Communication method, apparatus and system

Abstract

Provided in the present application is a communication method. The method can be applied to an encoder or a device provided with an encoder. The method comprises: acquiring N pieces of channel information, wherein the N pieces of channel information are determined on the basis of reference signals on K antenna port groups, N being a positive integer, and K being a positive integer less than or equal to N; compressing the N pieces of channel information by using a first encoder, so as to obtain a first sequence, wherein the first sequence is a joint feedback quantity of the N pieces of channel information; and sending the first sequence. In the method, channel information of analog beams is jointly compressed and fed back by using an encoder, for example, N pieces of channel information are compressed into a first sequence, such that the overheads of feeding back channel information are reduced.

Description

Communication method, device and system

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on September 28, 2023, with application number 202311282281.X, and priority to the Chinese patent application with the invention name “Communication Methods, Devices and Systems”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and more particularly, to a communication method, device, and system. Background Art

[0003] In higher-frequency communication systems, base stations (and terminals in some frequency bands) typically use large-scale array antennas. This high array gain counteracts the path loss associated with higher frequency bands and improves coverage. Different frequency bands and array sizes utilize different beamforming methods, such as digital beamforming (DBF), analog beamforming (ABF), or hybrid beamforming (HBF). In these beamforming methods, signal quality is improved when the beam is aligned with the communication target. However, the reporting overhead of multi-beam channel information during base station beam selection is high, and reducing feedback overhead is a critical issue.

[0004] Summary of the Invention

[0005] The present application provides a communication method, device, and system to reduce the overhead of reporting beam channel information.

[0006] In a first aspect, a communication method is provided. The method can be applied to a device equipped with an encoder, that is, can be performed by the encoder, a chip for the encoder, or a device including the encoder. The method includes: obtaining N channel information, where the N channel information is determined based on reference signals on K antenna port groups, where N is a positive integer and K is a positive integer less than or equal to N; compressing the N channel information using a first encoder to obtain a first sequence, where the first sequence is a joint feedback amount of the N channel information; and transmitting the first sequence.

[0007] Optionally, the K antenna port groups correspond to K analog beams respectively. This method uses an encoder to jointly compress and feed back the channel information of the analog beams, for example, compressing N channel information into a first sequence, thereby reducing the overhead of feeding back the channel information.

[0008] In certain implementations, the first encoder corresponds to a first parameter set, where the first parameter set includes at least one of the following parameters: a value of N, a joint feedback overhead X, the K antenna port groups corresponding to the N channel information, and N combination coefficient sets corresponding to the N channel information. When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, or when the first sequence is a sequence after quantization, the joint feedback overhead is the number of bits of the first sequence, X is a positive integer, and K is a positive integer.

[0009] Optionally, each of the N combination coefficient sets includes K combination coefficients.

[0010] Among them, the K antenna port groups corresponding to the N channel information and the N combination coefficient sets corresponding to the N channel information can enable the first encoder to determine the correlation between the compressed N channel information to determine at least one of the compression rate or compression method.

[0011] It should be understood that the first parameter set is only an example of a parameter, for example, the at least one parameter mentioned above may also be in the form of a parameter group. That is, the first parameter set is the first parameter group.

[0012] It should also be understood that quantization is an optional method, and the first sequence can be a sequence before quantization or a sequence after quantization.

[0013] In this manner, the first encoder corresponds to the first parameter set, or in other words, an encoder suitable for the first parameter set is selected to compress the channel information to support the encoder's compression of the channel information and improve compression efficiency.

[0014] In some implementations, the first encoder corresponds to at least one of the first parameter sets.

[0015] That is, the first encoder can be used to compress channel information corresponding to multiple parameter sets. In other words, the first encoder can be used to compress multiple channel information.

[0016] In this method, one encoder can be applied to the compression of a variety of information, thereby enhancing the functionality of the encoder.

[0017] In some implementations, second information is received, the second information indicating the first encoder.

[0018] Optionally, the second information may be an identifier of the first encoder.

[0019] In this manner, the encoder used to compress the channel information is indicated to a device equipped with an encoder, and the device does not need to make an independent determination, thereby reducing the complexity of compression.

[0020] Optionally, the device may also autonomously determine the encoder to be used.

[0021] In some implementations, the correspondence between the N channel information and the K antenna port groups is predefined or configured, so that the decoder can perform decoding output accordingly based on the correspondence.

[0022] In certain implementations, the N channel information is input to the first encoder in a predefined order and / or stacked manner, so that the decoder can perform decoding output accordingly based on the predefined order and / or stacked manner.

[0023] In some implementations, the N channel information are arranged according to a first order along the frequency domain direction on the frequency domain resource unit, for example, arranged according to the index size of the frequency domain resource, or the N channel information are arranged according to the second order along the port or port group domain direction on the frequency domain resource unit, for example, arranged based on the size of the port group identifier, or the N channel information are arranged according to the third order along the beam domain on the frequency domain resource unit, for example, arranged based on the identifier size of the beam.

[0024] In some implementations, the first order, the second order, and the third order are predefined or configured.

[0025] In some implementations, the frequency domain resources of the K antenna port groups include the same one or more subbands.

[0026] In other words, the frequency domain resources of the K antenna port groups include a common part or an overlapping part.

[0027] In certain implementations, the K antenna port groups include a first antenna port group and a second antenna port group, and time slot offsets of time domain resources corresponding to the first antenna port group and the second antenna port group are less than or equal to a first threshold. The first threshold may be predefined or configured.

[0028] In certain implementations, the N channel information is calculated based on K channel information measured by K antenna port groups and N combination coefficient sets. For example, each channel information in the N channel information is obtained based on the K channel information and a combination coefficient set including K coefficients, that is, each channel information in the N channel information is a function of the K channel information and a combination coefficient set including K coefficients. In one example, the K channel information are respectively multiplied by the K coefficients in combination coefficient set #1 to obtain channel information #1, where combination coefficient set #1 is one combination coefficient set among the N combination coefficient sets, and channel information #1 is one channel information among the N channel information.

[0029] In a second aspect, a communication method is provided. The method can be applied to a device equipped with a decoder, that is, can be executed by a decoder, a chip for a decoder, or a device including the decoder. The method includes:

[0030] Receive a first sequence, where the first sequence is a joint feedback amount of N channel information, where the N channel information is determined based on reference signals on K antenna port groups, where N is a positive integer and K is a positive integer less than or equal to N; and decompress the first sequence using a first decoder to obtain the N channel information.

[0031] Optionally, the K antenna port groups correspond to K simulated beams respectively.

[0032] In some implementations, the first decoder corresponds to a first parameter, and the first parameter includes at least one of the following:

[0033] The value of N, the joint feedback overhead X, the K antenna port groups corresponding to the N channel information, and the N combination coefficient sets corresponding to the N channel information.

[0034] Among them, the K antenna port groups corresponding to the N channel information and the N combination coefficient sets corresponding to the N channel information can enable the first encoder to determine the correlation between the compressed N channel information to determine at least one of the compression rate or compression method.

[0035] When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence; or when the first sequence is a sequence after quantization, the joint feedback overhead is the number of bits of the first sequence, X is a positive integer, and K is a positive integer.

[0036] In some implementations, the first decoder corresponds to at least one of the first parameter sets.

[0037] In some implementations, the correspondence between the N channel information and the K antenna port groups is predefined or configured.

[0038] In some implementations, the N channel information are output from the first decoder in a predefined order and / or in a stacked manner.

[0039] In some implementations, the frequency domain resources of the K antenna port groups include the same one or more subbands.

[0040] In certain implementations, the K antenna port groups include a first antenna port group and a second antenna port group, and time slot offsets of time domain resources corresponding to the first antenna port group and the second antenna port group are less than or equal to a first threshold. The first threshold may be predefined or configured.

[0041] In some implementations, the N channel information are calculated based on K channel information measured by K antenna port groups and N combination coefficient sets.

[0042] The beneficial effects of the second aspect and each possible design can be referred to the relevant description of the first aspect and will not be repeated here.

[0043] In a third aspect, a training method is provided, the method comprising: obtaining a first training data set, the first training data set comprising N data, the N data being determined based on reference signals on K antenna port groups, the N being a positive integer, and the K being a positive integer less than or equal to N; training a first model, the first model comprising a first sub-model and a second sub-model, the input of the first sub-model comprising first training data, the output of the first sub-model being the input of the second sub-model, the second sub-model outputting a second training data set, the second training data set indicating the N data, the output of the first sub-model being a first sequence, and the first sequence being a joint feedback amount of the N data.

[0044] It should be understood that the joint training of the encoder and decoder is taken as an example here, but the present application is not limited to this. For example, the encoder and decoder can also be trained independently.

[0045] In some implementations, the first model corresponds to a first parameter, and the first parameter includes at least one of the following: a value of N, a joint feedback overhead X, the K antenna port groups corresponding to the N data, and N combination coefficient sets corresponding to the N data.

[0046] Among them, the K antenna port groups corresponding to the N channel information and the N combination coefficient sets corresponding to the N channel information can enable the first encoder to determine the correlation between the compressed N channel information to determine at least one of the compression rate or compression method.

[0047] When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, or

[0048] When the first sequence is a quantized sequence, the joint feedback overhead is the number of bits of the first sequence, X is a positive integer, and K is a positive integer.

[0049] Optionally, each of the N combination coefficient sets includes K combination coefficients.

[0050] In some implementations, the first model corresponds to at least one first parameter set.

[0051] In some implementations, the first model corresponds to at least one training dataset, and the first training dataset belongs to the at least one training dataset.

[0052] That is, a training model can be trained on multiple training datasets.

[0053] In some implementations, the correspondence between the N data and the K antenna port groups is predefined or configured.

[0054] In some implementations, the N data are input into the first model in a predefined order and / or in a stacked manner.

[0055] In some implementations, the frequency domain resources of the K antenna port groups include the same one or more subbands.

[0056] In certain implementations, the K antenna port groups include a first antenna port group and a second antenna port group, and time slot offsets of time domain resources corresponding to the first antenna port group and the second antenna port group are less than or equal to a first threshold.

[0057] In some implementations, the N data are functions of K channel information measured according to K antenna port groups and N combination coefficient sets, wherein each channel information of the N channel information is a function of the K channel information and a combination coefficient set including K coefficients.

[0058] In a fourth aspect, a communication device is provided, configured to execute the method provided in the first, second, or third aspect. Specifically, the device may include units and / or modules, such as a processing unit and / or a communication unit, configured to execute the method provided in any of the aforementioned implementations of the first, second, or third aspects.

[0059] In one implementation, the apparatus is a communication device (e.g., an encoder or a decoder). When the apparatus is a communication device, the communication unit may be a transceiver or an input / output interface; the processing unit may be at least one processor. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0060] In another implementation, the apparatus is a chip, chip system, or circuit used in a communication device. When the apparatus is a chip, chip system, or circuit used in a terminal device, the communication unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; and the processing unit may be at least one processor, processing circuit, or logic circuit.

[0061] In a fifth aspect, a communication device is provided, which includes: at least one processor for executing a computer program or instruction stored in a memory to execute the method provided in any of the above-mentioned implementations of any of the above-mentioned first aspect, second aspect, or third aspect.

[0062] In one implementation, the apparatus is a communication device (such as an encoder or a decoder).

[0063] In another implementation, the apparatus is a chip, a chip system, or a circuit used in a communication device.

[0064] In yet another implementation, the device further includes a memory for storing programs; or the at least one processor includes the memory for storing programs.

[0065] In a sixth aspect, the present application provides a processor for executing the methods provided in the above aspects.

[0066] For the operations such as sending and acquiring / receiving involved in the processor, unless otherwise specified, or if they do not conflict with their actual functions or internal logic in the relevant descriptions, they can be understood as operations such as processor output and input, or as sending and receiving operations performed by the radio frequency circuit and antenna. This application does not limit this.

[0067] The processor may include processing circuitry and transceiver circuitry.

[0068] In the seventh aspect, a computer-readable storage medium is provided, which stores a program code for execution by a device, and the program code includes a method provided by any of the above-mentioned implementation methods for executing any of the above-mentioned first aspect, second aspect, or third aspect.

[0069] In an eighth aspect, a computer program product comprising instructions is provided, which, when run on a computer, enables the computer to execute the method provided by any one of the above-mentioned implementations of the first aspect, the second aspect, or the third aspect.

[0070] In the ninth aspect, a chip is provided, which includes a processor and a communication interface. The processor reads instructions stored in a memory through the communication interface and executes the method provided by any of the above-mentioned implementation methods of any of the above-mentioned first or second aspects.

[0071] Optionally, as an implementation method, the chip also includes a memory, in which a computer program or instruction is stored, and the processor is used to execute the computer program or instruction stored on the memory. When the computer program or instruction is executed, the processor is used to execute the method provided in any one of the above implementation methods of any one of the above-mentioned first aspect or second aspect.

[0072] In a tenth aspect, a communication system is provided, comprising the aforementioned encoder and decoder.

[0073] In this application, an encoder may also be referred to as an encoding device, which may have other functions besides encoding, and a decoder may also be referred to as a decoding device, which may have other functions besides decoding. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] FIG1 is a schematic diagram of a possible application framework in a communication system;

[0075] FIG2 is a schematic diagram of another possible application framework in a communication system;

[0076] FIG3 is a schematic diagram of a communication system applicable to an embodiment of the present application;

[0077] FIG4 is a schematic diagram of another communication system applicable to an embodiment of the present application;

[0078] FIG5 is a schematic block diagram of an autoencoder;

[0079] FIG6 is a schematic diagram of an AI application framework;

[0080] FIG7 is a schematic diagram of a digital beamforming architecture;

[0081] FIG8 is a schematic diagram of an analog beamforming architecture;

[0082] FIG9 is a schematic diagram of a hybrid beamforming architecture;

[0083] FIG10 is a schematic flow chart of a communication method according to an embodiment of the present application;

[0084] FIG11( a ) is a schematic flowchart of a method for determining a channel coefficient according to an embodiment of the present application;

[0085] FIG11( b ) is a schematic flowchart of another method for determining a channel coefficient according to an embodiment of the present application;

[0086] FIG12 is a schematic diagram of several channel information stacking methods according to an embodiment of the present application;

[0087] FIG13 is a schematic flow chart of an implementation method of a communication method according to an embodiment of the present application;

[0088] FIG14 is a schematic flow chart of a precoding matrix compression method according to an embodiment of the present application;

[0089] FIG15 is a schematic flow chart of a training method according to an embodiment of the present application;

[0090] FIG16 is a schematic flow chart of a joint training method according to an embodiment of the present application;

[0091] FIG17 is a schematic block diagram of a communication device 1700 provided in an embodiment of the present application;

[0092] FIG18 is a schematic diagram of another communication device 1800 provided in an embodiment of the present application;

[0093] FIG19 is a schematic diagram of a chip system 1900 provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION

[0094] The technical solution in this application will be described below with reference to the accompanying drawings.

[0095] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems, such as sixth generation (6G) mobile communication systems, or a fusion system of multiple systems. The technical solutions provided in this 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 or other communication systems.

[0096] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal may include information, signaling, or data, etc. The network element can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. The present disclosure uses the network element as an example for description. For example, the communication system may 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. It is understandable that the terminal device in the present disclosure can be replaced by the first network element, and the network device can be replaced by the second network element, and the two perform the corresponding communication methods in the present disclosure.

[0097] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0098] The terminal device may be a device that provides voice / data, such as a handheld device or vehicle-mounted device with a wireless connection function. At present, some examples of terminals are: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (PLMNs). The terminal equipment in the network (PLMN), etc., is not limited to this in the embodiments of the present application.

[0099] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0100] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description, and the embodiments of the present application are not limited to the solutions of the embodiments of the present application.

[0101] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station may broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, secondary station, multi-standard radio (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), radio unit (RU), positioning node, etc. A base station may 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 may also refer to a communication module, modem or chip that is set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a 6G network, a device that performs the base station function in future communication systems, etc. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0102] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0103] In some deployments, the network device referred to in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network device may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0104] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0105] The RAN node may support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another type of interface, relative to the CPRI, some of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation. In one possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0106] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0107] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0108] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0109] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0110] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of the terminal device and the network device.

[0111] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, and therefore the demands that need to be met are becoming increasingly diverse. For example, the network needs to be able to support ultra-high speeds, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as network functionality becomes increasingly powerful, such as supporting higher spectrum, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new demands, new scenarios, and new features have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. To meet this challenge, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence.

[0112] In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0113] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​node can be deployed separately, for example, in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements.

[0114] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0115] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0116] An AI node can be an AI network element or an AI module.

[0117] Figure 1 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 1, network elements in the communication system are connected through interfaces (such as NG, Xn) or air interfaces. One or more AI modules are provided in one or more devices of these network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals or OAM (for clarity, only one is shown in Figure 1). The access network node can be a separate RAN node, or it can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0118] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0119] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0120] Figure 2 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​modules 117 and 118 shown in Figure 1, which are used to implement AI-related functions. The RIC includes a near-real-time RIC (near-real time RIC, near-RT RIC) and a non-real-time RIC (non-real time RIC, Non-RT RIC). Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of this data can be in the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of this data is in the order of tens of milliseconds.

[0121] The near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. The near real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or a terminal. This information can be used as training data or reasoning data. Optionally, the near real-time RIC can deliver the reasoning result to the RAN node and / or the terminal. Optionally, the reasoning result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near real-time RIC delivers the reasoning result to the DU, and the DU sends it to the RU.

[0122] The non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0123] The near real-time RIC and non-real-time RIC may also be separately configured as a network element. Optionally, the near real-time RIC and non-real-time RIC may also be part of other devices. For example, the near real-time RIC is configured in a RAN node (e.g., a CU or DU), while the non-real-time RIC is configured in an OAM, a cloud server, a core network device, or other network device.

[0124] FIG3 is a schematic diagram of a communication system applicable to the communication method of an embodiment of the present application. As shown in FIG3 , the communication system 100 may include at least one network device, such as the network device 110 shown in FIG3 ; the communication system 100 may also include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in FIG3 . The network device 110 and the terminal device (such as the terminal device 120 and the terminal device 130) can communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, can communicate via multi-antenna technology.

[0125] Figure 4 is a schematic diagram of another communication system applicable to the communication method of an embodiment of the present application. Compared to the communication system 100 shown in Figure 3, the communication system 200 shown in Figure 4 also includes an AI network element 140. AI network element 140 is used to perform AI-related operations, such as constructing a training dataset or training an AI model.

[0126] In one possible implementation, the network device 110 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​network element 140 may send the results of the operations related to the AI ​​model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a portion of the trained AI model may be deployed on the network device 110, and another portion may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0127] It should be understood that Figure 4 illustrates only the example of a direct connection between AI network element 140 and network device 110. In other scenarios, AI network element 140 may also be connected to a terminal device. Alternatively, AI network element 140 may be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI network element 140 may be connected to network device 110 through a third-party network element. This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0128] The AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device shown in FIG3 .

[0129] It should be noted that Figures 3 and 4 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 3 and 4. In actual applications, the communication system may include multiple network devices and multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0130] To facilitate understanding of the solutions of the embodiments of the present application, the terms that may be involved in the embodiments of the present application are explained below.

[0131] 1. Artificial Intelligence: This refers to the ability of machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. Artificial Intelligence can be understood as the intelligence exhibited by machines created by humans. Generally, AI refers to the technology that represents human intelligence through computer programs. The goals of AI include understanding intelligence by constructing computer programs that can perform symbolic reasoning or deduction.

[0132] 2. Machine learning: This is an implementation of artificial intelligence. Machine learning is a method that empowers machines to learn, enabling them to perform functions that cannot be accomplished through direct programming. In practical terms, machine learning utilizes data to train models and then uses these models to make predictions. There are many machine learning methods, such as neural networks (NNs), decision trees, and support vector machines. Machine learning theory primarily involves the design and analysis of algorithms that enable computers to learn automatically. Machine learning algorithms automatically analyze data to identify patterns and use these patterns to make predictions about unknown data.

[0133] 3. Neural Network: A specific embodiment of machine learning. A neural network is a mathematical model that processes information by mimicking the behavioral characteristics of animal neural networks. The concept of a neural network is derived from the neuronal structure of the brain. Each neuron performs a weighted sum operation on its input values, and the result of this weighted summation is passed through an activation function to generate an output.

[0134] Neural networks generally comprise a multi-layer structure, with each layer comprising one or more logical decision units, referred to as neurons. Increasing the depth and / or width of a neural network can enhance its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can be understood as the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. In one possible implementation, a neural network comprises an input layer and an output layer. The input layer of the neural network processes the input through neurons and then passes the result to the output layer, which then obtains the output of the neural network. In another possible implementation, a neural network comprises an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the input through neurons and then passes the result to an intermediate hidden layer. The hidden layer then passes the calculation result to the output layer or an adjacent hidden layer, which then obtains the output of the neural network. A neural network can comprise one or more sequentially connected hidden layers, without limitation.

[0135] During neural network training, a loss function can be defined. This function measures the difference between the model's predicted value and the actual value. During neural network training, the loss function describes the gap or discrepancy between the neural network's output and the ideal target value. Neural network training involves adjusting neural network parameters to ensure that the loss function's value is below a threshold or meets the target requirement. Neural network parameters can include at least one of the following: the number of neural network layers, their width, neuron weights, and parameters in the neuron activation function.

[0136] Taking the AI ​​model type as a neural network as an example, the AI ​​model involved in this disclosure can be a deep neural network (DNN). Depending on the network construction method, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN).

[0137] 4. Deep neural network: A neural network with multiple hidden layers.

[0138] 5. Deep learning: Machine learning using deep neural networks.

[0139] 6. AI Model

[0140] An AI model is an algorithm or computer program that implements AI functionality. It represents the mapping between the model's inputs and outputs. AI models can be neural networks, linear regression models, decision tree models, support vector machines (SVMs), Bayesian networks, Q-learning models, or other machine learning (ML) models.

[0141] 7. Two-end model:

[0142] The two-end model can also be called a bilateral model, collaborative model, dual model, or two-side model. A two-end model is a model composed of multiple sub-models. The sub-models that make up the model must match each other. These sub-models can be deployed on different nodes.

[0143] The embodiments of the present application relate to an encoder for compressing CSI and a decoder for recovering compressed CSI. The encoder and decoder are used in combination, and it can be understood that the encoder and decoder are matching AI models. An encoder may include one or more AI models, and the decoder matched with the encoder also includes one or more AI models. The number of AI models included in the matching encoder and decoder is the same and corresponds one to one.

[0144] In one possible design, a matched set of encoders and decoders can be specifically two parts of the same auto-encoder (AE), as shown in Figure 5. An AE model, in which the encoder and decoder are deployed on different nodes, is a typical bilateral model. The encoder and decoder of an AE model are typically trained together and used in pairs. The encoder processes the input V to produce the processed output z, and the decoder decodes the encoder output z into the desired output V'.

[0145] An autoencoder is a type of neural network that performs unsupervised learning. Its characteristic is that it uses input data as labeled data. Therefore, an autoencoder can also be understood as a self-supervised learning neural network. Autoencoders can be used for both data compression and recovery. For example, the encoder in an autoencoder can compress (encode) data A to produce data B; the decoder in the autoencoder can decompress (decode) data B to recover data A. Alternatively, the decoder can be understood as the inverse operation of the encoder.

[0146] For example, the AI ​​model in the embodiments of the present application may include an encoder and a decoder. The encoder and decoder are used in combination, and it can be understood that the encoder and decoder are a matching AI model. The encoder and decoder can be deployed on terminal devices and network devices respectively.

[0147] Alternatively, the AI ​​model in the embodiment of the present application may be a single-end model, which may be deployed on a terminal device or a network device.

[0148] 8. Training data set and inference data:

[0149] In the field of machine learning, ground truth usually refers to data that is believed to be accurate or real.

[0150] A training dataset is used to train an AI model. It may include the input to the AI ​​model, or the input and target output of the AI ​​model. A training dataset includes one or more training data. Training data may include training samples input to the AI ​​model, or the target output of the AI ​​model. The target output may also be referred to as a label, sample label, or labeled sample. A label is the true value.

[0151] In the communications field, training datasets can include simulated data collected through simulation platforms, experimental data collected in experimental scenarios, or measured data collected in actual communication networks. Because the geographical environments and channel conditions in which data are generated vary, such as indoor and outdoor locations, mobile speeds, frequency bands, or antenna configurations, the collected data can be categorized during acquisition. For example, data with the same channel propagation environment and antenna configuration can be grouped together.

[0152] Model training essentially involves learning certain characteristics from training data. When training an AI model (such as a neural network), the goal is to ensure that the model's output is as close as possible to the desired predicted value. This is done by comparing the network's predictions with the desired target values. The weight vectors of each layer of the AI ​​model are then updated based on the difference between the two. (Of course, before the first update, there's usually an initialization process, which pre-configures the parameters for each layer of the AI ​​model.) For example, if the network's prediction is too high, the weight vectors are adjusted to predict a lower value. This adjustment is repeated until the AI ​​model predicts the desired target value, or a value very close to it. Therefore, it's necessary to predefine how to compare the difference between the predicted and target values. This is known as the loss function or objective function, a crucial equation used to measure the difference between the predicted and target values. For example, a higher loss function indicates a greater difference. Therefore, training an AI model becomes a process of minimizing this loss, keeping the loss function below a threshold or ensuring that the loss function meets the target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers, width, weights of neurons, or parameters in the activation function of neurons of the neural network.

[0153] Inference data can be used as input to a trained AI model for inference. During the inference process, the inference data is input into the AI ​​model, and the corresponding output is the inference result.

[0154] 9. AI model design:

[0155] The design of an AI model primarily involves data collection (e.g., collecting training data and / or inference data), model training, and model inference. Furthermore, it can also include the application of inference results.

[0156] FIG6 shows an AI application framework.

[0157] In the aforementioned data collection phase, the data source is used to provide training datasets and inference data. In the model training phase, an AI model is obtained by analyzing or training the training data provided by the data source. The AI ​​model represents the mapping relationship between the model's input and output. Learning the AI ​​model through the model training node is equivalent to learning the mapping relationship between the model's input and output using the training data. In the model inference phase, the AI ​​model trained in the model training phase is used to perform inference based on the inference data provided by the data source, obtaining an inference result. This phase can also be understood as inputting the inference data into the AI ​​model and obtaining an output from the AI ​​model, which is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object and / or the operations performed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be centrally planned by the execution (actor) entity, for example, the execution entity can send the inference result to one or more execution objects (e.g., network devices or terminal devices) for execution. Alternatively, the execution entity can provide feedback on the model's performance to the data source to facilitate subsequent model update and training.

[0158] It is understandable that a communication system may include network elements with artificial intelligence capabilities. The above-mentioned AI model design-related steps can be performed by one or more network elements with artificial intelligence capabilities. In one possible design, AI functions (such as AI modules or AI entities) can be configured in existing network elements in the communication system to implement AI-related operations, such as AI model training and / or inference. For example, the existing network element can be a network device or a terminal device. Alternatively, in another possible design, an independent network element can be introduced into the communication system to perform AI-related operations, such as training an AI model. The independent network element can be referred to as an AI network element or an AI node, etc., and the embodiments of the present application are not limited to these names. For example, the AI ​​network element can be directly connected to the network equipment in the communication system, or it can be indirectly connected to the network equipment through a third-party network element. The third-party network element can be a core network element such as an authentication management function (AMF) network element, a user plane function (UPF) network element, an operation administration and maintenance (OAM), a cloud server, or other network element, without limitation. Exemplarily, the independent network element can be deployed on one or more of the following: a network device side, a terminal device side, or a core network side. Optionally, it can be deployed on a cloud server. Exemplarily, the communication system shown in FIG4 introduces an AI network element 140.

[0159] The training process of different models can be deployed in different devices or nodes, or in the same device or node. The inference process of different models can be deployed in different devices or nodes, or in the same device or node. Taking the completion of the model training phase of a terminal device as an example, the terminal device can train the matching encoder and decoder, and then send the model parameters of the decoder to the network device. Taking the completion of the model training phase of a network device as an example, after the network device trains the matching encoder and decoder, it can indicate the model parameters of the encoder to the terminal device. Taking the completion of the model training phase of an independent AI network element as an example, the AI ​​network element can train the matching encoder and decoder, and then send the model parameters of the encoder to the terminal device and the model parameters of the decoder to the network device. Then, the model inference phase corresponding to the encoder is performed in the terminal device, and the model inference phase corresponding to the decoder is performed in the network device.

[0160] Among them, the model parameters may include one or more of the following structural parameters of the model (such as the number of layers and / or weights of the model, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0161] 10. Model training: The process of selecting a suitable loss function and using an optimization algorithm to train the model parameters so that the value of the loss function is less than the threshold, or the value of the loss function meets the target requirements.

[0162] 11. Model application: Use the trained model to solve practical problems.

[0163] 12. Channel status information:

[0164] In communication systems (e.g., LTE or NR), network equipment needs to determine the resource, MCS, and precoding configurations for scheduling downlink data channels of terminal devices based on CSI. It can be understood that CSI is a type of channel information that can reflect channel characteristics and channel quality.

[0165] CSI measurement refers to the receiver solving the channel information based on the reference signal sent by the transmitter, that is, estimating the channel information using the channel estimation method. Exemplarily, the reference signal may include one or more of the channel state information reference signal (CSI-RS), synchronization signal / physical broadcast channel block (SSB), sounding reference signal (SRS), or demodulation reference signal (DMRS). CSI-RS, SSB, and DMRS can be used to measure downlink CSI. SRS and DMRS can be used to measure uplink CSI.

[0166] Taking FDD communication scenarios as an example, in FDD communication scenarios, because uplink and downlink channels are not reciprocal or cannot be guaranteed, network equipment typically transmits a downlink reference signal to the terminal device. The terminal device performs channel and interference measurements based on the received downlink reference signal to estimate the downlink CSI. The terminal device generates a CSI report based on a protocol predefined method or a network device configuration method and feeds it back to the network device to obtain the downlink CSI.

[0167] Exemplarily, the CSI may include at least one of the following: channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), layer indicator (LI), reference signal receiving power (RSRP), or signal to interference plus noise ratio (SINR). The signal to interference plus noise ratio may also be referred to as the signal to interference plus noise ratio.

[0168] The RI indicates the number of downlink transmission layers recommended by the terminal device, the CQI indicates the modulation and coding scheme supported by the current channel conditions as determined by the terminal device, and the PMI indicates the precoding recommended by the terminal device. The number of precoding layers indicated by the PMI corresponds to the RI.

[0169] It should be understood that the RI, CQI, and PMI indicated in the above CSI report are only recommended values ​​for the terminal device, and the network device may perform downlink transmission according to part or all of the information indicated in the CSI report. Alternatively, the network device may not perform downlink transmission according to the information indicated in the CSI report.

[0170] The introduction of AI technology into wireless communication networks has resulted in a CSI feedback method based on AI models. Terminal devices use AI models to compress and feedback CSI, and network equipment uses AI models to recover the compressed CSI. AI-based CSI feedback transmits a sequence (such as a bit sequence), resulting in lower overhead than traditional CSI feedback.

[0171] Taking Figure 5 as an example, the encoder in Figure 5 can be a CSI generator, and the decoder can be a CSI reconstructor. The encoder can be deployed in a terminal device, and the decoder can be deployed in a network device. The terminal device can use the encoder to generate CSI feedback information z from the original CSI information V. The terminal device then reports a CSI report, which can include the CSI feedback information z. The network device can use the decoder to reconstruct the CSI information, thereby obtaining the recovered CSI information V'.

[0172] The CSI original information V may be obtained by the terminal device through CSI measurement. For example, the CSI original information V may include the channel response of the downlink channel or the eigenvector matrix (a matrix composed of eigenvectors) of the downlink channel. The encoder processes the eigenvector matrix of the downlink channel to obtain CSI feedback information z. In other words, the compression and / or quantization operation of the eigenmatrix according to the codebook in the related scheme is replaced by the operation of processing the eigenmatrix by the encoder to obtain CSI feedback information z. The terminal device reports the CSI feedback information z. The network device processes the CSI feedback information z through the decoder to obtain CSI recovery information V'.

[0173] The following further illustrates the training process and reasoning process of the AI ​​model in the embodiments of the present application.

[0174] The training data used to train AI models includes training samples and sample labels. For example, the training samples are channel information determined by the terminal device, and the sample labels are the actual channel information, i.e., the true value CSI. If the encoder and decoder belong to the same autoencoder, the training data can only include the training samples, or the training samples are the sample labels.

[0175] In the field of wireless communications, the true CSI may be high-precision CSI.

[0176] The specific training process is as follows: the model training node uses the encoder to process the channel information, that is, the training sample, to obtain CSI feedback information, and uses the decoder to process the feedback information to obtain the recovered channel information, that is, the CSI recovery information. Then calculate the difference between the CSI recovery information and the corresponding sample label, that is, the value of the loss function, and update the parameters of the encoder and decoder according to the value of the loss function, so that the difference between the recovered channel information and the corresponding sample label is minimized, that is, minimize the loss function. Exemplarily, the loss function can be the minimum mean square error (MSE) or cosine similarity. Repeat the above operations to obtain an encoder and decoder that meet the target requirements. The above model training node can be a terminal device, a network device, or other network elements with AI functions in a communication system.

[0177] It should be understood that the above description uses the AI ​​model for CSI compression as an example. The AI ​​model can also be used in other scenarios in CSI feedback. For example, the AI ​​model can be used for CSI prediction, that is, predicting channel information at one or more future moments based on channel information measured at one or more historical moments. The embodiments of this application do not limit the specific use of the AI ​​model in CSI feedback scenarios.

[0178] 13. Antenna port: Antenna port is a logical concept. An antenna port does not directly correspond to a physical antenna. Antenna ports are usually associated with reference signals, and their meaning can be understood as a transceiver interface on the channel that the reference signal passes through. For low frequencies, an antenna port may correspond to one or more antenna array elements. These array elements jointly transmit reference signals, and the receiver can treat them as a whole without distinguishing between these array elements. For high-frequency systems, an antenna port group may correspond to a beam. Similarly, the receiver only needs to regard this beam as an interface without distinguishing between each array element. Among them, an antenna port group can include one or more antenna ports.

[0179] 14. Port group: A port group refers to an antenna port group / reference signal port group. A port group may contain one or more antenna ports, and a port group may correspond to multiple reference signals. In the present application, a base station may use one or more reference signal port groups to measure the channel information under an analog beam. For example, the channel information of N analog beams may be obtained by measuring the reference signals of K antenna port groups, where N is a positive integer and K is a positive integer less than or equal to N. For example, the channel information of 8 analog beams may be obtained by measuring the reference signals of 4 antenna port groups, for example, a function of the 4 channel information obtained by measuring the reference signals of the 4 antenna port groups and one of the 8 combination coefficient sets related to the 4 channel information, where each combination coefficient set includes 4 coefficients.

[0180] 15. Beam: A beam is a communication resource. A beam can be wide, narrow, or other types of beams. The beamforming technology can be beamforming or other techniques. Beamforming technologies can specifically include digital beamforming, analog beamforming, and hybrid digital / analog beamforming. Different beams can be considered different resources. Different beams can transmit the same or different information. Optionally, multiple beams with the same or similar communication characteristics can be considered a single beam. A beam can include one or more antenna ports for transmitting data channels, control channels, and sounding signals. For example, a transmit beam can refer to the signal strength distribution in different spatial directions after a signal is transmitted by an antenna, while a receive beam can refer to the signal strength distribution in different spatial directions of a wireless signal received by an antenna. It is understood that the one or more antenna ports that form a beam can also be considered an antenna port set. Beams can also be reflected in the protocol as spatial parameters, such as spatial filters.

[0181] 16. Reference Signals: According to the Long Term Evolution (LTE) / NR protocol, at the physical layer, uplink communications include the transmission of uplink physical channels and uplink signals. Uplink physical channels include the random access channel (PRACH), the physical uplink control channel (PUCCH), and the physical uplink shared channel (PUSCH). Uplink signals include the sounding signal (SRS), the uplink control channel demodulation reference signal (PUCCH-DMRS), the uplink data channel demodulation reference signal (PUSCH-DMRS), the uplink phase noise tracking reference signal (PTRS), and the uplink positioning RS. Downlink communications include the transmission of downlink physical channels and downlink signals. The downlink physical channels include the physical broadcast channel (PBCH), the physical downlink control channel (PDCCH), the physical downlink shared channel (PDSCH), etc. The downlink signals include the primary synchronization signal (PSS) / secondary synchronization signal (SSS), the downlink control channel demodulation reference signal PDCCH-DMRS, the downlink data channel demodulation reference signal PDSCH-DMRS, the phase noise tracking signal PTRS, the channel status information reference signal (CSI-RS), the cell signal (CRS) (NR does not have), the time / frequency tracking reference signal (TRS) (LTE does not have), the LTE / NR positioning signal (positioning RS), etc.

[0182] 17. Precoding and Codebooks: Multiple Input Multiple Output (MIMO) technology is used to increase system capacity and improve throughput. The mathematical expression is y = Hx + n, where y is the received signal, H is the MIMO channel, x is the transmitted signal, and n is the noise. In a communication system with multiple antennas, the signals from multiple transmitting antennas are superimposed on any receiving antenna. Therefore, the method used by the transmitter to transmit signals affects system performance, and recovering the transmitted signal at the receiver is often complex. In this context, precoding is used to reduce system overhead and maximize MIMO system capacity, while also reducing the complexity of the receiver's implementation of mitigating inter-channel interference. The mathematical expression is y = HPx + n, where P is the precoding matrix (or vector). To simplify implementation complexity, P can be selected from a predefined set of matrices (or vectors), called a codebook. This method is also known as a codebook-based transmission method. If the transmitter can obtain all the information of H, then P can be obtained by the transmitter itself. This method is also called a non-codebook transmission method (NCB).

[0183] It should be understood that, in this application, indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication of information A refers to including information A; implicit indication of information A refers to indicating information A through the correspondence between information A and information B and the direct indication of information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0184] It should be understood that, in this application, information C is used to determine information D, which includes both information D being determined solely based on information C and information D being determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, where information D is determined based on information E, and information E is determined based on information C.

[0185] In addition, in each embodiment of the present application, "network element A sends information A to network element B" can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, which may include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, which may include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be elaborated here.

[0186] Exemplarily, the network device may be a core network device, an access network node (RAN node) or one or more devices in OAM shown in Figure 1. For example, the AI ​​module may be the RIC shown in Figure 2, such as a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is set in the RAN node (e.g., CU, DU), while the non-real-time RIC is set in the OAM, in the cloud server, in the core network device, or in other network devices. The RIC can be obtained by obtaining a subset from multiple terminal devices from a RAN node (e.g., CU, CU-CP, CU-UP, DU and / or RU), reorganizing it into a training data set #2, and training based on the training data set #2.

[0187] For example, the near real-time RIC and the non-real-time RIC may also be separately configured as a network element, and the network device may be the near real-time RIC or the non-real-time RIC.

[0188] Currently, in higher-frequency communication systems, network equipment (and terminals in some frequency bands) typically use large-scale array antennas (e.g., 500-1000 antenna elements) to counteract path loss caused by higher frequency bands through higher array gain, thereby improving coverage. From the perspective of network equipment implementation, even with large arrays, different frequency bands and array sizes use different array weighting methods (i.e., beamforming methods). Based on the beamforming implementation scheme, these can be roughly divided into the following three categories:

[0189] The first type: digital beamforming (DBF). Its basic structure is shown in Figure 7. Each antenna element or group of antenna elements is directly connected to a digital channel. Because each antenna signal is directly converted to the digital domain, subsequent array weighting is performed in the digital domain, hence the name digital beamforming. The digital domain offers high degrees of freedom for signal processing and can support complex signal processing methods. Therefore, DBF architectures offer superior performance at the same array size. On the other hand, due to the high power consumption and cost of analog-to-digital converters (ADCs / DACs), especially at large bandwidths, DBF is more expensive at the same array size.

[0190] The second type is analog beamforming (ABF). Its structure is shown in Figure 8. Each antenna element or group of antenna elements is connected to an analog phase shifter. Multiple antenna elements are combined in the analog domain and then passed through a digital-to-analog / analog-to-digital converter. Compared to DBF, ABF only has one digital-to-analog / analog-to-digital converter for the entire array. The ABF architecture has the advantages of low cost and power consumption. However, the phase shifter settings in the analog domain determine the beam direction after beamforming. Since the signals are directly combined electronically in the analog domain, they cannot be weighted using digital signal processing like DBF. ABF requires pre-configured phase shifter settings during transmission and reception (i.e., pointing the analog beam toward the target terminal). This process requires beam scanning during the link establishment phase, which introduces additional latency. Furthermore, if the analog beam is misaligned due to obstruction or movement, the system link quality will rapidly degrade and even terminate. Therefore, ABF may not offer the same communication reliability as DBF.

[0191] The third type: Hybrid beamforming (HBF), whose structure is shown in Figure 9, is an intermediate form between ABF and DBF. The example in the figure shows a three-channel HBF architecture with two analog phase shifters per channel. HBF has a certain number of digital ports to support digital beamforming, and each digital port drives an ABF subarray. Compared to ABF, for the same array size, each digital channel drives a smaller analog subarray, resulting in a wider beam, improved reliability, and reduced beam scanning overhead. The ratio of digital ports to analog phase shifters in HBF varies depending on the frequency and system design requirements. For example, high-frequency bands have a small number of digital ports (4 to 16), and each digital channel corresponds to a larger number of analog phase shifters (16 to 32), closer to ABF. Low-frequency band systems, on the other hand, have more digital ports (32 to 128) and fewer analog phase shifters per digital channel (for example, 2 to 10).

[0192] Both HBF and ABF architectures use analog beams. Signal quality improves only when the beams are aligned with the communication target. The direction of the analog beam (determined by the beam weight) is configured before transmission and reception. For a terminal, the process of network equipment selecting an analog beam is called beam training or beam scanning. Beam scanning typically involves the network equipment sending reference signals using different analog beam weights. The terminal then measures the reference signals and feeds back the measurement results to help the network equipment determine which beam has the best quality. Currently, terminals only perform independent measurements and channel information feedback for a single CSI-RS resource set, or for multiple CSI-RS resources within a single analog beam or multiple CSI-RS resource sets, resulting in high overhead. In addition, the coverage areas of multiple analog beams overlap to some extent, and the channel information between different analog beams has certain correlations and common characteristics. Independently measuring and reporting each beam will result in multiple reports of common information, causing feedback overhead to increase exponentially.

[0193] In view of this, an embodiment of the present application proposes a communication method to reduce the feedback overhead of a terminal.

[0194] The communication method provided by the embodiment of the present application will be described in detail below with reference to the accompanying drawings. The embodiment provided by the present application can be applied to the network architecture shown in FIG1 above, without limitation.

[0195] In the following embodiments, as examples, the encoder is a terminal device and the decoder is a network device; or the encoder is a terminal device and the decoder is another terminal device; or the encoder is a network device and the decoder is another network device; or the encoder is a network device and the decoder is a terminal device, without limitation. It is understood that the encoder mentioned below can be replaced by an encoding device, and the decoder can be replaced by a decoding device. In addition, it is also understood that the encoder mentioned below can include circuits other than the AI ​​model, such as processing circuits, storage circuits, transceiver circuits, etc.

[0196] In the following embodiments, the encoder can deploy multiple AI models, allowing the encoder to perform encoding based on the deployed AI models, such as compressing channel information. The decoder can also deploy multiple AI models, allowing the decoder to perform decoding based on the deployed AI models, such as recovering channel information from compressed information. For simplicity, the AI ​​model deployed by the encoder is referred to as the encoder's AI model, and the AI ​​model deployed by the decoder is referred to as the decoder's AI model.

[0197] FIG10 is a schematic diagram of a communication method 1000 provided in an embodiment of the present application. The method 1000 may include the following steps.

[0198] 1010. The transmitter obtains N channel information.

[0199] The N channel information is determined based on reference signals on K antenna port groups, where N is a positive integer and K is a positive integer less than or equal to N. In other words, the N channel information is used for association with the K antenna port groups.

[0200] For example, the antenna port group may be a CSI-RS port group.

[0201] The N channel information also corresponds to N analog beams.

[0202] In a possible implementation, the N simulated beams are different from each other, and there is an overlapping area in the coverage range of the N simulated beams.

[0203] For example, the coverage of some of the N simulated beams overlaps. For example, N is 5, including beam A, beam B, beam C, beam D, and beam E, where the coverage of beam A and beam B overlaps.

[0204] For example, the coverage areas of the N simulated beams all overlap. For example, N is 5, including beam A, beam B, beam C, beam D, and beam E, wherein the coverage areas of the five beams all overlap.

[0205] The N simulated beams correspond one-to-one to the N channel information. In other words, the N channel information is the channel information of the N simulated beams. For example, the channel information can be channel state information (CSI). For details, please refer to the description of CSI above and will not be repeated here.

[0206] That is, N analog beams are associated with K antenna port groups. For example, channel information of the N analog beams is determined based on reference signals of the K antenna port groups.

[0207] When N and K are equal, the N simulated beams correspond one-to-one to the N antenna port groups. For example, if N is 3, simulated beam A corresponds to antenna port group A, simulated beam B corresponds to antenna port group B, and simulated beam C corresponds to antenna port group C.

[0208] Among them, the N antenna port groups include antenna port group A and antenna port group B. The reference signal resource corresponding to antenna port group A is different from the reference signal resource corresponding to antenna port B. It should be understood that the antenna port group is used to send reference signals, and different reference signals correspond to different resources, such as time domain resources and / or frequency domain resources. For example, different antenna port groups can be distinguished by different groupings of reference signal resources. For example, the reference signal resources include reference signal resource group A, reference signal resource group B, and reference signal resource group C, wherein reference signal resource group A is used to send reference signal A, reference signal resource group B is used to send reference signal B, and reference signal A is sent through antenna port A, and reference signal B is sent through antenna port B. It should be understood that reference signal A or reference signal B can each include multiple reference signals.

[0209] The K antenna port groups correspond to K channel information, and the K channel information and N groups of combination coefficients determine N groups of channel information, where N is greater than or equal to K and K is a positive integer.

[0210] Specifically, the following uses the precoding matrix as an example of channel information, which can be divided into the following two cases:

[0211] Case 1: N is equal to K. That is, there are K antenna port groups, which are used to determine N=K groups of channel coefficients.

[0212] For example, the network device configures N antenna port groups for the terminal, each corresponding to an analog beam. As shown in Figure 11 (a), these K antenna port groups are used to measure the channel coefficients {H1, H2, H3, …} for N different analog beams (with analog weights {w1, w2, w3, …}) in the network device (e.g., base station) arrays A1, A2, D1, D2 (where A1 and A2 represent the number of horizontal and vertical array elements, and D1 and D2 represent the number of digital ports). The terminal then calculates the precoding matrices {v1, v2, v3, …} for the N different analog beams through SVD decomposition. The values ​​of the arrays A1, A2, D1, and D2 are related to the antenna array (or, more precisely, to the architecture of analog beamforming, which can be found in the previous section and will not be further elaborated here).

[0213] Case 2: N is greater than K. That is, K antenna port groups are used to determine N groups of channel coefficients.

[0214] For example, as shown in FIG11(b), K antenna port groups are used to obtain channel coefficients (or channel responses) of K antenna port groups, which are respectively denoted as h1, h2, ..., h K Based on the channel information of K antenna port groups and the channel combination coefficient The channel coefficients under N simulated beams can be obtained The terminal then performs SVD decomposition to calculate the precoding matrices {v1, v2, v3, …} for N different simulated beams.

[0215] That is, when the N channel information are N precoding matrices, the N channel information are obtained by decomposing the channel coefficients of the N analog beams, or the N channel information are obtained by decomposing the channel information of the K antenna port groups and the channel combination coefficients.

[0216] For example, the channel coefficients may be space-frequency domain channel responses, for example, a channel matrix may be used to represent the space-frequency domain channel responses.

[0217] In one possible implementation, the N channel information corresponds to N sequence numbers, and these N sequence numbers correspond one-to-one with the N simulated beams. In other words, the N simulated beams are associated with the N channel information through these N sequence numbers. For example, if N is 3, and the three simulated beams are beam A, beam B, and beam C, beam A corresponds to sequence number 1, beam B corresponds to sequence number 2, and beam C corresponds to sequence number 3. Furthermore, channel information A corresponds to sequence number 1, channel information B corresponds to sequence number 2, and channel information C corresponds to sequence number 3. Thus, channel information A corresponds to beam A, channel information B corresponds to beam B, and channel information C corresponds to beam C.

[0218] Optionally, the correspondence between the N channel information and the K antenna port groups is predefined or configured. In other words, the correspondence between the N channel information and the N simulated beams is predefined or configured.

[0219] For example, N channel information is input to the first encoder in a predefined order and / or in a stacked manner.

[0220] The predefined order may be the order in which the channel information and the beams are configured by sequence numbers.

[0221] The following describes the stacking method of channel information, assuming that N channel information are CSI#1 to CSI#N (beam domain), the number of subbands corresponding to the n-th channel information is Qn (frequency domain), and the number of ports of the n-th channel information is Pn (spatial domain). Taking the case where P and Q of the N channel information are equal as an example, the predefined stacking methods include the following:

[0222] Method 1: N channel information is stacked in the frequency domain.

[0223] Possibility 1: N channel information is stacked in the frequency domain first and then in the beam domain. For example, the reference signal corresponding to each of the N channel information occupies Q subbands. The Q subbands are different from each other. The N channel information is arranged sequentially in the frequency domain. For example, the N channel information is arranged in ascending order of index in the frequency domain.

[0224] For example, as shown in (a) of FIG12 , CSI#1 to CSI#N are arranged in ascending order of index in the frequency domain, wherein the reference signal corresponding to each CSI occupies Q subbands.

[0225] Possibility 2: N channel information is stacked in the beam domain first and then in the frequency domain. For example, within a subband, frequency domain resources for reference signals corresponding to multiple channel information are included. Furthermore, within Q subbands, each subband includes frequency domain resources for reference signals corresponding to multiple channel information. For example, the frequency domain resources within each subband are used to transmit reference signals for K antenna port groups. The Q subbands are arranged sequentially in the frequency domain. For example, the Q subbands are arranged in ascending order of subband index in the frequency domain.

[0226] For example, as shown in Figure 12(b), CSI#1 to CSI#N are arranged in ascending order of index within any subband. The reference signal corresponding to each CSI occupies Q subbands. Subband 0 to subband Q-1 are arranged in ascending order of index in the frequency domain.

[0227] Method 2: N channel information is stacked in the spatial domain.

[0228] Possibility 1: N channel information is stacked first in the spatial domain and then in the beam domain. For example, within the same subband, the channel information is first sorted by index size, for example, in ascending order. In a single pass of the channel information (i.e., a permutation of N channel information), each channel information corresponds to the same antenna port. The reference signals corresponding to these N channel information occupy Q subbands, and the channel information is stacked in the same manner within each of the Q subbands.

[0229] For example, as shown in (c) of Figure 12, within a subband, CSI#1 to CSI#N are arranged in ascending order of spatial indices. For example, for antenna port #0, CSI#1 to CSI#N are arranged in ascending order of indices. Antenna ports are also arranged in ascending order of indices in the spatial domain. For example, in the spatial direction, the port in the first set of correspondences is port #0, and the port in the last set of correspondences is port #Pn-1. In other words, each antenna port traverses CSI#1 to CSI#N. In the frequency domain, the order of antenna ports and CSI is the same within each subband.

[0230] Possibility 2: N channel information is stacked first in the beam domain and then in the spatial domain. For example, within the same subband, the antenna port index is sorted first, for example, from smallest to largest. In a single antenna port traversal (i.e., a permutation of all antenna ports), the channel information corresponding to each antenna port is identical. The reference signals corresponding to these N channel information occupy Q subbands, and the channel information is stacked in the same manner within each of these Q subbands.

[0231] For example, as shown in (d) of Figure 12, within a subband, CSI #1 to CSI #N are arranged in ascending order of spatial indices. For example, each CSI corresponds to antenna port #0 to antenna port #Pn-1, and the antenna ports are arranged in ascending order of spatial indices. That is, each CSI traverses antenna port #0 to antenna port #Pn-1. In the frequency domain, the antenna ports and CSI arrangement order remain the same within each subband.

[0232] Method 3: N channel information is stacked in the third dimension.

[0233] For example, N channel information is stacked in a certain order in the beam domain. For example, within the same subband, the information is sorted by antenna port index size, such as in ascending order of antenna port index. In a single antenna port traversal (i.e., a permutation of all antenna ports), the channel information corresponding to each antenna port is identical. The reference signals corresponding to these N channel information occupy Q subbands, and the channel information is stacked in the same manner within each of the Q subbands.

[0234] For example, as shown in Figure 12 (e), within a subband, CSI #1 to CSI #N are arranged in ascending order of index in the beam domain. Each CSI corresponds to antenna port #0 to antenna port #Pn-1, and the antenna ports are arranged in ascending order of index in the beam domain. That is, each CSI traverses antenna port #0 to antenna port #Pn-1. In the frequency domain, the antenna ports and CSI arrangement order are the same within each subband.

[0235] Optionally, the frequency domain resources of the K antenna port groups, or the frequency domain resources of the reference signals of the K antenna port groups, have the same portion. The frequency domain resources may be subbands or resource blocks. For example, the subbands occupied by the reference signals of the K antenna port groups may have the same subbands, or the resource blocks occupied by the reference signals of the K antenna port groups may have the same resource blocks.

[0236] For example, the value of K is 3, and the three antenna port groups are antenna port group A, antenna port group B, and antenna port group C. The reference signal of antenna port group A occupies subband 1, subband 2, and subband 3, the reference signal of antenna port group B occupies subband 1, subband 5, and subband 6, and the reference signal of antenna port group C occupies subband 1, subband 4, and subband 5. The reference signals of the three antenna port groups all occupy the same subband 1.

[0237] Optionally, the K antenna port groups include a first antenna port group and a second antenna port group, and the time slot interval corresponding to the first antenna port group and the second antenna port group is less than or equal to a first threshold. For example, the multiple antenna port groups are located in the same time slot or adjacent time slots, and the time slot interval between the multiple antenna port groups does not exceed t. t is an example of the first threshold, which may be predefined or configured.

[0238] The time slot interval corresponding to the antenna port group can be understood as the interval between the positions of the reference signals corresponding to different antenna port groups on the time domain resources.

[0239] 1020. The transmitting end compresses N channel information using a first encoder to obtain a first sequence.

[0240] The first sequence is a joint feedback amount of N channel information in 1010. In other words, the first sequence can indicate N channel information. In other words, the first sequence includes N channel information.

[0241] The first sequence may be a sequence before quantization. For example, the first sequence may be a one-dimensional real number or complex number sequence, representing N channel information.

[0242] The first sequence may be a quantized sequence. For example, the first sequence includes X bits. In other words, the X bits indicate N channel information.

[0243] Before using the first encoder to compress the N channel information, second information may also be received, where the second information indicates the first encoder. For example, the second information indicates an identifier of the first encoder. Furthermore, different encoders have different identifiers, and the first encoder belongs to at least one encoder.

[0244] Optionally, the first encoder corresponds to a first parameter set, and the first parameter set includes at least one of the following:

[0245] The value of N, the joint feedback overhead X, the K antenna port groups corresponding to the N channel information, the N combination coefficient sets corresponding to the N channel information,

[0246] When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, and the length of the first sequence can be understood as the number of elements included in the first sequence.

[0247] Alternatively, when the first sequence is a quantized sequence, the joint feedback overhead is the number of bits of the first sequence.

[0248] The K antenna port groups corresponding to the N channel information may be indicated by indexes of the K antenna port groups.

[0249] In other words, the first encoder is used to compress channel information corresponding to the first parameter set.

[0250] Optionally, different encoders correspond to different parameter sets.

[0251] For example, the second encoder corresponds to a second parameter set, and the parameters included in the parameter set corresponding to the second encoder are different from the parameters included in the parameter set corresponding to the first encoder. For example, the first parameter set includes parameters related to channel information, and the second parameter set includes parameters related to other information. That is, the first encoder is used to compress channel information, and the second encoder is used to compress other information.

[0252] For example, the values ​​of the parameters included in the parameter set corresponding to the second encoder are different from the values ​​of the parameters included in the parameter set corresponding to the first encoder. For example, the values ​​of the combination coefficient set included in the first parameter set are different from the values ​​of the combination coefficient set included in the second parameter set.

[0253] In one possible implementation, the first encoder may be used to compress channel information corresponding to multiple groups of simulated beams. In other words, the first encoder may correspond to different groups of simulated beams, or the first encoder may correspond to different groups of channel information.

[0254] 1030. The transmitting end sends a first sequence to the receiving end. Correspondingly, the receiving end receives the first sequence.

[0255] 1040. The receiving end uses a first decoder to decompress the first sequence to obtain N channel information.

[0256] In other words, the receiving end uses the first decoder to reconstruct the first sequence to obtain N channel information.

[0257] The first decoder corresponds to the first parameter set. The first parameter set can refer to the description in 1020 and will not be repeated here.

[0258] Optionally, different decoders correspond to different parameter sets.

[0259] For example, the second decoder corresponds to a second parameter set, and the parameters included in the parameter set corresponding to the second decoder are different from the parameters included in the parameter set corresponding to the first decoder. For example, the first parameter set includes parameters related to channel information, and the second parameter set includes parameters related to other information. That is, the first decoder is used to compress channel information, and the second decoder is used to compress other information.

[0260] For example, the values ​​of the parameters included in the parameter set corresponding to the second decoder are different from the values ​​of the parameters included in the parameter set corresponding to the first decoder. For example, the values ​​of the combination coefficient set included in the first parameter set are different from the values ​​of the combination coefficient set included in the second parameter set.

[0261] In one possible implementation, the first decoder may be used to compress channel information corresponding to multiple groups of analog beams. In other words, the first decoder may correspond to different groups of analog beams, or the first decoder may correspond to different groups of channel information.

[0262] It should be understood that the transmitting end can be understood as the transmitter of the first sequence, and the receiving end can be understood as the receiver of the first sequence. The transmitting end can be a device equipped with an encoder, and the receiving end can be a device equipped with a decoder. For example, the transmitting end can be a terminal device, and the receiving end can be a network device.

[0263] It should also be understood that the first sequence is only an example of compressing channel information.

[0264] This method uses an encoder to jointly compress and feed back the channel information of the simulated beam, and then uses a decoder to decompress the channel information of the simulated beam, thereby reducing the overhead of feeding back the channel information.

[0265] To facilitate a clear understanding of the method of the present application, a communication process diagram 13 is shown below. In this communication process, a network device and a terminal device are used as examples of the communicating parties. The terminal device is equipped with an encoder, and the network device is equipped with a decoder. The CSI-RS is used as an example of a reference signal, and the precoding matrix is ​​used as an example of channel information.

[0266] Specifically, the following steps are included:

[0267] 1310. The network device sends a reference signal and channel information reporting (or measurement) configuration information to the terminal device.

[0268] Reference signal configuration information includes information related to reference signal port grouping. For example, the number of groups is K, and the number of ports in each group is P. CSI-RS,k ,k=0,1,…,K-1. In one case, the number of ports in each port group is exactly the same, for example, P CSI-RS .

[0269] The reference signal configuration information also includes information related to the reference signal resource grouping. For example, the number of reference signal resource groups K, the number of reference signal resources and / or ports in each group P respectively. CSI-RS,k ,k=0,1,…,K-1. In one case, the total number of ports in each resource group is exactly the same, for example, P CSI-RS In the following text, unless otherwise specified, reference signal port groups (or port groups) are used as examples for description. The same method can be applied to the reference resource grouping scenario.

[0270] Channel information reporting configuration information, including the content and quantity of the report. For example, the configuration information includes the number of measured channel information groups N, the feedback overhead X, and the identifier (ID) of the encoder and / or decoder for joint compression and reconstruction;

[0271] The reference signal configuration information and / or the channel information reporting configuration information may further include a CSI-RS transmission method and / or a relationship between a CSI-RS port group and multi-analog beam channel information.

[0272] The CSI-RS may be sent in a time division, frequency division, or code division manner, which will be described in detail below (in step 1320).

[0273] The relationship between the CSI-RS port group and the multiple analog beam channel information can be the relationship between the number of CSI-RS port groups and the number of analog beam channel information, such as the number of CSI-RS port groups is less than the number of analog beam channel information, or the number of CSI-RS port groups is equal to the number of analog beam channel information. Further, as mentioned above, assuming that the number of CSI-RS port groups is less than the number of analog beam channel information, that is, the N analog beam channel information is determined based on the channel information and channel combination coefficients of the K CSI-RS port groups, the relationship between the CSI-RS port group and the multiple analog beam channel information can also be the correspondence between the N analog beam channel information and the associated K CSI-RS port groups. For example, the correspondence is indicated by the K port group combination coefficients. Optionally, the combination coefficient is represented in the form of a matrix, a sequence, or a character string.

[0274] This step 1310 is optional.

[0275] 1320. The network device sends a CSI-RS on the resources configured by the reference signal configuration information. Correspondingly, the terminal device receives the CSI-RS.

[0276] In one implementation, different CSI-RS port groups (an example of an antenna port group) transmit CSI-RS using a time-division approach, that is, transmitting CSI-RS on different time domain resources (i.e., time slots or OFDM symbols). This time-division approach facilitates the transmission of multiple reference signals based on different analog beams in the HBF architecture, enabling channel information measurement.

[0277] In one implementation, different CSI-RS port groups transmit CSI-RSs on different frequency domain resources (i.e., component carriers, resource blocks, or different subcarriers). For example, a first CSI-RS is transmitted on a first CSI-RS port group, and a second CSI-RS is transmitted on a second CSI-RS port group. Frequency-division transmission of reference signals enables base stations to quickly scan channel information, improving efficiency.

[0278] In one implementation, different CSI-RS port groups are transmitted using OCC code division. For example, the first antenna group transmits based on a first simulated beam, while the second antenna group transmits based on a second simulated beam orthogonal to the first. This approach can also be used in the HBF architecture to enable base stations to quickly scan channel information.

[0279] In one possible implementation, the base station configures CSI-RS port groups 1 to K separately. Multiple port groups are in the same frequency domain (but can still be located in different resource units of the same resource block) and occupy the same bandwidth. In addition, multiple port groups are located in the same time slot or adjacent time slots, and the time slot offset of the time domain resources of multiple CSI-RS port groups does not exceed t to ensure the timeliness of joint feedback of multiple groups of channel information and the performance of joint compression.

[0280] The value or value range of t may be predefined or configured.

[0281] This step 1320 is optional.

[0282] 1330. The terminal device reports configuration information according to the CSI-RS and channel information, and obtains the precoding matrix of N simulated beams.

[0283] Specifically, reference may be made to the methods of obtaining channel information in Case 1 and Case 2 in 1010 .

[0284] This step 1330 is optional.

[0285] 1340, the terminal device selects the encoder (ENC) according to the ID configured by the network device.

[0286] Here the encoder may include one or more AI models. It should be noted that the AI ​​model configured by the network device for joint feedback is related to the number of simulated beams N for joint feedback, the feedback overhead X, the K CSI-RS port groups and their combination coefficients. (If the channel information is obtained through case 2, it exists ) corresponding to.

[0287] It should be understood that step 1340 is optional. For example, if the network device is not configured with the encoder used by the terminal device, the terminal device can select an encoder on its own. The terminal device can also indicate to the network device the decoder used by the network device. In other words, regardless of how the encoder and decoder are configured, the encoder and decoder used by the terminal device and the network device correspond to the above parameters, thereby avoiding codec inconsistencies.

[0288] Specifically, the manner in which the terminal device indicates the encoder or decoder to the network device may refer to step 1360 .

[0289] 1350. The terminal device compresses the precoding matrix under N simulated beams.

[0290] As shown in Figure 14, the terminal combines the precoding matrices {v1, v2, v3, …} for N analog beams and jointly inputs them to the encoder for joint compression. The encoder outputs an X-bit sequence A, which is the joint feedback quantity corresponding to the precoding matrices for the N analog beams. It is important to note that the input arrangement and stacking of the precoding matrices for the N analog beams can be defined during training and should be consistent with the training process to ensure a one-to-one correspondence between the input logical numbers Beam 1 to Beam N and the N analog beams.

[0291] Optionally, the terminal device may further perform quantization after jointly compressing the precoding matrices of the N analog beams.

[0292] 1360. The terminal device sends sequence A to the network device, and correspondingly, the network device receives sequence A.

[0293] As shown in FIG14 , the network device receives a joint feedback amount sequence A.

[0294] Optionally, the terminal device further sends indication information to the network device, where the indication information indicates an encoder used by the terminal device. For example, the indication information indicates an ID of the encoder used by the terminal device.

[0295] Alternatively, the indication information indicates a decoder used by the network device. For example, the indication information indicates an ID of a decoder used by the network device.

[0296] 1370. The network device decompresses sequence A to obtain precoding matrices of N simulated beams.

[0297] For example, the network device configures the number of simulated beams N, the feedback overhead X, the K CSI-RS port groups and their combination coefficients for the joint feedback to the terminal device. (If the channel information is obtained through case 2, it exists ) selects the corresponding decoder (DEC) (defined as an AI model), and inputs the sequence into the decoder for reconstruction (also called decompression). The output is the precoding matrix {v1, v2, v3, …} under N simulated beams.

[0298] It should be noted that the output arrangement and stacking method of the precoding matrix of the N simulated beams can be defined during training and kept consistent with the training process to ensure that the input logical sequence numbers Beam 1 to Beam N maintain a one-to-one correspondence with the physical N simulated beams.

[0299] The embodiment of the present application also provides a training method, which takes offline joint training of a two-end network as an example below (it should be understood that offline joint training is not the only training method for a two-end network, and the network can still be trained offline through other training methods, such as independent training of the two ends).

[0300] The training method 1500 includes:

[0301] 1510, obtaining a first training data set,

[0302] The first training data set includes N data, where the N data are determined based on reference signals on K antenna port groups, where N is a positive integer and K is a positive integer less than or equal to N.

[0303] Specifically, the method for determining the N data may refer to the description of case 1 or case 2 in 910 .

[0304] For example, when collecting training data for a multi-beam precoding matrix, each data set must correspond to its parameter configuration, such as the number of simulated beams N, the corresponding K CSI-RS port groups, and their combination coefficients. (if any) etc. In each data sample, the beam-domain precoding matrix is ​​logically numbered Beam 1 to Beam N. These logical numbers must correspond one-to-one with the N simulated beams corresponding to the physical K CSI-RS port groups to ensure consistent understanding of the simulated beams by network devices and terminal devices.

[0305] 1520, training the first model.

[0306] The first model includes a first sub-model and a second sub-model. The input of the first sub-model includes a first training data set. The output of the first sub-model is the input of the second sub-model. The second sub-model outputs a second training data set. The second training data set indicates N data. The output of the first sub-model is a first sequence. The first sequence is the joint feedback amount of the N data.

[0307] It should be understood that the first sub-model and the second sub-model can also be trained independently.

[0308] The second training data set may be the same as the first training data set, that is, the second training data set is completely identical to the first training data set.

[0309] The second training dataset may also differ from the first training dataset. That is, the second training dataset may have a certain deviation / error from the first training dataset, and the deviation / error is within an allowable range. Alternatively, the deviation / error is within an acceptable range. The allowable range of the deviation / error may be predefined or configurable. Alternatively, the second training dataset may be a processed version of the first training dataset, for example, the second training dataset may include the first training dataset.

[0310] Optionally, the first sub-model may be an encoder, and the second sub-model may be a decoder.

[0311] Optionally, the encoder and decoder used for training and use can be aligned by defining the AI ​​model ID, as well as the simulated beam combination that supports joint feedback. A model ID combination (encoder ID-decoder ID) can correspond to one or more groups of feedback configuration parameters, including the number of joint feedback beams N, the joint feedback overhead X, the K CSI-RS port groups corresponding to the N simulated beams of joint feedback, and their combination coefficients. (If present). The terminal device or network device defines the model ID, uniformly defines one or more sets of feedback configuration parameters corresponding to the model ID combination, and selects the corresponding configuration data set for joint training. By associating the model ID group, feedback configuration parameters, and training data set, the performance of the dual-end AI model in joint feedback can be guaranteed.

[0312] As shown in Figure 16, after the model and its training dataset are determined, the encoder / decoder is jointly trained on the network device, terminal device or third party.

[0313] Optionally, after the joint training is completed, the trained encoder (ENC) is sent to the terminal device, and the decoder (DEC) is sent to the base station for joint feedback of the multi-beam precoding matrix.

[0314] It is important to note that during joint training, the terminal / base station must uniformly define the correspondence between the logical numbers Beam 1 to Beam N of the input and output precoding matrix simulated beams and the N simulated beams corresponding to the actual K CSI-RS port groups in a physical sense. The terminal / base station must also define the stacking method of the N simulated beam precoding matrices on the input and output sides to ensure a unified understanding of the N simulated beams on the input and output sides of the AI ​​model, thereby ensuring the joint compression performance of the solution. The stacking method of the N simulated beam precoding matrices on the input and output sides can be referred to the description of Methods 1 to 3 in 1010 and will not be repeated here.

[0315] This method enables the encoder-decoder to have the ability to compress and reconstruct the channel information of N simulated beams through joint training.

[0316] It is understood that in some of the above embodiments, terminal devices and network devices are mainly used as examples for illustration, and this is not limiting. For example, the terminal device can also be replaced by a component of the terminal device (such as a chip or circuit), and the network device can also be replaced by a component of the network device (such as a chip or circuit).

[0317] It can also be understood that the solutions in the various embodiments of the present application can be reasonably combined and used, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained with each other in the various embodiments, without limitation to this.

[0318] Figure 17 is a schematic block diagram of a communication device 1700 provided in an embodiment of the present application. Device 1700 includes a transceiver unit 1710 and a processing unit 1720. Transceiver unit 1710 can be used to implement corresponding communication functions. Transceiver unit 1710 can also be referred to as a communication interface or communication unit. Processing unit 1720 can be used to perform data processing.

[0319] Optionally, the device 1700 may further include a storage unit, which may be used to store instructions and / or data. The processing unit 1720 may read the instructions and / or data in the storage unit so that the device implements the aforementioned method embodiment.

[0320] As a design, the apparatus 1700 is configured to execute the steps or processes executed by the encoder, or a device equipped with an encoder, or a chip for an encoder, in the above method embodiments, such as the steps or processes executed by the transmitting end in the embodiment shown in FIG10 , and the steps or processes executed by the encoder in the embodiment shown in FIG15 . The transceiver unit 1710 is configured to execute the transceiver-related operations on the encoder side (or the transmitting end) in the above method embodiments, and the processing unit 1720 is configured to execute the processing-related operations on the encoder side (or the transmitting end) in the above method embodiments.

[0321] In one possible implementation, the processing unit 1720 is used to obtain N channel information, where the N channel information is determined based on the reference signal on K antenna port groups, where N is a positive integer and K is a positive integer less than or equal to N; the processing unit 1720 is also used to compress the N channel information using a first encoder to obtain a first sequence, where the first sequence is a joint feedback amount of the N channel information; the transceiver unit 1710 is used to send N compressed information to the decoder.

[0322] In one example, the first encoder corresponds to a first parameter set, and the first parameter set includes at least one of the following:

[0323] The value of N, the joint feedback overhead X, the K antenna port groups corresponding to the N channel information, and the N combination coefficient sets corresponding to the N channel information. When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, or when the first sequence is a sequence after quantization, the joint feedback overhead is the number of bits of the first sequence. X is a positive integer, and K is a positive integer.

[0324] In another example, the first encoder corresponds to at least one of the first parameter sets.

[0325] In another example, the device equipped with the encoder is a terminal device, and the device equipped with the decoder is a network device.

[0326] As another design, the apparatus 1700 is configured to execute the steps or processes executed by the decoder, or a device equipped with a decoder, or a chip for a decoder, in the above method embodiments, such as the steps or processes executed by the receiving end in the embodiment shown in FIG10 , and the steps or processes executed by the decoder in the embodiment shown in FIG15 . The transceiver unit 1710 is configured to execute the transceiver-related operations on the decoder side (or receiving end) in the above method embodiments, and the processing unit 1720 is configured to execute the processing-related operations on the decoder side (or receiving end) in the above method embodiments.

[0327] In one possible implementation, the transceiver unit 1710 is used to receive a first sequence, where the first sequence is a joint feedback amount of N channel information, where the N channel information is determined based on a reference signal on K antenna port groups, where N is a positive integer and K is a positive integer less than or equal to N; and the processing unit 1720 is used to decompress the first sequence using a first decoder to obtain the N channel information.

[0328] In one example, the first decoder corresponds to a first parameter, and the first parameter includes at least one of the following:

[0329] The value of N, the joint feedback overhead X, the K antenna port groups corresponding to the N channel information, and the N combination coefficient sets corresponding to the N channel information. When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, or when the first sequence is a sequence after quantization, the joint feedback overhead is the number of bits of the first sequence. X is a positive integer, and K is a positive integer.

[0330] In another example, the first decoder corresponds to at least one of the first parameter sets.

[0331] In another example, the device equipped with the encoder is a terminal device, and the device equipped with the decoder is a network device.

[0332] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0333] It should also be understood that the device 1700 here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a combined logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art will understand that the device 1700 can be specifically the first terminal device in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the first terminal device in the above-mentioned method embodiments, or the device 1700 can be specifically the second terminal device in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the second terminal device in the above-mentioned method embodiments. To avoid repetition, it will not be described here.

[0334] The apparatus 1700 of each of the above-mentioned solutions has the function of implementing the corresponding steps performed by the first terminal device in the above-mentioned method, or the apparatus 1700 of each of the above-mentioned solutions has the function of implementing the corresponding steps performed by the second terminal device in the above-mentioned method. The functions can be implemented by hardware, or can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending 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 to respectively perform the sending and receiving operations and related processing operations in each method embodiment.

[0335] In addition, the transceiver unit 1710 may also be a transceiver circuit (for example, may include a receiving circuit and a transmitting circuit), and the processing unit may be a processing circuit.

[0336] It should be noted that the apparatus in FIG17 may be a network element or device in the aforementioned embodiment, or may be a chip or chip system, such as a system on chip (SoC). The transceiver unit may be an input / output circuit or a communication interface; the processing unit may be a processor, microprocessor, or integrated circuit integrated on the chip. This is not limited here.

[0337] FIG18 is a schematic diagram of another communication device 1800 provided in an embodiment of the present application. The device 1800 includes a processing circuit 1810 coupled to a memory 1820. The memory 1820 is configured to store computer programs or instructions and / or data. The processing circuit 1810 is configured to execute the computer programs or instructions stored in the memory 1820, or read data stored in the memory 1820, to perform the methods described in the above method embodiments.

[0338] Optionally, the processing circuit 1810 is one or more processors or a circuit in one or more processors for processing or control.

[0339] Optionally, the memory 1820 is one or more.

[0340] Optionally, the memory 1820 is integrated with the processing circuit 1810 or provided separately.

[0341] Optionally, as shown in Figure 18, the device 1800 further includes a transceiver circuit 1830, which is used to receive and / or send signals. For example, the processing circuit 1810 is used to control the transceiver circuit 1830 to receive and / or send signals.

[0342] As an example, the processing circuit 1810 may have the function of the processing unit 1720 shown in FIG. 17 , the memory 1820 may have the function of a storage unit, and the transceiver circuit 1830 may have the function of the transceiver unit 1710 shown in FIG. 17 .

[0343] As a solution, the device 1800 is used to implement the operations performed by the encoder in the above various method embodiments.

[0344] For example, the processing circuit 1810 is configured to execute the computer program or instructions stored in the memory 1820 to implement the encoder-related operations in the various method embodiments described above, such as the method performed by the encoder in the embodiment shown in FIG. 10 , or the method performed by the terminal device in either of the embodiments shown in FIG. 13 or FIG. 15 .

[0345] As another solution, the device 1800 is used to implement the operations performed by the decoder in the above various method embodiments.

[0346] For example, the processing circuit 1810 is configured to execute the computer program or instructions stored in the memory 1820 to implement the decoder-related operations in the various method embodiments described above, such as the method performed by the decoder in the embodiment shown in FIG. 10 , or the method performed by the network device in either of the embodiments shown in FIG. 13 or FIG. 15 .

[0347] It should be understood that the apparatus 1800 may be the aforementioned encoder, decoder, a chip for an encoder or decoder, or a device including an encoder or decoder.

[0348] When the apparatus 1800 is a network device or a user equipment, the transceiver circuit 1830 may be a transceiver.

[0349] When the device 1800 is a chip for an encoder or a decoder, the transceiver circuit 1830 may be an input / output interface.

[0350] When the device 1800 is a device that is physically independent of the network device or user device, such as an OTT device or a cloud server, the device 1800 communicates with the network device or user device, such as sending or receiving the first sequence, through the air interface between the network device and the user device.

[0351] It should be understood that the processor mentioned in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0352] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory and / or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0353] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) can be integrated into the processor.

[0354] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0355] 19 is a schematic diagram of a chip system 1900 according to an embodiment of the present application. The chip system 1900 (or also referred to as a processing system) includes a processing circuit 1910 (also referred to as a logic circuit) and an input / output interface 1920.

[0356] Logic circuit 1910 may be a processing circuit within chip system 1900. Logic circuit 1910 may be coupled to a storage unit and invoke instructions within the storage unit, enabling chip system 1900 to implement the methods and functions of various embodiments of the present application. Input / output interface 1920 may be an input / output circuit within chip system 1900, outputting information processed by chip system 1900 or inputting data or signaling information to be processed into chip system 1900 for processing.

[0357] Specifically, for example, if the chip system 1900 is installed in an encoder, the logic circuit 1910 is coupled to the input / output interface 1920, and the logic circuit 1910 can send compressed information to the decoder through the input / output interface 1920. The compressed information can be obtained by the logic circuit 1910 by compressing the channel information; or the input / output interface 1920 can input a message from the second terminal device to the logic circuit 1910 for processing. For another example, if the chip system 1900 is installed in a decoder, the logic circuit 1910 is coupled to the input / output interface 1920, and the input / output interface 1920 can input the compressed information from the encoder to the logic circuit 1910 for processing.

[0358] As a solution, the chip system 1900 is used to implement the operations performed by the encoder in the above various method embodiments.

[0359] For example, the logic circuit 1910 is used to implement the processing-related operations performed by the encoder in the above method embodiments, such as the processing-related operations performed by the encoder (or transmitting end) in the embodiment shown in Figure 10, or the processing-related operations performed by the encoder in the embodiment shown in Figure 15; the input / output interface 1920 is used to implement the sending and / or receiving-related operations performed by the encoder in the above method embodiments, such as the sending and / or receiving-related operations performed by the encoder (or transmitting end) in the embodiment shown in Figure 10, or the sending and / or receiving-related operations performed by the encoder in the embodiment shown in Figure 15.

[0360] As another solution, the chip system 1900 is used to implement the operations performed by the decoder in the above various method embodiments.

[0361] For example, the logic circuit 1910 is used to implement the processing-related operations performed by the decoder in the above method embodiments, such as the processing-related operations performed by the decoder (or receiving end) in the embodiment shown in Figure 10, or the processing-related operations performed by the decoder in the embodiment shown in Figure 15; the input / output interface 1920 is used to implement the sending and / or receiving-related operations performed by the decoder (or receiving end) in the above method embodiments, such as the sending and / or receiving-related operations performed by the decoder (or receiving end) in the embodiment shown in Figure 10, or the sending and / or receiving-related operations performed by the decoder in the embodiment shown in Figure 15.

[0362] An embodiment of the present application further provides a computer-readable storage medium on which computer instructions for implementing the methods executed by the encoder or decoder in the above-mentioned method embodiments are stored.

[0363] For example, when the computer program is executed by a computer, the computer can implement the method performed by the encoder or decoder in each embodiment of the above method.

[0364] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed by a computer, implement the methods performed by the encoder or decoder in the above-mentioned method embodiments.

[0365] The present application also provides a communication system including the encoder and decoder of each of the above embodiments. For example, the system includes the transmitting end and receiving end shown in FIG10 , or the encoder and decoder of the embodiment shown in FIG15 . For another example, the system includes a terminal device equipped with an encoder and a network device equipped with a decoder.

[0366] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.

[0367] In the several embodiments provided in this 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. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0368] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part 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, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. For example, the computer can be a personal computer, a server, or a network device, etc. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)). For example, the aforementioned available medium includes, but is not limited to, various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0369] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: include: Acquire N channel information, where the N channel information is determined based on reference signals on K antenna port groups, where N is a positive integer, and K is a positive integer less than or equal to N; Compressing the N channel information using a first encoder to obtain a first sequence, where the first sequence is a joint feedback amount of the N channel information; The first sequence is transmitted.

2. The method according to claim 1, characterized in that The first encoder corresponds to a first parameter set, and the first parameter set includes at least one of the following: The value of N, the joint feedback overhead X, the K antenna port groups corresponding to the N channel information, the N combination coefficient sets corresponding to the N channel information, When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, or, When the first sequence is a quantized sequence, the joint feedback overhead is the number of bits of the first sequence, X is a positive integer, and K is a positive integer.

3. The method according to claim 2, characterized in that The first encoder corresponds to at least one of the first parameter sets.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Second information is received, the second information indicating the first encoder.

5. The method according to any one of claims 1 to 4, characterized in that The correspondence between the N channel information and the K antenna port groups is predefined or configured.

6. The method according to claim 5, characterized in that The N channel information is input into the first encoder in a predefined order and / or in a stacked manner.

7. The method according to any one of claims 1 to 6, characterized in that The N channel information are arranged in a first order along the frequency domain direction on the frequency domain resource unit, or, The N channel information is arranged in a second order along the port or port group domain direction on the frequency domain resource unit, or, The N channel information are arranged in a third order along the beam domain on the frequency domain resource unit.

8. The method according to claim 7, characterized in that The first order, the second order, and the third order are predefined or configured.

9. The method according to any one of claims 1 to 8, characterized in that The frequency domain resources of the K antenna port groups include the same one or more subbands.

10. The method according to any one of claims 1 to 9, characterized in that The K antenna port groups include a first antenna port group and a second antenna port group, and time slot offsets of time domain resources corresponding to the first antenna port group and the second antenna port group are less than or equal to a first threshold.

11. The method according to claim 10, characterized in that The first threshold is predefined or configured.

12. The method according to any one of claims 1 to 11, characterized in that The N channel information are calculated based on K channel information measured by K antenna port groups and N combination coefficient sets, wherein each channel information of the N channel information is obtained based on the K channel information and a combination coefficient set including K coefficients.

13. A communication method, characterized in that: include: receiving a first sequence, where the first sequence is a joint feedback amount of N channel information, where the N channel information is determined based on reference signals on K antenna port groups, where N is a positive integer, and K is a positive integer less than or equal to N; The first sequence is decompressed using a first decoder to obtain the N channel information.

14. The method according to claim 13, characterized in that The first decoder corresponds to a first parameter set, and the first parameter set includes at least one of the following: The value of N, the joint feedback overhead X, the K antenna port groups corresponding to the N channel information, the N combination coefficient sets corresponding to the N channel information, When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, or, When the first sequence is a quantized sequence, the joint feedback overhead is the number of bits of the first sequence, X is a positive integer, and K Is a positive integer.

15. The method according to claim 14, characterized in that The first decoder corresponds to at least one of the first parameter sets.

16. The method according to any one of claims 13 to 15, characterized in that The correspondence between the N channel information and the K antenna port groups is predefined or configured.

17. The method according to claim 16, characterized in that The N channel information is output from the first decoder in a predefined order and / or in a stacked manner.

18. The method according to any one of claims 13 to 17, characterized in that The frequency domain resources of the K antenna port groups include the same one or more subbands.

19. The method according to any one of claims 13 to 18, characterized in that The K antenna port groups include a first antenna port group and a second antenna port group, and time slot offsets of time domain resources corresponding to the first antenna port group and the second antenna port group are less than or equal to a first threshold.

20. The method according to claim 19, characterized in that The first threshold is predefined or configured.

21. The method according to any one of claims 13 to 20, characterized in that The N channel information are functions of K channel information measured according to K antenna port groups and N combination coefficient sets, wherein each channel information of the N channel information is a function of the K channel information and a combination coefficient set including K coefficients.

22. The method according to any one of claims 13 to 21, characterized in that The N channel information are calculated based on the K channel information measured by the K antenna port groups and the N combination coefficient sets.

23. A training method, characterized in that: The method includes: acquiring a first training data set, the first training data set including N data, the N data being determined based on reference signals on K antenna port groups, the N being a positive integer, and the K being a positive integer less than or equal to N; The first model is trained, wherein the first model includes a first sub-model and a second sub-model, the input of the first sub-model includes first training data, the output of the first sub-model is the input of the second sub-model, the second sub-model outputs a second training data set, the second training data set indicates the N data, and the output of the first sub-model is a first sequence, which is a joint feedback amount of the N data.

24. The method according to claim 23, characterized in that The first model corresponds to a first parameter set, and the first parameter set includes at least one of the following: a value of N, a joint feedback overhead X, the K antenna port groups corresponding to the N data, and N combination coefficient sets corresponding to the N data. When the first sequence is a sequence before quantization, the joint feedback overhead is the length of the first sequence, or, When the first sequence is a quantized sequence, the joint feedback overhead is the number of bits of the first sequence, X is a positive integer, and K is a positive integer.

25. The method according to claim 24, characterized in that The first model corresponds to at least one of the first parameter sets.

26. The method according to any one of claims 23 to 25, characterized in that The first model corresponds to at least one training data set, and the first training data set belongs to the at least one training data set.

27. The method according to any one of claims 23 to 26, characterized in that The correspondence between the N data and the K antenna port groups is predefined or configured.

28. The method according to any one of claims 23 to 27, characterized in that The N data are input into the first model in a predefined order and / or in a stacked manner.

29. The method according to any one of claims 23 to 28, characterized in that The frequency domain resources of the K antenna port groups include the same one or more subbands.

30. The method according to any one of claims 23 to 29, characterized in that The K antenna port groups include a first antenna port group and a second antenna port group, and time slot offsets of time domain resources corresponding to the first antenna port group and the second antenna port group are less than or equal to a first threshold.

31. The method according to any one of claims 23 to 30, characterized in that The N data are functions of K channel information measured according to K antenna port groups and N combination coefficient sets, wherein each channel information of the N channel information is a function of the K channel information and a combination coefficient set including K coefficients.

32. A communication device, characterized in that: The method comprises modules or units for executing the method according to any one of claims 1 to 31.

33. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or instruction, and when the computer program or instruction is executed on the communication device, the communication device executes the method according to any one of claims 1 to 31.

34. A computer program product, characterized in that The computer program product comprises a computer program or instructions for performing the method according to any one of claims 1 to 31 .

35. A chip, characterized in that: The chip includes a processor and a communication interface, and the processor reads instructions stored in a memory through the communication interface, so that the method according to any one of claims 1 to 31 is executed.

36. A communication system, characterized in that: The method comprises an encoder and a decoder, wherein the encoder is used to execute the method according to any one of claims 1 to 12, and the decoder is used to execute the method according to any one of claims 13 to 22.

Images