WO2023231934A1 - 一种通信方法及装置 - Google Patents

一种通信方法及装置 Download PDF

Info

Publication number
WO2023231934A1
WO2023231934A1 PCT/CN2023/096667 CN2023096667W WO2023231934A1 WO 2023231934 A1 WO2023231934 A1 WO 2023231934A1 CN 2023096667 W CN2023096667 W CN 2023096667W WO 2023231934 A1 WO2023231934 A1 WO 2023231934A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
model
reference signal
antenna
processor
Prior art date
Application number
PCT/CN2023/096667
Other languages
English (en)
French (fr)
Inventor
陈家璇
杭海存
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023231934A1 publication Critical patent/WO2023231934A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413—MIMO systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413—MIMO systems
    • H04B7/0456—Selection of precoding matrices or codebooks, e.g. using matrices antenna weighting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station

Definitions

  • the embodiments of the present application relate to the field of communication technology, and in particular, to a communication method and device.
  • the services supported by the network are becoming more and more diverse, and therefore the requirements that need to be met are becoming more and more diverse.
  • the network needs to be able to support ultra-high speeds, ultra-low latency, and/or ultra-large connections.
  • This feature makes network planning, network configuration, and/or resource scheduling increasingly complex.
  • the base station needs to obtain the channel status of the downlink channel Information (channel state information, CSI), so as to recover downlink channel information based on CSI to implement the above-mentioned new technologies. How to enable the base station to recover more accurate downlink channel information is a technical issue worthy of study.
  • CSI channel state information
  • This application provides a communication method and device to improve the recovery accuracy of downlink channel information on the network side.
  • the first aspect provides a communication method.
  • the execution subject of the method is an access network device, or a component (processor, chip or others) configured in the access network device.
  • the method includes: receiving a communication from a terminal device. First compressed information, the first compressed information is determined by the terminal device according to the first reference signal sent by the access network device using the first antenna activation mode, the first compressed information is used to characterize the first antenna The first downlink channel information corresponding to the activated antenna port in the activation mode; determine the second downlink channel information corresponding to the target antenna port according to the first compression information and the first information, the first information is determined according to the second reference.
  • the target antenna port includes an activated antenna port and an inactive antenna port in the first antenna activation mode, and the second reference signal is The reference signal received by the access network device from the terminal device, the second reference signal may be called an uplink reference signal, etc., without limitation.
  • the access network equipment uses the third model to use the base station
  • the processed information of the received second reference signal is used as input, and the parameter adjustment value of the first model is output, and the parameter adjustment value is used to adjust the parameters of the first model.
  • the parameters of the first model include some common features of uplink and downlink channels, such as correlation information between channels at different antenna ports. Therefore, the access network device can use the first model to more accurately restore the downlink channel information of all antenna ports based only on the first compressed information containing channel information of part of the antenna ports.
  • the operation of the first model should be different, and the first model is used to recover the downlink channel information. , or determine the precoding matrix, etc.
  • the first model may be called a CSI recovery model, a decoding model, a precoding model, or an AI model. Type, etc., are not limited. For example, in different antenna port activation modes, the activated antenna ports are different, and the degree of channel similarity between the activated antenna ports is also different. Therefore, the process of recovering all channel information from partial channel information in different activation modes is different.
  • the third model may include an additional input, namely the antenna activation pattern when the first reference signal is transmitted.
  • the reference signal received by the UE side only contains part of the channel information.
  • the UE can perform CSI feedback with less overhead, or improve the accuracy of CSI feedback with the same overhead.
  • the parameters of the first model can be adjusted to make up for the lack of channel information in the CSI feedback and improve the accuracy of CSI recovery.
  • the antenna activation mode when transmitting the first reference signal is specifically the antenna activation mode adopted by the base station when transmitting the first reference signal. It may also be called the antenna activation mode for transmitting the first reference signal and the antenna for the first reference signal. Activation mode, etc. are not distinguished.
  • determining the second downlink channel information corresponding to the target antenna port based on the first compression information and the first information includes: determining a parameter adjustment value of the first model based on the first information; According to the parameter adjustment value of the first model, the parameters of the first model are adjusted; according to the first compression information and the first model, second downlink channel information corresponding to the target antenna port is determined.
  • the method further includes: determining an adjustment value of the first reference signal according to the first information; and adjusting the first adjustment value sent by the access network device according to the adjustment value of the first reference signal. a reference signal.
  • the access network device can use the first information as input to the fourth model, and the output of the fourth model can be the adjustment value of the first reference signal, or can be determined based on the output of the fourth model. Adjustment value of the first reference signal. According to the adjustment value, the first reference signal sent to the UE is adjusted, so that the UE can better represent downlink channel information by receiving limited reference signals, thereby improving the performance of CSI compression and CSI recovery.
  • the method further includes: sending indication information of the first antenna activation mode to the terminal device.
  • a communication method is provided.
  • the execution subject of the method is a terminal device, or a component (processor, chip or other) configured in the terminal device.
  • the method includes: receiving a first reference from an access network device. signal; determine first compression information according to the first reference signal and the first antenna activation mode, where the first compression information is used to characterize the first downlink channel information corresponding to the antenna port activated in the first antenna activation mode; Send the first compressed information to the access network device.
  • determining the first compression information according to the first reference signal includes: determining a parameter adjustment value of the second model according to the first antenna activation mode; adjusting a parameter adjustment value according to the parameter adjustment value of the second model. Parameters of the second model; determining the first compression information based on the second model and the first reference signal.
  • the second model is used to compress the downlink channel information estimated and determined by the UE.
  • the second model may also be called a CSI compression model or the like.
  • the terminal can use the first antenna activation mode as input to the fifth model.
  • the output of the fifth model is the parameter adjustment value of the second model.
  • the fifth model can also be called a CSI compression module.
  • Adjust the network Adjust the parameters of the second model according to the parameter adjustment values of the second model; for example, the parameter adjustment values of the second model can be summed with the corresponding positions of the original parameters of the second model, or the parameters of the second model can be summed.
  • the parameter adjustment value, multiplied by the corresponding position of the original parameter of the second model, etc., is not limited.
  • the UE determines the first compression information according to the second model and the first reference signal.
  • the UE may use the first reference signal or the processed information of the first reference signal As input, it is input to the second model, and the output of the second model is the first compressed information.
  • AI models ie, second models
  • the adjustment parameters of the second model are determined according to different antenna port activation modes; and the parameters of the second model are adjusted according to the adjustment parameters, so that the second model is based on the channel similarity of the activated antenna ports. Compress the received channel information of the first reference signal, thereby improving CSI compression performance.
  • the method further includes: receiving indication information of the first antenna activation mode from the access network device.
  • a device including a unit for implementing the method of the first aspect.
  • a fourth aspect provides a device, including a processor and a memory, the processor is coupled to the memory, and the processor is used to implement the method of the first aspect.
  • a device including a unit for implementing the method of the second aspect.
  • a device including a processor and a memory, the processor and the memory are coupled, and the processor is used to implement the method of the second aspect.
  • a seventh aspect provides a communication system, including the device described in the third or fourth aspect, and the device described in the fifth or sixth aspect.
  • a computer-readable storage medium including instructions that, when run on a computer, cause the computer to perform the method in the first aspect or the second aspect.
  • a ninth aspect provides a chip system, which includes a processor and may also include a memory for implementing the method in the first aspect or the second aspect.
  • the chip system can be composed of chips or include chips and other discrete devices.
  • a computer program product including instructions that, when run on a computer, cause the computer to execute the method in the first aspect or the second aspect.
  • FIG. 1 is a schematic diagram of the communication system provided by this application.
  • FIGS. 2 and 3 are schematic diagrams of the communication architecture provided by this application.
  • Figure 4 is a schematic diagram of the architecture of the AI model provided by this application.
  • FIGS 5 and 6 are schematic diagrams of neurons provided by this application.
  • Figure 7 is a schematic diagram of AI encoding and decoding provided by this application.
  • Figure 8 is a flow chart of the communication method provided by this application.
  • FIG. 9 is a schematic diagram of the antenna activation mode provided by this application.
  • Figures 10, 11 and 12 are schematic diagrams of introducing uplink channel estimation and antenna activation modes provided by this application;
  • FIGS 13 and 14 are schematic diagrams of the communication device provided by this application.
  • FIG 1 is a schematic architectural diagram of a communication system 1000 to which the present application can be applied.
  • the communication system includes a wireless access network 100 and a core network 200.
  • the communication system 1000 may also include the Internet 300.
  • the wireless access network 100 may include at least one access network device (110a and 110b in Figure 1), and may also include at least A terminal device (120a-120j in Figure 1).
  • the terminal equipment is connected to the access network equipment through wireless means, and the access network equipment is connected to the core network through wireless or wired means.
  • the core network equipment and the access network equipment can be independent and different physical devices, or the functions of the core network equipment and the logical functions of the access network equipment can be integrated on the same physical device, or they can be integrated on one physical device.
  • Terminal equipment and terminal equipment and access network equipment and access network equipment can be connected to each other in a wired or wireless manner.
  • Figure 1 is only a schematic diagram.
  • the communication system may also include other network equipment, such as wireless relay equipment and wireless backhaul equipment, which are not shown in Figure 1 .
  • the access network equipment can be a base station, an evolved base station (evolved NodeB, eNodeB), a transmission reception point (TRP), or a next-generation base station in the fifth generation (5th generation, 5G) mobile communication system.
  • (next generation NodeB, gNB) access network equipment in the open radio access network (open radio access network, O-RAN), next-generation base stations in the sixth generation (6th generation, 6G) mobile communication system, future mobile
  • CU centralized unit
  • DU distributed distributed unit
  • CU control plane centralized unit control plane
  • CU-CP centralized
  • the access network equipment may be a macro base station (110a in Figure 1), a micro base station or an indoor station (110b in Figure 1), or a relay node or a donor node. This application does not limit the specific technologies and specific equipment forms used in access network equipment.
  • the device used to realize the function of the access network device may be the access network device; it may also be a device that can support the access network device to realize the function, such as a chip system, a hardware circuit, a software module, or a hardware device.
  • the circuit plus software module can be installed in the access network equipment or can be used in conjunction with the access network equipment.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the protocol layer structure may include a control plane protocol layer structure and a user plane protocol layer structure.
  • the control plane protocol layer structure may include a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a media layer.
  • Functions of protocol layers such as media access control (MAC) layer and physical layer.
  • the user plane protocol layer structure can include the functions of the PDCP layer, RLC layer, MAC layer and physical layer.
  • the PDCP layer can also include service data adaptation protocol (service data adaptation protocol). protocol, SDAP) layer.
  • the protocol layer structure between the access network device and the terminal device may also include an artificial intelligence (artificial intelligence, AI) layer for transmitting data related to the AI function.
  • AI artificial intelligence
  • Access devices may include CUs and DUs. Multiple DUs can be centrally controlled by one CU.
  • the interface between the CU and the DU may be called the F1 interface.
  • the control panel (CP) interface can be F1-C
  • the user panel (UP) interface can be F1-U. This application does not limit the specific names of each interface.
  • CU and DU can be divided according to the protocol layer of the wireless network: for example, the functions of the PDCP layer and above are set in the CU, and the functions of the protocol layers below the PDCP layer (such as the RLC layer and MAC layer, etc.) are set in the DU; for example, PDCP
  • the functions of the protocol layers above are set in the CU, and the functions of the PDCP layer and the lower protocol layers are set in the DU without restrictions.
  • the above-mentioned division of the CU and DU processing functions according to the protocol layer is only an example, and can also be divided in other ways.
  • the CU or DU can be divided into functions with more protocol layers, or the CU or DU can be divided into partial processing functions with protocol layers.
  • part of the functions of the RLC layer and the functions of the protocol layer above the RLC layer are set in the CU, and the remaining functions of the RLC layer and the functions of the protocol layer below the RLC layer are set in the DU.
  • the functions of CU or DU can also be divided according to business types or other system requirements, for example, according to delay, and the functions whose processing time needs to meet the delay requirements are set in DU, but do not need to meet the delay.
  • the required functionality is set in CU.
  • the CU may also have one or more functions of the core network.
  • the CU can be set on the network side to facilitate centralized management.
  • the radio unit (RU) of the DU is remotely located.
  • the RU can have radio frequency functionality.
  • DU and RU can be divided at the physical layer (PHY).
  • PHY physical layer
  • DU can implement high-level functions in the PHY layer
  • RU can implement low-level functions in the PHY layer.
  • the functions of the PHY layer can include at least one of the following: adding cyclic redundancy check (cyclic redundancy check, CRC) code, channel coding, rate matching, scrambling, modulation, layer mapping, precoding, Resource mapping, physical antenna mapping, or radio frequency transmission functions.
  • CRC cyclic redundancy check
  • the functions of the PHY layer may include at least one of the following: CRC check, channel decoding, derate matching, descrambling, demodulation, delayer mapping, channel detection, resource demapping, physical antenna demapping, or RF reception function.
  • the high-level functions in the PHY layer may include part of the functions of the PHY layer, for example, this part of the function is closer to the MAC layer, and the lower-layer functions of the PHY layer may include another part of the function of the PHY layer, for example, this part of the function is closer to the radio frequency function.
  • high-level functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, and layer mapping
  • low-level functions in the PHY layer may include precoding, resource mapping, physical antenna mapping, and radio frequency transmission.
  • the high-level functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, layer mapping, and precoding
  • the low-layer functions in the PHY layer may include resource mapping, physical antenna mapping, and radio frequency Send function.
  • the high-level functions in the PHY layer may include CRC check, channel decoding, rate matching, decoding, demodulation, and de-layer mapping
  • the low-level functions in the PHY layer may include channel detection, resource demapping, physical antenna demapping, and radio frequency reception functions
  • the high-level functions in the PHY layer may include CRC check, channel decoding, de-rate matching, decoding, demodulation, de-layer mapping, and channel detection
  • the low-layer functions in the PHY layer may include resource de-mapping , physical antenna demapping, and RF reception capabilities.
  • the functions of the CU may be implemented by one entity, or may be implemented by different entities.
  • the functions of the CU can be further divided, that is, the control plane and the user plane are separated and implemented through different entities, namely the control plane CU entity (i.e., CU-CP entity) and the user plane CU entity (i.e., CU-UP entity).
  • the CU-CP entity and the CU-UP entity can be coupled with the DU to jointly complete the functions of the access network equipment.
  • any one of the above DU, CU, CU-CP, CU-UP and RU can be a software module, a hardware structure, or a software module + hardware structure, without limitation.
  • the existence forms of different entities can be different and are not limited.
  • DU, CU, CU-CP, and CU-UP are software modules
  • RU is a hardware structure.
  • the access network equipment includes CU-CP, CU-UP, DU and RU.
  • the execution subject of this application includes DU, or includes DU and RU, or includes CU-CP, DU and RU, or includes CU-UP, DU and RU, without limitation.
  • the methods executed by each module are also within the protection scope of this application.
  • the terminal equipment may also be called a terminal, user equipment (UE), mobile station, mobile terminal equipment, etc.
  • Terminal devices can be widely used in communications in various scenarios, including but not limited to at least one of the following scenarios: device-to-device (D2D), vehicle to everything (V2X), machine-type communication (machine-type communication, MTC), Internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wear, smart transportation, or Smart cities, etc.
  • Terminal devices can be mobile phones, tablets, computers with wireless transceiver functions, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, or smart home devices, etc. This application does not limit the specific technology and specific equipment form used in the terminal equipment.
  • the device used to realize the function of the terminal device may be a terminal device; it may also be a device capable of supporting the terminal device to realize the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module.
  • the device may be installed in the terminal device or may be used in conjunction with the terminal device.
  • the following describes the technical solution provided by this application, taking the device for realizing the functions of the terminal device as a terminal device and the terminal device as a UE as an example.
  • Base stations and UEs can be fixed-location or mobile. Base stations and/or UEs can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed on aircraft, balloons and satellites in the air. This application does not limit the application scenarios of base stations and UEs.
  • the base station and the UE may be deployed in the same scenario or in different scenarios. For example, the base station and the UE may be deployed on land at the same time; or, the base station may be deployed on land and the UE may be deployed on water, etc. No examples will be given one by one.
  • the helicopter or drone 120i in Figure 1 may be configured as a mobile base station.
  • the UE 120i is a base station;
  • base station 110a, 120i is a UE, that is, communication between 110a and 120i is through a wireless air interface protocol.
  • 110a and 120i may also communicate through an interface protocol between base stations.
  • relative to 110a, 120i is also a base station. Therefore, both base stations and UEs can be collectively called communication devices, 110a and 110b in Figure 1 can be called communication devices with base station functions, and 120a-120j in Figure 1 can be called communication devices with UE functions.
  • independent network elements can be introduced into the aforementioned communication system shown in Figure 1 to implement AI-related operations.
  • the AI network elements can interact with the interfaces in the communication system. Access network devices are directly connected to each other, or indirect connections can be achieved through third-party network elements and access network devices.
  • the third-party network element can be an authentication management function (AMF) or a user plane function (UPF) and other core network elements; or, AI can be configured in other network elements in the communication system.
  • the other network elements can be access network equipment (such as gNB), core network equipment, or network management (operation, administration and maintenance, OAM), etc.
  • the network elements that perform AI-related operations are network elements with built-in AI functions.
  • the above-mentioned OAM is used to operate, manage and maintain access network equipment and/or core network equipment.
  • Figure 2 shows the architecture of a communication system provided by this application.
  • the access network equipment includes a near-real-time access network intelligent control (RAN intelligent controller, RIC) module for model training and inference.
  • RAN intelligent controller RIC
  • near real-time RIC can be used to train an AI model and use the AI model to perform inference.
  • the near-real-time RIC may obtain network-side and/or terminal-side information from at least one of CU, DU, or RU, and the information may be used as training data or inference data.
  • the near real-time RIC can submit the inference result to at least one of the CU, DU, RU or terminal device.
  • CU and DU can interact with inference results.
  • the inference results can be exchanged between DU and RU.
  • the near real-time RIC submits the inference results to the DU, and the DU forwards the inference results to the RU.
  • the access network equipment includes a non-real-time RIC (optional, the non-real-time RIC can be located in the OAM or the core network equipment) for model training and reasoning.
  • the non-real-time RIC can obtain network-side and/or terminal-side information from at least one of CU, DU, or RU. This information can be used as training data or inference data, and the inference results can be submitted to CU, DU, or RU. or at least one of the terminal devices.
  • CU and DU can interact with inference results.
  • the inference results can be exchanged between DU and RU.
  • the non-real-time RIC submits the inference results to the DU, and the DU forwards the inference results to the RU.
  • the access network equipment includes near-real-time RIC, and the access network equipment includes non-real-time RIC (optional, the non-real-time RIC can be located in the OAM or core network). in the device). Similar to the second design above, non-real-time RIC can be used for model training and inference. And/or, as with the first design above, near-real-time RIC can be used for model training and inference. And/or, non-real-time RIC performs model training.
  • Near-real-time RIC can obtain AI model information from non-real-time RIC, and obtain network-side and/or terminal-side information from at least one of CU, DU, or RU, and use this information and the AI model information to obtain inference results.
  • the near real-time RIC can submit the inference result to at least one of the CU, DU, RU or terminal device.
  • CU and DU can interact with inference results.
  • the inference results can be exchanged between DU and RU.
  • the near real-time RIC submits the inference results to the DU, and the DU forwards the inference results to the RU.
  • near real-time RIC is used to train model A, which is used for inference.
  • non-real-time RIC is used to train model B and model B is used for inference.
  • non-real-time RIC is used to train model C, and the information of model C is sent to near-real-time RIC, which uses model C for inference.
  • Figure 3 shows the architecture of another communication system provided by this application. Compared with Figure 2, Figure 3 separates CU into CU-CP, CU-UP, etc.
  • the AI model is the specific implementation of the AI function.
  • the AI model represents the mapping relationship between the input and output of the model.
  • AI models can be neural networks, linear regression models, decision tree models, support vector machines (SVM), Bayesian networks, Q learning models or other machine learning models.
  • AI functions may include at least one of the following: data collection (collecting training data and/or inference data), data preprocessing, model training (or model learning), model information release (configuring model information), Model verification, model inference, or inference result release. Among them, inference can also be called prediction.
  • the AI model may be referred to as a model for short.
  • Figure 4 shows a schematic diagram of an application architecture of the AI model.
  • Data source is used to store training data and inference data.
  • the model training node (model training host) obtains the AI model by analyzing or training the training data (training data) provided by the data source, and deploys the AI model in the model inference node (model inference host).
  • the model training node can also update the AI model deployed on the model inference node.
  • the model inference node can also feed back relevant information about the deployed model to the model training node, so that the model training node can optimize or update the deployed AI model.
  • the model inference node uses the AI model to perform inference based on the inference data provided by the data source to obtain inference results.
  • This method can also be described as: the model inference node inputs the inference data to the AI model, and obtains the output through the AI model, which is the inference result.
  • the inference result may indicate: configuration parameters used (executed) by the execution object, and/or operations performed by the execution object.
  • the inference results can be planned uniformly by the execution (actor) entity and sent to one or more execution objects (for example, network entities) for execution.
  • the execution entity or execution object can feed back the collected parameters or measurements to the data source.
  • This process can be called performance feedback, and the fed back parameters can be used as training data or inference data.
  • feedback information related to model performance can also be determined based on the inference results output by the model inference node. And the feedback information is fed back to the model inference node.
  • the model inference node can feedback the performance information of the model to the model training node based on the feedback information, so that the model training node can optimize or update the deployed AI model.
  • the process can be called model feedback.
  • the AI model can be a neural network or other machine learning model. Take neural network as an example. Neural network is a specific implementation form of machine learning technology. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, which enables neural networks to have the ability to learn arbitrary mappings. Therefore, neural networks can accurately abstractly model complex high-dimensional problems.
  • Each neuron performs a weighted sum operation on its input values, and generates an output through an activation function.
  • the form of the activation function can be diverse.
  • the output of the neuron is: x i , w i , and b can be decimals, integers (including 0, positive integers or negative integers, etc.), or complex numbers and other possible values.
  • the activation functions of different neurons in a neural network can be the same or different.
  • Neural networks generally include a multi-layer structure, and each layer may include one or more neurons. Increasing the depth and/or width of a neural network can improve the expressive ability of the neural network, providing more powerful information extraction and abstract modeling capabilities for complex systems. Among them, the depth of the neural network can refer to the number of layers included in the neural network, and the number of neurons included in each layer can be called the width of the layer. As shown in Figure 6, it is a schematic diagram of the layer relationship of the neural network.
  • the neural network includes an input layer and an output layer. The input layer of the neural network processes the received inputs through neurons and then passes the results to the output layer, which obtains the output results of the neural network.
  • the neural network includes an input layer, a hidden layer, and an output layer.
  • a neural network may include one or more hidden layers connected in sequence, without limitation.
  • a loss function can be defined. The loss function describes the gap or difference between the output value of the neural network and the ideal target value. This application does not limit the specific form of the loss function.
  • the training process of the neural network is to adjust the neural network parameters, such as the number of layers and width of the neural network, the weights of the neurons, and/or the parameters in the activation function of the neurons, etc., so that the value of the loss function is less than the threshold value. Or the process of meeting target needs.
  • MIMO massive multiple-input multiple-output
  • the base station can use the same time-frequency resources to send data to multiple UEs at the same time, that is, multi-user MIMO (MU-MIMO), or send multiple data streams to the same UE at the same time, that is, single-user MIMO ( Single-user MIMO, SU-MIMO), the data of multiple UEs or the multiple data streams of the same UE are space-division multiplexed, so it has become a key direction in the evolution of communication systems.
  • MU-MIMO multi-user MIMO
  • SU-MIMO single-user MIMO
  • the data of multiple UEs or the multiple data streams of the same UE are space-division multiplexed, so it has become a key direction in the evolution of communication systems.
  • the base station needs to use a precoding matrix to precode the downlink data sent by the UE.
  • Base stations use precoding technology to achieve spatial multiplexing between users or between different data streams of the same user, so that data between UEs or data between different data streams of the same UE are spatially isolated. This reduces the interference between different UEs or between different data streams of the same UE, and improves the receiving signal-to-interference-to-noise ratio of the UE.
  • the base station needs to obtain the channel state information (CSI) of the downlink channel. Determine the precoding matrix based on CSI.
  • CSI channel state information
  • the uplink and downlink channels do not have mutuality, and the base station needs to obtain downlink CSI through UE feedback.
  • the base station sends a downlink reference signal to the UE, and the UE receives the downlink reference signal. Since the UE knows the transmission sequence of the downlink reference signal, the UE can estimate or measure the downlink channel experienced by the downlink reference signal based on the received downlink reference signal. Then, the UE generates CSI based on the measured downlink channel, and will CSI is fed back to the base station.
  • FDD frequency division duplex
  • PMI precoding matrix indicator
  • 0 to 1 bits can be used to quantize the channel matrix or precoding matrix.
  • the design of PMI also called codebook design, is a basic issue in mobile communication systems.
  • the traditional codebook design method is to predefine or agree on a series of precoding matrices and corresponding numbers in the protocol. These precoding matrices are called codewords.
  • the channel matrix or precoding matrix can be approximated using a predefined codeword or a linear combination of multiple predefined codewords. Therefore, the UE can feedback the corresponding codeword number and weighting coefficient to the base station through PMI, which is used by the base station to restore the channel matrix or precoding matrix.
  • the number of supported antenna ports increases, and the dimensions of the corresponding channel matrix or precoding matrix also increase.
  • the overhead of the base station transmitting the reference signal will increase.
  • the error in approximately representing large-scale channel matrices and precoding matrices with limited predefined codewords will increase.
  • One way to improve the accuracy of channel recovery is to increase the number of codewords in the codebook, but this will lead to an increase in the overhead of CSI feedback (the CSI feedback includes the corresponding number of the codeword and one or more weighting coefficients). This in turn reduces the available resources for data transmission, causing system capacity loss.
  • the existence of correlation between different elements in the channel matrix means that there is a set of bases (which can be represented by matrices U 1 and U 2 ).
  • a sparse equivalent channel can be obtained, that is, H '
  • An AI-based CSI feedback scheme includes: UE receiving a reference signal from a base station; optionally, estimating downlink channel information based on the reference signal.
  • the reference signal or the estimated downlink channel information is used as the input of the encoder.
  • the output of the encoder is compressed channel information, and the compressed channel information is fed back to the base station.
  • the base station inputs the compressed channel information to the decoder and recovers the corresponding downlink channel information.
  • the encoder and decoder can be convolutional neural network (convolutional neural network, CNN), transformer neural network Transformer and other types of AI models.
  • the input of the encoder and the output of the decoder may correspond to downlink channel information in the same time slot, and the downlink channel information may include channel information on one or more subbands between the UE and the base station.
  • the uplink and downlink channels in the FDD system do not satisfy strict uplink and downlink reciprocity
  • experiments show that the uplink channel is in the angle domain, including angles of arrival (AoAs) and angles of transmission (angles of departure, AoDs), etc., and have high similarity with the delay domain. Therefore, the recovery accuracy of the downlink channel can be improved with the help of uplink channel information.
  • the UE will receive the reference signal, or determine the downlink
  • the channel information is taken as input to the encoder, and the output of the encoder is compressed channel information.
  • the compressed channel information can be called CSI.
  • the base station uses the received compressed channel information as the input of the first layer decoder, and the output of the first layer decoder is the preliminary restored downlink channel information.
  • the initially recovered downlink channel information and estimated uplink channel information are used as inputs to the second layer decoder to obtain the final recovered downlink channel information.
  • the first layer decoder may be called decoder 1
  • the second layer decoder may be called decoder 2.
  • the base station uses all antenna ports to send reference signals, and the UE feeds back the compressed channel information of the corresponding antenna port to the base station, that is, the UE feeds back CSI feedback of all antenna ports to the base station.
  • This application provides a communication method.
  • the base station uses partially activated antenna ports to send reference signals, and the UE feeds back the compressed channel information corresponding to the partially activated antenna ports.
  • the base station restores the channel information of all antenna ports based on the compressed channel information of some antenna ports fed back by the UE, thereby reducing the transmission overhead of reference signals and compressed channel information and improving system capacity.
  • the process of providing a communication method includes at least:
  • Step 800 The UE receives the first reference signal from the base station.
  • the first reference signal may be called a downlink reference signal, or the first reference signal may also be called a CSI-reference signal (RS).
  • the base station may only activate some antenna ports when sending the first reference signal.
  • the base station can support N antenna activation modes, and each antenna activation mode can correspond to different activated antenna ports. As shown in Figure 9, there are examples of two antenna activation modes. In Figure 9, a bold " ⁇ " represents an activated antenna port, and a non-bold " ⁇ " represents an inactive antenna port. In the description of this application, the antenna port may also be referred to as a port.
  • the base station can select the first antenna activation mode among multiple supported antenna activation modes. There are no restrictions on the rules for the base station to select the first antenna activation mode. For example, the base station can select the first antenna activation mode based on performance improvement considerations, or it can select the first antenna activation mode due to physical conditions, etc., without limitation.
  • the antenna activation mode can be represented by an integer vector with a length of Nt, where Nt represents the total number of antenna ports in the base station.
  • Nt represents the total number of antenna ports in the base station.
  • the i-th element in Nt is 0, which means that the i-th port is not activated
  • the i-th element is 1, which means that the i-th antenna port is activated
  • i is an integer greater than or equal to 1 and less than or equal to Nt.
  • K represents the activated antenna port
  • K is an integer less than or equal to Nt.
  • each element corresponds to an index of an activated antenna port. For example, for 32 antenna ports, the 1st, 2nd, 16th, and 17th antenna ports are activated, then the antenna activation mode can be represented by a vector (1, 2, 16, 17) with a length of 4.
  • Step 801 The UE determines first compression information according to the first reference signal.
  • the first compression information is used to represent the first downlink channel information corresponding to the antenna port activated in the first antenna activation mode, and sends it to the base station. the first compressed information.
  • the base station receives the first compressed information from the UE, the first compressed information is determined by the UE according to the first reference signal sent by the base station using the first antenna activation mode, and the first compressed information is used to characterize the First downlink channel information corresponding to the antenna port activated in the first antenna activation mode.
  • the UE when receiving the first reference signal, can determine the compression information of the downlink channel according to the first reference signal.
  • the compression information of the downlink channel is the first compression information in the aforementioned step 801, that is, the compression information in the step 801.
  • the first compressed information may also be called compressed information of the downlink channel, or may be called CSI feedback of the UE, etc., without limitation. It can be understood that since the base station uses the antenna port activated in the first antenna activation mode to transmit the first reference signal, the first compression information determined by the UE according to the first reference signal is the corresponding antenna port activated in the first antenna activation mode.
  • the downlink channel information is called the first downlink channel information in step 801.
  • the first compression information is determined using AI For example.
  • the UE preprocesses the received first reference signal and then inputs it into the second model to obtain the first compressed information.
  • the way for the UE to preprocess the received first reference signal may be that the UE directly inputs the first reference signal into the second model without processing it, or the UE performs channel estimation based on the received first reference signal and uses the estimated
  • the channel information H is input to the second model.
  • the dimensions of the estimated channel information H include a (Nt, Nr)-dimensional complex matrix.
  • Nt represents the number of transmitting antenna ports, that is, the number of antenna ports on the base station side.
  • Nr represents the number of receiving antenna ports, that is, the number of antenna ports on the UE side.
  • the channel information of multiple subbands can be combined, that is, the estimated channel information can be a three-dimensional tensor of (Nt, Nr, Nsub) dimensions, where Nsub represents the number of subbands.
  • the UE may also perform other preprocessing operations on the first reference signal or the corresponding channel information H, without limitation.
  • Step 802 The base station determines the second downlink channel information corresponding to the target antenna port based on the first compression information and the first information.
  • the first information is based on at least one of the second reference signal or the first antenna activation mode. It is determined that the target antenna ports include activated antenna ports and inactive antenna ports in the first antenna activation mode.
  • the UE may also send a second reference signal to the base station, and the second reference signal may also be an uplink reference signal.
  • the second reference signal may be predefined, or may be indicated to the UE by the base station, or may be selected by the UE without limitation.
  • the base station may determine the first information according to at least one of the second reference signal or the first antenna activation mode.
  • the first information includes the second reference signal; or in another implementation, the first information includes the first antenna activation mode; or in yet another implementation, the first information includes the second reference signal and the second reference signal.
  • One way of processing the second reference signal is for the base station to perform uplink channel estimation based on the second reference signal, and use the uplink channel estimation result determined thereby as information processed by the second reference signal.
  • one way to jointly process the second reference signal and the first antenna activation pattern is to splice the second reference signal and the first antenna activation pattern; for another example, to jointly process the second reference signal and the first antenna activation pattern.
  • One way of jointly processing the patterns is to splice the uplink channel estimation result obtained based on the second reference signal and the first antenna activation pattern.
  • the base station may determine the parameter adjustment value of the first model according to the first information; adjust the parameters of the first model according to the parameter adjustment value of the first model; and adjust the parameters of the first model according to the first compression information and the The first model is used to determine the second downlink channel information corresponding to the target antenna port.
  • a third model may be deployed in the base station, and the third model may be called an AI model, a downlink model adjustment network, etc.
  • the first information is used as the input of the third model, and the output of the third model is the parameter adjustment value of the first model; or, based on the output of the third model, the parameter adjustment value of the first model is determined; according to the parameter adjustment of the first model value, adjust the parameters of the first model.
  • the parameters of the model may include at least one of the number of layers and width of the neural network, the weight of the neuron, or the activation function of the neuron.
  • the parameter adjustment value of the first model can be adjusted according to the parameter adjustment value of the first model: the number of layers and width of the neural network, the weight of the neuron, or the activation function of the neuron, etc.
  • the parameter adjustment value of the first model can be summed with the corresponding position of the original parameter of the first model, or the parameter adjustment value of the first model can be multiplied by the corresponding position of the original parameter of the first model, etc., without limitation.
  • the base station uses the first compressed information received from the UE, such as CSI feedback, as the input of the first model.
  • the output of the first model is the restored channel information corresponding to the target antenna port. This channel information is called the second downlink in step 802. channel information.
  • the output of the first model can also be directly a downlink precoding matrix, without limitation.
  • the first model is used to recover downlink channel information, or determine the precoding matrix, etc.
  • the first model may be called a CSI recovery model, a decoding model, a precoding model, an AI model, etc., without limitation.
  • the target antenna port includes the first antenna activation mode activated in and inactive antenna ports. Or it can be described as: the base station can restore the downlink channel information of all antenna ports based on the first compressed information and the first information fed back by the UE, which includes part of the antenna port channel information, thereby reducing the air interface overhead of the first compressed information fed back by the UE.
  • the third model uses the processed information of the second reference signal received by the base station as Input, the output of the third model is the parameter adjustment value of the first model, and the parameter adjustment value is used to adjust the parameters of the first model.
  • the parameters of the first model include some common features of uplink and downlink channels, such as correlation information between channels at different antenna ports. Therefore, the first model can more accurately restore the downlink channel information of all antenna ports based only on the first compressed information containing channel information of part of the antenna ports.
  • the parameter adjustment values of the first model should be different.
  • the activated antenna ports are different, and the degree of channel similarity between the activated antenna ports is also different. Therefore, the process of recovering all channel information from partial channel information in different activation modes is different.
  • An intuitive example is to activate the first half of the antenna ports and restore the channel information corresponding to the second half of the antenna ports. In the mode where one antenna port is activated for every two adjacent antenna ports, the process of recovering the channel information of the remaining antenna ports is different.
  • the third model may include an additional input, namely the antenna activation pattern when the first reference signal is transmitted.
  • the antenna activation mode when transmitting the first reference signal is specifically the antenna activation mode adopted by the base station when transmitting the first reference signal. It may also be called the antenna activation mode for transmitting the first reference signal and the antenna for the first reference signal. Activation mode, etc. are not distinguished.
  • the base station may also determine the adjustment value of the first reference signal based on the first information; and adjust the first reference signal sent by the base station based on the adjustment value of the first reference signal.
  • the first information may be used as input to a fourth model, and the output of the fourth model may be an adjustment value of the first reference signal, or the adjustment value of the first reference signal may be determined based on the output of the fourth model.
  • a fourth model is added.
  • the inputs of this fourth model are the processed information of the second reference signal and the first antenna activation mode when the first reference signal is sent.
  • the fourth model The output of the model is the adjustment value of the first reference signal.
  • the adjustment value of the reference signal can be the adjustment value of the transmission power.
  • the adjustment value of the reference signal can be based on the adjustment value of the transmission power. Adjust the value to adjust the original power of the transmitted reference signal.
  • the adjustment value of the reference signal may be the modulation and coding scheme of the reference signal, etc., and the original modulation and coding scheme of the reference signal may be adjusted according to the modulation and coding scheme of the reference signal.
  • the UE can better represent the downlink channel information by receiving limited reference signals, thereby improving the performance of CSI compression and CSI recovery.
  • For processing the second reference signal one implementation is to obtain the uplink channel estimation result based on the second reference signal, or another implementation is to use the second reference signal directly as the input of the fourth model.
  • the base station may also send indication information of the first antenna activation mode to the UE.
  • the UE receives the indication information of the first antenna activation mode from the base station.
  • the UE can adjust parameters of the second model according to the first antenna activation mode.
  • the second model can also be called a CSI compression model.
  • UE according to the above An antenna activation mode determines the parameter adjustment value of the second model; for example, the UE can use the first antenna activation mode as input to the fifth model, and the output of the fifth model is the parameter adjustment value of the second model.
  • the fifth model can also be called the CSI compression module adjustment network.
  • the parameters of the second model please refer to the previous description.
  • Adjust the parameters of the second model according to the parameter adjustment values of the second model for example, the parameter adjustment values of the second model can be summed with the corresponding positions of the original parameters of the second model, or the parameters of the second model can be summed.
  • the parameter adjustment value, multiplied by the corresponding position of the original parameter of the second model, etc., is not limited.
  • the UE determines the first compression information according to the second model and the first reference signal. For example, the UE may use the first reference signal or the processed information of the first reference signal as input to the second model, and the output of the second model is the first compressed information.
  • the channel similarities of the activated antenna ports are different.
  • AI models ie, second models
  • the adjustment parameters of the second model are determined according to different antenna port activation modes; and the parameters of the second model are adjusted according to the adjustment parameters, so that the second model is based on the channel similarity of the activated antenna ports. Compress the received channel information of the first reference signal, thereby improving CSI compression performance.
  • the base station and the terminal include corresponding hardware structures and/or software modules that perform each function.
  • the units and method steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software driving the hardware depends on the specific application scenarios and design constraints of the technical solution.
  • Figures 13 and 14 are schematic structural diagrams of possible communication devices provided by embodiments of the present application. These communication devices can be used to implement the functions of the terminal or base station in the above method embodiments, and therefore can also achieve the beneficial effects of the above method embodiments.
  • the communication device may be one of the terminals 120a-120j as shown in Figure 1, or it may be the base station 110a or 110b as shown in Figure 1, or it may be applied to the terminal or the base station. Modules (such as chips).
  • the communication device 1300 includes a processing unit 1310 and a transceiver unit 1320.
  • the communication device 1300 is used to implement the functions of the terminal or the base station in the method embodiment shown in FIG. 8 .
  • the transceiver unit 1320 is used to receive the first compressed information from the terminal device, the first compressed information is the terminal device according to the access
  • the network device is determined by using the first reference signal sent by the first antenna activation mode, and the first compressed information is used to represent the first downlink channel information corresponding to the antenna port activated in the first antenna activation mode
  • processing unit 1310 configured to determine second downlink channel information corresponding to the target antenna port based on the first compression information and the first information, the first information being based on at least one of the second reference signal or the first antenna activation mode It is determined that the target antenna ports include activated antenna ports and inactive antenna ports in the first antenna activation mode.
  • the transceiver unit 1320 is used to receive the first reference signal from the access network device; the processing unit 1310 is used to process the first reference signal according to the first reference signal. and the first antenna activation mode, determine the first compression information, the first compression information is used to characterize the first downlink channel information corresponding to the antenna port activated in the first antenna activation mode; the transceiver unit 1320 is also used to send the The access network device sends the first compressed information.
  • the communication device 1400 includes a processor 1410 and an interface circuit 1420 .
  • Processor 1410 and Interface Circuits 1420 are coupled to each other.
  • the interface circuit 1420 may be a transceiver or an input-output interface.
  • the communication device 1400 may also include a memory 1430 for storing instructions executed by the processor 1410 or input data required for the processor 1410 to run the instructions or data generated after the processor 1410 executes the instructions.
  • the processor 1410 is used to implement the functions of the above-mentioned processing unit 1310
  • the interface circuit 1420 is used to implement the functions of the above-mentioned transceiver unit 1320.
  • the terminal chip implements the functions of the terminal in the above method embodiment.
  • the terminal chip receives information from other modules in the terminal (such as radio frequency modules or antennas), and the information is sent to the terminal by the base station; or, the terminal chip sends information to other modules in the terminal (such as radio frequency modules or antennas), and the terminal chip sends information to other modules in the terminal (such as radio frequency modules or antennas).
  • the information is sent by the terminal to the base station.
  • the base station module implements the functions of the base station in the above method embodiment.
  • the base station module receives information from other modules in the base station (such as radio frequency modules or antennas), and the information is sent by the terminal to the base station; or, the base station module sends information to other modules in the base station (such as radio frequency modules or antennas), and the base station module The information is sent by the base station to the terminal.
  • the base station module here can be the baseband chip of the base station, or it can be a DU or other module.
  • the DU here can be a DU under the open radio access network (O-RAN) architecture.
  • OF-RAN open radio access network
  • processor in the embodiment of the present application can be a central processing unit (CPU), or other general-purpose processor, digital signal processor (DSP), or application-specific integrated circuit (application specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.
  • CPU central processing unit
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • a general-purpose processor can be a microprocessor or any conventional processor.
  • the method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions.
  • Software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory In memory, register, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art.
  • An exemplary storage medium is coupled to the processor such that the processor can read information from the storage medium and write information to the storage medium.
  • the storage medium can also be an integral part of the processor.
  • the processor and storage media may be located in an ASIC. Additionally, the ASIC can be located in the base station or terminal. Of course, the processor and the storage medium may also exist as discrete components in the base station or terminal.
  • the computer program product includes one or more computer programs or instructions.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment, or other programmable device.
  • the computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another.
  • the computer program or instructions may be transmitted from a website, computer, A server or data center transmits via wired or wireless means to another website site, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media.
  • the available media may be magnetic media, such as floppy disks, hard disks, and tapes; optical media, such as digital video optical disks; or semiconductor media, such as solid-state hard drives.
  • the computer-readable storage medium may be volatile or non-volatile storage media, or may include both volatile and non-volatile storage media. Two types of lossless storage media.
  • “at least one” refers to one or more, and “plurality” refers to two or more.
  • “And/or” describes the relationship between associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the related objects before and after are an “or” relationship; in the formula of this application, the character “/” indicates that the related objects before and after are a kind of "division” Relationship.
  • “Including at least one of A, B and C” may mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B and C.

Landscapes

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

Abstract

一种通信方法及装置，该方法包括：接收来自终端设备的第一压缩信息，所述第一压缩信息是所述终端设备根据接入网设备采用第一天线激活模式发送的第一参考信号确定的，所述第一压缩信息用于表征所述第一天线激活模式中激活的天线端口对应的第一下行信道信息；根据所述第一压缩信息和第一信息，确定目标天线端口对应的第二下行信道信息，所述第一信息是根据第二参考信号或所述第一天线激活模式中的至少一项确定的，所述目标天线端口中包括所述第一天线激活模式中激活的天线端口和未激活的天线端口。在本申请中，接入网设备借助第一参考信号发送时的天线激活模式和接收的第二参考信号等，恢复下行信道信息，提高了下行信道信息的恢复精度。

Description

一种通信方法及装置
相关申请的交叉引用
本申请要求在2022年06月02日提交中国专利局、申请号为202210626470.3、申请名称为“一种通信方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及通信技术领域，尤其涉及一种通信方法及装置。
背景技术
在无线通信网络中，例如在移动通信网络中，网络支持的业务越来越多样，因此需要满足的需求越来越多样。例如，网络需要能够支持超高速率、超低时延、和/或超大连接。该特点使得网络规划、网络配置、和/或资源调度越来越复杂。此外，为了支持越来越强大的网络功能，例如支持高阶多入多出(multiple input multiple output，MIMO)、波束赋形、和/或波束管理等新技术，基站需要获得下行信道的信道状态信息(channel state information，CSI)，从而根据CSI恢复出下行信道信息，以用于实现上述的新技术。如何使得基站能够恢复出更为准确的下行信道信息，是一个值得研究的技术问题。
发明内容
本申请提供一种通信方法及装置，以提高网络侧对于下行信道信息的恢复精度。
第一方面，提供一种通信方法，该方法的执行主体为接入网设备，或者配置于接入网设备中的部件(处理器、芯片或其它等)，该方法包括：接收来自终端设备的第一压缩信息，所述第一压缩信息是所述终端设备根据接入网设备采用第一天线激活模式发送的第一参考信号确定的，所述第一压缩信息用于表征所述第一天线激活模式中激活的天线端口对应的第一下行信道信息；根据所述第一压缩信息和第一信息，确定目标天线端口对应的第二下行信道信息，所述第一信息是根据第二参考信号或所述第一天线激活模式中的至少一项确定的，所述目标天线端口中包括所述第一天线激活模式中激活的天线端口和未激活的天线端口，所述第二参考信号是所述接入网设备从所述终端设备接收的参考信号，所述第二参考信号可称为上行参考信号等，不作限制。
通过上述设计，以第一信息包括第二参考信号为例，为利用上下行部分互易性提升基站恢复下行信道的精度，或提升下行预编码的性能，接入网设备利用第三模型以基站接收的第二参考信号处理后的信息为输入，输出第一模型的参数调整值，该参数调整值用于调整第一模型的参数。经调整，所述第一模型的参数中包含了上下行信道共有的一些特征，如不同天线端口信道间的相关性信息等。因此，接入网设备利用第一模型可以仅根据包含部分天线端口信道信息的第一压缩信息，较准确地恢复全部天线端口的下行信道信息。
以第一信息包括第一天线激活模式为例，当第一压缩信息所包含的信道信息所对应的激活天线端口不同时，第一模型的运算应该有差异，第一模型用于恢复下行信道信息，或确定预编码矩阵等。该第一模型可称为CSI恢复模型、解码模型、预编码模型，或AI模 型等，不作限定。例如，不同的天线端口激活模式下，所激活的天线端口不同，所激活的天线端口间的信道相似程度也不同。因此，由不同激活模式下的部分信道信息恢复全部信道信息的过程是有差异的。一个直观的例子是，激活前半部分天线端口，恢复后半部分天线端口对应的信道信息。与每两个相邻天线端口中激活一个天线端口的模式下，恢复剩余天线端口信道信息的过程是有差异的。因此，当第一压缩信息中包含的信道信息所对应的天线端口激活模式不同时，对应的第一模型的参数应该相应进行调整。因此，第三模型可以包括额外的一个输入，即第一参考信号发送时的天线激活模式。在本申请中，第一参考信号发送时只激活部分天线端口，可有效降低发送参考信号的开销。同时，UE侧接收到的参考信号只包含部分信道信息，因此，UE可以用更少的开销进行CSI反馈，或在同等开销下提升CSI反馈的精度。此外，可基于第一参考信号发送时的天线激活模式，对第一模型的参数进行调整，以弥补CSI反馈中信道信息的缺失，提升CSI恢复的精度。可选的，第一参考信号发送时的天线激活模式，具体为基站发送第一参考信号时采用的天线激活模式，还可称为第一参考信号发送的天线激活模式、第一参考信号的天线激活模式等，不作区分。
在一种设计中，所述根据所述第一压缩信息和第一信息，确定目标天线端口对应的第二下行信道信息，包括：根据所述第一信息，确定第一模型的参数调整值；根据所述第一模型的参数调整值，调整第一模型的参数；根据所述第一压缩信息和所述第一模型，确定所述目标天线端口对应的第二下行信道信息。
在一种设计中，还包括：根据所述第一信息，确定所述第一参考信号的调整值；根据所述第一参考信号的调整值，调整所述接入网设备发送的所述第一参考信号。
通过上述设计，例如，接入网设备可将第一信息作为输入，输入到第四模型，该第四模型的输出可以为第一参考信号的调整值，或者，可根据第四模型的输出确定第一参考信号的调整值。根据所述调整值，调整向UE发送的第一参考信号，从而使得UE可以通过接收有限的参考信号，更好地表示下行信道信息，从而提升CSI压缩及CSI恢复的性能。
在一种设计中，还包括：向所述终端设备发送所述第一天线激活模式的指示信息。
第二方面，提供一种通信方法，该方法的执行主体为终端设备，或者配置于终端设备中的部件(处理器、芯片或其它)，该方法包括：接收来自接入网设备的第一参考信号；根据所述第一参考信号和第一天线激活模式，确定第一压缩信息，所述第一压缩信息用于表征第一天线激活模式中激活的天线端口对应的第一下行信道信息；向所述接入网设备发送所述第一压缩信息。
例如，所述根据所述第一参考信号，确定第一压缩信息，包括：根据所述第一天线激活模式，确定第二模型的参数调整值；根据所述第二模型的参数调整值，调整所述第二模型的参数；根据所述第二模型和所述第一参考信号，确定所述第一压缩信息。可选的，第二模型用于对UE估计确定的下行信道信息进行压缩，第二模型还可称为CSI压缩模型等。
通过上述设计，例如，终端可将第一天线激活模式作为输入，输入到第五模型中，该第五模型的输出为第二模型的参数调整值，该第五模型又可以称为CSI压缩模块调整网络。根据所述第二模型的参数调整值，调整所述第二模型的参数；例如，可将第二模型的参数调整值，与第二模型的原始参数对应位置求和，或者将第二模型的参数调整值，与第二模型的原始参数对应位置相乘等，不作限制。UE根据所述第二模型和所述第一参考信号，确定所述第一压缩信息。例如，UE可将第一参考信号，或第一参考信号的处理后的信息 作为输入，输入到第二模型，第二模型的输出为第一压缩信息。通过上述设计，不同的天线端口激活模式下，所激活的天线端口的信道相似性不同。对于不同的信道相似性，可以采用不同参数的AI模型(即第二模型)进行CSI压缩。在本设计中，根据不同的天线端口激活模式，确定第二模型的调整参数；且根据该调整参数，调整第二模型的参数，从而使得第二模型根据所激活的天线端口的信道相似性，对接收的第一参考信号的信道信息进行压缩，从而提高CSI压缩性能。
在一种设计中，还包括：接收来自所述接入网设备的所述第一天线激活模式的指示信息。
第三方面，提供一种装置，包括用于实现上述第一方面方法的单元。
第四方面，提供一种装置，包括处理器和存储器，所述处理器和存储器耦合，所述处理器用于实现上述第一方面的方法。
第五方面，提供一种装置，包括用于实现上述第二方面的方法的单元。
第六方面，提供一种装置，包括处理器和存储器，所述处理器和存储器耦合，所述处理器用于实现上述第二方面的方法。
第七方面，提供一种通信系统，包括第三方面或第四方面所述的装置，和第五方面或第六方面所述的装置。
第八方面，提供一种计算机可读存储介质，包括指令，当其在计算机上运行时，使得计算机执行第一方面或第二方面中的方法。
第九方面，提供一种芯片系统，该芯片系统包括处理器，还可以包括存储器，用于实现第一方面或第二方面中的方法。该芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
第十方面，提供一种计算机程序产品，包括指令，当其在计算机上运行时，使得计算机执行第一方面或第二方面中的方法。
附图说明
图1是本申请提供的通信系统的示意图；
图2和图3是本申请提供的通信架构示意图；
图4是本申请提供的AI模型的架构示意图；
图5和图6是本申请提供的神经元的示意图；
图7为本申请提供的AI编解码示意图；
图8为本申请提供的通信方法的流程图；
图9为本申请提供的天线激活模式的示意图；
图10、图11和图12为本申请提供的引入上行信道估计和天线激活模式的示意图；
图13和图14为本申请提供的通信装置的示意图。
具体实施方式
图1是本申请能够应用的通信系统1000的架构示意图。如图1所示，该通信系统包括无线接入网100和核心网200，可选的，通信系统1000还可以包括互联网300。其中，无线接入网100可以包括至少一个接入网设备(如图1中的110a和110b)，还可以包括至少 一个终端设备(如图1中的120a-120j)。终端设备通过无线的方式与接入网设备相连，接入网设备通过无线或有线方式与核心网连接。核心网设备与接入网设备可以是独立的不同的物理设备，或者可以是将核心网设备的功能与接入网设备的逻辑功能集成在同一个物理设备上，或者可以是一个物理设备上集成了部分核心网设备的功能和部分的接入网设备的功能。终端设备和终端设备之间以及接入网设备和接入网设备之间可以通过有线或无线的方式相互连接。图1只是示意图，该通信系统中还可以包括其它网络设备，如还可以包括无线中继设备和无线回传设备等，在图1中未画出。
接入网设备可以是基站(base station)、演进型基站(evolved NodeB，eNodeB)、发送接收点(transmission reception point，TRP)、第五代(5th generation，5G)移动通信系统中的下一代基站(next generation NodeB，gNB)、开放无线接入网(open radio access network，O-RAN)中的接入网设备、第六代(6th generation，6G)移动通信系统中的下一代基站、未来移动通信系统中的基站或无线保真(wireless fidelity，WiFi)系统中的接入节点等；或者可以是完成基站部分功能的模块或单元，例如，可以是集中式单元(central unit，CU)、分布式单元(distributed unit，DU)、集中单元控制面(CU control plane，CU-CP)模块、或集中单元用户面(CU user plane，CU-UP)模块。接入网设备可以是宏基站(如图1中的110a)，也可以是微基站或室内站(如图1中的110b)，还可以是中继节点或施主节点等。本申请中对接入网设备所采用的具体技术和具体设备形态不做限定。
在本申请中，用于实现接入网设备的功能的装置可以是接入网设备；也可以是能够支持接入网设备实现该功能的装置，例如芯片系统、硬件电路、软件模块、或硬件电路加软件模块，该装置可以被安装在接入网设备中或可以与接入网设备匹配使用。在本申请中，芯片系统可以由芯片构成，也可以包括芯片和其他分立器件。为了便于描述，下文以用于实现接入网设备的功能的装置是接入网设备，接入网设备为基站为例，描述本申请提供的技术方案。
(1)协议层结构。
接入网设备和终端设备之间的通信遵循一定的协议层结构。该协议层结构可以包括控制面协议层结构和用户面协议层结构。例如，控制面协议层结构可以包括无线资源控制(radio resource control，RRC)层、分组数据汇聚层协议(packet data convergence protocol，PDCP)层、无线链路控制(radio link control，RLC)层、媒体接入控制(media access control，MAC)层和物理层等协议层的功能。例如，用户面协议层结构可以包括PDCP层、RLC层、MAC层和物理层等协议层的功能，在一种可能的实现中，PDCP层之上还可以包括业务数据适配协议(service data adaptation protocol，SDAP)层。
可选的，接入网设备和终端设备之间的协议层结构还可以包括人工智能(artificial intelligence，AI)层，用于传输AI功能相关的数据。
(2)集中单元(central unit，CU)和分布单元(distributed unit，DU)。
接入设备可以包括CU和DU。多个DU可以由一个CU集中控制。作为示例，CU和DU之间的接口可以称为F1接口。其中，控制面(control panel，CP)接口可以为F1-C，用户面(user panel，UP)接口可以为F1-U。本申请不限制各接口的具体名称。CU和DU可以根据无线网络的协议层划分：比如，PDCP层及以上协议层的功能设置在CU，PDCP层以下协议层(例如RLC层和MAC层等)的功能设置在DU；又比如，PDCP层以上协议层的功能设置在CU，PDCP层及以下协议层的功能设置在DU，不予限制。
上述对CU和DU的处理功能按照协议层的划分仅仅是一种举例，也可以按照其他的方式进行划分。例如可以将CU或者DU划分为具有更多协议层的功能，又例如将CU或DU还可以划分为具有协议层的部分处理功能。在一种设计中，将RLC层的部分功能和RLC层以上的协议层的功能设置在CU，将RLC层的剩余功能和RLC层以下的协议层的功能设置在DU。在另一种设计中，还可以按照业务类型或者其他系统需求对CU或者DU的功能进行划分，例如按时延划分，将处理时间需要满足时延要求的功能设置在DU，不需要满足该时延要求的功能设置在CU。在另一种设计中，CU也可以具有核心网的一个或多个功能。示例性的，CU可以设置在网络侧方便集中管理。在另一种设计中，将DU的无线单元(radio unit，RU)拉远设置。可选的，RU可以具有射频功能。
可选的，DU和RU可以在物理层(physical layer，PHY)进行划分。例如，DU可以实现PHY层中的高层功能，RU可以实现PHY层中的低层功能。其中，用于发送时，PHY层的功能可以包括以下至少一项：添加循环冗余校验(cyclic redundancy check，CRC)码、信道编码、速率匹配、加扰、调制、层映射、预编码、资源映射、物理天线映射、或射频发送功能。用于接收时，PHY层的功能可以包括以下至少一项：CRC校验、信道解码、解速率匹配、解扰、解调、解层映射、信道检测、资源解映射、物理天线解映射、或射频接收功能。其中，PHY层中的高层功能可以包括PHY层的一部分功能，例如该部分功能更加靠近MAC层，PHY层中的低层功能可以包括PHY层的另一部分功能，例如该部分功能更加靠近射频功能。例如，PHY层中的高层功能可以包括添加CRC码、信道编码、速率匹配、加扰、调制、和层映射，PHY层中的低层功能可以包括预编码、资源映射、物理天线映射、和射频发送功能；或者，PHY层中的高层功能可以包括添加CRC码、信道编码、速率匹配、加扰、调制、层映射和预编码，PHY层中的低层功能可以包括资源映射、物理天线映射、和射频发送功能。例如，PHY层中的高层功能可以包括CRC校验、信道解码、解速率匹配、解码、解调、和解层映射，PHY层中的低层功能可以包括信道检测、资源解映射、物理天线解映射、和射频接收功能；或者，PHY层中的高层功能可以包括CRC校验、信道解码、解速率匹配、解码、解调、解层映射、和信道检测，PHY层中的低层功能可以包括资源解映射、物理天线解映射、和射频接收功能。
示例性的，CU的功能可以由一个实体来实现，或者也可以由不同的实体来实现。例如，可以对CU的功能进行进一步划分，即将控制面和用户面分离并通过不同实体来实现，分别为控制面CU实体(即CU-CP实体)和用户面CU实体(即CU-UP实体)。该CU-CP实体和CU-UP实体可以与DU相耦合，共同完成接入网设备的功能。
可选的，上述DU、CU、CU-CP、CU-UP和RU中的任一个可以是软件模块、硬件结构、或者软件模块+硬件结构，不予限制。其中，不同实体的存在形式可以是不同的，不予限制。例如DU、CU、CU-CP、CU-UP是软件模块，RU是硬件结构。这些模块及其执行的方法也在本申请的保护范围内。
一种可能的实现中，接入网设备包括CU-CP、CU-UP、DU和RU。例如，本申请的执行主体包括DU，或者包括DU和RU，或者包括CU-CP、DU和RU，或者包括CU-UP、DU和RU，不予限制。各模块所执行的方法也在本申请的保护范围内。
终端设备也可以称为终端、用户设备(user equipment，UE)、移动台、移动终端设备等。终端设备可以广泛应用于各种场景中的通信，例如包括但不限于以下至少一个场景：设备到设备(device-to-device，D2D)、车物(vehicle to everything，V2X)、机器类通信 (machine-type communication，MTC)、物联网(internet of things，IOT)、虚拟现实、增强现实、工业控制、自动驾驶、远程医疗、智能电网、智能家具、智能办公、智能穿戴、智能交通、或智慧城市等。终端设备可以是手机、平板电脑、带无线收发功能的电脑、可穿戴设备、车辆、无人机、直升机、飞机、轮船、机器人、机械臂、或智能家居设备等。本申请对终端设备所采用的具体技术和具体设备形态不做限定。
在本申请中，用于实现终端设备的功能的装置可以是终端设备；也可以是能够支持终端设备实现该功能的装置，例如芯片系统、硬件电路、软件模块、或硬件电路加软件模块，该装置可以被安装在终端设备中或可以与终端设备匹配使用。为了便于描述，下文以用于实现终端设备的功能的装置是终端设备，终端设备为UE为例，描述本申请提供的技术方案。
基站和UE可以是固定位置的，也可以是可移动的。基站和/或UE可以部署在陆地上，包括室内或室外、手持或车载；也可以部署在水面上；还可以部署在空中的飞机、气球和人造卫星上。本申请对基站和UE的应用场景不做限定。基站和UE可以部署在相同的场景或不同的场景，例如，基站和UE同时部署在陆地上；或者，基站部署在陆地上，UE部署在水面上等，不再一一举例。
基站和UE的角色可以是相对的，例如，图1中的直升机或无人机120i可以被配置成移动基站，对于那些通过120i接入到无线接入网100的UE120j来说，UE120i是基站；但对于基站110a来说，120i是UE，即110a与120i之间是通过无线空口协议进行通信的。110a与120i之间也可以是通过基站与基站之间的接口协议进行通信的，此时，相对于110a来说，120i也是基站。因此，基站和UE都可以统一称为通信装置，图1中的110a和110b可以称为具有基站功能的通信装置，图1中的120a-120j可以称为具有UE功能的通信装置。
在本申请中，可在前述图1所示的通信系统中引入独立的网元如称为AI网元、或AI节点等)来实现AI相关的操作，AI网元可以和通信系统中的接入网设备之间直接连接，或者可以通过第三方网元和接入网设备实现间接连接。其中，第三方网元可以是认证管理功能(authentication management function，AMF)、或用户面功能(user plane function，UPF)等核心网网元；或者，可以在通信系统中的其他网元内配置AI功能、AI模块或AI实体来实现AI相关的操作，例如该其他网元可以是接入网设备(如gNB)、核心网设备、或网管(operation,administration and maintenance，OAM)等，在这种情况下，执行AI相关的操作的网元为内置AI功能的网元。其中，上述OAM用于对接入网设备和/或核心网设备等进行操作、管理和维护等。
可选的，图2为本申请提供的一种通信系统的架构。如图2所示，在第一种设计中，接入网设备中包括近实时接入网智能控制(RAN intelligent controller，RIC)模块，用于进行模型训练和推理。例如，近实时RIC可以用于训练AI模型，利用该AI模型进行推理。例如，近实时RIC可以从CU、DU或RU中的至少一项获得网络侧和/或终端侧的信息，该信息可以作为训练数据或者推理数据。可选的，近实时RIC可以将推理结果递交至CU、DU、RU或终端设备中的至少一项。可选的，CU和DU之间可以交互推理结果。可选的，DU和RU之间可以交互推理结果，例如近实时RIC将推理结果递交至DU，由DU转发给RU。
或者，在第二种设计中，如图2所示，接入网设备之外包括非实时RIC(可选的，非实时RIC可以位于OAM中或者核心网设备中)，用于进行模型训练和推理。例如，非实 时RIC用于训练AI模型，利用该模型进行推理。例如，非实时RIC可以从CU、DU或RU中的至少一项获得网络侧和/或终端侧的信息，该信息可以作为训练数据或者推理数据，该推理结果可以被递交至CU、DU、RU或终端设备中的至少一项。可选的，CU和DU之间可以交互推理结果。可选的，DU和RU之间可以交互推理结果，例如非实时RIC将推理结果递交至DU，由DU转发给RU。
或者，在第三种设计中，如图2所示，接入网设备中包括近实时RIC，接入网设备之外包括非实时RIC(可选的，非实时RIC可以位于OAM中或者核心网设备中)。同上述第二种设计，非实时RIC可以用于进行模型训练和推理。和/或，同上述第一种设计，近实时RIC可以用于进行模型训练和推理。和/或，非实时RIC进行模型训练，近实时RIC可以从非实时RIC获得AI模型信息，并从CU、DU或RU中的至少一项获得网络侧和/或终端侧的信息，利用该信息和该AI模型信息得到推理结果。可选的，近实时RIC可以将推理结果递交至CU、DU、RU或终端设备中的至少一项。可选的，CU和DU之间可以交互推理结果。可选的，DU和RU之间可以交互推理结果，例如近实时RIC将推理结果递交至DU，由DU转发给RU。例如，近实时RIC用于训练模型A，利用模型A进行推理。例如，非实时RIC用于训练模型B，利用模型B进行推理。例如，非实时RIC用于训练模型C，将模型C的信息发送给近实时RIC，近实时RIC利用模型C进行推理。
图3为本申请提供的另一种通信系统的架构。相对图2，图3中将CU分离成为了CU-CP和CU-UP等。
AI模型是AI功能的具体实现，AI模型表征了模型的输入和输出之间的映射关系。AI模型可以是神经网络、线性回归模型、决策树模型、支持向量机(support vector machine，SVM)、贝叶斯网络、Q学习模型或者其他机器学习模型等。本申请中，AI功能可以包括以下至少一项：数据收集(收集训练数据和/或推理数据)、数据预处理、模型训练(或称为，模型学习)、模型信息发布(配置模型信息)、模型校验、模型推理、或推理结果发布。其中，推理又可以称为预测。本申请中，可以将AI模型简称为模型。
如图4所示为AI模型的一种应用架构示意图。数据源(data source)用于存储训练数据和推理数据。模型训练节点(model trainning host)通过对数据源提供的训练数据(training data)进行分析或训练，得到AI模型，且将AI模型部署在模型推理节点(model inference host)中。可选的，模型训练节点还可以对已部署在模型推理节点的AI模型进行更新。模型推理节点还可以向模型训练节点反馈已部署模型的相关信息，以使得模型训练节点对已部署的AI模型进行优化或更新等。
其中，通过模型训练节点学习得到AI模型，相当于由模型训练节点利用训练数据学习得到模型的输入和输出之间的映射关系。模型推理节点使用AI模型，基于数据源提供的推理数据进行推理，得到推理结果。该方法还可以描述为：模型推理节点将推理数据输入到AI模型，通过AI模型得到输出，该输出即为推理结果。该推理结果可以指示：由执行对象使用(执行)的配置参数、和/或由执行对象执行的操作。推理结果可以由执行(actor)实体统一规划，并发送给一个或多个执行对象(例如，网络实体)去执行。可选的，执行实体或者执行对象可以将其收集到的参数或测量量反馈给数据源，该过程可以称为表现反馈，所反馈的参数可以作为训练数据或推理数据。可选的，还可以根据模型推理节点所输出的推理结果，确定模型性能相关的反馈信息， 且将该反馈信息反馈给模型推理节点，模型推理节点可根据该反馈信息，向模型训练节点反馈该模型的性能信息等，以使得模型训练节点对已部署的AI模型进行优化或更新等，该过程可称为模型反馈。
AI模型可以是神经网络或其它机器学习模型。以神经网络为例，神经网络是机器学习技术的一种具体实现形式。根据通用近似定理，神经网络在理论上可以逼近任意连续函数，从而使得神经网络具备学习任意映射的能力。因此神经网络可以对复杂的高维度问题进行准确的抽像建模。
神经网络的思想来源于大脑组织的神经元结构。每个神经元都对其输入值做加权求和运算，将加权求和结果通过一个激活函数产生输出。如图5所示，为神经元结构示意图。假设神经元的输入为x＝[x0,x1,…,xn],与各输入对应的权值分别为w＝[w,w1,…,wn],加权求和的偏置为b。激活函数的形式可以多样化，假设一个神经元的激活函数为：y＝f(z)＝max(0,z)，该神经元的输出为：再例如一个神经元的激活函数为：y＝f(z)＝z，该神经元的输出为： xi、wi、和b可以为小数、整数(包括0、正整数或负整数等)、或复数等各种可能的取值。神经网络中不同神经元的激活函数可以相同或不同。
神经网络一般包括多层结构，每层可包括一个或多个神经元。增加神经网络的深度和/或宽度可以提高该神经网络的表达能力，为复杂系统提供更强大的信息提取和抽象建模能力。其中，神经网络的深度可以指神经网络包括的层数，每层包括的神经元个数可以称为该层的宽度。如图6所示，为神经网络的层关系示意图。一种实现中，神经网络包括输入层和输出层。神经网络的输入层将接收到的输入经过神经元处理后，将结果传递给输出层，由输出层得到神经网络的输出结果。另一种实现中，神经网络包括输入层、隐藏层和输出层。神经网络的输入层将接收到的输入经过神经元处理后，将结果传递给中间的隐藏层，隐藏层再将计算结果传递给输出层或者相邻的隐藏层，最后由输出层得到神经网络的输出结果。一个神经网络可以包括一层或多层依次连接的隐藏层，不予限制。神经网络的训练过程中，可以定义损失函数。损失函数描述了神经网络的输出值和理想目标值之间的差距或差异，本申请不限制损失函数的具体形式。神经网络的训练过程就是通过调整神经网络参数，如神经网络的层数、宽度、神经元的权值、和/或神经元的激活函数中的参数等，使得损失函数的值小于阈值门限值或者满足目标需求的过程。
随着无线通信技术的发展，所支持的业务不断增多，在系统容量、通信时延等指标上均对通信系统提出了更高的要求。其中，大规模多输入多输出(multiple-input multiple-ouput，MIMO)系统通过在收发端配置大规模天线阵列，可实现空域的分集增益，进而显著地增加系统容量。例如，基站可以利用相同的时频资源向多个UE同时发送数据，即多用户MIMO(multi-user MIMO，MU-MIMO)，或者向同一个UE同时发送多个数据流，即单用户MIMO(single-user MIMO，SU-MIMO)，该多个UE的数据之间或者同一个UE的多个数据流之间是空分复用的，因此成为通信系统演进中一个关键的方向。
大规模MIMO系统中，基站需要利用预编码矩阵对UE发送的下行数据进行预编码。基站使用预编码技术可以实现用户间或者同一个用户的不同数据流间的空分复用(spatial multiplexing)，使得UE间的数据或同一个UE的不同数据流间的数据在空间上进行隔离，从而降低不同UE间或同一UE不同数据流间的干扰，提升UE端的接收信干噪比。为了计算预编码矩阵，基站需要获取下行信道的信道状态信息(channel state information,CSI)， 根据CSI确定预编码矩阵。但是，在目前广泛应用的基于频分双工(frequency division duplex,FDD)的通信系统中，上下行信道不具备互异性，基站需要通过UE反馈获得下行CSI。例如，基站向UE发送下行参考信号，UE接收该下行参考信号。由于UE已知下行参考信号的发送序列，UE可以基于接收到的下行参考信号，估计或测量出该下行参考信号所经历的下行信道，进而，UE基于该测量得到的下行信道生成CSI，且将CSI反馈给基站。
在FDD系统中，CSI反馈的一个重要部分是预编码矩阵指示(precoding matrix indicator，PMI)，在CSI中可采用0至1比特来量化信道矩阵或预编码矩阵。PMI的设计，也称为码本设计，是移动通信系统中的一个基本问题。传统的码本设计方法是协议中预定义或约定一系列预编码矩阵及相应编号，这些预编码矩阵称为码字。采用预定义码字或多个预定义码字的线性组合可近似信道矩阵或预编码矩阵。因此，UE可通过PMI向基站反馈码字相应的编号以及加权系数等，用于基站恢复信道矩阵或预编码矩阵。
随着MIMO系统天线阵列规模不断增大，可支持的天线端口数增多，对应的信道矩阵或预编码矩阵的维度也增长。为使得UE能够对下行信道进行估计或测量，基站下发参考信号的开销将增加。同时，用有限的预定义码字近似表示大规模信道矩阵和预编码矩阵的误差会增大。一种提高信道恢复精度的方法是增加码本中码字的数量，但这会导致CSI反馈(该CSI反馈中包括码字相应的编号以及加权系数中的一个或多个)的开销增大，进而降低数据传输的可用资源，造成系统容量损失。综上，需要研究在不增加下发参考信号的开销以及CSI反馈开销的同时，如何更有效地对信道信息进行压缩表示，以及如何根据反馈信息对信道信息进行更有效地恢复。
基站与UE间的下行信道矩阵中不同元素间存在相关性，此外，不同时隙的下行信道矩阵间也存在相关性。例如，信道矩阵中不同元素间存在相关性意味着，存在一组基底(可用矩阵U1,U2表示)，将信道矩阵H投影到该组基底下时可得到稀疏的等效信道，即H’
＝U1 HHU2为稀疏矩阵，其中上标H表示共轭转置操作。理论上，仅需通过参考信号下发对H’中的非零元素进行估计并反馈即可恢复信道矩阵H。因此，参考信号的下发以及CSI反馈的开销具有压缩空间。但是，传统CSI反馈方案如上所述基于码本的反馈方式等，信道压缩空间未被充分利用，信道压缩过程可能造成较大信息损失。机器学习，如深度学习(deep learning，DL)，的方法具有更强的非线性特征提取能力，因此可以对信道矩阵间相关性做更有效的提取，进而，相比于传统方案可以更有效地对信道信息进行压缩表示，以及根据反馈信息对信道进行更有效地恢复。
一种基于AI的CSI反馈方案包括：UE接收来自基站的参考信号；可选的，根据该参考信号，估计下行信道信息。该参考信号或估计得到的下行信道信息，作为编码器的输入，编码器的输出为压缩的信道信息，将压缩的信道信息反馈给基站。基站将压缩的信道信息输入到解码器，恢复出对应的下行信道信息。其中，编码器与解码器可以为卷积神经网络(convolutional neural network，CNN)、变换神经网络Transformer等类型的AI模型。可选的，编码器的输入和解码器的输出可对应同一个时隙的下行信道信息，该下行信道信息中可包括UE与基站间的一个或多个子带上的信道信息。
在另一种方案中，虽然在FDD系统中上下行信道不满足严格的上下行互易性，但是实验表明上行信道在角度域，包括到达角(angles of arrival,AoAs)和发送角(angles of departure，AoDs)等，和时延域等具有较高的相似性。因此，可借助上行信道信息提高下行信道的恢复精度。如图7所示，UE将接收到的参考信号，或根据参考信号确定的下行 信道信息作为输入，输入到编码器，该编码器的输出为压缩的信道信息，该压缩的信道信息可称为CSI。基站将接收的压缩的信道信息作为第一层解码器的输入，第一层解码器的输出为初步恢复的下行信道信息。将初步恢复的下行信道信息和估计的上行信道信息，作为第二层解码器的输入，得到最终恢复的下行信道信息。该第一层解码器可称为解码器1，第二层解码器可称为解码器2。
在上述两种方案中，基站是采用全部天线端口发送参考信号，UE向基站反馈对应天线端口的压缩信道信息，即UE向基站反馈全部天线端口的CSI反馈。而随着MIMO系统天线阵列规模不断增大，基站可支持的天线端口数量增多，基站发送参考信号的开销，以及UE反馈CSI的开销势必都相应的增加。本申请提供一种通信方法，在该方法中，基站采用部分激活的天线端口发送参考信号，而UE反馈该部分天线端口对应的压缩信道信息。基站根据UE反馈的部分天线端口的压缩信道信息，恢复全部天线端口的信道信息，从而降低参考信号和压缩信道信息的传输开销，提高系统容量。
如图8所示，提供一种通信方法的流程，至少包括：
步骤800：UE接收来自基站的第一参考信号。
可选的，第一参考信号可以称为下行参考信号，或者该第一参考信号也可以称为CSI-参考信号(reference signal，RS)。为了降低基站发送第一参考信号的开销以及UE反馈压缩信息的开销，基站在发送第一参考信号时可以仅激活部分天线端口。可选的，基站可以支持N种天线激活模式，每种天线激活模式可对应不同的激活的天线端口。如图9所示，为2种天线激活模式的示例。在图9中，加粗的“×”代表激活的天线端口，未加粗的“×”代表未激活的天线端口。在本申请的描述中，天线端口还可称为端口。基站可以在支持的多种天线激活模式中，选择第一天线激活模式。关于基站选择第一天线激活模式的规则不作限制，比如基站可以基于性能提升的考虑选择第一天线激活模式，或者可以出于物理条件的限制，选择第一天线激活模式等，不作限定。
可选的，天线激活模式的表示方式可以为：用Nt长的整数向量表示，Nt表示基站中天线端口的总数量。其中，Nt中的第i个元素为0表示第i个端口未被激活，第i个元素为1表示第i个天线端口被激活，i为大于或等于1，小于或等于Nt的整数。或者可以用K长的整数向量表示，K表示激活的天线端口，K为小于或等于Nt的整数。其中，每一个元素对应一个激活天线端口的下标。例如，对于32天线端口，第1、2、16、17个天线端口被激活，则天线激活模式可用长度为4的向量(1、2、16、17)表示。
步骤801:UE根据所述第一参考信号，确定第一压缩信息，所述第一压缩信息用于表征第一天线激活模式中激活的天线端口对应的第一下行信道信息，且向基站发送所述第一压缩信息。相应的，基站接收来自UE的第一压缩信息，所述第一压缩信息是所述UE根据基站采用第一天线激活模式发送的第一参考信号确定的，所述第一压缩信息用于表征所述第一天线激活模式中激活的天线端口对应的第一下行信道信息。
可选的，UE在接收到第一参考信号时，可根据第一参考信号，确定下行信道的压缩信息，该下行信道的压缩信息即为前述步骤801中的第一压缩信息，即步骤801中的第一压缩信息也可称为下行信道的压缩信息，或者称为UE的CSI反馈等，不作限制。可以理解的是，由于基站采用第一天线激活模式中激活的天线端口发送第一参考信号，UE根据该第一参考信号，确定的第一压缩信息是第一天线激活模式中激活的天线端口对应的下行信道信息，在步骤801中称为第一下行信道信息。示例的，以AI方式确定第一压缩信息 为例。一种实现方式为，UE将接收的第一参考信号经预处理后输入到第二模型，得到第一压缩信息。UE对接收的第一参考信号进行预处理的方式可能为，UE对第一参考信号不做处理直接输入第二模型，或者，UE根据接收到的第一参考信号进行信道估计，将估计得到的信道信息H输入到第二模型。可选的，估计得到的信道信息H的维度包括(Nt，Nr)维的复数矩阵。其中，Nt表示发送天线端口数，即基站侧天线端口数。Nr表示接收天线端口数，即UE侧天线端口数。进一步，可把多个子带的信道信息进行合并，即估计得到的信道信息可以为(Nt，Nr，Nsub)维的三维张量，Nsub表示子带数。可选的，UE还可对第一参考信号或者对应的信道信息H作其它的预处理操作，不做限定。
步骤802：基站根据所述第一压缩信息和第一信息，确定目标天线端口对应的第二下行信道信息，所述第一信息是根据第二参考信号或所述第一天线激活模式中的至少一项确定的，所述目标天线端口中包括所述第一天线激活模式中激活的天线端口和未激活的天线端口。
可选的，UE还可以向基站发送第二参考信号，该第二参考信号也可为上行参考信号。可选的，该第二参考信号可以是预定义的，或者基站指示给UE的，或者，UE自行选择的，不作限制。基站可根据第二参考信号或第一天线激活模式中的至少一项，确定第一信息。一种实现方式，第一信息包括第二参考信号；或者，另一种实现方式是第一信息包括第一天线激活模式；或者，又一种实现方式是第一信息包括第二参考信号和第一天线激活模式；或者，又一种实现方式是第一信息包括对第二参考信号进行相应处理后的信息；或者，又一种实现方式是第一信息包括对第二参考信号和第一天线激活模式进行联合处理后的信息。其中，对第二参考信号进行处理的一种方式为，基站基于第二参考信号进行上行信道估计，将由此确定的上行信道估计结果作为第二参考信号处理后的信息。又例如，对第二参考信号和第一天线激活模式进行联合处理的一种方式为，将第二参考信号和第一天线激活模式进行拼接；再例如，对第二参考信号和第一天线激活模式进行联合处理的一种方式为，将根据第二参考信号得到的上行信道估计结果和第一天线激活模式进行拼接。
在本申请中，基站可根据所述第一信息，确定第一模型的参数调整值；根据所述第一模型的参数调整值，调整第一模型的参数；根据所述第一压缩信息和所述第一模型，确定所述目标天线端口对应的第二下行信道信息。
举例来说，基站中可部署有第三模型，第三模型可称为AI模型、下行模型调整网络等。将第一信息作为第三模型的输入，第三模型的输出为第一模型的参数调整值；或者，根据第三模型的输出，确定第一模型的参数调整值；根据第一模型的参数调整值，调整第一模型的参数。以模型采用神经网络为例，模型的参数可包括神经网络的层数、宽度、神经元的权值、或神经元的激活函数等中的至少一项。也就是说，可根据第一模型的参数调整值，调整第一模型的以下至少一项参数：神经网络的层数、宽度、神经元的权值、或神经元的激活函数等。例如，可将第一模型的参数调整值，与第一模型的原始参数对应位置求和，或者，将第一模型的参数调整值，与第一模型的原始参数对应位置相乘等，不作限定。基站将从UE接收的第一压缩信息，例如CSI反馈，作为第一模型的输入，第一模型的输出为恢复的目标天线端口对应的信道信息，该信道信息在步骤802中称为第二下行信道信息。可选的，第一模型的输出还可以直接为下行预编码矩阵，不作限定。第一模型用于恢复下行信道信息，或确定预编码矩阵等。该第一模型可称为CSI恢复模型、解码模型、预编码模型，或AI模型等，不作限定。该目标天线端口包括该第一天线激活模式中激活 和未激活的天线端口。或者可描述为：基站根据UE反馈的包含部分天线端口信道信息的第一压缩信息和第一信息，可恢复全部天线端口的下行信道信息，从而可减少UE反馈第一压缩信息的空口开销。
举例来说，如图10所示，为利用上下行部分互易性提升基站恢复下行信道的精度，或提升下行预编码的性能，第三模型以基站接收的第二参考信号处理后的信息为输入，第三模型的输出为第一模型的参数调整值，该参数调整值用于调整第一模型的参数。经调整，所述第一模型的参数中包含了上下行信道共有的一些特征，如不同天线端口信道间的相关性信息等。因此，第一模型可以仅根据包含部分天线端口信道信息的第一压缩信息，较准确地恢复全部天线端口的下行信道信息。
进一步的，当第一压缩信息所包含的信道信息所对应的激活天线端口不同时，第一模型的参数调整值应该有差异。例如，不同的天线端口激活模式下，所激活的天线端口不同，所激活的天线端口间的信道相似程度也不同。因此，由不同激活模式下的部分信道信息恢复全部信道信息的过程是有差异的。一个直观的例子是，激活前半部分天线端口，恢复后半部分天线端口对应的信道信息。与每两个相邻天线端口中激活一个天线端口的模式下，恢复剩余天线端口信道信息的过程是有差异的。因此，在图10中，当第一压缩信息中包含的信道信息所对应的天线端口激活模式不同时，对应的第一模型的参数应该相应进行调整。因此，第三模型可以包括额外的一个输入，即第一参考信号发送时的天线激活模式。
在本申请中，第一参考信号发送时只激活部分天线端口，可有效降低发送参考信号的开销。同时，UE侧接收到的参考信号只包含部分信道信息，因此，UE可以用更少的开销进行CSI反馈，或在同等开销下提升CSI反馈的精度。此外，可基于第一参考信号发送时的天线激活模式，对第一模型的参数进行调整，以弥补CSI反馈中信道信息的缺失，提升CSI恢复的精度。可选的，第一参考信号发送时的天线激活模式，具体为基站发送第一参考信号时采用的天线激活模式，还可称为第一参考信号发送的天线激活模式、第一参考信号的天线激活模式等，不作区分。
可选的，基站还可根据所述第一信息，确定所述第一参考信号的调整值；根据所述第一参考信号的调整值，调整基站发送的所述第一参考信号。例如，可将第一信息作为输入，输入到第四模型，该第四模型的输出可以为第一参考信号的调整值，或者，可根据第四模型的输出确定第一参考信号的调整值。根据所述调整值，调整向UE发送的第一参考信号。如图11所示，在图10的基础上，增加第四模型，该第四模型的输入为第二参考信号处理后的信息和第一参考信号发送时的第一天线激活模式，该第四模型的输出为第一参考信号的调整值，根据该调整值，对基站发送的第一参考信号进行调整，例如，该参考信号的调整值可以为发送功率的调整值，可根据该发送功率的调整值，调整发送参考信号的原始功率。或者，该参考信号的调整值可以为参考信号的调制编码方案等，可根据该参考信号的调制编码方案，调整参考信号的原调制编码方案等。采用上述方法，可使得UE可以通过接收有限的参考信号，更好地表示下行信道信息，从而提升CSI压缩及CSI恢复的性能。其中第二参考信号的处理，一种实现方式是根据第二参考信号得到上行信道估计结果，或者另一种实现方式是将第二参考信号直接作为第四模型的输入。
可选的，基站还可以向UE发送第一天线激活模式的指示信息。相应的，UE接收来自基站的第一天线激活模式的指示信息。如图12所示，UE可以根据第一天线激活模式，对第二模型的参数进行调整，该第二模型又可以称为CSI压缩模型。例如：UE根据所述第 一天线激活模式，确定第二模型的参数调整值；例如，UE可将第一天线激活模式作为输入，输入到第五模型中，该第五模型的输出为第二模型的参数调整值，该第五模型又可以称为CSI压缩模块调整网络。关于第二模型的参数，可参见前述说明。根据所述第二模型的参数调整值，调整所述第二模型的参数；例如，可将第二模型的参数调整值，与第二模型的原始参数对应位置求和，或者将第二模型的参数调整值，与第二模型的原始参数对应位置相乘等，不作限制。UE根据所述第二模型和所述第一参考信号，确定所述第一压缩信息。例如，UE可将第一参考信号，或第一参考信号的处理后的信息作为输入，输入到第二模型，第二模型的输出为第一压缩信息。
在本申请中，不同的天线端口激活模式下，所激活的天线端口的信道相似性不同。对于不同的信道相似性，可以采用不同参数的AI模型(即第二模型)进行CSI压缩。在本设计中，根据不同的天线端口激活模式，确定第二模型的调整参数；且根据该调整参数，调整第二模型的参数，从而使得第二模型根据所激活的天线端口的信道相似性，对接收的第一参考信号的信道信息进行压缩，从而提高CSI压缩性能。
可以理解的是，为了实现上述实施例中功能，基站和终端包括了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本申请中所公开的实施例描述的各示例的单元及方法步骤，本申请能够以硬件或硬件和计算机软件相结合的形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用场景和设计约束条件。
图13和图14为本申请的实施例提供的可能的通信装置的结构示意图。这些通信装置可以用于实现上述方法实施例中终端或基站的功能，因此也能实现上述方法实施例所具备的有益效果。在本申请的实施例中，该通信装置可以是如图1所示的终端120a-120j中的一个，也可以是如图1所示的基站110a或110b，还可以是应用于终端或基站的模块(如芯片)。
如图13所示，通信装置1300包括处理单元1310和收发单元1320。通信装置1300用于实现上述图8中所示的方法实施例中终端或基站的功能。
当通信装置1300用于实现图8所示的方法实施例中的基站功能时：收发单元1320用于接收来自终端设备的第一压缩信息，所述第一压缩信息是所述终端设备根据接入网设备采用第一天线激活模式发送的第一参考信号确定的，所述第一压缩信息用于表征所述第一天线激活模式中激活的天线端口对应的第一下行信道信息；处理单元1310用于根据所述第一压缩信息和第一信息，确定目标天线端口对应的第二下行信道信息，所述第一信息是根据第二参考信号或所述第一天线激活模式中的至少一项确定的，所述目标天线端口中包括所述第一天线激活模式中激活的天线端口和未激活的天线端口。
当通信装置1300用于实现图8所示的方法实施例中终端的功能时：收发单元1320用于接收来自接入网设备的第一参考信号；处理单元1310用于根据所述第一参考信号和第一天线激活模式，确定第一压缩信息，所述第一压缩信息用于表征第一天线激活模式中激活的天线端口对应的第一下行信道信息；收发单元1320还用于向所述接入网设备发送所述第一压缩信息。
有关上述处理单元1310和收发单元1320更详细的描述可以直接参考图8所示的方法实施例中相关描述直接得到，这里不加赘述。
如图14所示，通信装置1400包括处理器1410和接口电路1420。处理器1410和接口 电路1420之间相互耦合。可以理解的是，接口电路1420可以为收发器或输入输出接口。可选的，通信装置1400还可以包括存储器1430，用于存储处理器1410执行的指令或存储处理器1410运行指令所需要的输入数据或存储处理器1410运行指令后产生的数据。
当通信装置1400用于实现图8所示的方法时，处理器1410用于实现上述处理单元1310的功能，接口电路1420用于实现上述收发单元1320的功能。
当上述通信装置为应用于终端的芯片时，该终端芯片实现上述方法实施例中终端的功能。该终端芯片从终端中的其它模块(如射频模块或天线)接收信息，该信息是基站发送给终端的；或者，该终端芯片向终端中的其它模块(如射频模块或天线)发送信息，该信息是终端发送给基站的。
当上述通信装置为应用于基站的模块时，该基站模块实现上述方法实施例中基站的功能。该基站模块从基站中的其它模块(如射频模块或天线)接收信息，该信息是终端发送给基站的；或者，该基站模块向基站中的其它模块(如射频模块或天线)发送信息，该信息是基站发送给终端的。这里的基站模块可以是基站的基带芯片，也可以是DU或其他模块，这里的DU可以是开放式无线接入网(open radio access network，O-RAN)架构下的DU。
可以理解的是，本申请的实施例中的处理器可以是中央处理单元(central processing unit，CPU)，还可以是其它通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field programmable gate array，FPGA)或者其它可编程逻辑器件、晶体管逻辑器件，硬件部件或者其任意组合。通用处理器可以是微处理器，也可以是任何常规的处理器。
本申请的实施例中的方法步骤可以通过硬件的方式来实现，也可以由处理器执行软件指令的方式来实现。软件指令可以由相应的软件模块组成，软件模块可以被存放于随机存取存储器、闪存、只读存储器、可编程只读存储器、可擦除可编程只读存储器、电可擦除可编程只读存储器、寄存器、硬盘、移动硬盘、CD-ROM或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于基站或终端中。当然，处理器和存储介质也可以作为分立组件存在于基站或终端中。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序或指令。在计算机上加载和执行所述计算机程序或指令时，全部或部分地执行本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、网络设备、用户设备或者其它可编程装置。所述计算机程序或指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机程序或指令可以从一个网站站点、计算机、服务器或数据中心通过有线或无线方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是集成一个或多个可用介质的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，例如，软盘、硬盘、磁带；也可以是光介质，例如，数字视频光盘；还可以是半导体介质，例如，固态硬盘。该计算机可读存储介质可以是易失性或非易失性存储介质，或可包括易失性和非易 失性两种类型的存储介质。
在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，不同的实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
本申请中，“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，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的情况，其中A,B可以是单数或者复数。在本申请的文字描述中，字符“/”，一般表示前后关联对象是一种“或”的关系；在本申请的公式中，字符“/”，表示前后关联对象是一种“相除”的关系。“包括A，B和C中的至少一个”可以表示：包括A；包括B；包括C；包括A和B；包括A和C；包括B和C；包括A、B和C。
可以理解的是，在本申请的实施例中涉及的各种数字编号仅为描述方便进行的区分，并不用来限制本申请的实施例的范围。上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定。

Claims (17)

  1. 一种通信方法，其特征在于，包括：
    接收来自终端设备的第一压缩信息，所述第一压缩信息是所述终端设备根据接入网设备采用第一天线激活模式发送的第一参考信号确定的，所述第一压缩信息用于表征所述第一天线激活模式中激活的天线端口对应的第一下行信道信息；
    根据所述第一压缩信息和第一信息，确定目标天线端口对应的第二下行信道信息，所述第一信息是根据第二参考信号或所述第一天线激活模式中的至少一项确定的，所述目标天线端口中包括所述第一天线激活模式中激活的天线端口和未激活的天线端口，所述第二参考信号是所述接入网设备从所述终端设备接收的参考信号。
  2. 如权利要求1所述的方法，其特征在于，所述根据所述第一压缩信息和第一信息，确定目标天线端口对应的第二下行信道信息，包括：
    根据所述第一信息，确定第一模型的参数调整值；
    根据所述第一模型的参数调整值，调整第一模型的参数；
    根据所述第一压缩信息和所述第一模型，确定所述目标天线端口对应的第二下行信道信息。
  3. 如权利要求1或2所述的方法，其特征在于，还包括：
    根据所述第一信息，确定所述第一参考信号的调整值；
    根据所述第一参考信号的调整值，调整所述接入网设备发送的所述第一参考信号。
  4. 如权利要求1至3中任一项所述的方法，其特征在于，还包括：
    向所述终端设备发送所述第一天线激活模式的指示信息。
  5. 一种通信方法，其特征在于，包括：
    接收来自接入网设备的第一参考信号；
    根据所述第一参考信号和第一天线激活模式，确定第一压缩信息，所述第一压缩信息用于表征第一天线激活模式中激活的天线端口对应的第一下行信道信息；
    向所述接入网设备发送所述第一压缩信息。
  6. 如权利要求5所述的方法，其特征在于，所述根据所述第一参考信号和第一天线激活模式，确定第一压缩信息，包括：
    根据所述第一天线激活模式，确定第二模型的参数调整值；
    根据所述第二模型的参数调整值，调整所述第二模型的参数；
    根据所述第二模型和所述第一参考信号，确定所述第一压缩信息。
  7. 如权利要求5或6所述的方法，其特征在于，还包括：
    接收来自所述接入网设备的所述第一天线激活模式的指示信息。
  8. 一种通信装置，其特征在于，包括用于实现权利要求1至4中任一项所述方法的单元。
  9. 一种通信装置，其特征在于，包括处理器和存储器，所述处理器和存储器耦合，所述处理器用于实现权利要求1至4中任一项所述的方法。
  10. 一种通信装置，其特征在于，包括处理器和接口电路，所述接口电路用于接收来自所述通信装置之外的其它通信装置的信号并传输至所述处理器或将来自所述处理器的信号发送给所述通信装置之外的其它通信装置，所述处理器通过逻辑电路或执行代码指令用 于实现如权利要求1至4中任一项所述的方法。
  11. 一种通信装置，其特征在于，包括用于实现权利要求5至7中任一项所述方法的单元。
  12. 一种通信装置，其特征在于，包括处理器和存储器，所述处理器和存储器耦合，所述处理器用于实现权利要求5至7中任一项所述的方法。
  13. 一种通信装置，其特征在于，包括处理器和接口电路，所述接口电路用于接收来自所述通信装置之外的其它通信装置的信号并传输至所述处理器或将来自所述处理器的信号发送给所述通信装置之外的其它通信装置，所述处理器通过逻辑电路或执行代码指令用于实现如权利要求5至7中任一项所述的方法。
  14. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有指令，所述指令在计算机上运行时，使得计算机执行权利要求1至4中任一项所述的方法，或者权利要求5至7中任一项所述的方法。
  15. 一种芯片，其特征在于，包括处理器，所述处理器与存储器耦合，用于执行所述存储器中存储的计算机程序或指令，使得所述芯片实现权利要求1至4中任一项所述的方法，或者实现权利要求5至7中任一项所述的方法。
  16. 一种计算机程序产品，其特征在于，包括计算机程序或指令，当计算机程序或指令被装置运行时，使得权利要求1至4中任一项所述的方法被执行，或者权利要求5至7中任一项所述的方法被执行。
  17. 一种通信系统，其特征在于，包括：第一通信装置，所述第一通信装置用于实现权利要求1至4中任一项所述的方法；
    第二通信装置，所述第二通信装置用于实现权利要求5至7中任一项所述的方法。
PCT/CN2023/096667 2022-06-02 2023-05-26 一种通信方法及装置 WO2023231934A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210626470.3 2022-06-02
CN202210626470.3A CN117220737A (zh) 2022-06-02 2022-06-02 一种通信方法及装置

Publications (1)

Publication Number Publication Date
WO2023231934A1 true WO2023231934A1 (zh) 2023-12-07

Family

ID=89026906

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/096667 WO2023231934A1 (zh) 2022-06-02 2023-05-26 一种通信方法及装置

Country Status (2)

Country Link
CN (1) CN117220737A (zh)
WO (1) WO2023231934A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170195100A1 (en) * 2014-08-01 2017-07-06 Lg Electronics Inc. Method for reporting channel state, and device therefor
CN109728841A (zh) * 2019-01-04 2019-05-07 北京邮电大学 一种多天线系统中基于接收天线激活模式的安全传输方法
US20210218455A1 (en) * 2018-09-03 2021-07-15 Samsung Electronics Co., Ltd. Method and apparatus for configuring terminal antenna in wireless communication system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170195100A1 (en) * 2014-08-01 2017-07-06 Lg Electronics Inc. Method for reporting channel state, and device therefor
US20210218455A1 (en) * 2018-09-03 2021-07-15 Samsung Electronics Co., Ltd. Method and apparatus for configuring terminal antenna in wireless communication system
CN109728841A (zh) * 2019-01-04 2019-05-07 北京邮电大学 一种多天线系统中基于接收天线激活模式的安全传输方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZTE: "On UE Adaptation to Maximum Number of MIMO Layers", 3GPP TSG RAN WG1 #101 E-MEETING R1-2003488, 16 May 2020 (2020-05-16), XP051885272 *

Also Published As

Publication number Publication date
CN117220737A (zh) 2023-12-12

Similar Documents

Publication Publication Date Title
US20240348478A1 (en) Communication method and apparatus
US20240171429A1 (en) Communication method and apparatus
WO2024164641A1 (zh) 一种csi发送和接收方法及装置
WO2024051789A1 (zh) 一种波束管理方法
WO2023126007A1 (zh) 信道信息传输方法及装置
WO2023098860A1 (zh) 通信方法和通信装置
WO2023231934A1 (zh) 一种通信方法及装置
WO2023231881A1 (zh) 一种模型应用方法及装置
US20240356595A1 (en) Uplink precoding method and apparatus
EP4447334A1 (en) Uplink precoding method and apparatus
US20240357560A1 (en) Data processing method for model, and apparatus
WO2024027424A1 (zh) 一种数据质量度量方法及装置
WO2024008004A1 (zh) 一种通信方法及装置
WO2024208316A1 (zh) 一种压缩信息的反馈方法及装置
WO2023125985A1 (zh) 模型的数据处理方法及装置
WO2023036323A1 (zh) 一种通信方法及装置
WO2024169757A1 (zh) 一种通信的方法和通信装置
WO2023016503A1 (zh) 一种通信方法及装置
WO2023174108A1 (zh) 一种通信方法及装置
WO2023125699A1 (zh) 一种通信方法及装置
WO2023115254A1 (zh) 处理数据的方法及装置
WO2024046215A1 (zh) 一种通信方法及装置
WO2023202514A1 (zh) 一种通信方法及装置
WO2024169600A1 (zh) 一种通信方法及装置
WO2022262687A1 (zh) 一种数据处理方法及装置

Legal Events

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

Ref document number: 23815117

Country of ref document: EP

Kind code of ref document: A1