储器可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(Read-Only Memory,ROM)、可编程只读存储器(Programmable ROM,PROM)、可擦除可编程只读存储器(Erasable PROM,EPROM)、电可擦除可编程只读存储器(Electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存 取存储器(Random Access Memory,RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(Static RAM,SRAM)、动态随机存取存储器(Dynamic RAM,DRAM)、同步动态随机存取存储器(Synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM,DR RAM)。应注意,本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
应理解,上述存储器为示例性但不是限制性说明,例如,本申请实施例中的存储器还可以是静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(dynamic RAM,DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synch link DRAM,SLDRAM)以及直接内存总线随机存取存储器(Direct Rambus RAM,DR RAM)等等。也就是说,本申请实施例中的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本申请实施例还提供了一种计算机可读存储介质,用于存储计算机程序。
可选的,该计算机可读存储介质可应用于本申请实施例中的网络设备,并且该计算机程序使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
可选地,该计算机可读存储介质可应用于本申请实施例中的移动终端/终端设备,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移动终端/终端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。
可选的,该计算机程序产品可应用于本申请实施例中的网络设备,并且该计算机程序指令使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
可选地,该计算机程序产品可应用于本申请实施例中的移动终端/终端设备,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移动终端/终端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。
可选的,该计算机程序可应用于本申请实施例中的网络设备,当该计算机程序在计算机上运行时,使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
可选地,该计算机程序可应用于本申请实施例中的移动终端/终端设备,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移动终端/终端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。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请 各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
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 (80)

  1. 一种无线通信的方法,其特征在于,包括:
    网络设备获取第一数据集,所述第一数据集包括M1个空间滤波器的标识信息,和/或,所述M1个空间滤波器的测量结果,所述M1为正整数;
    将所述第一数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,K为正整数。
  2. 根据权利要求1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。
  3. 根据权利要求1或2所述的方法,其特征在于,
    所述第一数据集是终端设备对候选空间滤波器集合中的部分空间滤波器进行测量得到的,其中,所述候选空间滤波器集合包括N个空间滤波器,其中,N为正整数。
  4. 根据权利要求3所述的方法,其特征在于,
    所述候选空间滤波器集合包括N个发射空间滤波器;或者
    所述候选空间滤波器集合包括N个发射空间滤波器和接收空间滤波器的组合。
  5. 根据权利要求1-4中任一项所述的方法,其特征在于,所述目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出所述K个空间滤波器的标识信息,所述第二目标模型用于输出所述K个空间滤波器的测量结果。
  6. 根据权利要求1-5中任一项所述的方法,其特征在于,所述第一数据集是从终端设备获取的。
  7. 根据权利要求1-6中任一项所述的方法,其特征在于,所述目标模型是所述网络设备训练得到的。
  8. 根据权利要求7所述的方法,其特征在于,所述方法还包括:
    所述网络设备获取第二数据集;
    根据所述第二数据集对所述目标模型进行训练,得到所述目标模型的模型参数。
  9. 根据权利要求8所述的方法,其特征在于,所述第二数据集包括以下至少之一:
    M2个空间滤波器的标识信息,其中M2为正整数;
    M2个空间滤波器的测量结果;
    P个最优的空间滤波器的标识信息,其中,P为正整数;
    P个最优的空间滤波器的测量结果。
  10. 根据权利要求9所述的方法,其特征在于,所述M2个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述P个空间滤波器是终端设备对所述候选空间滤波器集合中的所有空间滤波器进行测量得到的。
  11. 根据权利要求1-6中任一项所述的方法,其特征在于,所述目标模型是终端设备训练得到的。
  12. 根据权利要求11所述的方法,其特征在于,所述方法还包括:
    所述网络设备接收所述终端设备发送的所述目标模型的模型类型和/或模型参数信息。
  13. 根据权利要求1-12中任一项所述的方法,其特征在于,所述方法还包括:
    所述网络设备向终端设备发送第一指示信息,所述第一指示信息用于指示所述K个空间滤波器。
  14. 根据权利要求13所述的方法,其特征在于,所述K个空间滤波器为K个发射空间滤波器,所述第一指示信息用于指示K个传输配置指示TCI状态,所述K个TCI状态对应所述K个发射空间滤波器。
  15. 根据权利要求13所述的方法,其特征在于,所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,所述第一指示信息用于指示K个TCI状态,所述K个TCI状态对应所述K个发射空间滤波器和接收空间滤波器的组合中的K个发射空间滤波器;或者
    所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,所述第一指示信息用于指示K个TCI状态,所述K个TCI状态对应K个发射空间滤波器和接收空间滤波器的组合;或者
    所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,所述第一指示信息用于指示所述K个组合中的每个组合中的发射空间滤波器的标识信息以及接收空间滤波器的标识信息;或者
    所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,所述第一指示信息为所述K个组合中的每个组合的标识信息。
  16. 根据权利要求13-15中任一项所述的方法,其特征在于,在所述K个空间滤波器属于所述M1个空间滤波器的情况下,所述网络设备向所述终端设备发送所述第一指示信息。
  17. 根据权利要求1-12中任一项所述的方法,其特征在于,所述K个空间滤波器包括第一发射空间滤波器,或第一发射空间滤波器和第一接收空间滤波器的组合,所述M1个空间滤波器包括M1个发射空间滤波器,或者M1个发射空间滤波器和接收空间滤波器的组合,在所述第一发射空间滤波器不属于所述M1个空间滤波器的情况下,所述方法还包括:
    所述网络设备向终端设备发送第一触发信息,所述第一触发信息用于触发所述终端设备遍历所有接收空间滤波器接收所述第一发射空间滤波器发送的下行参考信号以确定最优的接收空间滤波器。
  18. 根据权利要求1-17中任一项所述的方法,其特征在于,所述方法还包括:
    所述网络设备接收终端设备发送的第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测所述目标信息的能力。
  19. 根据权利要求18所述的方法,其特征在于,所述第一能力信息包括以下至少之一:
    所述终端设备是否支持基于模型预测所述目标信息;
    所述终端设备支持的训练数据集的大小;
    所述终端设备支持的模型的类型;
    所述终端设备支持的模型的配置;
    所述终端设备支持的用于预测所述目标信息的数据类型。
  20. 根据权利要求18或19所述的方法,其特征在于,所述方法还包括:
    所述网络设备根据所述第一能力信息,向所述终端设备发送第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
  21. 根据权利要求20所述的方法,其特征在于,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
  22. 根据权利要求20或21所述的方法,其特征在于,所述第一配置信息通过无线资源控制RRC信令发送。
  23. 一种无线通信的方法,其特征在于,包括:
    终端设备获取第三数据集,所述第三数据集包括M3个空间滤波器的标识信息,和/或,所述M3个空间滤波器的测量结果,所述M3为正整数;
    将所述第三数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,其中,K为正整数。
  24. 根据权利要求23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。
  25. 根据权利要求23或24所述的方法,其特征在于,
    所述第三数据集是终端设备对候选空间滤波器集合中的部分空间滤波器进行测量得到的,其中,所述候选空间滤波器集合包括N个空间滤波器,其中,N为正整数。
  26. 根据权利要求25所述的方法,其特征在于,
    所述候选空间滤波器集合包括N个发射空间滤波器;或者
    所述候选空间滤波器集合包括N个发射空间滤波器和接收空间滤波器的组合。
  27. 根据权利要求23-26中任一项所述的方法,其特征在于,所述目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出所述K个空间滤波器的标识信息,所述第二目标模型用于输出所述K个空间滤波器的测量结果。
  28. 根据权利要求23-27中任一项所述的方法,其特征在于,所述目标模型是网络设备训练得到的。
  29. 根据权利要求28所述的方法,其特征在于,所述方法还包括:
    所述终端设备向所述网络设备发送第四数据集,所述第四数据集用于所述网络设备对所述目标模型进行训练,得到所述目标模型的模型参数。
  30. 根据权利要求29所述的方法,其特征在于,所述第四数据集包括以下至少之一:
    M4个空间滤波器的标识信息,其中M4为正整数;
    M4个空间滤波器的测量结果;
    Q个最优的空间滤波器的标识信息,其中Q为正整数;
    Q个最优的空间滤波器的测量结果。
  31. 根据权利要求30所述的方法,其特征在于,所述M4个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述Q个空间滤波器是终端设备对所述候选空间滤波器集合中的所有空间滤波器进行测量得到的。
  32. 根据权利要求28-31中任一项所述的方法,其特征在于,所述方法还包括:
    所述终端设备接收所述网络设备发送的所述目标模型的模型类型和/或模型参数信息。
  33. 根据权利要求23-27中任一项所述的方法,其特征在于,所述目标模型是所述终端设备训练得到的。
  34. 根据权利要求33所述的方法,其特征在于,所述方法还包括:
    所述终端设备获取第五数据集;
    所述终端设备根据所述第五数据集对所述目标模型进行训练,得到所述目标模型的模型参数。
  35. 根据权利要求34所述的方法,其特征在于,所述第五数据集包括以下至少之一:
    M5个空间滤波器的标识信息,其中M5为正整数;
    M5个空间滤波器的测量结果;
    X个最优的空间滤波器的标识信息,其中X为正整数;
    X个最优的空间滤波器的测量结果。
  36. 根据权利要求35所述的方法,其特征在于,所述M5个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述X个空间滤波器是终端设备对所述候选空间滤波器集合中的所有空间滤波器进行测量得到的。
  37. 根据权利要求35或36所述的方法,其特征在于,所述方法还包括:
    所述终端设备向网络设备发送所述目标模型的模型类型和/或模型参数信息。
  38. 根据权利要求23-37中任一项所述的方法,其特征在于,所述方法还包括:
    所述终端设备向网络设备发送第二指示信息,所述第二指示信息用于指示所述K个空间滤波器。
  39. 根据权利要求38所述的方法,其特征在于,所述K个空间滤波器为K个发射空间滤波器,所述第二指示信息用于指示所述K个发射空间滤波器的标识信息。
  40. 根据权利要求38所述的方法,其特征在于,所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,所述第二指示信息用于指示所述K个组合中的每个组合中的发射空间滤波器的标识信息;或者
    所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,所述第二指示信息用于指示所述K个组合中的每个组合的标识信息;或者
    所述K个空间滤波器为K个发射空间滤波器和接收空间滤波器的组合,所述第二指示信息用于指示所述K个组合中的每个组合中的发射空间滤波器的标识信息以及接收空间滤波器的标识信息。
  41. 根据权利要求38至40中任一项所述的方法,其特征在于,在所述K个空间滤波器属于所述M3个空间滤波器的情况下,所述终端设备向所述网络设备发送所述第二指示信息。
  42. 根据权利要求38-41中任一项所述的方法,其特征在于,所述方法还包括:
    所述终端设备接收所述网络设备发送的第三指示信息,所述第三指示信息用于指示所述网络设备在所述K个空间滤波器中确定的目标空间滤波器。
  43. 根据权利要求42所述的方法,其特征在于,所述目标滤波器包括目标发射空间滤波器,所述第三指示信息用于指示至少一个传输配置指示TCI状态,所述至少一个TCI状态对应所述目标发射空间滤波器。
  44. 根据权利要求42所述的方法,其特征在于,
    所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示至少一个TCI状态,所述至少一个TCI状态对应所述组合中的目标发射空间滤波器;或者
    所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示至少一个TCI状态,所述至少一个TCI状态对应所述组合;或者
    所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示所述目标发射空间滤波器的标识信息以及所述目标接收空间滤波器的标识信息;或者
    所述目标滤波器包括目标发射空间滤波器和目标接收滤波器的组合,所述第三指示信息用于指示所述组合的标识信息。
  45. 根据权利要求23-37中任一项所述的方法,其特征在于,在所述K个空间滤波器中的第二空间滤波器不属于所述M3个空间滤波器的情况下,所述方法还包括:
    所述终端设备向网络设备发送第四指示信息,所述第四指示信息用于触发所述网络设备使用所述第二空间滤波器发送下行参考信号。
  46. 根据权利要求23-45中任一项所述的方法,其特征在于,所述方法还包括:
    所述终端设备向网络设备发送第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测所述目标信息的能力。
  47. 根据权利要求46所述的方法,其特征在于,所述第一能力信息包括以下至少之一:
    所述终端设备是否支持基于模型预测所述目标信息;
    所述终端设备支持的训练数据集的大小;
    所述终端设备支持的模型的类型;
    所述终端设备支持的模型的配置;
    所述终端设备支持的用于预测所述目标信息的数据类型。
  48. 根据权利要求46或47所述的方法,其特征在于,所述方法还包括:
    所述终端设备接收网络设备的第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
  49. 根据权利要求48所述的方法,其特征在于,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
  50. 根据权利要求48或49所述的方法,其特征在于,所述第一配置信息通过无线资源控制RRC信令发送。
  51. 一种无线通信的方法,其特征在于,包括:
    网络设备获取第六数据集,所述第六数据集包括终端设备对多个空间滤波器的测量信息;
    根据所述第六数据集对目标模型进行训练,得到所述目标模型的模型参数,其中,所述目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
  52. 根据权利要求51所述的方法,其特征在于,所述第六数据集包括以下至少之一:
    M6个空间滤波器的标识信息,其中M6为正整数;
    M6个空间滤波器的测量结果;
    Y个最优的空间滤波器的标识信息,其中,Y为正整数;
    Y个最优的空间滤波器的测量结果。
  53. 根据权利要求52所述的方法,其特征在于,所述M6个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述Y个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
  54. 根据权利要求51-53中任一项所述的方法,其特征在于,所述目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出K个空间滤波器的标识信息,所述第二目标模型用于输出所述K个空间滤波器的测量结果,其中K为正整数。
  55. 根据权利要求51-54中任一项所述的方法,其特征在于,所述方法还包括:
    所述网络设备向所述终端设备发送所述目标模型的模型类型和/或模型参数信息。
  56. 根据权利要求51-55中任一项所述的方法,其特征在于,所述方法还包括:
    所述网络设备接收终端设备发送的第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测所述目标信息的能力。
  57. 根据权利要求56所述的方法,其特征在于,所述第一能力信息包括以下至少之一:
    所述终端设备是否支持基于模型预测所述目标信息;
    所述终端设备支持的训练数据集的大小;
    所述终端设备支持的模型的类型;
    所述终端设备支持的模型的配置;
    所述终端设备支持的用于预测所述目标信息的数据类型。
  58. 根据权利要求56或57所述的方法,其特征在于,所述方法还包括:
    所述网络设备向终端设备发送第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
  59. 根据权利要求58所述的方法,其特征在于,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
  60. 根据权利要求58或59所述的方法,其特征在于,所述第一配置信息通过无线资源控制RRC信令发送。
  61. 一种无线通信的方法,其特征在于,包括:
    终端设备获取第七数据集,所述第七数据集包括所述终端设备对多个空间滤波器的测量信息;
    根据所述第七数据集对目标模型进行训练,得到所述目标模型的模型参数,其中,所述目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
  62. 根据权利要求61所述的方法,其特征在于,所述第七数据集包括以下至少之一:
    M7个空间滤波器的标识信息,其中M7为正整数;
    M7个空间滤波器的测量结果;
    Z个最优的空间滤波器的标识信息,其中,Z为正整数;
    Z个最优的空间滤波器的测量结果。
  63. 根据权利要求62所述的方法,其特征在于,所述M7个空间滤波器包括候选空间滤波器集合中的部分空间滤波器,所述Z个空间滤波器是终端设备对候选空间滤波器集合中的所有空间滤波器进行测量得到的。
  64. 根据权利要求61-63中任一项所述的方法,其特征在于,所述目标模型包括第一目标模型和第二目标模型,所述第一目标模型用于输出K个空间滤波器的标识信息,所述第二目标模型用于输出所述K个空间滤波器的测量结果,其中K为正整数。
  65. 根据权利要求61-64中任一项所述的方法,其特征在于,所述方法还包括:
    所述终端设备向网络设备发送所述目标模型的模型类型和/或模型参数信息。
  66. 根据权利要求61-65中任一项所述的方法,其特征在于,所述方法还包括:
    所述终端设备向网络设备发送第一能力信息,其中,所述第一能力信息用于指示所述终端设备对所述目标模型进行训练的能力和/或所述终端设备使用所述目标模型预测所述目标信息的能力。
  67. 根据权利要求66所述的方法,其特征在于,所述第一能力信息包括以下至少之一:
    所述终端设备是否支持基于模型预测所述目标信息;
    所述终端设备支持的训练数据集的大小;
    所述终端设备支持的模型的类型;
    所述终端设备支持的模型的配置;
    所述终端设备支持的用于预测所述目标信息的数据类型。
  68. 根据权利要求66或67所述的方法,其特征在于,所述方法还包括:
    所述终端设备接收网络设备的第一配置信息,所述第一配置信息用于配置所述终端设备进行所述目标模型的训练和/或使用所述目标模型预测所述目标信息。
  69. 根据权利要求68所述的方法,其特征在于,所述第一配置信息还用于配置所述终端设备使用的所述目标模型的类型。
  70. 根据权利要求68或69所述的方法,其特征在于,所述第一配置信息通过无线资源控制RRC信令发送。
  71. 一种网络设备,其特征在于,包括:
    通信单元,用于获取第一数据集,所述第一数据集包括M1个空间滤波器的标识信息,和/或,所述M1个空间滤波器的测量结果,所述M1为正整数;
    处理单元,用于将所述第一数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,K为正整数。
  72. 一种终端设备,其特征在于,包括:
    处理单元,用于获取第三数据集,所述第三数据集包括M3个空间滤波器的标识信息,和/或,所述M3个空间滤波器的测量结果,所述M3为正整数;以及
    将所述第三数据集输入至目标模型,输出目标信息,所述目标信息包括K个空间滤波器的标识信息,和/或,所述K个空间滤波器的测量结果,其中,K为正整数。
  73. 一种网络设备,其特征在于,包括:
    通信单元,用于获取第六数据集,所述第六数据集包括终端设备对多个空间滤波器的测量信息;
    处理单元,用于根据所述第六数据集对目标模型进行训练,得到所述目标模型的模型参数,其中,所述目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
  74. 一种终端设备,其特征在于,包括:
    处理单元,用于获取第七数据集,所述第七数据集包括所述终端设备对多个空间滤波器的测量信息;以及
    根据所述第七数据集对目标模型进行训练,得到所述目标模型的模型参数,其中,所述目标模型用于根据多个空间滤波器的测量结果在所述多个空间滤波器中确定目标空间滤波器。
  75. 一种网络设备,其特征在于,包括:处理器和存储器,该存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,执行如权利要求1至22中任一项所述的方法,或如权利要求51至60中任一项所述的方法。
  76. 一种终端设备,其特征在于,包括:处理器和存储器,该存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,执行如权利要求23至50中任一项所述的方法,或如权利要求61至70中任一项所述的方法。
  77. 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22中任一项所述的方法,或,如权利要求23至50中任一项所述的方法,或如权利要求51至60中任一项所述的方法,或如权利要求61至70中任一项所述的方法。
  78. 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,所述计算机程序使得计算机执行如权利要求1至22中任一项所述的方法,或,如权利要求23至50中任一项所述的方法,或如权利要求51至60中任一项所述的方法,或如权利要求61至70中任一项所述的方法。
  79. 一种计算机程序产品,其特征在于,包括计算机程序指令,该计算机程序指令使得计算机执行如权利要求1至22中任一项所述的方法,或,如权利要求23至50中任一项所述的方法,或如权利要求51至60中任一项所述的方法,或如权利要求61至70中任一项所述的方法。
  80. 一种计算机程序,其特征在于,所述计算机程序使得计算机执行如权利要求1至22中任一项所述的方法,或,如权利要求23至50中任一项所述的方法,或如权利要求51至60中任一项所述的方法,或如权利要求61至70中任一项所述的方法。
PCT/CN2022/089649 2022-04-27 2022-04-27 无线通信的方法、网络设备和终端设备 WO2023206163A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/089649 WO2023206163A1 (zh) 2022-04-27 2022-04-27 无线通信的方法、网络设备和终端设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/089649 WO2023206163A1 (zh) 2022-04-27 2022-04-27 无线通信的方法、网络设备和终端设备

Publications (1)

Publication Number Publication Date
WO2023206163A1 true WO2023206163A1 (zh) 2023-11-02

Family

ID=88516687

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/089649 WO2023206163A1 (zh) 2022-04-27 2022-04-27 无线通信的方法、网络设备和终端设备

Country Status (1)

Country Link
WO (1) WO2023206163A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019176428A (ja) * 2018-03-29 2019-10-10 株式会社Nttドコモ 基地局、及びユーザ装置
CN111543012A (zh) * 2017-12-15 2020-08-14 高通股份有限公司 用于动态波束对确定的方法和设备
WO2021002859A1 (en) * 2019-07-03 2021-01-07 Nokia Technologies Oy Measurement reporting in wireless network
WO2021112592A1 (ko) * 2019-12-03 2021-06-10 엘지전자 주식회사 무선 통신 시스템에서 인공 지능 기반의 빔 관리 방법 및 이에 대한 장치
CN113905393A (zh) * 2020-06-22 2022-01-07 华为技术有限公司 一种确定波束对的方法及装置
CN113994598A (zh) * 2019-04-17 2022-01-28 诺基亚技术有限公司 无线网络的波束预测

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111543012A (zh) * 2017-12-15 2020-08-14 高通股份有限公司 用于动态波束对确定的方法和设备
JP2019176428A (ja) * 2018-03-29 2019-10-10 株式会社Nttドコモ 基地局、及びユーザ装置
CN113994598A (zh) * 2019-04-17 2022-01-28 诺基亚技术有限公司 无线网络的波束预测
WO2021002859A1 (en) * 2019-07-03 2021-01-07 Nokia Technologies Oy Measurement reporting in wireless network
WO2021112592A1 (ko) * 2019-12-03 2021-06-10 엘지전자 주식회사 무선 통신 시스템에서 인공 지능 기반의 빔 관리 방법 및 이에 대한 장치
CN113905393A (zh) * 2020-06-22 2022-01-07 华为技术有限公司 一种确定波束对的方法及装置

Similar Documents

Publication Publication Date Title
WO2021217519A1 (zh) 用于调整神经网络的方法和装置
JP2021503845A (ja) 通信方法および通信デバイス
US20230262696A1 (en) Method for determining uplink transmission parameter, and terminal device
CN109672510A (zh) 通信方法和通信装置
US20230308141A1 (en) Communication Method, Device, and System
WO2020073257A1 (zh) 无线通信方法和终端设备
US20220167181A1 (en) Reference signal transmission method and device
WO2023133761A1 (zh) Csi报告的发送方法、接收方法、装置、设备及介质
WO2022021131A1 (zh) 重选初始带宽部分bwp的方法、终端设备和网络设备
WO2023206163A1 (zh) 无线通信的方法、网络设备和终端设备
US20230007682A1 (en) Data transmission method, terminal device and network device
WO2023123062A1 (zh) 虚拟信道样本的质量评估方法和设备
US20220394503A1 (en) Wireless communication method and device
WO2022012256A1 (zh) 通信的方法及通信装置
WO2024065696A1 (zh) 无线通信的方法、终端设备和网络设备
WO2024092498A1 (zh) 无线通信的方法及设备
WO2024000521A1 (zh) 通信方法和设备
WO2023197260A1 (zh) 无线通信的方法、终端设备和网络设备
WO2024065697A1 (zh) 模型监测的方法、终端设备和网络设备
WO2023201594A1 (zh) 一种指示方法、终端设备和网络设备
WO2023035144A1 (zh) 无线通信的方法、终端设备和网络设备
WO2023102814A1 (zh) 无线通信的方法、终端设备和网络设备
WO2023184391A1 (zh) 无线通信的方法、终端设备和网络设备
WO2024011588A1 (zh) 无线通信的方法、终端设备和网络设备
WO2024055197A1 (zh) 模型监测的方法及设备

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: 22939016

Country of ref document: EP

Kind code of ref document: A1