Method for determining wireless channel and communication apparatus

Abstract

Provided in the present application are a method for determining a wireless channel and a communication apparatus. The method comprises: a first device determines and sends configuration information, wherein the configuration information comprises information used for indicating M models, the M models corresponding to M weightings, the M models and the M weightings being used for reconstructing a wireless channel, and M being an integer greater than or equal to 1. In the method, a model combination consisting of at least one model in the configuration information and the weighting corresponding to the model are used for reconstructing the channel, thereby avoiding the problem in existing solutions that a multipath transient part cannot be obtained, and the channel is reconstructed by means of the channel model most approximating an actual channel model, thus improving the accuracy of wireless channel reconstruction.

Description

Method and communication apparatus for determining wireless channel

[0001] The present application claims priority to the Chinese patent application No. 202411175884.4, filed on August 23, 2024, and entitled "Method and communication apparatus for determining wireless channel", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and more particularly, to a method and communication apparatus for determining wireless channel. BACKGROUND

[0003] In the scenario of multipath propagation, it is crucial to predict the multipath in the wireless transmission environment for the performance of the communication system. The prediction of the multipath refers to predicting the possible multipath characteristics of the terminal communication device when communicating with a certain base station at a certain spatial position, such as the number of paths, the strength of the paths, the angle of the paths, the time delay spread of the multipath, the angle spread of the multipath, etc. The existing method for predicting the multipath is to model the environment in a virtual physical world, and to simulate the determinate part of the multipath between the terminal device and the network device in the virtual physical environment by using the ray tracing technology or the artificial intelligence technology, such as the number of paths, the strength of the paths, the angle of the paths, the time delay spread of the multipath, and the angle spread of the multipath. However, the phase of the multipath changes at the wavelength level, which cannot be obtained by simulation, resulting in a large error between the reconstructed channel information and the original channel information. SUMMARY

[0004] The present application provides a method and communication apparatus for determining wireless channel, which can improve the accuracy of reconstructing the wireless channel.

[0005] In a first aspect, a method for determining wireless channel is provided, which can be executed by a first device. In the absence of special description, the first device in the present application can refer to a communication device (e.g., a terminal device or a network device), a component (e.g., a communication module, a processor, a circuit, a chip, or a chip system, etc.) in the communication device, or a logic module or software capable of realizing all or part of the functions of the communication device.

[0006] The method can include determining configuration information, the configuration information being used to indicate information of M models, the M models corresponding to M weights one by one, and the M models and the M weights being used to reconstruct the wireless channel; and sending the configuration information, M being an integer greater than or equal to 1.

[0007] It should be understood that the information of the M models included in the configuration information is used for the first device and the second device to align the information of the M models. Wherein, the configuration information used for indicating the information of the M models can be direct indication or indirect indication. For example, the configuration information can carry the information of the M models, wherein the information can be one or more of identification information corresponding to the models, serial numbers corresponding to the models, input / output dimensions corresponding to the models, or neural network parameters, and the like.

[0008] It should also be understood that the M weights can be the same or different, which is not limited in the present application.

[0009] It should also be understood that one or more of the M models can exist in the form of a model combination / model set. The present application exemplarily introduces a model combination, wherein the correlation or similarity between the models included in the model combination and the actual channel model is greater than or equal to a preset threshold, for example, the models in the model combination are the channel models most approximating the actual channel model, that is, at least one model included in the model combination greatly improves the channel reconstruction accuracy when reconstructing the wireless channel (or referred to as the reconstructed channel).

[0010] According to the method provided in the present application, the configuration information is used to indicate M model combinations, and the M models and the M weights corresponding to the M models are used to reconstruct the wireless channel. Compared with the prior art, only the deterministic part of the multipath can be obtained by predicting the radio map, and the instantaneous part cannot be obtained, resulting in poor accuracy of the reconstructed channel. In the method provided in the present application, the M models and the M weights are used to reconstruct the channel, avoiding the problem that the instantaneous part of the multipath cannot be obtained in the prior art, and by using the channel model most approximating the actual channel model to reconstruct the channel, the accuracy of the reconstructed wireless channel is improved.

[0011] In combination with the first aspect, in some possible implementation manners, the method further includes: receiving capability information of the second device, wherein the capability information is used to indicate that the second device supports the capability of selecting a model.

[0012] It should be understood that the capability information of the second device can be used by the first device to determine that the second device supports the capability of selecting a model, so as to further determine the first selected model according to the capability of the second device supporting the selection of the model, and carry the first selected model and / or the identification information of the first selected model in the configuration information.

[0013] With reference to the first aspect, in some possible implementation manners, the method further includes: receiving first information, the first information including at least one first model combination and at least one first weight, the at least one first model combination and the at least one first weight being determined based on the first selected model and the first parameter, a model in the at least one first model combination being from the M models, the at least one first model combination corresponding to the first parameter, each first weight in the at least one first weight corresponding to each model in the at least one first model combination; and reconstructing the wireless channel according to the first information and the channel measurement result, wherein the first parameter includes one or more of an identifier of a region where the second device is located, a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device.

[0014] It should be understood that the channel measurement result can be obtained by measuring a reference signal transmitted on a communication channel between the first device and the second device. Assuming that the first device is a network device and the second device is a terminal device, for uplink transmission, the channel measurement result can be determined by the network device based on a received uplink reference signal. Assuming that the first device is a network device and the second device is a terminal device, for downlink transmission, the channel measurement result can be determined by the terminal device based on a received downlink reference signal.

[0015] Based on the above technical solution, the first device reconstructs the wireless channel according to the received first information and the channel measurement result. The at least one first model combination and the at least one first weight included in the first information are used to approximate the actual channel in the process of reconstructing the wireless channel, thereby improving the accuracy of reconstructing the wireless channel.

[0016] With reference to the first aspect, in some possible implementation manners, the configuration information is further used to indicate the first selected model.

[0017] It should be understood that the configuration information is further used to indicate the first selected model. For example, the configuration information can further carry information of the first selected model, which can be an identifier corresponding to the first selected model, a serial number corresponding to the first selected model, or specific content of the first selected model, and the like. The configuration information used to indicate the first selected model can be used by the first device and the second device to align related information of the first selected model.

[0018] It should also be understood that the first selected model can be in the form of a function, the input of the function being the first parameter and the output being the N models and the N weights corresponding to the N models. The first selected model can also be in the form of a neural network, the input of the neural network being the first parameter and the output being the N models and the N weights corresponding to the N models. The specific form of the first selected model is not limited in the present application.

[0019] With reference to the first aspect, in some possible implementation modes, before the wireless channel is reconstructed according to the first information and the channel measurement result, the method further includes: receiving the first parameter, and reconstructing the wireless channel according to the first information and the channel measurement result includes: determining, according to the first information and the first parameter, at least one second model combination from the at least one first model combination, and at least one second weight corresponding to the at least one second model combination, one second weight in the at least one second weight corresponding to one model in the at least one second model combination; and reconstructing the wireless channel according to the at least one second model combination, the at least one second weight and the channel measurement result.

[0020] It should be understood that the channel measurement result can be a sparse channel measurement result obtained by performing sparse channel measurement, and the present application does not limit this. For example, the sparse channel measurement can be understood as a measurement result obtained by measuring a reference signal transmitted on some specific time-frequency points (for example, four time-frequency points determined by symbol 1, symbol 3, subcarrier 10 and subcarrier 5).

[0021] With reference to the first aspect, in some possible implementation modes, before the first information is received, the method further includes: receiving at least one third model combination and at least one third weight, the at least one third model combination being determined according to the second selected model and the first parameter, one model in the at least one third model combination corresponding to one third weight in the at least one third weight; reconstructing the wireless channel according to the at least one third model combination and the at least one third weight, determining a reconstruction loss of the reconstructed wireless channel; and sending information indicating the reconstruction loss, the reconstruction loss being used for training the second selected model, the first selected model being a selected model trained by the second selected model.

[0022] With reference to the first aspect, in some possible implementation modes, before the at least one third model combination and the at least one third weight are received, the method further includes: sending the first parameter.

[0023] With reference to the first aspect, in some possible implementation modes, the method further includes: sending second information, the second information including at least one first model combination and at least one first weight, the at least one first model combination and the at least one first weight being determined by the first selected model from the M models according to the first parameter, the at least one first model combination corresponding to the first parameter, and the at least one first weight corresponding to the at least one first model combination, wherein the first parameter includes: the first parameter includes one or more of an identifier of a region where the second device is located, a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device.

[0024] With reference to the first aspect, in some possible implementation modes, the method further includes: sending the first parameter.

[0025] With reference to the first aspect, in some possible implementation manners, before the second information is sent, the method further includes: sending at least one third model combination and at least one third weight, the at least one third model combination being determined according to the second selected model and the first parameter, one model in the at least one third model combination corresponding to one third weight in the at least one third weight; receiving information indicating a reconstruction loss, the reconstruction loss being determined according to the at least one third model combination and the at least one third weight; training the second selected model according to the reconstruction loss to obtain a first selected model, the first selected model being a selected model for which the training of the second selected model is completed; and determining the at least one first model combination and the at least one first weight according to the first parameter and the first selected model.

[0026] With reference to the first aspect, in some possible implementation manners, before the at least one third model combination and the at least one third weight are sent, the method further includes: receiving the first parameter.

[0027] The second aspect provides a method for determining a wireless channel, which can be executed by a second device. Without special indication, the second device in the present application can refer to a communication device (for example, a network device or a terminal device), a component (for example, a communication module, a processor, a circuit, a chip, or a chip system) in the communication device, or a logic module or software capable of realizing all or part of the functions of the communication device.

[0028] The method can include: receiving configuration information, the configuration information being used to indicate information of M models, the M models corresponding to M weights, the M models and the M weights being used to reconstruct the wireless channel, M being an integer greater than or equal to 1.

[0029] It should be understood that the first aspect corresponds to the second aspect, and the specific description and technical effects can be referred to the related description of the first aspect.

[0030] With reference to the second aspect, in some possible implementation manners, the method further includes: sending capability information of the second device, the capability information being used to indicate a capability of the second device supporting the selected model.

[0031] With reference to the second aspect, in some possible implementation manners, the method further includes: sending the first information, the first information including at least one first model combination and at least one first weight, the at least one first model combination and the at least one first weight being determined based on the first selected model and the first parameter, a model in the at least one first model combination being from the M models, the at least one first model combination corresponding to the first parameter, the at least one first weight corresponding to each model in the at least one first model combination, and wherein the first parameter includes one or more of an identifier of a region where the second device is located, a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device.

[0032] With reference to the second aspect, in some possible implementation manners, the configuration information is further used to indicate the first selected model.

[0033] With reference to the second aspect, in some possible implementation manners, the method further includes: sending the first parameter.

[0034] With reference to the second aspect, in some possible implementation manners, before the first information is sent, the method further includes: sending at least one third model combination and at least one third weight, the at least one third model combination being determined according to a second selected model and the first parameter, each model in the at least one third model combination corresponding to the at least one third weight; receiving information indicating a reconstruction loss, the reconstruction loss being determined according to the at least one third model combination and the at least one third weight; training the second selected model according to the reconstruction loss to obtain the first selected model, the first selected model being a selected model for which the training of the second selected model is completed; and determining the at least one first model combination and the at least one first weight according to the first parameter and the first selected model.

[0035] With reference to the second aspect, in some possible implementation manners, before the at least one third model combination and the at least one third weight are sent, the method further includes: receiving the first parameter.

[0036] With reference to the second aspect, in some possible implementation manners, the method further includes: receiving second information, the second information including the at least one first model combination and the at least one first weight, the at least one first model combination and the at least one first weight being determined by the first selected model from the M models according to the first parameter, the at least one first model combination corresponding to the first parameter, and the at least one first weight corresponding to the at least one first model combination; and reconstructing the wireless channel according to the second information and the channel measurement result, wherein the first parameter includes one or more of an identifier of a region where the second device is located, a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device.

[0037] In some possible implementation manners of the second aspect, before the wireless channel is reconstructed according to the second information and the channel measurement result, the method further includes: receiving the first parameter, and reconstructing the wireless channel according to the second information and the channel measurement result includes: determining, according to the second information and the first parameter, at least one second model combination from the at least one first model combination, and at least one second weight corresponding to the at least one second model combination, one second weight in the at least one second weight corresponding to one model in the at least one second model combination; and reconstructing the wireless channel according to the at least one second model combination, the at least one second weight, and the channel measurement result.

[0038] In some possible implementation manners of the second aspect, before the second information is received, the method further includes: receiving at least one third model combination and at least one third weight, the at least one third model combination being determined according to the second selected model and the first parameter, each model in the at least one third model combination corresponding to one third weight; reconstructing the wireless channel according to the at least one third model combination and the at least one third weight, determining a reconstruction loss of the reconstructed wireless channel, and sending information indicating the reconstruction loss, the reconstruction loss being used for training the second selected model, the first selected model being a selected model trained by the second selected model.

[0039] In some possible implementation manners of the second aspect, before the at least one third model combination and the at least one third weight are received, the method further includes: receiving the first parameter.

[0040] In a third aspect, a communication apparatus is provided, which is configured to execute the method in any possible implementation manner of the first aspect or the second aspect. Specifically, the apparatus can include units and / or modules configured to execute the method in any possible implementation manner of the first aspect or the second aspect, such as a processing unit and / or a communication unit.

[0041] In one implementation manner, the apparatus is a communication device (for example, the second device, or for example, the first device). When the apparatus is the communication device, the communication unit can be a transceiver, or an input / output interface; and the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0042] In another implementation manner, the apparatus is a chip, a chip system, or a circuit for a communication device (for example, the second device, or for example, the first device). When the apparatus is the chip, the chip system, or the circuit for the communication device, the communication unit can be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or a related circuit on the chip, the chip system, or the circuit; and the processing unit can be at least one processor, a processing circuit, or a logic circuit.

[0043] In a fourth aspect, a communication apparatus is provided, which comprises at least one processor configured to execute computer programs or instructions to perform the method in any possible implementation of the first aspect or the second aspect. Optionally, the apparatus further comprises a memory configured to store the computer programs or instructions. Optionally, the apparatus further comprises a communication interface through which the processor reads the computer programs or instructions.

[0044] In an implementation, the apparatus is a communication device (e.g., the second device, or the first device).

[0045] In another implementation, the apparatus is a chip, chip system or circuit for a communication device (e.g., the second device, or the first device).

[0046] In a fifth aspect, a processor is provided, which is configured to perform the method in the first aspect or the second aspect.

[0047] For the sending, obtaining / receiving and other operations involved by the processor, if no special description is made, or if it is not contrary to the actual role or inherent logic in the related description, it can be understood as the output and receiving, input operations of the processor, or the sending and receiving operations performed by the radio frequency circuit and the antenna, which are not limited in the present application.

[0048] Optionally, the apparatus further comprises a memory configured to store programs; and the at least one processor is configured to execute the computer programs or instructions in the memory.

[0049] Optionally, the apparatus further comprises a communication interface. The communication interface is coupled with the processor, and can be used to input information to the processor, or output information in the processor.

[0050] In a sixth aspect, a computer readable storage medium is provided, which stores program codes for execution by an apparatus, and the program codes comprise codes for performing the method in any possible implementation of the first aspect or the second aspect.

[0051] In a seventh aspect, a computer program product containing instructions which, when the computer program product runs on a computer, enables the computer to perform the method in any possible implementation of the first aspect or the second aspect.

[0052] In an eighth aspect, a chip is provided, which comprises a processor and a communication interface. The processor reads instructions on the memory through the communication interface, and performs the method in any possible implementation of the first aspect or the second aspect.

[0053] Optionally, as an implementation manner, the chip further comprises a memory, the memory storing a computer program or instructions, and the processor is configured to execute the computer program or instructions stored on the memory, and when the computer program or instructions are executed, the processor is configured to execute the method provided by any of the implementation manners of the method in the first aspect or the second aspect.

[0054] In a ninth aspect, a computer program product comprising instructions which, when the computer program product is executed on a computer, cause the computer to carry out the method provided by any of the implementation manners of the first aspect.

[0055] In a tenth aspect, a communication system is provided, comprising one or more of the first device and the second device, wherein the first device is configured to implement the method provided by the first aspect and any possible implementation manner of the first aspect; and the second device is configured to implement the method provided by the second aspect and any possible implementation manner of the second aspect. BRIEF DESCRIPTION OF DRAWINGS

[0056] FIG. 1 is a schematic diagram of a wireless communication system suitable for embodiments of the present application.

[0057] FIG. 2 is a schematic diagram of a method for obtaining a deterministic part of a multipath based on a predicted multipath.

[0058] FIG. 3 is a schematic diagram of a compressed feedback of a frequency domain channel.

[0059] FIG. 4 is a schematic flowchart of a communication method provided by embodiments of the present application.

[0060] FIG. 5 is a schematic diagram of a model library suitable for embodiments of the present application.

[0061] FIG. 6 is a schematic diagram of selecting a model suitable for embodiments of the present application.

[0062] FIG. 7 is a schematic diagram of a model of a radio map suitable for embodiments of the present application.

[0063] FIG. 8 is a schematic flowchart of another communication method provided by embodiments of the present application.

[0064] FIG. 9 is a schematic diagram of a communication apparatus 900 provided by embodiments of the present application.

[0065] FIG. 10 is a schematic diagram of another communication apparatus 1000 provided by embodiments of the present application.

[0066] FIG. 11 is a schematic diagram of another communication apparatus 1100 provided by embodiments of the present application. DETAILED DESCRIPTION

[0067] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0068] The technical solutions provided in the present application can be applied to various communication systems, for example, a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, and the like. The technical solutions provided in the present application can also be applied to future communication systems. The technical solutions provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and internet of things (IoT) communication systems. The technical solutions provided in the present application can also be applied to low-frequency scenarios, high-frequency scenarios, terahertz, optical communication, licensed frequency bands, and unlicensed frequency bands, and the like. The technical solutions provided in the present application can also be applied to non-terrestrial network (NTN) systems such as inter-satellite communication and satellite communication. As an example, a satellite communication system includes a satellite base station and a terminal device. The satellite base station provides communication services for the terminal device. The satellite base station can also communicate with a base station. The satellite can act as a base station or a terminal device. The satellite can refer to a drone, a hot air balloon, a low-orbit satellite, a medium-orbit satellite, a high-orbit satellite, and the like. The satellite can also refer to a non-ground base station or a non-ground device, and the like.

[0069] A device in a communication system can send a signal to another device or receive a signal from another device. The signal can include information, signaling, or data, and the like. The device can be replaced by an entity, a network entity, a network element, a communication device, a communication module, a node, a communication node, and the like. The present disclosure describes the device as an example. For example, the communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device.

[0070] The terminal device in the embodiments of the present application includes various devices with wireless communication functions, which can be used to connect people, things, machines, etc. The terminal device can be widely used in various scenarios, such as: cellular communication, D2D, V2X, peer to peer, M2M, MTC, IoT, virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, intelligent transportation, smart city unmanned aerial vehicle, robot, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery, etc. The terminal device can be a terminal in any of the above scenarios, such as an MTC terminal, an IoT terminal, etc. The terminal device can be a user equipment (UE) of the 3rd generation partnership project (3GPP) standard, a terminal, a fixed device, a mobile station device or a mobile device, a subscriber unit, a handheld device, a vehicle-mounted device, a wearable device, a cellular phone, a smart phone, a session initiation protocol (SIP) phone, a wireless data card, a personal digital assistant (PDA), a computer, a tablet computer, a notebook computer, a wireless modem, a handset, a laptop computer, a computer with wireless transceiver function, a smart book, a vehicle, a satellite, a global positioning system (GPS) device, a target tracking device, an aircraft (such as a drone, a helicopter, a multi-helicopter, a four-helicopter, or an airplane, etc.), a ship, a remote control device, a smart home device, an industrial device, or a device built-in in the above devices (such as a communication module, a modem or a chip in the above devices, etc.), or other processing devices connected to the wireless modem. For the sake of convenience, the terminal device will be described below by taking a terminal or a user as an example.

[0071] It should be understood that in some scenarios, the UE can also be used to act as a base station. For example, the UE can act as a scheduling entity, which provides sidelink signals between UEs in V2X, D2D or peer to peer scenarios, etc.

[0072] In the embodiments of the present application, the device for implementing the function of the terminal device, i.e., the terminal device, can be a terminal device or a device capable of supporting the terminal device to implement the function, such as a chip system or a chip, which can be installed in the terminal device. In the embodiments of the present application, the chip system can be composed of a chip or can include a chip and other discrete devices.

[0073] The network device in the embodiments of the present application can be a device for communicating with the terminal device, which can also be referred to as an access network device or a radio access network device, such as a network device, which can be a base station. The network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) for accessing the terminal device to a wireless network. The base station can broadly cover various names in the following or be replaced by the following names, such as: Node B (NodeB), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmission point, primary station, secondary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit. The base station can be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station can also refer to a communication module, modem or chip for being arranged in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device assuming a base station function in D2D, V2X, M2M communication, a network side device in a future network, a device assuming a base station function in a future communication system, etc. The base station can support networks of the same or different access technologies. The embodiments of the present application do not limit the specific technologies and specific device forms adopted by the network device.

[0074] In some deployments, the network device mentioned in embodiments of the application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the network device can include a gNB-CU-CP, a gNB-CU-UP and a gNB-DU.

[0075] In some deployments, wireless access is assisted by multiple RAN nodes cooperating to serve a terminal, and different RAN nodes respectively implement part of the functions of a base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can also be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, an AAU or an RRH.

[0076] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, the radio access network can also be an open radio access network (O-RAN) architecture, and in the O-RAN system, the CU can also be referred to as an open CU (O-CU), the DU can also be referred to as an open DU (O-DU), the CU-CP can also be referred to as an open CU-CP (O-CU-CP), the CU-UP can also be referred to as an open CU-UP (O-CU-UP), and the RU can also be referred to as an open RU (O-RU). Any of the CU (or CU-CP, CU-UP), DU and RU in the present application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0077] The base station can be fixed, or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station. In other examples, the helicopter or the drone can be configured to act as a device that communicates with another base station.

[0078] In an embodiment of the present application, the apparatus for implementing the function of the network device can be a network device, or can be an apparatus capable of supporting the network device to implement the function, such as a chip system or a chip, which can be installed in the network device. In an embodiment of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices. In an embodiment of the present application, only the apparatus for implementing the function of the network device is taken as an example of the network device, and the scheme of the embodiment of the present application is not limited.

[0079] The network device and the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water surface; and can also be deployed on aircraft, balloons and satellites in the air. The scenario where the network device and the terminal device are located is not limited in the embodiments of the present application. In addition, the terminal device and the network device can be hardware devices, or can be software functions running on special hardware, software functions running on general hardware, such as virtualized functions instantiated on a platform (for example, a cloud platform), or entities including special or general hardware devices and software functions. The specific form of the terminal device and the network device is not limited in the present application.

[0080] In addition, in order to support artificial intelligence (AI) technology in the wireless network, an AI node can also be introduced into the network.

[0081] Optionally, the AI node can be deployed in one or more of the following positions in the communication system: an access network device, a terminal device, or a core network device, etc., or the AI node can also be deployed separately, for example, deployed in a position other than any of the above devices, such as a host or a cloud server of an over the top (OTT) system. The AI node can communicate with other devices in the communication system, which can be one or more of the following: a network device, a terminal device, or a network element of a core network, etc.

[0082] It can be understood that the number of AI nodes is not limited in the present application. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes responsible for different functions.

[0083] It can also be understood that the AI node can be a device independent of each other, or can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or can be a software function running on special hardware, or can be a virtualized function instantiated on a platform (for example, a cloud platform), and the specific form of the AI node is not limited in the present application.

[0084] The AI node can be an AI network element or an AI module.

[0085] First, a communication system suitable for the embodiments of the present application is briefly introduced as follows.

[0086] Referring to FIG. 1, FIG. 1 is a schematic diagram of a wireless communication system suitable for the embodiments of the present application.

[0087] As shown in FIG. 1, the wireless communication system includes a radio access network 100. The radio access network 100 can be a future radio access network, or a traditional (for example, 5G, 4G, 3G or 2G) radio access network. One or more terminal devices (120a-120j, collectively referred to as 120) can be connected to each other or to one or more network devices (110a, 110b, collectively referred to as 110) in the radio access network 100. The network elements in the wireless communication system are connected through interfaces (for example, NG, Xn), or air interfaces. In addition, one or more AI modules can be arranged in each network element in the wireless communication system. The AI modules deployed in different network elements can be the same or different.

[0088] FIG. 1 is only a schematic diagram, and the wireless communication system can also include other devices, such as core network devices, wireless relay devices, and / or wireless backhaul devices, etc., which are not shown in FIG. 1.

[0089] In order to better understand the technical solutions of the present application, some related technologies related to the technical solutions of the present application are introduced.

[0090] 1. Multipath propagation

[0091] Multipath propagation refers to the fact that a signal in a wireless propagation environment reaches a receiving antenna after being transmitted through multiple (two or more) paths. Among them, the multipath is mainly caused by the reflection, refraction, scattering or diffraction of electromagnetic waves by objects in the environment. The signals through different paths have different time delays and phases, and the receiving antenna receives the superposition of these multipath signals. The time delay spread of multipath causes inter-symbol interference. The amplitude and phase of the received signal change due to multipath transmission, resulting in signal fading and distortion. Although multipath can bring these problems to the communication system, multipath also increases the space division multiplexing stream number of the communication system. Therefore, it is crucial to predict the multipath in the wireless propagation environment to improve the service capability of the communication system. Predicting multipath means predicting the possible multipath characteristics of a terminal communication device when communicating with a certain base station at a certain spatial location, such as the number of paths, the strength of the paths, the angle of the paths, the time delay spread of the multipath, the angle spread of the multipath, etc.

[0092] One possible method for predicting multipath is to model the real environment in a virtual physical world, as much as possible to restore the size, position and material of objects in the real world. By placing network devices and terminal devices in the virtual physical world at the positions where multipath is desired to be predicted, and then using ray-tracing method to simulate the multipath of the transmission signal between the network devices and the terminal devices; or an artificial intelligence (AI) neural network model can be used to process environmental information to obtain the multipath of the transmission signal between the network devices and the terminal devices.

[0093] Referring to FIG. 2, FIG. 2 is a schematic diagram of obtaining the deterministic part of the multipath based on the above-mentioned method for predicting multipath. As can be seen from FIG. 2, based on the radio map combined with ray-tracing or AI simulation, the deterministic part of the multipath can be obtained, and the phase part of the multipath cannot be obtained. Although the multipath component (MPC) including the number of multipaths, the strength of the multipath, the angle of the multipath, and the time delay of the multipath can be obtained, the phase of each path cannot be obtained by simulation. Among them, the phase of the path changes with the change of the wavelength level in the environment, but the position of the communication device and the environmental information cannot be accurately determined to the wavelength level, so the phase of the multipath in the actual scene cannot be obtained by simulation. Similarly, the frequency shift, time offset, frequency offset, and instantaneous channel error of the communication channel may also not be obtained by simulation. At the same time, these information (especially the phase of the path) has a great influence on the characteristic mode between the communication devices, and further affects the accuracy of the channel information.

[0094] Referring to FIG. 3, FIG. 3 is a schematic diagram of compressively feeding back the frequency domain channel. As can be seen from FIG. 3, after the frequency domain channel information is quantitatively compressed by an encoder, it is converted into bits to be fed back (for example, 010100111001, 11001111001), and the original frequency domain channel information can be restored by decoding (decoder) at the receiving end. At present, the AI or preset codebook method is mainly used to compressively feed back the channel information, but it mainly processes the channel in the frequency domain. The dimension of the frequency domain channel increases with the increase of the number of antennas and the number of bands, and different communication parameters need to be processed in different ways, resulting in poor generalization of the compression feedback method. At the same time, in order to feed back the frequency domain channel, the compression feedback method shown in FIG. 3 needs to measure the frequency domain channel, resulting in a large overhead of the pilot.

[0095] Therefore, the present application proposes a method for reconstructing the actual channel by combining the deterministic part of the multipath and the channel measurement result based on the channel model, thereby improving the accuracy of the reconstructed wireless channel.

[0096] Before introducing the scheme of the present application, the following points are explained.

[0097] (1) In the present application, "indication" can include direct indication, indirect indication, explicit indication, and implicit indication. When it is described that certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A.

[0098] In the present application, the information indicated by the indication information is referred to as to-be-indicated information. In the implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol), thereby reducing the indication overhead to a certain extent. In addition, the to-be-indicated information can be sent as a whole, or can be sent separately into multiple sub-information, and the sending period and / or sending time of these sub-information can be the same or different.

[0099] (2) In the present application, "sending" and "receiving" represent the direction of signal transmission. For example, "sending information to XX" can be understood as that the destination of the information is XX, which can include direct sending through the air interface, or indirect sending through the air interface by other units or modules. "Receiving information from YY" can be understood as that the source of the information is YY, which can include direct receiving from YY through the air interface, or indirect receiving from YY through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface. In other words, sending and receiving can be carried out between devices, for example, between network devices and terminal devices, or can be carried out within a device, for example, between components, modules, chips, software modules or hardware modules within a device through a bus, wire or interface. In addition, in the case where it is not specifically stated, "transmission" includes receiving and / or sending. For example, transmitting a signal can include receiving a signal and / or sending a signal.

[0100] (3) In the present application, information C is used for the determination of information D, which includes that information D is determined based on information C, and includes that information D is determined based on information C and other information. In addition, information C can also be used for the determination of information D in an indirect determination manner, such as the case where information D is determined based on information E, and information E is determined based on information C.

[0101] (4) The terms "comprising" and "including," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, product or apparatus that comprises a list of steps or elements not expressly listed is not excluded from equivalence as long as other steps or elements do not alter the basic functionality of the process, method, system, product or apparatus.

[0102] (5) In each of the embodiments of the present application, the terms and / or descriptions in different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0103] (6) In the present application, "first", "second" are only convenient for description, used for distinguishing objects, and not used for limiting the scope of the embodiments of the present application. It is not used to describe the order or sequence of characteristics. It should be understood that the objects thus described can be interchanged under appropriate circumstances, so as to be able to describe the schemes other than the embodiments of the present application.

[0104] (7) In the present application, "predefined" can mean standard protocol predefined, or can also mean pre-agreed or pre-negotiated between devices.

[0105] The method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments provided by the present application can be applied to the communication system shown in Figure 1, without limitation.

[0106] Referring to Figure 4, Figure 4 is a schematic flow chart of a communication method provided by an embodiment of the present application. As shown in the method of Figure 4, the method can include the following steps:

[0107] 401, the first device determines configuration information.

[0108] It should be understood that the configuration information is used to indicate information of M models corresponding to M weights (or scores), and the M models and the M weights can be used to reconstruct a wireless channel, and M is an integer greater than or equal to 1.

[0109] In a possible implementation manner, the first device and the second device can be predefined or preconfigured with a model library by the system, which can be referred to as a channel expert knowledge (CEK) model library. As shown in FIG. 5, the model library can include information of at least one model, which includes M models. For example, the model library includes information such as a serial number corresponding to the at least one model, specific content corresponding to the at least one model, and a tunable variable corresponding to the at least one model. Two models are exemplarily introduced in FIG. 5, where the model library can include a model corresponding to serial number 0 and a model corresponding to serial number 1. The model corresponding to serial number 0 is a model based on a formula (or referred to as a tunable time-frequency domain conversion expert knowledge model, or referred to as a CEK model), where variables involved in the formula can be tuned in the process of matching an actual channel. The model corresponding to serial number 1 is a model based on a channel impulse response (CIR) self-supervised neural network, where a variable parameter in the neural network can be tuned in the process of matching the actual channel.

[0110] Taking the model corresponding to serial number 0 as an example, updating the tunable CIR is updating the variable parameter, to obtain an updated CIR, that is, a reconstructed CIR. A reconstructed channel frequency response (CFR) satisfies:

[0111] where CIR n The CIR can be calculated by multipath component (MPC) and antenna information through the following formula, for example:

[0112] It should be understood that the model corresponding to serial number 0 is from the 38.901 standard document, and detailed parameter introduction and parameter determination process can be referred to the detailed introduction in the existing document. In addition, the model library can also include other models in the existing document, which is not limited by the present application.

[0113] where CFR represents the reconstructed CFR, n represents the number of multipaths, f represents the carrier frequency, and τ represents the time delay information of the multipath. CIR represents a time domain channel, and CFR represents a frequency domain channel. The above formula can be understood as a process of transforming the time domain channel to the frequency domain channel. CFR is a method for describing how the frequency components of a signal change from the sending end to the receiving end on a specific transmission medium. CFR reflects the amplification or attenuation ability of a communication channel to different frequency signals, and affects the quality of the signal and the reliability of the communication. CIR represents the response of a unit impulse signal after passing through a system. The tunable CIR can be represented as CIR B*N*R*TThe variable parameters include B (the number of samples), N (the number of multipaths), R (the number of receiving antennas), and T (the number of transmitting antennas).

[0114] Taking the model corresponding to the serial number 1 as an example, the CIR-based self-supervised neural network model can include an encoding module and a decoding module, which can be a pre-trained network, that is, the data input into the self-supervised neural network can also be used as the output of the self-supervised neural network. The encoding module is used to quantitatively compress the CIR, and the decoding module is used to reconstruct the CIR. Specifically, the encoding module can be used to compress the variable CIR to obtain intermediate information, and the decoding module is used to output the reconstructed CIR. That is, the self-supervised neural network is used to compress the variable CIR into an intermediate representation, and then reconstruct the CIR using the intermediate representation, to realize the compression and reconstruction process.

[0115] Similarly, the model library can also include a plurality of (for example, hundreds or thousands of) models, and the models included in the model library can approximate the actual channel. Specifically, the specific models included in the model library will not be enumerated one by one.

[0116] It should be understood that the configuration information is used to indicate the information of the M models, and the information used to indicate the M models can include the specific content of the M models and the serial number corresponding to each model in the M models. The configuration information is used to align the models in the model library and the serial numbers corresponding to the models between the first device and the second device.

[0117] As an example, the configuration information is used to indicate the information of the M models, and the form of the information used to indicate the M models can be as shown in Table 1:

[0118] Table 1

[0119] In Table 1, the models in the model configuration table #1 can be models used in urban environments, and the models in the model configuration table #2 can be models used in rural environments. The model configuration table #3 can also be included in Table 1, and the models in the model configuration table #3 can be models used in satellite communications, and so on. The present application will not be enumerated one by one.

[0120] In Table 1, the models can also be classified by levels. For example, the models can be classified into two levels of models. For example, the model f1 corresponding to the serial number 1 included in the model configuration table #1 in Table 1 can be understood as a model of a certain type, which can be a first-level model; the model f 1，1 It can be understood as a specific model in a certain type of model, which can be a second-level model.

[0121] It should be understood that the above Table 1 is only an example given for the convenience of understanding, and other schemes are not excluded. The present application does not limit the number of corresponding relationships in the above Table 1 (for example, a row in the table), for example, one or more rows can be added or reduced. Alternatively, Table 1 can also be split into multiple independent tables, and the present application does not limit the splitting manner, for example, the model number and the model configuration table #1 can be independently formed into a new table, and the model number and the model configuration table #2 can be independently formed into a new table.

[0122] It should also be understood that the configuration information used to indicate the information of the M models and the mapping relationship between the M model numbers and the M models can also be implemented by code, function, text, string or other methods that can be used to indicate related information (for example, the information of the M models), and the present application does not limit the specific implementation manner.

[0123] It should be understood that the first device can send the currently adopted model configuration table and the model numbers corresponding to each model in the model configuration table to the second device through the configuration information, and correspondingly, the second device determines the optional model and the serial number corresponding to the optional model according to the configuration information after receiving the configuration information.

[0124] It should also be understood that the first device or the second device can select one or more models from the above model library that can best approximate the real channel, and the one or more models can constitute (or be referred to as constitute) at least one model combination (or be referred to as model set).

[0125] In a possible implementation manner, taking the first device side as an example, the first device can select one or more models that can best approximate the real channel from a plurality of models by selecting a model (for example, a first selected model). As shown in FIG. 6, the selected model can be understood as a function ω(y) about y, where y can be one or more of the current area identity (ID) of the second device, the device type of the second device, the communication parameter (for example, frequency point, antenna configuration) of the second device, and the like, and ω can be based on any algorithm (such as formula or neural network, etc.), and ω(y) represents the output of the "selected model", that is, the selected model, and each model f i Corresponding weight ω(y) i The final reconstructed channel frequency response (CFR) result is the result of mixing a plurality of models, which can be represented as: f(x) = ∑ i ω(y) i f i (x). Wherein, when the selected model ω(y) needs to support the output of two levels of models (such as the models f 1，1) and the case of a fraction, for example, can be expressed as: f(x) = ∑ i ω(y) i ∑ j ω(y) j|i f j|i (x), where i represents the serial number of the first level (for example, i = 1), and j represents the serial number of the second level (for example, j = 1).

[0126] It should also be understood that the first device or the second device determines the model combination according to the selected model, and detailed descriptions of the respective models in the model combination and the weights corresponding to the respective models can be found in Examples 1-4 below, which will not be described here.

[0127] 402, the first device sends configuration information, and the second device receives the configuration information accordingly.

[0128] It should be understood that the configuration information is used to align the models and the serial numbers corresponding to the models between the second device and the first device. After aligning the models and the serial numbers corresponding to the models between the second device and the first device, the second device or the first device can use the model combination composed of at least one aligned model and the weight corresponding to each model in the model combination to reconstruct the wireless channel in the process of reconstructing the channel.

[0129] It should also be understood that the method shown in Figure 4 above can further include:

[0130] The second device sends the capability information of the second device to the first device, and the first device receives the capability information of the second device accordingly.

[0131] It should be understood that this step can be performed before step 401 or before step 402, which is not limited by the present application.

[0132] It should be understood that the capability information can be used to indicate whether the second device supports the capability of selecting the model. For example, the first device receives the capability information of the second device, which is used to indicate that the second device supports the capability of selecting the model, the first device determines that the second device supports the capability of selecting the model, and the first device sends the configuration information to the second device, that is, step 402 is performed.

[0133] In a possible implementation, after the second device is connected to an LTE 4G core network, for example, an evolved packet core (EPC), the second device can send the capability information to the first device to indicate whether the second device can initiate selection of the model (for example, CEK); or after the second device is connected to a 5G core network (5GC), the second device can send the capability information to the first device to indicate whether the second device can initiate selection of the model (for example, CEK).

[0134] As an example, the field corresponding to the capability information can be represented as a UE-Capability field, which can include CEK-EPC and / or CEK-5GC. The CEK-EPC is used to indicate whether the second device can initiate selection of the model after being connected to the EPC, and the CEK-5GC is used to indicate whether the second device can initiate selection of the model after being connected to the 5GC.

[0135] In another possible implementation, the second device sending the capability information of the second device to the first device can be performed before step 401, and accordingly, the first device determines the configuration information according to the capability information of the second device in step 401. The configuration information can also be used to indicate whether the second device initiates the capability supported by the second device, or the configuration information can also indicate that the second device initiates the capability supported by the second device under certain conditions.

[0136] It should be understood that the certain conditions can be preset, preconfigured, predefined, determined by the first device itself, negotiated by the first device and the second device, or determined by the second device and fed back to the first device, which is not limited in the present application.

[0137] As an example, assuming that the capability information of the second device indicates that the second device can initiate selection of the model when being connected to the 5GC or the EPC. The first device indicates in the configuration information that the second device initiates the capability supported by the second device, that is, initiates selection of the model when the second device is connected to the 5GC, based on the capability information of the second device; or the first device indicates in the configuration information that the second device initiates the capability supported by the second device, that is, initiates selection of the model when the second device is connected to the EPC, based on the capability information of the second device.

[0138] Next, the detailed process of the first device and the second device reconstructing the wireless channel will be introduced by way of examples one to four.

[0139] Example one: the first device reconstructs the channel

[0140] After step 402, the method shown in FIG. 4 can further include the following steps:

[0141] 403, the second device sends the first information, and the first device receives the first information accordingly.

[0142] It should be understood that the first information can include one first model combination and at least one first weight. The one first model combination and the at least one first weight are determined by the first selection model according to the first parameter. The one first model combination corresponds to the first parameter, and each of the at least one first weight corresponds to at least one model included in one first model combination.

[0143] The first parameter can include one or more of the following: an identifier of a region where the second device is located, a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device.

[0144] In one possible implementation, the second device inputs the first parameter into the first selection model, and the first selection model outputs one first model combination and at least one first weight according to the first parameter.

[0145] It should be understood that the second device inputs the first parameter into the first selection model, and outputs one first model combination and the at least one first weight through processing of the first selection model. Accordingly, the second device sends the first information including the one first model combination and the at least one first weight to the first device. Details of how the first selection model determines the output of one first model and at least one first weight based on the input of the first parameter can be referred to the detailed description of FIG. 6 above.

[0146] As an example, it is assumed that the second device and the first device can agree in advance that the identification information of the area where the second device is currently located is the first parameter, and determine the model combination and the corresponding weight. The selection model is located at the second device side, and the second device inputs the first parameter into the first selection model, and the first selection model outputs the first model combination and at least one first weight, wherein the first selection model can be an algorithm, a neural network or the like, which is not limited in the present application. In combination with the model information shown in Table 1, the second device can input the identification information of the area where the second device is located into the first selection model, and the first selection model outputs "0-0.5, 1-0.5" after processing, wherein "0" and "1" represent the model serial numbers of the two models included in the first model combination, and the weight corresponding to the model with the model serial number "0" is "0.5", and the weight corresponding to the model with the model serial number "1" is "0.5". The first model combination included in the first information can include the model serial numbers "0" and "1", or the first model combination can include the specific models corresponding to the model serial numbers "0" and "1". The first model information further includes the weights "0.5" corresponding to the model serial numbers "0" and "1" respectively.

[0147] 404, the first device reconstructs the wireless channel.

[0148] It should be understood that after the first device receives the first information, the first device reconstructs the wireless channel according to the first model combination and the at least one first weight in the first information, in combination with the channel measurement result.

[0149] It should also be understood that the channel measurement result can be determined by the second device and sent to the first device. The second device determines the channel measurement result, which can be referred to in other documents for detailed description, and will not be described in detail here.

[0150] In a possible implementation manner, the first device reconstructs the channel according to the first model combination and the at least one first weight in the first information, and the channel measurement result.

[0151] As an example, in combination with the example in step 403 described above, assuming that the first information includes a first model combination of model numbers "0" and "1", and the weight "0.5" corresponding to the model numbers "0" and "1" respectively, the first device can determine, in combination with the above table 1, that the model corresponding to the model number "0" is f0, the model corresponding to the model number "1" is f1, and the weight corresponding to the model f0 and the model f1 is 0.5 respectively, and the sparse measurement result and the MPC can be represented as x. When the second device is located in the range indicated by the area identification information included in the first parameter, the first device can determine the final reconstruction CFR result according to the first information and the channel measurement result, which is the result of the mixing of the two models in the first model combination, and can be represented as: f(x) = [0.5*f1(x)] + [0.5*f0(x)].

[0152] It should be understood that in the above example one, the first device reconstructs the wireless channel according to the one first model combination and the at least one first weight in the first information, and the channel measurement result. Among them, the second device feeds back one first model combination and at least one first weight corresponding to at least one model included in the first model combination, and the first device reconstructs the wireless channel based on at least one model included in the first model combination, at least one first weight and channel measurement result.

[0153] Example two: the first device reconstructs the channel

[0154] After step 402, the method shown in FIG. 4 can further include the following steps:

[0155] 405, the second device sends the first information, and correspondingly, the first device receives the first information.

[0156] It should be understood that the first information can include a plurality of first model combinations and at least one first weight. The plurality of first model combinations and the at least one first weight are determined by the first selection model according to the first parameter, and each first weight in the at least one first weight corresponds to each model included in the plurality of first model combinations one by one.

[0157] Among them, the first parameter can include one or more of the following: the identification of the area where the second device is located, the frequency point of the second device, the antenna configuration parameter of the second device, or the device type of the second device.

[0158] In a possible implementation manner, the second device takes the first parameter as the input of the first selection model, and the first selection model outputs the plurality of first model combinations and the at least one first weight through the first parameter.

[0159] It should be understood that the second device inputs the first parameter as an input of the first selection model, and outputs a plurality of first model combinations and the at least one first weight through processing of the first selection model. Correspondingly, the second device sends the first information including the plurality of first model combinations and the at least one first weight to the first device. Wherein, the detailed introduction of the first selection model outputting the plurality of first model combinations and the at least one first weight based on the input of the first parameter can be referred to the detailed introduction of FIG. 6.

[0160] As an example, it is assumed that the first parameter includes a plurality of region identification information, each region identification information corresponding to a different region. The selection model is located at the second device side, and the second device inputs the plurality of region identification information included in the first parameter into the first selection model, and the first selection model outputs a plurality of first model combinations and at least one first weight, wherein the first selection model can be an algorithm, or a neural network, etc., which is not limited by the present application, and each of the plurality of first model combinations can correspond to each of the plurality of region identification information. As shown in FIG. 7, in combination with the model information shown in Table 1 described above, the plurality of regions corresponding to the plurality of region identification information can be the regions shown in FIG. 7, and the second device can input the identification information of each region in the plurality of regions into the first selection model, and the first selection model outputs the first model combination corresponding to each region in the plurality of regions and the corresponding weight after processing. As shown in FIG. 7, taking the four regions in FIG. 7 as an example, wherein the first model combination and the weight corresponding to region #0 can be "0-0.5, 1-0.5", the first model combination and the weight corresponding to region #1 can be "0-0.25, 2-0.25, 95-0.25, 186-0.25", the first model combination and the weight corresponding to region #2 can be "1-0.1, 5-0.5, 13-0.4", and the first model combination and the weight corresponding to region #3 can be "1-1".

[0161] It should also be understood that in the case where the first information includes the plurality of first model combinations and the at least one first weight, the second device can also send the first parameter to the first device, and the first parameter is used by the first device to determine the model combination and the weight corresponding to the specific parameter.

[0162] 406, the second device sends the first parameter to the first device, and correspondingly, the first device receives the first parameter of the second device.

[0163] Wherein, the specific parameter included in the first parameter is consistent with the parameter input by the second device into the first selection model.

[0164] It should be understood that the first parameter can be transmitted in the same message as the first information in step 405 described above, or transmitted in different messages, which is not limited by the present application.

[0165] 407, the first device reconstructs the wireless channel.

[0166] It should be understood that after the first device receives the first information and the first parameter, the first device determines at least one second model combination and at least one second weight from the plurality of first model combinations and the at least one first weight in the first information according to the first parameter, and reconstructs the wireless channel by combining the at least one second model combination and the at least one second weight with the channel measurement result.

[0167] It should also be understood that the channel measurement result can be determined by the second device and sent to the first device. The second device determining the channel measurement result can be described in detail in other documents, which will not be described in detail here.

[0168] In one possible implementation, the first device reconstructs the channel according to the first parameter, the plurality of first model combinations and the at least one first weight in the first information, and the channel measurement result.

[0169] As an example, in combination with the example in step 405 described above, assuming that the first information includes the plurality of first model combinations and the at least one first weight, the first device selects at least one second model combination from the plurality of first model combinations according to the first parameter, and determines at least one second weight corresponding to at least one model included in the at least one second model combination from the at least one first weight, and reconstructs the wireless channel by combining the channel measurement result.

[0170] Assuming that the first parameter is the area information of the second device, i.e., the second device is located in area #1, the first device determines that the first model combination corresponding to area #1 is first model serial numbers "0", "2", "95" and "186", and the weights corresponding to the model serial numbers "0", "2", "95" and "186" are "0.25" respectively according to the received first information. The first device determines the model corresponding to the model serial number "0" as f0, the model corresponding to the model serial number "2" as f2, the model corresponding to the model serial number "95" as f95, and the model corresponding to the model serial number "186" as f186 from the pre-defined model library. 95 , the model corresponding to the model serial number "186" as f 186 , the model f0, the model f2, f 95 and f 186 respectively are 0.25, and the sparse measurement result and the MPC can be represented as x. When the second device is located in area #1, the first device can finally determine the reconstructed CFR result as the result of mixing two models in the first model combination according to the first information and the channel measurement result, which can be represented as: f(x) = [0.25*f0(x)] + [0.25*f2(x)] + [0.25*f95(x)] + [0.25*f186(x)].

[0171] It should be understood that, in the case that the first parameter is a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device, similar to the case that the first parameter is identification information of a region where the second device is located, examples will not be listed one by one.

[0172] It should be understood that, in the second example, the first device selects, based on the first parameter, at least one second model combination and at least one second weight corresponding to the first parameter, and reconstructs the wireless channel in combination with the channel measurement result.

[0173] It should also be understood that, in the first example and the second example, the at least one first model combination and the at least one first weight are determined by the second device, and it can be seen that the first selected model is located at the second device. Details of how the second device determines the first selected model can be found in the detailed description of FIG. 8 below, and will not be repeated here.

[0174] Example Three: Channel Reconstruction by the Second Device

[0175] After step 402, the method shown in FIG. 4 can further include the following steps:

[0176] 408. The first device sends second information, and the second device correspondingly receives the second information.

[0177] It should be understood that the second information can include one first model combination and at least one first weight. The one first model combination and the at least one first weight are determined by the first selected model based on the first parameter. The one first model combination corresponds to the first parameter, and each of the at least one first weight corresponds to at least one model included in the one first model combination.

[0178] The first parameter includes one or more of the following: identification of a region where the second device is located, a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device.

[0179] In a possible implementation manner, the first device inputs the first parameter into the first selected model, and the first selected model determines one first model combination and at least one first weight based on the input of the first parameter.

[0180] It should be understood that the first device inputs the first parameter into the first selected model, and the first selected model outputs one first model combination and the at least one first weight after processing. Correspondingly, the first device sends second information including the one first model combination and the at least one first weight to the second device. Details of how the first selected model determines the output of one first model and at least one first weight based on the input of the first parameter can be found in the detailed description of FIG. 6 above.

[0181] It should also be understood that the first device determines a first model combination and at least one first weight based on the first selection model, which is similar to the step 403 in the above example one, and the specific example can be referred to the description of the step 403 above, which will not be repeated here.

[0182] 409, the second device reconstructs the wireless channel.

[0183] It should be understood that after the second device receives the second information, the second device reconstructs the wireless channel according to a first model combination and at least one first weight in the second information and the channel measurement result.

[0184] It should also be understood that the channel measurement result can be determined by the second device itself. The second device determining the channel measurement result can be referred to the detailed description in other documents, which will not be repeated here.

[0185] It should also be understood that the second device reconstructs the channel according to the first model combination and at least one first weight in the second information and the channel measurement result. This is similar to the step 404 in the above example one, and the specific example can be referred to the description of the step 404 above, which will not be repeated here.

[0186] It should be understood that the second device reconstructs the wireless channel according to the first model combination and at least one first weight in the second information and the channel measurement result in the above example three. The first device feeds back a first model combination and at least one first weight corresponding to at least one model included in the first model combination, and the second device reconstructs the wireless channel based on at least one model included in the first model combination, at least one first weight and the channel measurement result.

[0187] Example four: the second device reconstructs the channel

[0188] After the step 402, the method shown in the figure 4 can further include the following steps:

[0189] 410, the first device sends the second information, and correspondingly, the second device receives the second information.

[0190] It should be understood that the second information can include a plurality of first model combinations and at least one first weight. The plurality of first model combinations and at least one first weight are determined by the first selection model according to the first parameter, and each first weight in the at least one first weight corresponds to each model included in the plurality of first model combinations.

[0191] The first parameter includes one or more of the following: an identifier of a region where the second device is located, a frequency point of the second device, an antenna configuration parameter of the second device, or a device type of the second device.

[0192] In a possible implementation, the first device inputs the first parameter into a first selection model, and the first selection model determines a plurality of first model combinations and at least one first weight based on the first parameter.

[0193] It should be understood that the first device inputs the first parameter into the first selection model, and the first selection model outputs the plurality of first model combinations and the at least one first weight after processing. Accordingly, the first device sends second information including the plurality of first model combinations and the at least one first weight to the second device. The detailed description of how the first selection model outputs the plurality of first model combinations and the at least one first weight based on the input of the first parameter can be referred to the detailed description of FIG. 6.

[0194] It should also be understood that the first device determines the plurality of first model combinations and the at least one first weight based on the first selection model, which is similar to the step 405 in Example II in which the second device determines the plurality of first model combinations and the at least one first weight based on the first selection model. The specific example can be referred to the description of the step 405, which will not be repeated here.

[0195] It should also be understood that, when the second information includes the plurality of first model combinations and the at least one first weight, the first device can further send the first parameter to the second device, where the first parameter is used by the second device to determine the model combination and the weight corresponding to the specific parameter.

[0196] 411. The first device sends the first parameter to the second device, and accordingly, the second device receives the first parameter from the first device.

[0197] The specific parameter included in the first parameter is consistent with the parameter input into the first selection model by the first device.

[0198] It should be understood that the first parameter can be transmitted in the same message as the first information in the step 410, or transmitted in different messages, which is not limited in the present application.

[0199] 412. The second device reconstructs the wireless channel.

[0200] It should be understood that, after receiving the second information and the first parameter, the second device determines at least one second model combination and at least one second weight from the plurality of first model combinations and the at least one first weight in the second information based on the first parameter, and reconstructs the wireless channel by combining the at least one second model combination and the at least one second weight with the channel measurement result.

[0201] It should also be understood that the channel measurement result can be determined by the second device itself. The second device determining the channel measurement result can be referred to detailed description in other files, which will not be repeated here.

[0202] It should also be understood that the second device determines at least one second model combination and at least one second weight from the plurality of first model combinations and the at least one first weight in the second information according to the first parameter, and reconstructs the specific example of the channel by combining the at least one second model combination and the at least one second weight with the channel measurement result, which is similar to step 407 in the above-mentioned example two, and can be referred to detailed description in the above-mentioned step 407.

[0203] It should be understood that in the above-mentioned example four, the second device selects the corresponding model combination (for example, at least one second model combination) and weight (for example, at least one second weight) based on the first parameter, and reconstructs the wireless channel by combining the channel measurement result.

[0204] It should also be understood that in the above-mentioned example three and example four, the first device determines the at least one first model combination and the at least one first weight, and it can be seen that the first selected model is located at the first device side. Detailed description of how the first device determines the first selected model can be referred to detailed description of the following figure 8, which will not be repeated here.

[0205] Referring to FIG. 8, FIG. 8 is a flowchart of another communication method provided by the embodiments of the present application.

[0206] It should be understood that the first communication device in the above-mentioned figure 8 can be the second device, and the second communication device can be the first device, or the first communication device can be the first device, and the second communication device can be the second device.

[0207] Assuming that the first communication device is the second device and the second communication device is the first device, the method shown in the above-mentioned figure 8 can be regarded as that the selected model is located at the second device side, and the second device trains the selected model and obtains the first selected model, which is used for subsequent implementation of the method shown in the above-mentioned example one and two in the above-mentioned figure 4. Assuming that the first communication device is the first device and the second communication device is the second device, the method shown in the above-mentioned figure 8 can be regarded as that the selected model is located at the first device side, and the first device trains the selected model and obtains the first selected model, which is used for subsequent implementation of the method shown in the above-mentioned example three and four in the above-mentioned figure 4.

[0208] The method shown in the above-mentioned figure 8 can include the following steps:

[0209] 801, the first communication device sends at least one third model combination and at least one third weight to the second communication device, and correspondingly, the second communication device receives at least one third model combination and at least one third weight.

[0210] The at least one third model combination is determined by the first communication device according to the second selected model and a first parameter, and one model in the at least one third model combination corresponds to one third weight in the at least one third weight.

[0211] It should be understood that the first parameter can be determined by the first communication device itself or received from the second communication device, which is not limited in the present application.

[0212] It should be further understood that before step 801, the method can further include:

[0213] The second communication device sends the first parameter, and correspondingly, the first communication device receives the first parameter.

[0214] It should be understood that the first parameter includes one or more of the following: an identifier of an area where the first communication device is located, a frequency point of the first communication device, an antenna configuration parameter of the first communication device, or a device type of the first communication device.

[0215] It should be further understood that after the first communication device receives the first parameter, the first communication device takes the first parameter as an input of the second selected model to obtain the at least one third model combination and the at least one third weight.

[0216] It should be further understood that before the second communication device sends the first parameter to the first communication device, the method shown in FIG. 8 can further include that the first communication device starts training the selected model. The first communication device starting to train the model can be an internal operation of the first communication device, i.e., this step is an optional operation in the flowchart.

[0217] 802, the second communication device sends information for indicating the reconstruction loss to the first communication device, and correspondingly, the first communication device receives the information for indicating the reconstruction loss from the second communication device.

[0218] For example, after the second communication device receives the at least one third model combination and the at least one third weight, the second communication device reconstructs the wireless channel according to the at least one third model combination and the at least one third weight, and determines a reconstruction loss between the reconstructed wireless channel and the actual channel. The second communication device indicates the calculated reconstruction loss to the first communication device through the information for indicating the reconstruction loss.

[0219] As an example, assuming that the actual channel is CFR, the second communication device reconstructs the channel based on at least one third model combination and at least one third weight, and the reconstructed channel is CFR', based on the actual channel and the reconstructed channel, the second network device can determine the reconstruction loss as: Loss = f(CFR, CFR'), where Loss represents a weighted sum, the function f can be a function of calculating a normalized mean squared error (NMSE) or a correlation of CFR and CFR', or the like, the reconstruction loss represents a difference between the actual channel and the reconstructed channel, and the second communication device can indicate information indicating the reconstruction loss to the first communication device.

[0220] 803, the first communication device trains the second selected model according to the information indicating the reconstruction loss, and determines the first selected model.

[0221] For example, after the first communication device receives the information indicating the reconstruction loss, the first communication device trains the second selected model in combination with the information indicating the reconstruction loss, for example, adjusts the parameters, model architecture or algorithm in the second selected model, and reduces the reconstruction loss.

[0222] In a possible implementation manner, the first communication device trains the second selected model according to the information indicating the reconstruction loss, and the first communication device determines that the second selected model after training has overcome the reconstruction loss, that is, the first communication device can use the trained second selected model (or referred to as the first selected model) for subsequent determination of at least one first model combination and at least one first weight in the method shown in FIG. 4.

[0223] In another implementation manner, the first communication device trains the second selection model according to the information indicating the reconstruction loss, inputs the first parameters into the trained second selection model, obtains a new at least one third model combination and a new at least one third weight, and sends the new at least one third model combination and the new at least one third weight to the second communication device again. The second communication device determines the reconstruction loss between the reconstructed channel and the actual channel again based on the new at least one third model combination and the new at least one third weight, and feeds back the information indicating the reconstruction loss to the first communication device. Assuming that the first communication device receives the information indicating the reconstruction loss, and determines that the reconstruction loss satisfies a first condition, the first communication device can use the trained second selection model as the first selection model for subsequent determination of the at least one first model combination and the at least one first weight in the method shown in FIG. 4. Assuming that the first communication device receives the information indicating the reconstruction loss, and determines that the reconstruction loss does not satisfy the first condition, the first communication device continues to train the trained second selection model based on the information indicating the reconstruction loss until the second selection model output by the training satisfies the first condition, and then uses the second selection model satisfying the first condition as the first selection model for subsequent determination of the at least one first model combination and the at least one first weight in the method shown in FIG. 4.

[0224] It should be understood that the first condition can be predefined or preconfigured by a system or a protocol, and the present application does not limit the same. The specific content of the first condition can be related to a threshold of the reconstruction loss, or related to other parameters, and the present application does not limit the same.

[0225] The above describes the method provided by the embodiments of the present application in detail in combination with FIGS. 4 to 8. The following describes the apparatus provided by the embodiments of the present application in combination with FIGS. 9 to 11. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments, and therefore, the content not described in detail can be referred to the method embodiments described above, and will not be described here for brevity.

[0226] Referring to FIG. 9, FIG. 9 is a schematic diagram of a communication apparatus 900 provided by an embodiment of the present application. The apparatus 900 includes a transceiver unit 910. The transceiver unit 910 can be used to implement corresponding communication functions. The transceiver unit 910 can also be referred to as a communication interface or a communication unit. Optionally, the apparatus 900 further includes a processing unit 920. The processing unit 920 can be used for processing, such as reconstruction of a wireless channel.

[0227] Optionally, the apparatus 900 further includes a storage unit, which can be used to store instructions and / or data. The processing unit 920 can read the instructions and / or data in the storage unit to cause the apparatus to implement the foregoing method embodiments.

[0228] Optionally, the transceiver unit 910 can include a receiving unit and a sending unit. The receiving unit can be used to perform operations related to receiving (e.g., operations of receiving data or messages), and the sending unit can be used to perform operations related to sending (e.g., operations of sending data or messages).

[0229] In a first possible design, the apparatus 900 can be the first device in the foregoing embodiments, and the apparatus 900 can implement steps or procedures corresponding to those performed by the first device in the foregoing method embodiments. The transceiver unit 910 can be used to perform operations related to sending and / or receiving (e.g., operations of sending and / or receiving data or messages) by the first device in the foregoing method embodiments, e.g., the transceiver unit 910 can be used to perform operations related to sending and / or receiving by the first device in the embodiments of FIGS. 4-8. The processing unit 920 can be used to perform operations related to processing or operations other than sending and / or receiving (e.g., operations other than sending and / or receiving data or messages) by the first device in the foregoing method embodiments, e.g., the processing unit 920 can be used to perform operations related to processing by the first device in the embodiments of FIGS. 4-8.

[0230] In one possible implementation, the processing unit 920 is configured to determine configuration information, the configuration information being used to indicate M models, the M models being in one-to-one correspondence with M weights, the M models and the M weights being used to reconstruct a wireless channel, M being an integer greater than or equal to 1; and the receiving unit 910 is configured to send the configuration information.

[0231] In a second possible design, the apparatus 900 can be the second device in the foregoing embodiments, and the apparatus 900 can implement steps or procedures corresponding to those performed by the second device in the foregoing method embodiments. The transceiver unit 910 can be used to perform operations related to sending and / or receiving (e.g., operations of sending and / or receiving data or messages) by the second device in the foregoing method embodiments, e.g., the transceiver unit 910 can be used to perform operations related to sending and / or receiving by the second device in the embodiments of FIGS. 4-8. The processing unit 920 can be used to perform operations related to processing or operations other than sending and / or receiving (e.g., operations other than sending and / or receiving data or messages) by the second device in the foregoing method embodiments, e.g., the processing unit 920 can be used to perform operations related to processing by the second device in the embodiments of FIGS. 4-8.

[0232] In a possible implementation, the receiving unit 910 is configured to receive configuration information, where the configuration information is used to indicate M models, the M models correspond to M weights one by one, and the M models and the M weights are used to reconstruct a wireless channel, where M is an integer greater than or equal to 1.

[0233] It should be understood that the specific process in which each unit performs the corresponding steps described above has been described in detail in the method embodiments described above, and for the sake of brevity, will not be repeated here.

[0234] It should also be understood that the apparatus 900 herein is embodied in the form of functional units. The term "unit" herein can refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (for example, a shared processor, a dedicated processor, or a group processor, etc.) and a memory for executing one or more software or firmware programs, a combination of logical circuits, and / or other suitable components that support the described functions. In an optional example, those skilled in the art can understand that the apparatus 900 can be embodied as the communication device in the above embodiments, and can be used to perform the processes and / or steps corresponding to the communication device in each of the method embodiments described above. To avoid repetition, they will not be repeated here.

[0235] The apparatus 900 of each of the above schemes has the function of implementing the corresponding steps performed by the communication device in the above method. The function can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (for example, the transmitting unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as the processing unit, can be replaced by a processor, which respectively performs the transceiving operations and related processing operations in each of the method embodiments.

[0236] In addition, the transceiver unit 910 described above can also be a transceiver circuit (for example, it can include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit.

[0237] It should be noted that the apparatus in FIG. 9 can be a communication device in the above embodiments, or a chip or a chip system, for example, a system on chip (SoC). Wherein, the transceiver unit can be an input / output circuit, a communication interface; the processing unit is a processor or microprocessor or integrated circuit integrated on the chip. Not limited here.

[0238] Referring to FIG. 10, FIG. 10 is a schematic diagram of another apparatus 1000 according to an embodiment of the present application. The apparatus 1000 includes a processor 1010, and the processor 1010 is coupled to a memory 1020. The memory 1020 is configured to store computer programs or instructions and / or data. The processor 1010 is configured to execute the computer programs or instructions stored in the memory 1020, or read the data stored in the memory 1020, to perform the methods in the above method embodiments.

[0239] Optionally, the processor 1010 is one or more.

[0240] Optionally, the memory 1020 is one or more.

[0241] Optionally, the memory 1020 is integrated with the processor 1010, or is separately arranged.

[0242] Optionally, as shown in FIG. 10, the apparatus 1000 further includes a transceiver 1030, which is configured to receive and / or send signals. For example, the processor 1010 is configured to control the transceiver 1030 to receive and / or send signals.

[0243] For example, the processor 1010 can have the functions of the processing unit 900 shown in FIG. 9, the memory 1020 can have the functions of a storage unit, and the transceiver 1030 can have the functions of the transceiving unit 910 shown in FIG. 9.

[0244] As an example, the apparatus 1000 is configured to implement the operations performed by the communication apparatus (e.g., the first device, the second device) in the above method embodiments.

[0245] For example, the processor 1010 is configured to execute computer programs or instructions, such as the computer programs or instructions stored in the memory 1020, to implement the related operations of the first device in the above method embodiments.

[0246] For another example, the processor 1010 is configured to execute computer programs or instructions, such as the computer programs or instructions stored in the memory 1020, to implement the related operations of the second device in the above method embodiments.

[0247] It should be appreciated that a processor as mentioned in this application can be any known or future developed processor, and more particularly, a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like. The general purpose processor can be a microprocessor, but in the alternative, the processor can be any conventional processor, controller, microcontroller, or state machine, etc.

[0248] It should also be appreciated that a memory as mentioned in this application can be any known or future developed memory, and more particularly, a volatile memory or a non-volatile memory. The non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM). For example, the RAM can be used as the external cache. By way of example and not limitation, the RAM includes the following types: static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0249] It should be noted that when the processor is a general purpose processor, a DSP, an ASIC, a FPGA, or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like, the memory (storage module) can be integrated in the processor.

[0250] It should also be noted that the memory described herein is intended to include, but not be limited to, the following types of memory, and any other memory types that become available in the future.

[0251] Referring to FIG. 11, FIG. 11 is a schematic diagram of a chip system 1100 according to an embodiment of the present application. The chip system 1100 (or also referred to as a processing system) includes a logic circuit 1110 and an input / output interface 1120.

[0252] The logic circuit 1110 can be a processing circuit in the chip system 1100. The logic circuit 1110 can be coupled to a storage unit, and invoke instructions in the storage unit, so that the chip system 1100 can implement the methods and functions of the embodiments of the present application. The input / output interface 1120 can be an input / output circuit in the chip system 1100, and output information processed by the chip system 1100, or input data or signaling information to be processed by the chip system 1100.

[0253] Optionally, the logic circuit 1110 can be implemented by one or more processors, including the one or more processors or processing portions in the one or more processors.

[0254] Optionally, the input / output interface 1120 can include a transceiver circuit, a transceiver, an input / output circuit or a communication interface.

[0255] As an option, the chip system 1100 is configured to implement operations performed by a communication apparatus (e.g., the second device, or the first device) in the above method embodiments.

[0256] For example, the logic circuit 1110 is configured to implement processing-related operations performed by a communication apparatus (e.g., the second device, or the first device) in the above method embodiments; and the input / output interface 1120 is configured to implement sending and / or receiving-related operations performed by a communication apparatus (e.g., the second device, or the first device) in the above method embodiments.

[0257] The embodiments of the present application also provide a computer readable storage medium, having stored thereon computer instructions for implementing the method performed by a communication apparatus (e.g., the second device, or the first device) in the above method embodiments.

[0258] For example, the computer program is executed by a computer, so that the computer can implement the method performed by a communication apparatus (e.g., the second device, or the first device) in the above method embodiments.

[0259] The embodiments of the present application also provide a computer program product, including instructions, which are executed by a computer to implement the method performed by a communication apparatus (e.g., the second device, or the first device) in the above method embodiments.

[0260] The embodiments of the present application further provide a communication system, comprising at least one of the first device and the second device in the above embodiments.

[0261] The explanations and beneficial effects of the related contents in any of the above provided devices can refer to the corresponding method embodiments provided above, and will not be repeated here.

[0262] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0263] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. For example, the computer can be a personal computer, a server, a network device, or the like. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media sets. The available media can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD), etc. For example, the foregoing available media includes but is not limited to: a variety of media that can store program codes such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0264] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining a wireless channel, the method comprising: The method comprises: determining configuration information, the configuration information being used to indicate M models, the M models corresponding to M weights one by one, the M models and the M weights being used to reconstruct a wireless channel, M being an integer greater than or equal to 1; sending the configuration information.

2. The method of claim 1, wherein, The method further comprises: receiving first information, the first information comprising at least one first model combination and at least one first weight, the at least one first model combination and the at least one first weight being determined based on the first selected model and a first parameter, a model in the at least one first model combination being from the M models, the at least one first model combination corresponding to the first parameter, each first weight in the at least one first weight corresponding to each model in the at least one first model combination; reconstructing the wireless channel according to the first information and a channel measurement result, wherein the first parameter comprises one or more of an identifier of a region where a terminal device is located, a frequency point of the terminal device, an antenna configuration parameter of the terminal device, or a device type of the terminal device.

3. The method of claim 2, wherein, The configuration information is further used to indicate the first selected model.

4. The method according to claim 2 or 3, characterized in that, Before the channel is reconstructed according to the first information and the channel measurement result, the method further comprises: receiving the first parameter, The reconstructing the wireless channel according to the first information and the channel measurement result comprises: determining, according to the first information and the first parameter, at least one second model combination from the at least one first model combination and at least one second weight corresponding to the at least one second model combination, one second weight in the at least one second weight corresponding to one model in the at least one second model combination; reconstructing the wireless channel according to the at least one second model combination, the at least one second weight, and the channel measurement result.

5. The method according to any one of claims 2 to 4, characterized in that, Before the first information is received, the method further comprises: receiving at least one third model combination and at least one third weight, the at least one third model combination being determined according to a second selected model and the first parameter, one model in the at least one third model combination corresponding to one third weight in the at least one third weight; reconstructing the wireless channel according to the at least one third model combination and the at least one third weight, to determine a reconstruction loss of the reconstructed wireless channel; sending information used to indicate the reconstruction loss, the reconstruction loss being used to train the second selected model, the first selected model being a selected model after the training of the second selected model is completed.

6. The method of claim 1, wherein, The method further comprises: sending second information, the second information comprising at least one first model combination and at least one first weight, the at least one first model combination and the at least one first weight being based on the first selected model and a first parameter, a model in the at least one first model combination being from the M models, the at least one first model combination corresponding to the first parameter, the at least one first weight corresponding to the at least one first model combination, The first parameter comprises one or more of an identifier of a region where the terminal device is located, a frequency point of the terminal device, an antenna configuration parameter of the terminal device, or a device type of the terminal device.

7. The method of claim 6, wherein, The method further comprises: sending the first parameter.

8. The method according to claim 6 or 7, characterized in that, Before sending the second information, the method further comprises: sending at least one third model combination and at least one third weight, the at least one third model combination being determined according to a second selected model and the first parameter, one model in the at least one third model combination corresponding to one third weight in the at least one third weight; receiving information indicating a reconstruction loss, the reconstruction loss being determined according to the at least one third model combination and the at least one third weight; training the second selected model according to the reconstruction loss to obtain the first selected model, the first selected model being a selected model trained to completion of the second selected model; determining the at least one first model combination and the at least one first weight according to the first parameter and the first selected model.

9. A method for determining a wireless channel, the method comprising: comprises: receiving configuration information, the configuration information being used to indicate M models, the M models corresponding to M weights, the M models and the M weights being used to reconstruct a wireless channel, M being an integer greater than or equal to 1.

10. The method of claim 9, wherein, The method further comprises: sending first information, the first information comprising at least one first model combination and at least one first weight, the at least one first model combination and the at least one first weight being determined based on the first selected model and a first parameter, a model in the at least one first model combination being from the M models, the at least one first model combination corresponding to the first parameter, the at least one first weight corresponding to each model in the at least one first model combination, The first parameter comprises one or more of an identifier of a region where the terminal device is located, a frequency point of the terminal device, an antenna configuration parameter of the terminal device, or a device type of the terminal device.

11. The method of claim 10, wherein, The configuration information is further used to indicate the first selected model.

12. The method according to claim 10 or 11, characterized in that, The method further comprises: sending the first parameter.

13. The method according to any one of claims 10 to 12, characterized in that, Before sending the first information, the method further comprises: sending at least one third model combination and at least one third weight, the at least one third model combination being determined according to a second selected model and the first parameter, each model in the at least one third model combination corresponding to the at least one third weight; receiving information indicating a reconstruction loss, the reconstruction loss being determined according to the at least one third model combination and the at least one third weight; training the second selected model according to the reconstruction loss to obtain the first selected model, the first selected model being a selected model trained to completion of the second selected model; determining the at least one first model combination and the at least one first weight according to the first parameter and the first selected model.

14. The method of claim 9, wherein, The method further comprises: receiving second information, the second information comprising at least one first model combination and at least one first weight, the at least one first model combination and the at least one first weight being based on the first selected model and a first parameter, a model in the at least one first model combination being from the M models, the at least one first model combination corresponding to the first parameter, the at least one first weight corresponding to the at least one first model combination; reconstructing the wireless channel according to the second information and a channel measurement result, wherein the first parameter comprises one or more of an identifier of a region where a terminal device is located, a frequency point of the terminal device, an antenna configuration parameter of the terminal device, or a device type of the terminal device.

15. The method of claim 14, wherein, Before the reconstructing the wireless channel according to the second information and the channel measurement result, the method further comprises: receiving the first parameter, reconstructing the wireless channel according to the second information and the channel measurement result, comprising: determining at least one second model combination and at least one second weight corresponding to the at least one second model combination from the at least one first model combination according to the second information and the first parameter, one second weight in the at least one second weight corresponding to one model in the at least one second model combination; reconstructing the wireless channel according to the at least one second model combination, the at least one second weight and the channel measurement result.

16. The method according to claim 14 or 15, characterized in that Before the receiving the second information, the method further comprises: receiving at least one third model combination and at least one third weight, the at least one third model combination being determined according to a second selected model and the first parameter, each model in the at least one third model combination corresponding to the at least one third weight; reconstructing the wireless channel according to the at least one third model combination and the at least one third weight, and determining a reconstruction loss of the reconstructing the wireless channel; sending information indicating the reconstruction loss, the reconstruction loss being used for training the second selected model, the first selected model being a selected model trained by the second selected model.

17. A communications device, characterized by means or units for performing the method of any one of claims 1 to 8, or means or units for performing the method of any one of claims 9 to 16.

18. A communications device, characterized by a processor configured to execute computer programs or instructions to cause the apparatus to perform the method of any one of claims 1 to 8, or to cause the apparatus to perform the method of any one of claims 9 to 16.

19. The apparatus of claim 18, wherein the apparatus further comprises a memory configured to store the computer programs or instructions; and / or the apparatus further comprises a communication interface coupled to the processor, the communication interface configured to input and / or output information.

20. A computer-readable storage medium, characterized in that, The computer readable storage medium has stored thereon computer programs or instructions, which, when executed on a communication device, cause the communication device to perform the method of any one of claims 1 to 16.

21. A computer program product, characterised in that, The computer program product comprises computer programs or instructions for performing the method of any one of claims 1 to 16.

Images