Data transmission method and communication device

Abstract

The present application relates to a data transmission method and a communication device. The method comprises: a first communication device sends processing data, the processing data being obtained by processing a plurality of pieces of information to be processed. According to embodiments of the present application, the plurality of pieces of information to be processed are processed, and then the processing data is transmitted, so that the amount of data needing to be transmitted can be reduced, thereby reducing the signaling overhead of a system.

Description

Data transmission method and communication device TECHNICAL FIELD

[0001] The present application relates to the field of communication, and more particularly, to a data transmission method and a communication device. BACKGROUND

[0002] Artificial intelligence (AI) based solutions are increasingly applied in wireless communication systems. For example, channel state information (CSI) feedback, CSI prediction, etc. are implemented through artificial intelligence. The performance evaluation results of the AI solution and other information can bring a large amount of data transmission and signaling overhead.

[0003] SUMMARY

[0004] Embodiments of the present application provide a data transmission method and a communication device, which can reduce the amount of data to be transmitted.

[0005] Embodiments of the present application provide a data transmission method, comprising: a first communication device sending processed data, the processed data being obtained by processing a plurality of to-be-processed information.

[0006] Embodiments of the present application provide a data transmission method, comprising: a second communication device receiving processed data, the processed data being obtained by a first communication device processing a plurality of to-be-processed information.

[0007] Embodiments of the present application provide a first communication device, comprising: a sending unit configured to send processed data, the processed data being obtained by processing a plurality of to-be-processed information.

[0008] Embodiments of the present application provide a second communication device, comprising: a receiving unit configured to receive processed data, the processed data being obtained by a first communication device processing a plurality of to-be-processed information.

[0009] Embodiments of the present application provide a communication device, comprising a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and run the computer program stored in the memory, so that the communication device executes the above-mentioned data transmission method.

[0010] Embodiments of the present application provide a chip for implementing the above-mentioned data transmission method. Specifically, the chip comprises a processor configured to call and run a computer program from a memory, so that a device installed with the chip executes the above-mentioned data transmission method.

[0011] The embodiment of the present application provides a computer readable storage medium, used for storing a computer program, which, when executed by a device, causes the device to perform the data transmission method.

[0012] The embodiment of the present application provides a computer program product, comprising computer program instructions, which cause a computer to perform the data transmission method.

[0013] The embodiment of the present application provides a computer program, which, when executed on a computer, causes the computer to perform the data transmission method.

[0014] The embodiment of the present application processes a plurality of to-be-processed information, and then transmits the processed data, so that the amount of data to be transmitted is reduced, and system signaling overhead is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0015] FIG. 1 is a schematic diagram of an application scenario according to the embodiment of the present application.

[0016] FIG. 2A is a schematic flowchart of a CSI feedback problem.

[0017] FIG. 2B is a schematic flowchart of a CSI prediction problem.

[0018] FIG. 3 is a schematic flowchart of a data transmission method according to the embodiment of the present application.

[0019] FIG. 4 is a schematic flowchart of a data transmission method according to the embodiment of the present application.

[0020] FIG. 5A is a schematic diagram of a UE transmitting first data to a network.

[0021] FIGS. 5B to 5E are schematic diagrams of examples of the UE transmitting first data to the network.

[0022] FIG. 6A is a schematic diagram of a network transmitting second data to a UE.

[0023] FIGS. 6B to 6E are schematic diagrams of examples of the network transmitting second data to the UE.

[0024] FIG. 7 is a schematic block diagram of a first communication device according to the embodiment of the present application.

[0025] FIG. 8 is a schematic block diagram of a second communication device according to the embodiment of the present application.

[0026] FIG. 9 is a schematic block diagram of a communication device according to the embodiment of the present application.

[0027] FIG. 10 is a schematic block diagram of a chip according to the embodiment of the present application.

[0028] FIG. 11 is a schematic block diagram of a communication system according to the embodiment of the present application. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

[0030] The technical solutions in the embodiments of the present application can be applied to various communication systems, such as a Global System of Mobile communication (GSM) system, a Code Division Multiple Access (CDMA) system, a Wideband Code Division Multiple Access (WCDMA) system, a General Packet Radio Service (GPRS), a Long Term Evolution (LTE) system, an Advanced long term evolution (LTE-A) system, a New Radio (NR) system, an evolved system of the NR system, an LTE-based access to unlicensed spectrum (LTE-U) system, an NR-based access to unlicensed spectrum (NR-U) system, a Non-Terrestrial Networks (NTN) system, a Universal Mobile Telecommunication System (UMTS), a Wireless Local Area Networks (WLAN), a Wireless Fidelity (WiFi), a 5th-Generation (5G) system, or other communication systems, etc.

[0031] Generally, a conventional communication system supports a limited number of connections and is easy to implement. However, with the development of communication technology, a mobile communication system will not only support conventional communication, but also support, for example, Device to Device (D2D) communication, Machine to Machine (M2M) communication, Machine Type Communication (MTC), Vehicle to Vehicle (V2V) communication, or Vehicle to everything (V2X) communication, and the like. Embodiments of the present application can also be applied to these communication systems.

[0032] In an embodiment, the communication system in the embodiments of the present application can be applied to a Carrier Aggregation (CA) scenario, can also be applied to a Dual Connectivity (DC) scenario, and can also be applied to a Standalone (SA) network deployment scenario.

[0033] In an embodiment, the communication system in the embodiments of the present application can be applied to an unlicensed spectrum, which can also be considered as a shared spectrum, or can be applied to a licensed spectrum, which can also be considered as a non-shared spectrum.

[0034] Embodiments of the present application describe various embodiments in combination with network devices and terminal devices, wherein the terminal device can also be referred to as User Equipment (UE), access terminal, subscriber unit, subscriber station, mobile station, mobile, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user equipment, etc.

[0035] The terminal device can be a station (STATION, ST) in a WLAN, can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device, or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0036] In the embodiments of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; can also be deployed on the water surface (such as ships, etc.); and can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0037] In the embodiments of the present application, the terminal device can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self driving, a wireless terminal device in remote medical treatment, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, or a wireless terminal device in smart home, etc.

[0038] By way of example and not limitation, in the embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing and shoes, etc. The wearable device is a portable device that is directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also has powerful functions through software support and data interaction and cloud interaction. The general wearable smart device includes devices with complete functions, large size, and the ability to realize complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, etc., and devices that focus on a certain type of application function and need to be used in cooperation with other devices such as smart phones, such as various smart wristbands and smart jewelry for monitoring vital signs, etc.

[0039] In embodiments of the present application, the network device can be a device for communicating with the mobile device, and the network device can be an access point (AP) in a WLAN, a base transceiver station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved node B (eNB or eNodeB) in LTE, or a relay station or an access point, or a vehicle-mounted device, a wearable device, a network device in an NR network (gNB), or a network device in a future evolved PLMN network, or a network device in an NTN network, etc.

[0040] By way of example and not limitation, in embodiments of the present application, the network device can have a mobile characteristic, for example, the network device can be a mobile device. Alternatively, the network device can be a satellite, a balloon station. For example, the satellite can be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Alternatively, the network device can also be a base station arranged at a location on land, water, etc.

[0041] In embodiments of the present application, the network device can serve a cell, and the terminal device communicates with the network device through a transmission resource (for example, a frequency domain resource, or a spectrum resource) used by the cell. The cell can be a cell corresponding to the network device (for example, a base station), and the cell can belong to a macro base station or a base station corresponding to a small cell. The small cell can include a metro cell, a micro cell, a pico cell, a femto cell, etc., and these small cells have the characteristics of small coverage and low transmit power, and are suitable for providing high-speed data transmission services.

[0042] FIG. 1 illustrates a communication system 100. The communication system includes one network device 110 and two terminal devices 120. In an implementation, the communication system 100 can include multiple network devices 110, and each network device 110 can include other numbers of terminal devices 120 within its coverage, which is not limited in embodiments of the present application.

[0043] In an implementation, the communication system 100 can further include a mobility management entity (MME), an access and mobility management function (AMF), and other network entities, which are not limited herein.

[0044] The network device can include an access network device and a core network device. That is, the wireless communication system further includes a plurality of core networks for communicating with the access network device. The access network device can be an evolved node B (eNB or e-NodeB) macro base station, a micro base station (also referred to as a "small base station"), a pico base station, an access point (AP), a transmission point (TP), or a new generation Node B (gNodeB) in a long-term evolution (LTE) system, a next radio (NR) system, or an authorized auxiliary access long-term evolution (LAA-LTE) system.

[0045] It should be understood that the devices with communication functions in the network / system in the embodiments of the present application can be referred to as communication devices. For example, the communication system shown in FIG. 1, the communication devices can include network devices and terminal devices with communication functions, which can be specific devices in the embodiments of the present application, and will not be described herein. The communication devices can also include other devices in the communication system, such as network controllers, mobility management entities, and other network entities, which are not limited herein.

[0046] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" herein is only used to describe the association relationship between the associated objects. For example, A and / or B can represent three cases: A alone, A and B together, and B alone. In addition, the character " / " generally represents an "or" relationship between the associated objects.

[0047] It should be understood that the "indication" mentioned in the embodiments of the present application can be direct indication, or indirect indication, or can be an indication of an associated relationship. For example, A indicates B, which can mean that B can be obtained by A directly; or A indirectly indicates B, for example, A indicates C, and B can be obtained by C; or A and B have an associated relationship.

[0048] In the description of the embodiments of the present application, the term "corresponding" can mean a direct or indirect corresponding relationship between the two, or an associated relationship between the two, or an indication and an indicated, a configuration and a configured relationship.

[0049] In order to facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described as follows, which can be combined with the technical solutions of the embodiments of the present application in any way, and all belong to the protection scope of the embodiments of the present application.

[0050] The CSI feedback problem, as shown in FIG. 2A, can realize the compression and feedback of AI-based CSI information through an AI encoder and an AI decoder. The CSI prediction problem, as shown in FIG. 2B. The measured CSI (Measured CSI) is input into a CSI prediction model (CSI prediction model), and the predicted CSI (Predicted CSI) can be obtained. Wherein, the subscript of W represents the time, for example, W t-10 represents the CSI information at (t-10) time.

[0051] For AI / Machine Learning (ML) based solutions, their performance can be affected by scenarios, data, and application conditions, and such effects have problems such as fluctuations, disturbances, irregular changes, etc. For example, AI / ML based solutions can include AI / ML based CSI compression, recovery, or AI / ML based prediction, or other AI / ML based solutions. In actual use of the system, if the AI / ML solution is determined to fail because of a short-term performance decline, unnecessary determination of the failure of the AI / ML solution and unnecessary scheme switching can be introduced, and unnecessary model, scheme updating, reconfiguration and other additional processes and signaling overheads can also be brought. For example, if a CSI compression and recovery scheme recovers normal use after a short-term failure, it is not necessary to determine that the scheme fails and then trigger a new replacement scheme, or it is not necessary to first determine that the scheme fails, then trigger a new replacement scheme, and then replace the scheme. The current basic solution is to evaluate the performance of AI / ML, such as through multiple evaluations (including multiple transmissions of evaluation data and multiple performance judgments) to obtain a relatively stable evaluation result.

[0052] Although multiple performance evaluations can obtain relatively stable AI / ML scheme performance evaluation results, a large amount of evaluation-related data transmission and signaling overheads may be caused. For example, in a CSI compression, recovery, or CSI prediction scheme, if the difference between the original CSI information and the CSI information after CSI compression and recovery is taken as the evaluation object, the UE needs to transmit the original CSI information to the network multiple times, or the network needs to transmit the CSI information after compression and recovery to the UE multiple times when multiple evaluations are needed. The sum of the air interface overheads caused by frequent transmission and the amount of information transmitted each time will be a very large evaluation overhead.

[0053] FIG. 3 is a schematic flowchart of a data transmission method 300 according to an embodiment of the present application. The method can be optionally applied to the system shown in FIG. 1, but is not limited thereto. The method includes at least part of the following content.

[0054] S310, the first communication device transmits processing data, which is obtained by processing a plurality of to-be-processed information.

[0055] In the embodiments of the present application, the first communication device can transmit the processing data to the second communication device. For example, the first communication device is a terminal device, and the second communication device is a network device. For another example, the first communication device is a network device, and the second communication device is a terminal device. For another example, the first communication device is a first terminal device, and the second communication device is a second terminal device. The plurality of to-be-processed information can include a plurality of information that the first communication device needs to transmit to the second communication device. After the plurality of to-be-processed information is processed in the first communication device, the processing data is obtained, and then the processing data can be transmitted to the second communication device, which can reduce the amount of data transmitted and further reduce the signaling overhead.

[0056] In an implementation manner, the plurality of to-be-processed information includes related data for model performance monitoring, training, testing, or use in the first communication device. In the embodiments of the present application, the first communication device and / or the second communication device can have a model for a communication scenario problem. For example, a CSI-related model. The plurality of to-be-processed information can be various types of data for the performance monitoring, training, testing, or use stage of the model, such as input data, output data, label data, evaluation data, and the like of the model.

[0057] In an implementation manner, one to-be-processed information in the plurality of to-be-processed information includes at least one of the following: a channel; a feature vector representing channel state information (CSI); input information of a model; and output information of a model.

[0058] In the embodiments of the present application, the plurality of to-be-processed information can include a plurality of channels. For example, a channel H1 estimated by a UE. For another example, a channel H2 obtained by a network through a channel information recovery scheme or a prediction scheme. The plurality of to-be-processed information can include a plurality of eigenvectors representing CSI. For example, an eigenvector representing CSI information obtained by the UE through SVD decomposition of the channel H1. For another example, an eigenvector representing CSI information obtained by the network through a CSI information recovery scheme or a prediction scheme.

[0059] In an embodiment, the channel includes at least one of:

[0060] a channel constituted by time domain information, frequency domain information, angle domain information, and antenna domain information;

[0061] a channel obtained by extracting information in the time domain from the initial channel and selecting a subset of partial time domain information;

[0062] a channel obtained by extracting information in the frequency domain from the initial channel and selecting a subset of partial frequency domain information;

[0063] a channel obtained by extracting information in the angle domain from the initial channel and selecting a subset of partial angle domain information;

[0064] a channel obtained by extracting information in the antenna domain from the initial channel and selecting a subset of partial antenna domain information;

[0065] a channel obtained by quantizing the initial channel. For example, a channel obtained by K-bit quantization of the channel H1 by a terminal device. For another example, a channel obtained by K-bit quantization of the channel H2 by a network device.

[0066] For example, a channel constituted by time domain information can include a channel on a plurality of symbols, a plurality of time slots in the time domain. A channel constituted by frequency domain information can include a channel on a plurality of subcarriers, a plurality of RBs in the frequency domain. A channel constituted by angle domain information can include a channel on a plurality of transmission angles, a plurality of receiving angles in the angle domain. A channel constituted by antenna domain information can include a channel on a plurality of transmission antennas, a plurality of transmission ports in the antenna domain.

[0067] In an embodiment, the eigenvector representing CSI includes at least one of:

[0068] an eigenvector representing CSI obtained by singular value decomposition (SVD) of the channel;

[0069] an eigenvector representing CSI information obtained through a CSI information recovery scheme;

[0070] an eigenvector representing CSI information obtained through a CSI information prediction scheme.

[0071] For example, the first communication device is a terminal device, which can perform SVD on the channel H1 to obtain the eigenvector representing the CSI. For another example, the first communication device is a network device. In the AI / ML-based CSI compression and recovery process, the network device can obtain the eigenvector representing the CSI information through the CSI information recovery scheme. In the AI / ML-based CSI prediction process, the network device can obtain the eigenvector representing the CSI information through the CSI information prediction scheme.

[0072] In an implementation, the input information of the model includes the channel and / or the eigenvector representing the CSI. For example, the input information of the model can also be referred to as label data, input data, initial data, expected data, etc.

[0073] In an implementation, the output information of the model includes the channel and / or the eigenvector representing the CSI. For example, the output information of the model can also be referred to as evaluation data, output data, prediction data, etc.

[0074] In an implementation, the processing manner of the plurality of to-be-processed information includes:

[0075] Obtaining the mean value of the plurality of to-be-processed information;

[0076] Obtaining the mean value of the plurality of to-be-processed information after element processing.

[0077] In an implementation, the element processing of the plurality of to-be-processed information includes at least one of the following:

[0078] Taking the absolute value of the element in the plurality of to-be-processed information;

[0079] Taking the modulus value of the element in the plurality of to-be-processed information;

[0080] Taking the square of the absolute value of the element in the plurality of to-be-processed information;

[0081] Taking the square of the modulus value of the element in the plurality of to-be-processed information;

[0082] Multiplying the element in the plurality of to-be-processed information by the conjugate of the element.

[0083] In this embodiment, the mean can be directly obtained from the elements of multiple pieces of information to be processed, or the elements can be processed first by taking the absolute value, modulo, squaring, or conjugate operations before taking the mean. The above-described element processing methods are merely examples and not limitations; other processing methods can be applied to the elements as needed. In this embodiment, averaging multiple pieces of information to be processed helps reduce the amount of data. Performing element processing on multiple pieces of information before averaging, using methods such as taking the absolute value, modulo, squaring, and conjugate operations, better reflects the cumulative effect of errors. For example, the original data may contain both positive and negative values; taking the absolute value first and then the mean will not cancel out the positive and negative errors, but will accumulate.

[0084] For example, the elements of a piece of information D1 to be processed include {d11, d12, d13, d14}. Taking the absolute value of this information, we get the absolute values ​​of the elements of D1 as {|d11|, |d12|, |d13|, |d14|}. Squaring the absolute value of this information, we get the squares of the absolute values ​​of the elements of D1 as {|d11|, |d12|, |d13|, |d14|}. 2 ,|d12| 2 ,|d13| 2 ,|d14| 2 After taking the modulus of the information to be processed, the modulo values ​​of the elements of D1 are {||d11||,||d12||,||d13||,||d14||}. After taking the modulus of the information to be processed and squaring it, the squares of the modulo values ​​of the elements of D1 are {||d11||}. 2 ,||d12|| 2 ,||d13|| 2 ,||d14|| 2}. Perform a dot product of the element to be processed with its conjugate [|d11.*d11'|,|d12.*d12'|,|d13.*d13'|,|d14.*d14'|]. Here, d11.*d11' represents the dot product of d11 and its conjugate d11'.

[0085] In one implementation, mean acquisition includes at least one of the following:

[0086] The information is averaged based on the sample size.

[0087] The information is averaged based on its internal elements;

[0088] After averaging the information by its internal elements, average the data by the number of samples.

[0089] In one implementation, averaging the information by its internal elements includes:

[0090] averaging the information according to the total number of internal elements;

[0091] averaging the information according to the number of dimension elements of internal elements.

[0092] In the embodiments of the present application, the averaging manner of the plurality of to-be-processed information can include averaging according to the number of samples, the number of internal elements, the number of dimension elements, etc. For example, the number of dimension elements can include the number of subbands, the number of sending ports, the real and imaginary dimensions of complex numbers, etc.

[0093] For example, N is the number of samples, and the N to-be-processed information can be averaged according to the number of samples N to obtain one processed information. It is assumed that the plurality of to-be-processed information includes D1, D2 and D3. The elements of D1 include {d11, d12, d13, d14}; the elements of D2 include {d21, d22, d23, d24}; and the elements of D3 include {d31, d32, d33, d34}. If the elements in D1, D2 and D3 are averaged according to N=3, {D11, D12, D13, D14} can be obtained. Wherein, D11=(d11+d21+d31)÷3, D12=(d12+d22+d32)÷3, D13=(d13+d23+d33)÷3, and D14=(d14+d24+d34)÷3.

[0094] For another example, if the elements in D1, D2 and D3 are first taken absolute values, and then the absolute values of the elements in D1, D2 and D3 are averaged according to the number of samples N=3, {D21, D22, D23, D23} can be obtained. Wherein, D21=(|d11|+|d21|+|d31|)÷3, D22=(|d12|+|d22|+|d32|)÷3, D23=(|d13|+|d23|+|d33|)÷3, and D24=(|d14|+|d24|+|d34|)÷3.

[0095] For another example, M is the element data in a to-be-processed information. The M elements in each to-be-processed information of the N to-be-processed information can be averaged according to the number of elements M to obtain N processed information. If the elements in D1, D2 and D3 are averaged according to M=4, {D31, D32, D33} can be obtained. Wherein, D31=(d11+d12+d13+d14)÷4, D32=(d21+d22+d23+d24)÷4, and D33=(d31+d32+d33+d34)÷4.

[0096] For another example, M = d1 * d2, where d1 and d2 are dimension numbers. The elements in each of the N pieces of information to be processed can be subjected to a modulo operation, and then an average is taken according to the dimension number d1 or d2 to obtain N pieces of processed information. If the elements in D1, D2 and D3 described above are subjected to a modulo operation, and then an average is taken according to d2 = 4, {D41, D42, D43} can be obtained. Wherein, D41 = (||d11|| + ||d12|| + ||d13|| + ||d14||) ÷ 4, D42 = (||d21|| + ||d22|| + ||d23|| + ||d24||) ÷ 4, D43 = (||d31|| + ||d32|| + ||d33|| + ||d34||) ÷ 4.

[0097] Further, the N pieces of processed information can be further averaged according to N to obtain one piece of processed information.

[0098] In an embodiment, the first communication device is a terminal device, the plurality of pieces of information to be processed includes a plurality of first information to be processed in the terminal device, and the processing data includes first data obtained by processing the plurality of first information in the first processing manner. In the embodiments of the present application, the first information can include at least one of a first channel, a first feature vector representing CSI, and input information of a model. The processing manner of the terminal device for the first channel, the first feature vector representing CSI, and the input information of the model can refer to the related description and examples described above. For example, the terminal device can send the first data to a network device or another terminal device.

[0099] In an embodiment, the first information includes at least one of label data, auxiliary data, and input data of a model in the terminal device. In the embodiments of the present application, at least one of the label data, the auxiliary data, and the input data can be input into the model for processing.

[0100] In an embodiment, the model in the terminal device is an encoder of a CSI generation model. For example, at least one of the label data, the auxiliary data, and the input data of the CSI generation model can include CSI to be processed. The CSI to be processed is input into an AI encoder of the CSI generation model as shown in FIG. 2A. The CSI generation model can be used in scenarios such as CSI feedback and CSI prediction. After the encoding processing of the AI encoder, compressed CSI is obtained. The terminal device can send the compressed CSI to a network device or another terminal for decoding processing. The terminal device can also send a plurality of CSIs to be processed, i.e., a plurality of first information, to a network device or another terminal device after processing, to assist the network device or the other terminal device in performance evaluation of the model.

[0101] In an implementation, the first data is transmitted by at least one of the following:

[0102] a Radio Resource Control (RRC) message; Uplink Control Information (UCI); an uplink message in a random access procedure; a Physical Uplink Control Channel (PUCCH); a Physical Uplink Shared Channel (PUSCH); an AI and / or ML dedicated uplink channel; a terminal device capability reporting message; a Sidelink Control Information (SCI) message; a Physical Sidelink Control Channel (PSCCH); a Physical Sidelink Shared Channel (PSSCH).

[0103] For example, the terminal device can report the first data to the network device through a RRC message, UCI, a PUCCH, a PUSCH, an uplink message in a random access procedure, an AI dedicated uplink channel, an ML dedicated uplink channel, or a terminal device capability reporting message. For another example, the first terminal device can send the first data to the second terminal device through a SCI, a PSCCH, or a PSSCH. If a large amount of data needs to be transmitted, the first data can be transmitted through a RRC message, a PUSCH, or a PSSCH, etc. If high timeliness is required, the first data can be transmitted through UCI, a PUCCH, an uplink message in a random access procedure, an AI dedicated uplink channel, an ML dedicated uplink channel, a terminal device capability reporting message, a SCI, or a PSCCH, etc.

[0104] In an implementation, the first communication device is a network device, the plurality of to-be-processed information includes a plurality of second information to be processed in the network device, and the processing data includes second data obtained by processing the plurality of second information in a second processing manner. In the embodiments of the present application, the first information can include at least one of a second channel, a second feature vector representing a CSI, and output information of a model. The processing manner of the terminal device on the second channel, the second feature vector representing the CSI, and the output information of the model can be referred to the related description and examples described above. For example, the network device can send the first data to the terminal device.

[0105] In an embodiment, the second information comprises at least one of evaluation data, auxiliary data and output data of the model in the network device. In the embodiments of the present application, the model in the network device can be the same as, related to or different from the model in the terminal device. The model in the network device can output at least one of evaluation data, auxiliary data and output data.

[0106] In an embodiment, the model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model. In the embodiments of the present application, the model in the network device can be the same as, related to or different from the model in the terminal device. For example, the first model in the terminal device comprises an encoder of a CSI generation model, and the second model in the network device comprises a decoder of a CSI recovery model and / or a CSI prediction model. For example, as shown in FIG. 2A, after the terminal device transmits the compressed CSI obtained through the AI encoder to the network device, the network device can input the compressed CSI into the decoder of the CSI recovery model and / or the CSI prediction model to obtain decoded CSI. The network device can also compare the decoded CSI with the received multiple CSIs to be processed to obtain a performance evaluation result.

[0107] In the embodiments of the present application, the network device can also transmit the multiple decoded CSIs or the multiple performance evaluation results to the terminal device after processing, to assist the terminal device in evaluating the performance of the model.

[0108] In an embodiment, the second data is transmitted through at least one of the following:

[0109] a broadcast message; an RRC message; a Medium Access Control (MAC) control element (CE); a Downlink Control Information (DCI) message; a downlink message in a random access procedure; a Physical Downlink Control Channel (PDCCH); a Physical Downlink Shared Channel (PDSCH); an AI and / or ML dedicated downlink channel; a capability indication of the network side; SCI; PSCCH; PSSCH.

[0110] For example, after the network device processes the plurality of second information to obtain second data, the network device can deliver the second data to the terminal device through a broadcast message, an RRC message, a MAC CE, a DCI, a PDCCH, a PDSCH, a downlink message in a random access process, an AI-dedicated downlink channel, a ML-dedicated downlink channel, and a capability indication of the network side. For another example, the second terminal device can send the second data to the first terminal device through an SCI, a PSCCH, or a PSSCH. If a large amount of data needs to be transmitted, the second data can be transmitted through a broadcast message, an RRC message, a PDSCH, or a PSSCH. If high timeliness is required, the second data can be transmitted through a MAC CE, a DCI, a PDCCH, a downlink message in a random access process, an AI-dedicated downlink channel, a ML-dedicated downlink channel, a capability indication of the network side, an SCI, or a PSCCH.

[0111] FIG. 4 is a schematic flowchart of a data transmission method 400 according to an embodiment of the present application. The method can be optionally applied to the system shown in FIG. 1, but is not limited thereto. The method includes at least part of the following content.

[0112] S410, the second communication device receives processing data, which is obtained by processing a plurality of to-be-processed information by the first communication device.

[0113] In an implementation, the plurality of to-be-processed information includes relevant data of model performance monitoring, training, testing, or use in the second communication device.

[0114] In an implementation, one to-be-processed information in the plurality of to-be-processed information includes at least one of the following:

[0115] a channel;

[0116] a feature vector representing CSI;

[0117] input information of a model;

[0118] output information of a model.

[0119] In an implementation, the channel includes at least one of the following:

[0120] an initial channel composed of time domain information, frequency domain information, angle domain information, and antenna domain information;

[0121] a channel obtained by extracting information in the time domain from the initial channel and selecting a part of a time domain information subset;

[0122] a channel obtained by extracting information in the frequency domain from the initial channel and selecting a part of a frequency domain information subset;

[0123] The initial channel is subjected to information extraction in the angle domain, and a channel obtained by selecting a partial angle domain information subset is obtained;

[0124] The initial channel is subjected to information extraction in the antenna domain, and a channel obtained by selecting a partial antenna domain information subset is obtained;

[0125] The initial channel is subjected to quantization, and a channel obtained by quantization is obtained.

[0126] In an embodiment, the eigenvector representing the CSI includes an eigenvector representing the CSI obtained by SVD of the channel.

[0127] In an embodiment, the input information of the model includes the channel and / or the eigenvector representing the CSI.

[0128] In an embodiment, the output information of the model includes the channel and / or the eigenvector representing the CSI.

[0129] In an embodiment, the processing manner of the plurality of to-be-processed information includes:

[0130] Mean value acquisition of the plurality of to-be-processed information;

[0131] Mean value acquisition of the plurality of to-be-processed information after element processing.

[0132] In an embodiment, the element processing of the plurality of to-be-processed information includes at least one of:

[0133] Taking absolute value of the element in the plurality of to-be-processed information;

[0134] Taking modulus value of the element in the plurality of to-be-processed information;

[0135] Taking square of the absolute value of the element in the plurality of to-be-processed information;

[0136] Taking square of the modulus value of the element in the plurality of to-be-processed information;

[0137] Multiplying the element in the plurality of to-be-processed information with the conjugate of the element.

[0138] In an embodiment, the mean value acquisition includes at least one of:

[0139] Taking mean value of the information according to sample number;

[0140] Taking mean value of the information according to internal element;

[0141] Taking mean value of the information according to internal element, and then taking mean value according to sample number.

[0142] In an embodiment, taking mean value of the information according to internal element includes:

[0143] average the information by the total number of internal elements;

[0144] average the information by the number of dimension elements of internal elements.

[0145] In an embodiment, the second communication device is a terminal device, the plurality of to-be-processed information includes a plurality of first information to be processed in the terminal device, and the processing data includes first data obtained by processing the plurality of first information in a first processing manner.

[0146] In an embodiment, the first information includes at least one of label data, auxiliary data, and input data of a model in the terminal device.

[0147] In an embodiment, the model in the terminal device is an encoder of a CSI generation model.

[0148] In an embodiment, the first data is transmitted by at least one of the following:

[0149] an RRC message; uplink control information (UCI); an uplink message in a random access procedure; a PUCCH; a PUSCH; an uplink channel dedicated to AI and / or ML; a terminal device capability reporting message, SCI, PSCCH, and PSSCH.

[0150] In an embodiment, the second communication device is a network device, the plurality of to-be-processed information includes a plurality of second information to be processed in the network device, and the processing data includes second data obtained by processing the plurality of second information in a second processing manner.

[0151] In an embodiment, the second information includes at least one of evaluation data, auxiliary data, and output data of a model in the network device.

[0152] In an embodiment, the model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model.

[0153] In an embodiment, the second data is transmitted by at least one of the following:

[0154] a broadcast message; an RRC message; a MAC CE; DCI; a downlink message in a random access procedure; a PDCCH; a PDSCH; a downlink channel dedicated to AI and / or ML; a capability indication of a network side; SCI; PSCCH; and PSSCH.

[0155] The communication device of the embodiment performs a specific example of the data transmission method 400. For brevity, the related description of the communication device in the data transmission method 300 is not repeated here.

[0156] The data transmission method of the embodiments of the present application can include the following parts:

[0157] I. Evaluation data construction method.

[0158] The design of the construction method includes: in the performance evaluation of the AI / ML scheme, avoiding the multiple transmissions of the label data and the evaluation data, and using the processed data of the label data and the evaluation data as the label data and the evaluation data.

[0159] The basic idea of the above design includes: when the AI / ML scheme evaluation does not strictly depend on a single evaluation result, but depends on the comprehensive result of multiple evaluations, the transmission of multiple evaluation data can be avoided. The way of integrating multiple evaluation information before transmitting the evaluation information is adopted, the information preprocessing is used to replace the transmission of redundant air interface information, and the corresponding signaling design is used to support that the UE and the network can understand the evaluation scheme that can be used or selected.

[0160] 1. UE transmits first data to network

[0161] In the problems of AI / ML-based CSI compression, recovery, and CSI prediction, the UE transmits first data to the network. The first data is obtained by a first processing method on the first information.

[0162] The first information A1 can be one of the following information:

[0163] (1) Channel H1. For example, the channel H1 obtained by the UE through channel estimation. For example, the channel H1 composed of time domain information, frequency domain information, angle domain information, and antenna domain information. For example, the channel H1 obtained by selecting part of the time domain information subset, the frequency domain information subset, the angle domain information subset, and the antenna domain information subset after information extraction on the above H1 (which can also be marked as channel H1-1, etc. to distinguish from H1 before extraction). For example, the H1 obtained by quantizing the above H1 by k bits (which can also be marked as channel H1-2, etc. to distinguish from H1 before quantization).

[0164] (2) Feature vector W1 representing CSI information. For example, the feature vector W1 representing CSI information obtained by the UE through SVD decomposition on the channel H1.

[0165] (3) Input information X1 of the AI / ML model. For example, the input information of the AI / ML CSI compression and recovery model is H1 or W1.

[0166] The above first processing method can be one of the following methods:

[0167] (1) Mean value acquisition of the first information A1, for example:

[0168] For example, when the first information A1 is composed of M1 elements. For example, the first information A1 is a matrix of [s1, s2, s3] dimensions, and s1*s2*s3=M1.

[0169] The first data B1 can be at least one of the following examples:

[0170] N first information A1s are averaged by sample number (averaged by N) to obtain the first data B1.

[0171] N first information A1s, each composed of M1 elements, are averaged by internal elements (averaged by M1, or averaged by s1, or averaged by s2, or averaged by s3) for each first information A1 to obtain the first data B1.

[0172] N first information A1s, each composed of M1 elements, are averaged by internal elements (averaged by M1, or averaged by s1, or averaged by s2, or averaged by s3) for each first information A1, and the N first information A1s are averaged by sample number (averaged by N) to obtain the first data B1.

[0173] (2) The average of the processed elements of the first information A1 is obtained, for example, as follows:

[0174] For example, when the first information A1 is composed of M1 elements. For example, the first information A1 is a matrix of [s1, s2, s3] dimensions, and s1*s2*s3=M1.

[0175] The first data B1 can be at least one of the following examples:

[0176] N first information A1s, each composed of M1 elements, are processed for the M1 elements of each first information A1, such as taking the absolute value of the element in the sample, or the modulus value of the element in the sample, or the square of the absolute value of the element in the sample, or the square of the modulus value of the element in the sample, or the element in the sample is multiplied by the conjugate of the element, etc. The N samples after the above processing are averaged (averaged by N) to obtain the first data B1.

[0177] N first information A1s, each composed of M1 elements, are processed for the M1 elements of each first information A1, such as taking the absolute value, or the modulus value, or the square of the absolute value, or the square of the modulus value, or the square of the modulus value of the element in the sample, or the element in the sample is multiplied by the conjugate of the element, etc. The N samples after the above processing are averaged by internal elements (averaged by M1, or averaged by s1, or averaged by s2, or averaged by s3) to obtain the first data B1.

[0178] N pieces of first information A1, each first information A1 consists of M1 elements, and M1 elements of each first information A1 are processed, such as taking absolute value, or modulus value, or taking square of absolute value, or taking square of modulus value, or taking square of modulus value of elements in sample, or multiplying elements in sample with conjugate of the elements, etc. The N samples after the above processing are averaged by elements within the sample (averaged by M1, or averaged by s1, or averaged by s2, or averaged by s3), and averaged by the number of samples (averaged by N), to obtain first data B1.

[0179] 1.2 Network transmission to UE

[0180] In the problems of AI / ML-based CSI compression, recovery, CSI prediction, etc., the network transmits second data to the UE. The second data is obtained by the second information through the second processing mode.

[0181] The second information A2 can be one of the following information:

[0182] (1) Channel H2.

[0183] For example, in the process of AI / ML-based channel information compression and recovery, the channel H2 obtained by the network through the channel information recovery scheme. For another example, the channel H2 composed of time domain information, frequency domain information, angle domain information, antenna domain information. For another example, the channel H2 obtained by selecting part of the time domain information subset, frequency domain information subset, angle domain information subset, antenna domain information subset after information extraction of the above H2 in time domain, frequency domain, angle domain, time delay domain (which can also be marked as channel H2-1, etc. to distinguish from H2 before extraction). For another example, the H2 obtained by quantizing the above H2 by k bits (which can also be marked as channel H2-2, etc. to distinguish from H2 before quantization).

[0184] For example, in the process of AI / ML-based channel information prediction, the channel H2 obtained by the network through the channel information prediction scheme. For another example, the channel H2 composed of time domain, frequency domain information and angle domain, time delay domain information. For example, the channel H2 obtained by selecting part of the time domain information subset, frequency domain information subset, angle domain information subset, antenna domain information subset after information extraction of the above H2 in time domain, frequency domain, angle domain, time delay domain (which can also be marked as channel H2-3, etc. to distinguish from H2 before extraction). For another example, the H2 obtained by quantizing the above H2 by k bits (which can also be marked as channel H2-4, etc. to distinguish from H2 before quantization).

[0185] (2) Feature vector W2 representing CSI information, for example:

[0186] For example, in the process of AI / ML-based CSI compression and recovery, the feature vector W2 representing CSI information obtained by the network through the CSI information recovery scheme.

[0187] For example, in the AI / ML based CSI prediction process, the network gets a feature vector W2 representing the CSI information through the CSI information prediction scheme.

[0188] (3) The output information X2 of the AI / ML model.

[0189] For example, the output information of the AI / ML based CSI compression and recovery model is H2 or W2. For example, the output information of the AI / ML based CSI prediction model is H2 or W2.

[0190] In example one and example two, A1 and A2 are similar in description, but the two information can be two different types of information. For example, A1 is the original information obtained at the UE side, which can be a reference information and / or a label information. A2 is obtained by the network through CSI feedback or CSI prediction, etc., which can be a lossy information, and is the information to be evaluated. The performance evaluation comparison can compare how different the above A1 and A2 are.

[0191] The second processing mode described above can be one of the following modes:

[0192] (1) The mean value of the second information A2 is obtained, for example, as follows:

[0193] For example, when the second information A2 is composed of M2 elements. For example, the second information A2 is a matrix of [q1, q2, q3] dimensions, and q1*q2*q3=M2.

[0194] The second data B2 can be at least one of the following:

[0195] The second data B2 is obtained by taking the mean value of N second information A2s according to the sample number (taking the mean value according to N).

[0196] N second information A2s, each composed of M2 elements. The second data B2 is obtained by taking the mean value of each second information A2 according to the internal elements (taking the mean value according to M2, or taking the mean value according to q1, or taking the mean value according to q2, or taking the mean value according to q3).

[0197] N second information A2s, each composed of M2 elements. The mean value of each second information A2 is taken according to the internal elements (taking the mean value according to M2, or taking the mean value according to q1, or taking the mean value according to q2, or taking the mean value according to q3). The second data B2 is obtained by taking the mean value of N second information A2s according to the sample number (taking the mean value according to N).

[0198] (2) The mean value of the second information A2 after element processing is obtained, for example, as follows:

[0199] For example, when the second information A2 is composed of M2 elements. For example, the second information A2 is a matrix of [q1, q2, q3] dimensions, and q1*q2*q3=M2.

[0200] The second data B2 can be at least one of the following:

[0201] N second information A2s, each composed of M2 elements. Process the M2 elements of each second information A2. For example, take the absolute value, or the modulus value, or the square of the absolute value, or the square of the modulus value, or the square of the modulus value of the sample element, or multiply the sample element by the conjugate of the element, etc. Take the mean value of the N samples after the above processing (take the mean value according to N), to obtain the second data B2.

[0202] N second information A2s, each composed of M2 elements. Process the M2 elements of each second information A2. For example, take the absolute value, or the modulus value, or the square of the absolute value, or the square of the modulus value, or the square of the modulus value of the sample element, or multiply the sample element by the conjugate of the element, etc. Take the mean value of the N samples after the above processing (take the mean value according to N), to obtain the second data B2.

[0203] N second information A2s, each composed of M2 elements. Process the M2 elements of each second information A2. For example, take the absolute value, or the modulus value, or the square of the absolute value, or the square of the modulus value, or the square of the modulus value of the sample element, or multiply the sample element by the conjugate of the element, etc. Take the mean value of the N samples after the above processing (take the mean value according to N), to obtain the second data B2.

[0204] Compared with the method of transmitting multiple samples for AI / ML performance supervision, the scheme of the present application can use the processing results of transmitting multiple samples for statistical processing, thereby greatly reducing the air interface overhead required for transmission of to-be-evaluated data, label data, etc.

[0205] 1.3 Some examples in specific AI / ML-based CSI compression, recovery, and prediction schemes are as follows:

[0206] Example 1:

[0207] In AI / ML-based CSI feedback schemes, or in CSI prediction schemes, where AI / ML performance evaluation is performed on the network side, the UE transmits a feature vector W1 representing CSI information to the network. The number of elements in W1 is, for example, M1; the dimensions of W1 are, for example, [s1, s2], where s1 is the number of sub-bands and s2 is the number of transmitting ports. Alternatively, the dimensions of W1 can be, for example, [s1, s2, s3], where s1 is the number of sub-bands, s2 is the number of transmitting ports, and s3 represents both the real and virtual dimensions of the complex number.

[0208] The first piece of information W1 consists of M1 elements, for example, W1 can be represented as [w_1, w_2, ..., w_M1]. The M1 elements of W1 are processed, for example, by taking the absolute value of each element [|w_1|,|w_2|, ...,|w_M1|], or the modulus of each element [||w_1||,||w_2||, ...,||w_M1||], or by taking the square of the absolute value of each element [|w_1|,||w_2||, ...,||w_M1||]. 2 ,|w_2| 2 ,…,|w_M1| 2 ], or the square of the modulo value of each element [||w_1|| 2 ,||w_2|| 2 ,…,||w_M1|| 2 Alternatively, each element can be multiplied by its conjugate [|w_1.*w_1'|,|w_2.*w_2'|,…,|w_M1.*w_M1'|], etc., to form the processed first information W1 (which can also be labeled W1', etc., to distinguish it from the unprocessed W1; the following examples are similar). N such processed first information W1s are then generated. For example, N such processed first information W1_1,…W1_N are averaged over N samples to obtain the second data B1, for example…

[0209] Example 2:

[0210] In AI / ML-based CSI feedback schemes, or in CSI prediction schemes, where AI / ML performance evaluation is performed on the UE side, the network needs to transmit a feature vector W2 representing CSI information to the UE. The number of elements in W2 is, for example, M2; the dimensions of W2 are, for example, [q1, q2], where q1 is the number of subbands and q2 is the number of transmitting ports. Alternatively, the dimensions of W2 can be, for example, [q1, q2, q3], where q1 is the number of subbands, q2 is the number of transmitting ports, and q3 represents both the real and virtual dimensions of the complex number.

[0211] The second information W2 is composed of M2 elements, for example, W2 can be represented as [w_1, w_2, …, w_M2]. The M2 elements of W2 are processed, for example, each element takes the absolute value [|w_1|, |w_2|, …, |w_M2|], or each element takes the modulus value [||w_1||, ||w_2||, …, ||w_M2||], or each element takes the square of the absolute value [|w_1| 2 , |w_2| 2 , …, |w_M2| 2 ], or each element takes the square of the modulus value [||w_1|| 2 , ||w_2|| 2 , …, ||w_M2|| 2 ], or each element is multiplied by the conjugate of the element [|w_1.*w_1’|, |w_2.*w_2’|, …, |w_M2.*w_M2’|], etc., to form the processed first information W2. N pieces of the above-mentioned processed first information W2, for example, W2_1, …, W2_N, are averaged according to N pieces of samples to obtain the second data B2, for example

[0212] Example 3:

[0213] In the AI / ML-based CSI feedback scheme, or in the CSI prediction scheme, for example, the performance evaluation of AI / ML is done at the network side, and the UE transmits the channel information H1 to the network. The number of elements of H1 is M1, for example, and the dimension of H1 is [s1, s2], for example. The first dimension is s1 time domain information or frequency domain information, and the second dimension is s2 angle domain information or antenna domain information. The dimension of H1 is [s1, s2, s3], for example. The first dimension is s1 time domain information or frequency domain information, the second dimension is s2 angle domain information or antenna domain information, and the third dimension is the real and imaginary parts of a complex number.

[0214] The first information H1 is composed of M1 elements, for example, H1 can be represented as [h_1, h_2, …, h_M1]. The M1 elements of H1 are processed, for example, each element takes the absolute value [|h_1|, |h_2|, …, |h_M1|], or each element takes the modulus value [||h_1||, ||h_2||, …, ||h_M1||], or each element takes the square of the absolute value [|h_1| 2 , |h_2| 2 , …, |h_M1| 2 ], or each element takes the square of the modulus value [||h_1|| 2 , ||h_2|| 2 , …, ||h_M1|| 2, or each element multiplied by the conjugate of the element [ |h_1.*h_1'|, |h_2.*h_2'|, …, |h_M1.*h_M1'| ], etc., to form the processed first information H1. N pieces of the above-mentioned processed first information H1, such as N pieces of the above-mentioned processed first information H1_1, …, H1_N, are averaged according to N pieces of samples to obtain second data B1, such as

[0215] Example 4:

[0216] In the AI / ML-based CSI feedback scheme, or in the CSI prediction scheme, for example, the performance evaluation of AI / ML is done at the UE side, and the network transmits the channel information H2 to the UE. The number of elements of H2 is, for example, M2, and the dimension of H2 is, for example, [s1, s2]. The first dimension is s1 pieces of time domain information or frequency domain information, and the second dimension is s2 pieces of angle domain or antenna domain information. The dimension of H2 is, for example, [s1, s2, s3]. The first dimension is s1 pieces of time domain information or frequency domain information, the second dimension is s2 pieces of angle domain or antenna domain information, and the third dimension is the real and imaginary parts of a complex number.

[0217] The second information H2 is composed of M2 elements, for example, H2 can be represented as [h_1, h_2, …, h_M2]. The M2 elements of H2 are processed, for example, each element takes the absolute value [ |h_1|, |h_2|, …, |h_M2| ], or each element takes the modulus [ ||h_1||, ||h_2||, …, ||h_M2|| ], or each element takes the square of the absolute value [ |h_1| 2 , |h_2| 2 , …, |h_M2| 2 ], or each element takes the square of the modulus [ ||h_1|| 2 , ||h_2|| 2 , …, ||h_M2|| 2 ], or each element multiplied by the conjugate of the element [ |h_1.*h_1'|, |h_2.*h_2'|, …, |h_M2.*h_M2'| ], etc., to form the processed first information H2. N pieces of the above-mentioned processed first information H2, such as N pieces of the above-mentioned processed first information H2_1, …, H2_N, are averaged according to N pieces of samples to obtain second data B2, such as

[0218] 2: Evaluation data indication and / or transmission method

[0219] The first part mainly includes the evaluation data construction method, and the second part can specifically explain the evaluation data indication and / or transmission scheme.

[0220] 2.1 UE transmits first data to network, e.g. base station, as shown in FIG. 5A.

[0221] (1) UE indicates the provided label data type and / or configuration, as shown in FIG. 5B. Then, UE transmits first data to network again.

[0222] (2) Network indicates the required label data type and / or configuration, as shown in FIG. 5C. Then, UE transmits first data to network again.

[0223] (3) UE reports the supported label data type and / or configuration, and network indicates the required label data type and / or configuration, as shown in FIG. 5D. Then, UE transmits first data to network again.

[0224] (4) Network indicates the supported label data type and / or configuration, and UE indicates the provided label data type and / or configuration, as shown in FIG. 5E. Then, UE transmits first data to network again. Or, UE can transmit first data to network at the same time of indicating the provided label data type and / or configuration.

[0225] 2.2 Network, e.g. base station, transmits second data to UE, as shown in FIG. 6A.

[0226] (1) UE indicates the required evaluation data type and / or configuration, as shown in FIG. 6B. Then, network transmits second data to UE again.

[0227] (2) Network indicates the provided evaluation data type and / or configuration, as shown in FIG. 6C. Then, network transmits second data to UE again. Or, network can transmit second data to UE at the same time of indicating the provided evaluation data type and / or configuration.

[0228] (3) UE reports the supported evaluation data type and / or configuration, and network indicates the provided evaluation data type and / or configuration, as shown in FIG. 6D. Then, network transmits second data to UE again. Or, network can transmit second data to UE at the same time of indicating the provided evaluation data type and / or configuration.

[0229] (4) Network indicates the supported evaluation data type and / or configuration, and UE indicates the required evaluation data type and / or configuration, as shown in FIG. 6E. Then, network transmits second data to UE again.

[0230] The uplink transmission in the embodiments of the present application can be completed by one or more of the following ways when UE transmits to base station:

[0231] (1) RRC message, (2) UCI, (3) uplink message in random access procedure, e.g. MsgA, Msg3, (4) PUCCH, (5) PUSCH, (6) AI / ML dedicated uplink channel, (7) UE capability reporting.

[0232] The downlink transmission involved in the embodiments of the present application can be completed by one or more of the following ways when the base station transmits to the UE:

[0233] (1) Broadcast message, such as MIB, SIB1, SIBx, (2) RRC message, (3) MAC CE, (4) DCI, (5) downlink message in random access procedure, e.g. MsgB, Msg2, Msg4. (4) PDCCH, (5) PDSCH, (6) AI / ML dedicated downlink channel, (7) network side capability indication.

[0234] The base station in the above examples can also be replaced by other terminals in the sidelink communication scenario.

[0235] 2.3 The indicated and reported content above can be one or more of the following information:

[0236] (1) Label data and / or evaluation data type, e.g.: channel H1, representing the feature vector W1 of CSI information, input information X1 of AI / ML model.

[0237] (2) Label data and / or evaluation data configuration, e.g.: sample number N used for statistics, processing, and averaging to obtain the first data.

[0238] (3) Label data and / or evaluation data configuration, e.g.: method used for statistics, processing, and averaging to obtain the first data.

[0239] For example, the indicated method is: taking the mean value of the first information; taking the mean value of the elements processed by the first information.

[0240] For example, taking the mean value is to take the mean value of N samples, to take the mean value of each element in the sample, to take the mean value of N samples and different elements in the sample.

[0241] For example, the processing is to take the absolute value of the element in the sample, or the modulus value of the element in the sample, or the square of the absolute value of the element in the sample, or the square of the modulus value of the element in the sample, or the multiplication of the element in the sample and the conjugate of the element.

[0242] (4) Label data and / or evaluation data configuration, for example: format of channel information H1, frequency domain configuration, time domain configuration, angle domain configuration, antenna domain configuration, time domain information subset of H1, frequency domain information subset, angle domain information subset, antenna domain information subset of H1, for example, channel information on a specific time delay, channel information on a specific frequency domain, channel information on a specific angle, channel information on a specific antenna (antenna port).

[0243] (5) Label data and / or evaluation data configuration, for example: frequency domain configuration, time domain configuration, angle domain configuration, antenna domain configuration of channel, acquisition scheme indication of channel information W1, W1 format, sub-band indication of W1, for example, sub-band size, sub-band quantity, etc.

[0244] (6) Indicatable label data and / or evaluation data configuration includes: quantization scheme, quantization granularity, quantization step, quantization precision information.

[0245] The data transmission method of the embodiments of the present application can include a wireless AI data label transmission, mean value transmission, and transmission scheme of auxiliary information. In AI / ML scheme performance evaluation, multiple transmissions of label data and evaluation data are avoided, and processed data of the label data and the evaluation data are used as the label data and the evaluation data. Therefore, when AI / ML scheme evaluation does not strictly depend on a single evaluation result, but depends on a comprehensive result of multiple evaluations, multiple evaluation data transmissions can be avoided, and a multiple evaluation information integration processing method before transmission of evaluation information is used to replace transmission of redundant air interface information.

[0246] FIG. 7 is a schematic block diagram of a first communication device 700 according to an embodiment of the present application. The first communication device 700 can include a sending unit 701 configured to send processed data, the processed data being obtained by processing a plurality of to-be-processed information.

[0247] In an implementation, the plurality of to-be-processed information includes related data of model performance monitoring, training, testing, or use in the first communication device.

[0248] In an implementation, one to-be-processed information in the plurality of to-be-processed information includes at least one of the following:

[0249] a channel;

[0250] a feature vector representing CSI;

[0251] input information of a model;

[0252] output information of a model.

[0253] In an implementation, the channel includes at least one of the following:

[0254] The initial channel is composed of time domain information, frequency domain information, angle domain information and antenna domain information.

[0255] The initial channel is processed in the time domain to extract information, and a channel is obtained by selecting a subset of partial time domain information.

[0256] The initial channel is processed in the frequency domain to extract information, and a channel is obtained by selecting a subset of partial frequency domain information.

[0257] The initial channel is processed in the angle domain to extract information, and a channel is obtained by selecting a subset of partial angle domain information.

[0258] The initial channel is processed in the antenna domain to extract information, and a channel is obtained by selecting a subset of partial antenna domain information.

[0259] The initial channel is quantized to obtain a channel.

[0260] In an embodiment, the eigenvector representing the CSI includes an eigenvector representing the CSI obtained by performing SVD on the channel.

[0261] In an embodiment, the input information of the model includes the channel and / or the eigenvector representing the CSI.

[0262] In an embodiment, the output information of the model includes the channel and / or the eigenvector representing the CSI.

[0263] In an embodiment, the processing method of the plurality of to-be-processed information includes:

[0264] Obtaining the mean value of the plurality of to-be-processed information;

[0265] Obtaining the mean value of the plurality of to-be-processed information after element processing.

[0266] In an embodiment, the element processing of the plurality of to-be-processed information includes at least one of:

[0267] Taking the absolute value of the element in the plurality of to-be-processed information;

[0268] Taking the modulus value of the element in the plurality of to-be-processed information;

[0269] Taking the square of the absolute value of the element in the plurality of to-be-processed information;

[0270] Taking the square of the modulus value of the element in the plurality of to-be-processed information;

[0271] Multiplying the element in the plurality of to-be-processed information by the conjugate of the element.

[0272] In an embodiment, the mean value acquisition includes at least one of:

[0273] The information is averaged based on the sample size.

[0274] The information is averaged based on its internal elements;

[0275] After averaging the information by its internal elements, average the data by the number of samples.

[0276] In one implementation, averaging the information by its internal elements includes:

[0277] The information is averaged based on the total number of its internal elements;

[0278] The information is averaged by the number of elements in each dimension.

[0279] In one embodiment, the first communication device is a terminal device, the plurality of information to be processed includes a plurality of first information to be processed in the terminal device, and the processing data includes first data obtained after processing the plurality of first information using a first processing method.

[0280] In one implementation, the first information includes at least one of the model's label data, auxiliary data, and input data in the terminal device.

[0281] In one implementation, the model in the terminal device is an encoder for CSI-generated models.

[0282] In one implementation, the first data is transmitted via at least one of the following:

[0283] Radio Resource Control (RRC) messages; Uplink Control Information (UCI); Uplink messages during random access procedures; Physical Uplink Control Channel (PUCCH); Physical Uplink Shared Channel (PUSCH); Uplink channels dedicated to Artificial Intelligence (AI) and / or Machine Learning (ML); Terminal Equipment Capability Reporting (TAC) messages, Sideline Control Information (SCI), Physical Sideline Control Channel (PSCCH), and Physical Sideline Shared Channel (PSSCH).

[0284] In one embodiment, the first communication device is a network device, the plurality of information to be processed includes a plurality of second information to be processed in the network device, and the processing data includes second data obtained after processing the plurality of second information using a second processing method.

[0285] In one implementation, the second information includes at least one of the model's evaluation data, auxiliary data, and output data in the network device.

[0286] In one implementation, the model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model.

[0287] In one implementation, the second data is transmitted via at least one of the following:

[0288] broadcast message; RRC message; media access control, MAC, control element, CE; downlink control information, DCI; downlink message in random access procedure; physical downlink control channel, PDCCH; physical downlink shared channel, PDSCH; downlink channel dedicated for AI and / or ML; capability indication of network side; SCI; PSCCH; PSSCH.

[0289] The first communication device 700 of the embodiments of the present application can realize the corresponding functions of the first communication device in the foregoing method embodiments. The corresponding processes, functions, implementation manners, and beneficial effects of each module (sub-module, unit, or component, etc.) in the first communication device 700 can be referred to the corresponding description in the foregoing method embodiments, which will not be described here again. It should be noted that the functions described with respect to each module (sub-module, unit, or component, etc.) in the first communication device 700 of the embodiments of the present application can be realized by different modules (sub-modules, units, or components, etc.), or can be realized by the same module (sub-module, unit, or component, etc.).

[0290] FIG. 8 is a schematic block diagram of a second communication device 800 according to an embodiment of the present application. The second communication device 800 can include a receiving unit 801 configured to receive processing data, the processing data being obtained by a first communication device processing a plurality of to-be-processed information.

[0291] In an implementation manner, the plurality of to-be-processed information includes data related to model performance monitoring, training, testing, or use in the second communication device.

[0292] In an implementation manner, one to-be-processed information in the plurality of to-be-processed information includes at least one of the following:

[0293] a channel;

[0294] a feature vector representing CSI;

[0295] input information of a model;

[0296] output information of a model.

[0297] In an implementation manner, the channel includes at least one of the following:

[0298] an initial channel composed of time domain information, frequency domain information, angle domain information, and antenna domain information;

[0299] a channel obtained by extracting information in the time domain from the initial channel and selecting a part of a time domain information subset;

[0300] a channel obtained by extracting information in the frequency domain from the initial channel and selecting a part of a frequency domain information subset;

[0301] The initial channel is subjected to information extraction in the angle domain, and a channel obtained by selecting a partial angle domain information subset is obtained;

[0302] The initial channel is subjected to information extraction in the antenna domain, and a channel obtained by selecting a partial antenna domain information subset is obtained;

[0303] The initial channel is subjected to quantization, and a channel obtained by quantization is obtained.

[0304] In an embodiment, the eigenvector representing the CSI includes an eigenvector representing the CSI obtained by SVD of the channel.

[0305] In an embodiment, the input information of the model includes the channel and / or the eigenvector representing the CSI.

[0306] In an embodiment, the output information of the model includes the channel and / or the eigenvector representing the CSI.

[0307] In an embodiment, the processing mode of the plurality of to-be-processed information includes:

[0308] Mean value acquisition of the plurality of to-be-processed information;

[0309] Mean value acquisition of the plurality of to-be-processed information after element processing.

[0310] In an embodiment, the element processing of the plurality of to-be-processed information includes at least one of:

[0311] Taking absolute value of the element in the plurality of to-be-processed information;

[0312] Taking modulus value of the element in the plurality of to-be-processed information;

[0313] Taking square of the absolute value of the element in the plurality of to-be-processed information;

[0314] Taking square of the modulus value of the element in the plurality of to-be-processed information;

[0315] Multiplying the element in the plurality of to-be-processed information with the conjugate of the element.

[0316] In an embodiment, the mean value acquisition includes at least one of:

[0317] Taking mean value of the information according to sample number;

[0318] Taking mean value of the information according to internal element;

[0319] Taking mean value of the information according to internal element, and then taking mean value according to sample number.

[0320] In an embodiment, taking mean value of the information according to internal element includes:

[0321] average the information by the total number of internal elements;

[0322] average the information by the number of dimension elements of internal elements.

[0323] In an embodiment, the second communication device is a terminal device, the plurality of to-be-processed information includes a plurality of first information to be processed in the terminal device, and the processing data includes first data obtained by processing the plurality of first information in a first processing manner.

[0324] In an embodiment, the first information includes at least one of label data, auxiliary data, and input data of a model in the terminal device.

[0325] In an embodiment, the model in the terminal device is an encoder of a CSI generation model.

[0326] In an embodiment, the first data is transmitted by at least one of the following:

[0327] a radio resource control (RRC) message, uplink control information (UCI), an uplink message in a random access procedure, a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), an uplink channel dedicated to artificial intelligence (AI) and / or machine learning (ML), a terminal device capability reporting message, a scheduling information (SCI), a PSCCH, and a PSSCH.

[0328] In an embodiment, the second communication device is a network device, the plurality of to-be-processed information includes a plurality of second information to be processed in the network device, and the processing data includes second data obtained by processing the plurality of second information in a second processing manner.

[0329] In an embodiment, the second information includes at least one of evaluation data, auxiliary data, and output data of a model in the network device.

[0330] In an embodiment, the model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model.

[0331] In an embodiment, the second data is transmitted by at least one of the following:

[0332] a broadcast message, an RRC message, a MAC CE, a DCI, a downlink message in a random access procedure, a PDCCH, a PDSCH, a downlink channel dedicated to AI and / or ML, a capability indication of a network side, an SCI, a PSCCH, and a PSSCH.

[0333] The second communication device 800 of the embodiments of the present application can realize the corresponding functions of the second communication device in the method embodiments described above. The processes, functions, implementation manners and advantages of each module (sub-module, unit or component, etc.) in the second communication device 800 can be referred to the corresponding description in the method embodiments described above, and will not be repeated here. It should be noted that the functions described with respect to each module (sub-module, unit or component, etc.) in the second communication device 800 of the embodiments of the present application can be realized by different modules (sub-modules, units or components, etc.), or by the same module (sub-module, unit or component, etc.).

[0334] FIG. 9 is a schematic structural diagram of a communication device 900 according to the embodiments of the present application. The communication device 900 includes a processor 910. The processor 910 can call and run a computer program from a memory to enable the communication device 900 to implement the methods in the embodiments of the present application.

[0335] In an implementation manner, the communication device 900 can further include a memory 920. The processor 910 can call and run a computer program from the memory 920 to enable the communication device 900 to implement the methods in the embodiments of the present application.

[0336] The memory 920 can be a separate device independent of the processor 910, or can be integrated in the processor 910.

[0337] In an implementation manner, the communication device 900 can further include a transceiver 930. The processor 910 can control the transceiver 930 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0338] The transceiver 930 can include a transmitter and a receiver. The transceiver 930 can further include an antenna, and the number of antennas can be one or more.

[0339] In an implementation manner, the communication device 900 can be the first communication device of the embodiments of the present application, and the communication device 900 can realize the corresponding processes realized by the first communication device in the methods of the embodiments of the present application. For the sake of brevity, details will not be repeated here.

[0340] In an implementation manner, the communication device 900 can be the second communication device of the embodiments of the present application, and the communication device 900 can realize the corresponding processes realized by the second communication device in the methods of the embodiments of the present application. For the sake of brevity, details will not be repeated here.

[0341] FIG. 10 is a schematic structural diagram of a chip 1000 according to an embodiment of the present application. The chip 1000 comprises a processor 1010, which can invoke and run a computer program from a memory to implement the method in the embodiments of the present application.

[0342] In an embodiment, the chip 1000 can further comprise a memory 1020. The processor 1010 can invoke and run a computer program from the memory 1020 to implement the method performed by the first communication device or the second communication device in the embodiments of the present application.

[0343] The memory 1020 can be a separate device independent of the processor 1010, or can be integrated in the processor 1010.

[0344] In an embodiment, the chip 1000 can further comprise an input interface 1030. The processor 1010 can control the input interface 1030 to communicate with other devices or chips, and specifically, can acquire information or data sent by other devices or chips.

[0345] In an embodiment, the chip 1000 can further comprise an output interface 1040. The processor 1010 can control the output interface 1040 to communicate with other devices or chips, and specifically, can output information or data to other devices or chips.

[0346] In an embodiment, the chip can be applied to the first communication device in the embodiments of the present application, and the chip can implement the corresponding procedures in the various methods of the embodiments of the present application performed by the first communication device. For brevity, details are not described herein.

[0347] In an embodiment, the chip can be applied to the second communication device in the embodiments of the present application, and the chip can implement the corresponding procedures in the various methods of the embodiments of the present application performed by the second communication device. For brevity, details are not described herein.

[0348] The chip applied to the first communication device and the second communication device can be the same chip or different chips.

[0349] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system chip, a system-on-chip, a chip system or a system-on-chip, etc.

[0350] The aforementioned processor can be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC) or other programmable logic device, a transistor logic device, a discrete hardware component, and the like. Among them, the aforementioned general-purpose processor can be a microprocessor or any conventional processor and the like.

[0351] The aforementioned memory can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM).

[0352] It should be understood that the aforementioned memory is an exemplary but non-limiting description, for example, the memory in the embodiments of the present application can also be a static RAM (SRAM), a dynamic RAM (DRAM), a synchronous DRAM (SDRAM), a double data rate SDRAM (DDR SDRAM), an enhanced SDRAM (ESDRAM), a synch link DRAM (SLDRAM) and a direct memory bus random access memory (Direct Rambus RAM, DR RAM) and the like. That is, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable type of memory.

[0353] FIG. 11 is a schematic block diagram of a communication system 1100 according to an embodiment of the present application. The communication system 1100 includes a first communication device 1110 and a second communication device 1120.

[0354] The first communication device 1110 is configured to send processing data, the processing data being obtained by processing a plurality of to-be-processed information.

[0355] The second communication device 1120 is configured to receive the processing data, the processing data being obtained by processing a plurality of to-be-processed information by the first communication device.

[0356] The first communication device 1110 can be configured to implement the corresponding functions of the first communication device in the above method, and the second communication device 1120 can be configured to implement the corresponding functions of the second communication device in the above method. For brevity, details are not repeated here.

[0357] In the above embodiments, all or part of the above-mentioned system, device, unit and method can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the above-mentioned system, device, unit and method can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed by a computer, all or part of the above-mentioned system, device, unit and method can generate the flow or function according to the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. 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 through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, solid state disk (SSD)) and the like.

[0358] It should be understood that in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0359] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-mentioned system, device and unit can refer to the corresponding process in the foregoing method embodiments, and details are not repeated here.

[0360] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A data transmission method, comprising: a first communication device sending processed data, the processed data being obtained by processing a plurality of to-be-processed information.

2. The method of claim 1, wherein, The plurality of to-be-processed information comprises relevant data of model performance monitoring, training, testing or use in the first communication device.

3. The method of claim 1, wherein, One to-be-processed information in the plurality of to-be-processed information comprises at least one of: a channel; a feature vector representing channel state information (CSI) ; input information of a model; output information of the model.

4. The method of claim 3, wherein, The channel comprises at least one of: an initial channel composed of time domain information, frequency domain information, angle domain information and antenna domain information; a channel obtained by performing information extraction in the time domain on the initial channel and selecting a partial time domain information subset; a channel obtained by performing information extraction in the frequency domain on the initial channel and selecting a partial frequency domain information subset; a channel obtained by performing information extraction in the angle domain on the initial channel and selecting a partial angle domain information subset; a channel obtained by performing information extraction in the antenna domain on the initial channel and selecting a partial antenna domain information subset; a channel obtained by quantizing the initial channel.

5. The method of claim 3, wherein, The feature vector representing the CSI comprises a feature vector representing the CSI obtained by singular value decomposition (SVD) on the channel.

6. The method of claim 3, wherein, The input information of the model comprises the channel and / or the feature vector representing the CSI.

7. The method of claim 3, wherein, The output information of the model comprises the channel and / or the feature vector representing the CSI.

8. The method of any one of claims 1 to 7, wherein, The processing mode of the plurality of to-be-processed information comprises: mean value acquisition of the plurality of to-be-processed information; mean value acquisition after element processing of the plurality of to-be-processed information.

9. The method of claim 8, wherein, The element processing of the plurality of to-be-processed information comprises at least one of: taking an absolute value of an element in the plurality of to-be-processed information; taking a modulus value of the element in the plurality of to-be-processed information; taking a square of the absolute value of the element in the plurality of to-be-processed information; taking a square of the modulus value of the element in the plurality of to-be-processed information; multiplying the element in the plurality of to-be-processed information by a conjugate of the element.

10. The method of claim 8 or 9, wherein, The mean value acquisition comprises at least one of: taking a mean value of information according to a sample number; taking a mean value of information according to an internal element; taking a mean value of information according to an internal element and then taking a mean value according to a sample number.

11. The method of claim 10, wherein, Taking a mean value of information according to an internal element comprises: taking a mean value of information according to a total number of internal elements; taking a mean value of information according to a dimension element number of internal elements.

12. The method of any one of claims 1 to 11, wherein, The first communication device is a terminal device, the plurality of to-be-processed information comprises a plurality of first information to be processed in the terminal device, and the processed data comprises first data obtained by processing the plurality of first information in a first processing mode.

13. The method of claim 12, wherein, The first information comprises at least one of label data, auxiliary data and input data of a model in the terminal device.

14. The method of claim 13, wherein, The model in the terminal device is an encoder of a CSI generation model.

15. The method of any one of claims 12 to 14, wherein, The first data is transmitted by at least one of: A radio resource control (RRC) message; uplink control information (UCI); an uplink message in a random access procedure; a physical uplink control channel (PUCCH); a physical uplink shared channel (PUSCH); an uplink channel dedicated to artificial intelligence (AI) and / or machine learning (ML); a terminal device capability reporting message, sidelink control information (SCI), a physical sidelink control channel (PSCCH), and a physical sidelink shared channel (PSSCH).

16. The method of any one of claims 1 to 11, wherein, The first communication device is a network device, and the plurality of to-be-processed information includes a plurality of second information to be processed in the network device, and the processed data includes second data obtained by processing the plurality of second information in a second processing manner.

17. The method of claim 16, wherein, The second information includes at least one of evaluation data, auxiliary data, and output data of a model in the network device.

18. The method of claim 17, wherein, The model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model.

19. The method of any one of claims 16-18, wherein, The second data is transmitted by at least one of the following: a broadcast message; an RRC message; a medium access control (MAC) control element (CE); downlink control information (DCI); a downlink message in a random access procedure; a physical downlink control channel (PDCCH); a physical downlink shared channel (PDSCH); a downlink channel dedicated to AI and / or ML; a capability indication of a network side; SCI; a PSCCH; and a PSSCH.

20. A data transmission method, comprising: a second communication device receiving processed data, the processed data being obtained by a first communication device processing a plurality of to-be-processed information.

21. The method of claim 20, wherein, The plurality of to-be-processed information includes data related to model performance monitoring, training, testing, or use in the second communication device.

22. The method of claim 20, wherein, One of the plurality of to-be-processed information includes at least one of the following: a channel; a feature vector representing a CSI; input information of a model; output information of a model.

23. The method of claim 22, wherein, The channel includes at least one of the following: an initial channel composed of time domain information, frequency domain information, angle domain information, and antenna domain information; a channel obtained by performing information extraction in the time domain on the initial channel and selecting a subset of partial time domain information; a channel obtained by performing information extraction in the frequency domain on the initial channel and selecting a subset of partial frequency domain information; a channel obtained by performing information extraction in the angle domain on the initial channel and selecting a subset of partial angle domain information; a channel obtained by performing information extraction in the antenna domain on the initial channel and selecting a subset of partial antenna domain information; a channel obtained by quantizing the initial channel.

24. The method of claim 22, wherein, The feature vector representing the CSI includes a feature vector representing the CSI obtained by performing SVD on the channel.

25. The method of claim 22, wherein, The input information of the model includes the channel and / or the feature vector representing the CSI.

26. The method of claim 22, wherein, The output information of the model includes the channel and / or the feature vector representing the CSI.

27. The method of any one of claims 20 to 26, wherein, The processing manner of the plurality of to-be-processed information includes: mean value acquisition of the plurality of to-be-processed information; mean value acquisition after element processing of the plurality of to-be-processed information.

28. The method of claim 27, wherein, The element processing of the plurality of to-be-processed information includes at least one of the following: taking an absolute value of an element in the plurality of to-be-processed information; taking a modulus value of an element in the plurality of to-be-processed information; An element in the plurality of to-be-processed information takes an absolute value square; An element in the plurality of to-be-processed information takes a modulus value square; An element in the plurality of to-be-processed information is multiplied by a conjugate of the element.

29. The method of claim 27 or 28, wherein, The mean value acquisition includes at least one of the following: Taking the information as a mean value according to a sample number; Taking the information as a mean value according to an internal element; Taking the information as a mean value according to an internal element and then taking the information as a mean value according to a sample number.

30. The method of claim 29, wherein, Taking the information as a mean value according to an internal element includes: Taking the information as a mean value according to a total number of internal elements; Taking the information as a mean value according to a dimension element number of internal elements.

31. The method of any one of claims 20-30, wherein, The second communication device is a terminal device, the plurality of to-be-processed information includes a plurality of first information to be processed in the terminal device, and the processing data includes first data obtained by processing the plurality of first information in a first processing mode.

32. The method of claim 31, wherein, The first information includes at least one of label data, auxiliary data, and input data of a model in the terminal device.

33. The method of claim 32, wherein, The model in the terminal device is an encoder of a CSI generation model.

34. The method of any one of claims 31 to 33, wherein, The first data is transmitted by at least one of the following: A radio resource control (RRC) message, uplink control information (UCI), an uplink message in a random access process, a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), an artificial intelligence (AI) and / or machine learning (ML) dedicated uplink channel, a terminal device capability reporting message, a scheduling information (SCI), a PSCCH, and a PSSCH.

35. The method of any one of claims 20 to 30, wherein, The second communication device is a network device, the plurality of to-be-processed information includes a plurality of second information to be processed in the network device, and the processing data includes second data obtained by processing the plurality of second information in a second processing mode.

36. The method of claim 35, wherein, The second information includes at least one of evaluation data, auxiliary data, and output data of a model in the network device.

37. The method of claim 36, wherein, The model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model.

38. The method of any one of claims 35-37, wherein, The second data is transmitted by at least one of the following: A broadcast message, an RRC message, a MAC CE, DCI, a downlink message in a random access process, a PDCCH, a PDSCH, an AI and / or ML dedicated downlink channel, a capability indication of a network side, an SCI, a PSCCH, and a PSSCH.

39. A first communication device, comprising: a sending unit configured to send processing data, the processing data being obtained by processing a plurality of to-be-processed information.

40. A first communications device according to Claim 39, wherein, The plurality of to-be-processed information includes related data for model performance monitoring, training, testing, or use in the first communication device.

41. The first communication device of claim 39, wherein, One to-be-processed information in the plurality of to-be-processed information includes at least one of the following: a channel; a feature vector representing a CSI; input information of a model; output information of a model.

42. The first communication device of claim 41, wherein, The channel includes at least one of the following: an initial channel composed of time domain information, frequency domain information, angle domain information, and antenna domain information; a channel obtained by performing information extraction on the initial channel in the time domain and selecting a part of a time domain information subset; a channel obtained by performing information extraction on the initial channel in the frequency domain and selecting a part of a frequency domain information subset; a channel obtained by performing information extraction on the initial channel in the angle domain and selecting a part of an angle domain information subset; The initial channel is quantized to obtain a channel. The initial channel is quantized to obtain a channel.

43. The first communication device of claim 42, wherein, The characteristic vector representing the CSI includes a characteristic vector representing the CSI obtained by performing SVD on the channel.

44. The first communication device of claim 42, wherein, The input information of the model includes the channel and / or the characteristic vector representing the CSI.

45. The first communication device of claim 42, wherein, The output information of the model includes the channel and / or the characteristic vector representing the CSI.

46. A first communications device according to any one of claims 39 to 45, wherein, The processing mode of the plurality of to-be-processed information includes: The mean value of the plurality of to-be-processed information is obtained. The mean value of the plurality of to-be-processed information after element processing is obtained.

47. A first communications device according to Claim 46, wherein, The element processing of the plurality of to-be-processed information includes at least one of: The element in the plurality of to-be-processed information takes an absolute value. The element in the plurality of to-be-processed information takes a modulus value. The element in the plurality of to-be-processed information takes the square of the absolute value. The element in the plurality of to-be-processed information takes the square of the modulus value. The element in the plurality of to-be-processed information is multiplied by the conjugate of the element.

48. A first communications device according to claim 46 or 47, wherein, The mean value includes at least one of: The information is averaged according to the number of samples. The information is averaged according to the internal elements. The information is averaged according to the internal elements, and then averaged according to the number of samples.

49. The first communication device of claim 48, wherein, The information is averaged according to the total number of internal elements. The information is averaged according to the number of dimension elements of the internal elements. The first communication device is a terminal device, the plurality of to-be-processed information includes a plurality of first information to be processed in the terminal device, and the processed data includes first data obtained by processing the plurality of first information in a first processing mode.

50. A first communications device according to any one of claims 39 to 49, wherein, The first information includes at least one of label data, auxiliary data, and input data of a model in the terminal device.

51. The first communication device of claim 50, wherein, The model in the terminal device is an encoder of a CSI generation model.

52. The first communication device of claim 51, wherein, The first data is transmitted by at least one of:

53. A first communications device according to any one of claims 50 to 52, wherein, A radio resource control (RRC) message; a UCI; an uplink message in a random access process; a PUCCH; a PUSCH; an AI and / or ML dedicated uplink channel; a terminal device capability reporting message, a SCI, a PSCCH, and a PSSCH. The first communication device is a network device, the plurality of to-be-processed information includes a plurality of second information to be processed in the network device, and the processed data includes second data obtained by processing the plurality of second information in a second processing mode.

54. The first communication device of any one of claims 39 to 49, wherein, The second information includes at least one of evaluation data, auxiliary data, and output data of a model in the network device.

55. A first communications device according to Claim 54, wherein, The model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model.

56. The first communication device of claim 55, wherein, The second data is transmitted by at least one of:

57. A first communications device according to any one of claims 54 to 56, wherein, A broadcast message; an RRC message; a media access control (MAC) control element (CE); a downlink control information (DCI); a downlink message in a random access process; a physical downlink control channel (PDCCH); a physical downlink shared channel (PDSCH); an AI and / or ML dedicated downlink channel; a capability indication of a network side; a SCI; a PSCCH; and a PSSCH.

58. A second communication device, comprising: ​ A receiving unit is configured to receive processing data, which is obtained by processing a plurality of to-be-processed information by a first communication device.

59. The second communication device of claim 58, wherein, The plurality of to-be-processed information includes relevant data of model performance monitoring, training, testing or use in the second communication device.

60. The second communication device of claim 58, wherein, One of the plurality of to-be-processed information includes at least one of the following: a channel; a feature vector representing CSI; input information of a model; output information of a model.

61. The second communication device of claim 60, wherein, The channel includes at least one of the following: an initial channel composed of time domain information, frequency domain information, angle domain information and antenna domain information; a channel obtained by extracting information in the time domain from the initial channel and selecting a subset of partial time domain information; a channel obtained by extracting information in the frequency domain from the initial channel and selecting a subset of partial frequency domain information; a channel obtained by extracting information in the angle domain from the initial channel and selecting a subset of partial angle domain information; a channel obtained by extracting information in the antenna domain from the initial channel and selecting a subset of partial antenna domain information; a channel obtained by quantizing the initial channel.

62. The second communication device of claim 60, wherein, The feature vector representing the CSI includes a feature vector representing the CSI obtained by performing SVD on the channel.

63. The second communication device of claim 60, wherein, The input information of the model includes the channel and / or the feature vector representing the CSI.

64. The second communication device of claim 60, wherein, The output information of the model includes the channel and / or the feature vector representing the CSI.

65. A second communications device according to any one of claims 58 to 64, wherein, The processing mode of the plurality of to-be-processed information includes: mean value acquisition of the plurality of to-be-processed information; mean value acquisition after element processing of the plurality of to-be-processed information.

66. The second communication device of claim 65, wherein, The element processing of the plurality of to-be-processed information includes at least one of the following: taking absolute value of the elements in the plurality of to-be-processed information; taking modulus value of the elements in the plurality of to-be-processed information; taking square of the absolute value of the elements in the plurality of to-be-processed information; taking square of the modulus value of the elements in the plurality of to-be-processed information; multiplying the elements in the plurality of to-be-processed information by the conjugate of the elements.

67. A second communications device according to claim 65 or 66, wherein, The mean value acquisition includes at least one of the following: taking mean value of information according to sample number; taking mean value of information according to internal elements; taking mean value of information according to internal elements and then taking mean value according to sample number.

68. The second communication device of claim 67, wherein, Taking mean value of information according to internal elements includes: taking mean value of information according to total number of internal elements; taking mean value of information according to dimension element number of internal elements.

69. A second communications device according to any one of claims 58 to 68, wherein, The second communication device is a terminal device, and the plurality of to-be-processed information includes a plurality of first information to be processed in the terminal device, and the processing data includes first data obtained by processing the plurality of first information by a first processing mode.

70. A second communications device according to Claim 69 wherein, The first information includes at least one of label data, auxiliary data and input data of a model in the terminal device.

71. The second communication device of claim 70, wherein, The model in the terminal device is an encoder of a CSI generation model.

72. A second communications device according to any one of claims 69 to 71, wherein, The first data is transmitted by at least one of the following: RRC message; UCI; uplink message in random access process; PUCCH; PUSCH; AI and / or ML dedicated uplink channel; terminal device capability reporting message, SCI, PSCCH and PSSCH.

73. A second communications device according to any one of claims 58 to 69, wherein, The second communication device is a network device, the plurality of to-be-processed information includes a plurality of second information to be processed in the network device, and the processing data includes second data obtained by processing the plurality of second information in a second processing mode.

74. A second communications device according to Claim 73, wherein, The second information includes at least one of evaluation data, auxiliary data, and output data of a model in the network device.

75. A second communications device according to Claim 74, wherein, The model in the network device is a decoder of a CSI recovery model and / or a CSI prediction model.

76. A second communications device according to any one of claims 73 to 75, wherein, The second data is transmitted by at least one of the following: a broadcast message; an RRC message; a MAC CE; DCI; a downlink message in a random access process; a PDCCH; a PDSCH; an AI and / or ML dedicated downlink channel; a capability indication of a network side; SCI; a PSCCH; and a PSSCH.

77. A communication device, comprising: A processor and a memory, the memory being configured to store a computer program, and the processor being configured to invoke and run the computer program stored in the memory, so that the communication device executes the method according to any one of claims 1 to 19 or any one of claims 20 to 38.

78. A chip comprising: A processor configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 1 to 19 or any one of claims 20 to 38.

79. A computer-readable storage medium configured to store a computer program, which, when executed by a device, causes the device to execute the method according to any one of claims 1 to 19 or any one of claims 20 to 38.

80. A computer program product comprising computer program instructions configured to cause a computer to execute the method according to any one of claims 1 to 19 or any one of claims 20 to 38.

81. A computer program configured to cause a computer to execute the method according to any one of claims 1 to 19 or any one of claims 20 to 38.

Images