WO2023125240A1

WO2023125240A1 - Channel data processing or inverse processing method and apparatus, terminal, and network device

Info

Publication number: WO2023125240A1
Application number: PCT/CN2022/141064
Authority: WO
Inventors: 周化雨; 马大为; 陈咪咪; 潘振岗
Original assignee: 展讯通信（上海）有限公司
Priority date: 2021-12-31
Filing date: 2022-12-22
Publication date: 2023-07-06
Also published as: CN116436500A

Abstract

Disclosed by the present application are a channel data processing or inverse processing method and apparatus, terminal, and network device; the method comprises: obtaining first channel data; processing the first channel data to obtain second channel data; correspondingly, obtaining second channel data; performing inverse processing on the second channel data to obtain first channel data. In the process of directly feeding back (or reporting) the channel data to a CSI feedback architecture by means of an AI model, in order to adapt to the AI model used for image processing, the situation that the AI model cannot process the channel data or the AI model's processing efficiency is low because the number of elements in the channel data inputted into the AI model exceeds the range is avoided; the terminal must process the obtained first channel data such that the second channel data meets the requirements of the AI model adapted to image processing, and thus it is ensured that the AI model can successfully process the input second channel data or achieve high processing efficiency.

Description

Channel data processing or anti-processing method and device, terminal and network equipment

technical field

The present application relates to the technical field of communication, and in particular to a channel data processing or inverse processing method and device, terminal and network equipment.

Background technique

In the evolution of wireless communication systems, people have been exploring the integration of artificial intelligence (AI) and the physical layer. Among them, AI can include machine learning (machine learning, ML), deep learning (deep learning, DL) and so on. Introducing AI into the physical layer algorithm can solve some problems that are difficult to solve with traditional modeling methods, such as some nonlinear problems and too complex parameters. AI algorithms can bypass traditional modeling methods and build some problem-solving models through training with large amounts of data. With the maturity of AI algorithms and the maturity of hardware suitable for AI algorithms, the introduction of AI into physical layer algorithms has attracted more and more attention.

As a typical application, AI can be introduced into Channel State Information (CSI) feedback. In the scenario where AI is introduced into CSI feedback, the terminal can directly feed back (or report) the precoding matrix or channel data through the AI neural network (which can be referred to as AI model for short), that is, the terminal directly feeds back the precoding matrix or channel matrix to the CSI feedback framework (Including the overall feedback mechanism of CQI, PMI, RI, CRI (or SSBRI), etc.). AI models can include convolutional neural network (CNN), deep neural network (DNN), etc.

In some scenarios, direct feedback of precoding matrix or channel data has more information than codebook-based feedback, such as amplitude information (eigenvectors have no amplitude information), and is more suitable for multi-user multi-input and multi-output (multi-user multi-output) -input multi-output, MU-MIMO), etc.

Since most AI models are used for image processing, and a pixel in an image is one or a set of gray values, the image input to the AI model is a real number greater than or equal to zero. However, when the terminal estimates the precoding matrix or channel matrix by referring to the signal, each element in the precoding matrix or channel matrix may be a complex value, even if the precoding matrix or channel matrix is divided into real part data and imaginary part data. Part data, the elements in the real part data or imaginary part data may still be positive or negative. Therefore, in the process of directly feeding back the precoding matrix or channel matrix to the CSI feedback architecture through the AI model, in order to adapt the AI model for image processing, it is necessary to process the channel data to be fed back (or reported).

Contents of the invention

The first aspect is a channel data processing method of the present application, including:

Obtain the first channel data;

Process the first channel data to obtain second channel data.

It can be seen that in the process of directly feeding back (or reporting) channel data to the CSI feedback architecture through the AI model, in order to adapt the AI model used for image processing, it is necessary to avoid the out-of-range number of elements in the input channel data of the AI model. As a result, the AI model cannot process the channel data or the AI model processing efficiency is low. The terminal in the embodiment of the present application needs to process the channel data (that is, the first channel data) to be fed back (or reported), so that the processed channel data (that is, The second channel data) meet the requirements of the AI model adapted to image processing, which is beneficial to ensure that the AI model can successfully process the input processed channel data or achieve higher processing efficiency.

The second aspect is a channel data inverse processing method of the present application, including:

Obtain second channel data;

Reverse processing is performed on the second channel data to obtain the first channel data.

It can be seen that in the process of directly feeding back channel data to the CSI feedback architecture through the AI model, in order to adapt the AI model used for image processing, the terminal needs to process the fed back (or reported) channel data before performing feedback (or report), so when the network device obtains the processed channel data (that is, the second channel data), the network device needs to inversely process the processed channel data to obtain the first channel data, so that the network device can pass the first The channel data performs related operations, for example, the network device calculates the CQI through the first channel data, calculates the corresponding SINR and the corresponding MCS through the first channel data so as to schedule the terminals through the MCS, and so on.

The third aspect is a channel data processing device of the present application, the device includes a processing unit, and the processing unit is used for:

Obtain the first channel data;

Process the first channel data to obtain second channel data.

The fourth aspect is a channel data inverse processing device of the present application, the device includes a processing unit, and the processing unit is used for:

Obtain second channel data;

In the fifth aspect, the steps in the method designed in the above-mentioned first aspect are applied to the terminal.

In a sixth aspect, the steps in the method designed in the above-mentioned second aspect are applied to a network device.

The seventh aspect is a terminal of the present application, including a processor, a memory, and computer programs or instructions stored on the memory, wherein, the processor executes the computer program or instructions to implement the above-mentioned first aspect. steps in the designed method.

The eighth aspect is a network device of the present application, including a processor, a memory, and computer programs or instructions stored on the memory, wherein the processor executes the computer program or instructions to implement the second aspect above Steps in the method designed in.

A ninth aspect is a chip of the present application, including a processor, wherein the processor executes the steps in the method designed in the first aspect or the second aspect.

The tenth aspect is a chip module of the present application, including a transceiver component and a chip, and the chip includes a processor, wherein the processor executes the steps in the method designed in the first aspect or the second aspect.

The eleventh aspect is a computer-readable storage medium of the present application, wherein computer programs or instructions are stored on the computer-readable storage medium, and when the computer programs or instructions are executed by a processor, the above-mentioned first aspect is realized Or a step in the method as contemplated in the second aspect.

The twelfth aspect is a computer program product of the present application, including computer programs or instructions, wherein, when the computer programs or instructions are executed by a processor, the above-mentioned methods in the first or second aspect are implemented. step.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings that are required in the embodiments or the description of the prior art.

FIG. 1 is a schematic structural diagram of a wireless communication system according to an embodiment of the present application;

FIG. 2 is a schematic flowchart of a method for channel data processing and inverse processing according to an embodiment of the present application;

FIG. 3 is a block diagram of functional units of a channel data processing device according to an embodiment of the present application;

FIG. 4 is a block diagram of functional units of a channel data inverse processing device according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a network device according to an embodiment of the present application.

Detailed ways

In order for those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Apparently, the described embodiments are some of the embodiments of the present application, but not all of them. With regard to the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

It should be understood that the terms "first", "second" and the like involved in the embodiments of the present application are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, software, product, or device that includes a series of steps or units is not limited to the listed steps or units, but also includes steps or units that are not listed, or includes , other steps or units inherent in the product or equipment.

The "embodiments" referred to in the embodiments of the present application means that specific features, structures or characteristics described in conjunction with the embodiments may be included in at least one embodiment of the present application. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments.

"At least one" in the embodiments of the present application refers to one or more, and multiple refers to two or more.

"And/or" in the embodiment of this application describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and/or B, which may indicate the following three situations: A exists alone, and A and B exist simultaneously , B exists alone. Wherein, A and B may be singular or plural. The character "/" can indicate that the contextual objects are an "or" relationship. In addition, the symbol "/" can also represent a division sign, that is, to perform a division operation.

"At least one of the following" or similar expressions in the embodiments of the present application refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one item (piece) of a, b or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b and c. Wherein, each of a, b, and c may be an element, or a set containing one or more elements.

It should be noted that the "connection" in the embodiments of the present application refers to various connection modes such as direct connection or indirect connection to realize communication between devices, and there is no limitation on this. "Network" and "system" in the embodiments of the present application express the same concept, and the communication system is the communication network.

The technical solutions of the embodiments of the present application can be applied to various wireless communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, broadband code division multiple Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, evolution system of NR system, LTE (LTE-based Access to Unlicensed Spectrum, LTE-U) system on unlicensed spectrum, NR (NR-based Access to Unlicensed Spectrum, LTE-U) system on unlicensed spectrum to Unlicensed Spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunications System (UMTS), Wireless Local Area Networks (WLAN), wireless security True (Wireless Fidelity, WiFi), the 6th generation (6th-Generation, 6G) communication system or other communication systems, etc.

It should be noted that the number of connections supported by a traditional wireless communication system is limited and easy to implement. However, with the development of communication technology, the wireless communication system can not only support the traditional wireless communication system, but also support such as device to device (device to device, D2D) communication, machine to machine (machine to machine, M2M) communication, machine Type communication (machine type communication, MTC), inter-vehicle (vehicle to vehicle, V2V) communication, vehicle networking (vehicle to everything, V2X) communication, narrowband Internet of things (narrow band internet of things, NB-IoT) communication, etc., so The technical solutions of the embodiments of the present application may also be applied to the foregoing wireless communication system.

Optionally, the wireless communication system in this embodiment of the present application may be applied to beamforming (beamforming), carrier aggregation (carrier aggregation, CA), dual connectivity (dual connectivity, DC) or independent (standalone, SA) deployment scenarios, etc.

Optionally, the wireless communication system in this embodiment of the present application may be applied to an unlicensed spectrum. Wherein, the unlicensed spectrum can also be regarded as a shared spectrum. Alternatively, the wireless communication system in this embodiment may also be applied to licensed spectrum. Wherein, the licensed spectrum can also be regarded as a non-shared spectrum.

Since the embodiments of the present application describe various embodiments in conjunction with a terminal and a network device, the related terminal and network device will be specifically described below.

Specifically, the terminal may be user equipment (user equipment, UE), remote terminal (remote UE), relay equipment (relay UE), access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, mobile equipment, user terminal, smart terminal, wireless communication device, user agent or user device. It should be noted that the relay device is a terminal capable of providing relay and forwarding services for other terminals (including remote terminals). In addition, the terminal can also be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a wireless Handheld devices with communication functions, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, terminals in next-generation communication systems (such as NR communication systems, 6G communication systems) or future evolution of public land mobile communications Terminals in the network (public land mobile network, PLMN), etc., are not specifically limited.

Furthermore, the terminal can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can be deployed on water (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

Further, the terminal may be a mobile phone, a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (virtual reality, VR) terminal device, an augmented reality (augmented reality, AR) terminal device, an industrial control ( Wireless terminal equipment in industrial control, wireless terminal equipment in unmanned automatic driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid, transportation safety Wireless terminal devices in smart cities, wireless terminal devices in smart cities, or wireless terminal devices in smart homes.

Specifically, the network device may be a device for communicating with the terminal, which is responsible for radio resource management (radio resource management, RRM), service quality (quality of service, QoS) management, data compression and encryption, Data sending and receiving, etc. Wherein, the network device may be a base station (base station, BS) in a communication system or a device deployed in a radio access network (radio access network, RAN) to provide a wireless communication function. For example, base transceiver station (BTS) in GSM or CDMA communication system, node B (node B, NB) in WCDMA communication system, evolved node B (evolutional node B, eNB or eNodeB) in LTE communication system , the next generation evolved node B (next generation evolved node B, ng-eNB) in the NR communication system, the next generation node B (next generation node B, gNB) in the NR communication system, the master node in the dual link architecture (master node, MN), second node or secondary node (secondary node, SN) in the dual-link architecture, etc., there is no specific limitation on this.

Further, the network device may also be other devices in the core network (core network, CN), such as access and mobility management function (access and mobility management function, AMF), user plan function (user plan function, UPF), etc.; It may also be an access point (access point, AP) in a wireless local area network (wireless local area network, WLAN), a relay station, a communication device in a future evolved PLMN network, a communication device in an NTN network, and the like.

Further, the network device may include an apparatus having a wireless communication function for the terminal, such as a chip system. Exemplarily, the chip system may include a chip, and may also include other discrete devices.

Further, the network device can communicate with an Internet Protocol (Internet Protocol, IP) network. For example, the Internet (internet), a private IP network or other data networks and the like.

It should be noted that, in some network deployments, the network device may be an independent node to implement all the functions of the above-mentioned base station, which may include a centralized unit (centralized unit, CU) and a distributed unit (distributed unit, DU), Such as gNB-CU and gNB-DU; can also include active antenna unit (active antenna unit, AAU). Among them, the CU can realize some functions of the network equipment, and the DU can also realize some functions of the network equipment. For example, CU is responsible for processing non-real-time protocols and services, implementing radio resource control (radio resource control, RRC) layer, service data adaptation protocol (service data adaptation protocol, SDAP) layer, packet data convergence (packet data convergence protocol, PDCP) layer function. The DU is responsible for processing physical layer protocols and real-time services, realizing the functions of the radio link control (radio link control, RLC) layer, medium access control (medium access control, MAC) layer and physical (physical, PHY) layer. In addition, the AAU can implement some physical layer processing functions, radio frequency processing and related functions of active antennas. Since the information of the RRC layer will eventually become the information of the PHY layer, or be converted from the information of the PHY layer, under this network deployment, high-level signaling (such as RRC layer signaling) can be considered to be sent by the DU, Or sent jointly by DU and AAU. It can be understood that the network device may include at least one of CU, DU, and AAU. In addition, the CU can be divided into network devices in an access network (radio access network, RAN), and the CU can also be divided into network devices in a core network, which is not specifically limited.

Further, the network device may have a mobile feature, for example, the network device may be a mobile device. Optionally, the network equipment may be a satellite or a balloon station. For example, the satellite can be a low earth orbit (low earth orbit, LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geosynchronous earth orbit (geosynchronous earth orbit, GEO) satellite, a high elliptical orbit (high elliptical orbit, HEO) satellite. ) Satellite etc. Optionally, the network device may also be a base station installed on land, water, and other locations.

Furthermore, the network device can provide services for the cell, and the terminals in the cell can communicate with the network device through transmission resources (such as spectrum resources). Wherein, the cell may include a macro cell, a small cell, a metro cell, a micro cell, a pico cell, a femto cell, and the like.

In combination with the foregoing description, an exemplary description of the wireless communication system according to the embodiment of the present application is given below.

For example, please refer to FIG. 1 for the wireless communication system of the embodiment of the present application. The wireless communication system 10 may include a network device 110 and a terminal 120 , and the network device 110 may be a device performing communication with the terminal 120 . Meanwhile, the network device 110 may provide communication coverage for a specific geographical area, and may communicate with the terminal 120 located within the coverage area.

Optionally, the wireless communication system 10 may also include multiple network devices, and a certain number of terminals may be included within the coverage of each network device, which is not specifically limited here.

Optionally, the wireless communication system 10 may further include other network entities such as a network controller and a mobility management entity, which are not specifically limited here.

Optionally, the communication between the network device and the terminal and between the terminals in the wireless communication system 10 may be wireless communication or wired communication, which is not specifically limited here.

The relevant content involved in the embodiment of the present application is introduced below.

1. Multiple Input Multiple Output (MIMO)

MIMO technology has many advantages such as high spectrum efficiency and large system capacity. Among them, the MIMO signal model can be expressed as:

r=Hs+n;

Among them, r represents the received signal vector; H represents the channel matrix for the MIMO channel; s represents the transmitted signal vector; n represents the additive noise vector.

In the precoding system, the transmitter can optimize the spatial characteristics of the transmitted signal according to the channel matrix, so that the spatial distribution characteristics of the transmitted signal match the channel matrix, which can effectively reduce the dependence on the receiver algorithm.

Precoding can use linear or non-linear methods. Due to reasons such as complexity, generally only linear precoding is considered in current wireless communication systems. After precoding, the MIMO signal model can be expressed as:

r=HWs+n;

Wherein, W represents a precoding matrix.

2. Channel state information (Channel State Information, CSI) feedback (feedback) or report (report)

The protocol standard formulated by the 3rd generation partnership project (3rd generation partnership project, 3GPP) conducts related research on channel state information (Channel State Information, CSI). CSI is the channel state information used by the terminal to feed back the quality of the downlink channel to the network device, so that the network device can select an appropriate modulation and coding strategy (modulation and coding Scheme, MCS) for the transmission of downlink data, and reduce the error block of downlink data transmission Rate (block error rate, BLER) and perform corresponding beam management, mobility management, adaptation tracking, rate matching and other processing.

CSI feedback may include channel state information reference signal resource indicator (CSI reference signal resource indicator, CRI), rank indicator (rank indicator, RI), precoding matrix indicator (precoding matrix indicator, PMI), channel quality indicator (channel quality indicator, At least one of CQI), synchronization signal block resource indicator (SS/PBCH block resource indicator, SSBRI), layer indicator (layer indicator, LI) and the like.

The CRI (or SSBRI) may represent the CSI-RS (or SSB) resource set recommended (or selected) by the terminal. Wherein, one CSI-RS (or SSB) resource set may represent one beam or antenna direction.

The CQI may represent the quality of the current wireless channel fed back by the terminal to the network device. Wherein, the terminal needs to calculate the CQI and report the largest CQI index. The CQI index can enable the terminal to receive a PDSCH transmission block with a transport block error probability not exceeding 0.1. The PDSCH transmission block has a modulation format, a target code rate, and a transmission block size. The PDSCH transmission block corresponds to the CQI Indexed, and occupied CSI reference resources.

RI may indicate the number of layers recommended (or selected) by the terminal, and the number of layers may determine which codebook. Wherein, each layer number corresponds to a codebook, and a codebook is composed of one or more codewords. For example, a codebook with a layer number of 2 or a codebook with a layer number of 1. In addition, in the MIMO technology, the number of layers can be used to represent the number of transmission links between the sending end and the receiving end.

The PMI may represent the index of the codeword in the codebook recommended (or selected) by the terminal. Wherein, one codeword corresponds to one precoding matrix. RI and PMI can integrally represent the number of layers and the precoding matrix recommended by the UE.

The terminal can perform downlink channel estimation/measurement according to a downlink reference signal (such as CSI-RS) to obtain a channel matrix. In codebook-based precoding, the terminal can select the precoding matrix that best matches the channel matrix from the codebook according to a certain optimization criterion, and feed back its index to the network device through the feedback link. At the same time, the terminal can calculate the channel quality after using the PMI according to the recommended PMI, and report the CQI. In the process of calculating the PMI and the CQI, the terminal needs to consider its own reception processing algorithm.

During downlink transmission, the network device uses the PMI reported by the terminal as a reference to precode data. When the downlink precoding matrix used by the network device is inconsistent with the PMI reported by the terminal, in order to ensure that the terminal can know the precoded equivalent channel and coherently demodulate the downlink data, the network device needs to send the downlink control information (downlink control information, DCI) indicates the precoding matrix it adopts.

It should be noted that the number of layers and the precoding matrix recommended (or selected) by the terminal reflect the eigenvector of the channel matrix. Therefore, the terminal can derive the number of layers and the precoding matrix through the channel matrix.

In addition, when calculating the CQI, the terminal may select a PMI/RI combination corresponding to a precoding matrix. Under the assumption of the precoding matrix, the terminal needs to calculate the current signal to interference and noise ratio (SINR) through the estimated channel matrix and the covariance matrix of the interference noise. The SINR can also be called post-equalizer SINR (post-equalizer SINR), because its corresponding SINR calculation method takes into account the influence of the equalizer, and the equalizer can also be called a MIMO receiver.

Or, under the assumption of the precoding matrix, the terminal needs to calculate the current SINR through the estimated channel matrix, the covariance matrix of the interference noise, and the decoder. The SINR can also be called post-decoder SINR (post-decoder SINR), because its corresponding SINR calculation method takes into account the influence of the equalizer and decoder.

Therefore, the CQI calculated by the terminal according to the selected (or recommended) PMI, RI and CRI (or SSBRI) may correspond to one SINR. At the same time, the terminal can feed back (or report) the calculated CQI to the network device.

After obtaining the CQI, the network device can deduce the SINR in reverse, and can perform certain processing on the SINR according to the PMI and RI (corresponding to the precoding matrix) reported by the terminal (or independently selected) and the SINR during downlink transmission. For example, the network device can use experience In this way, the SINR is increased or decreased, and an appropriate modulation and coding format is selected to schedule the terminal.

3. CSI feedback and artificial intelligence (AI)

In the evolution of wireless communication systems, people have been exploring the use of artificial intelligence and the integration of the physical layer. Among them, AI can include machine learning (machine learning, ML), deep learning (deep learning, DL) and so on. Introducing AI into the physical layer algorithm can solve some problems that are difficult to solve with traditional modeling methods, such as some nonlinear problems and too complex parameters. AI algorithms can bypass traditional modeling methods and build some problem-solving models through training with large amounts of data. With the maturity of AI algorithms and the maturity of hardware suitable for AI algorithms, the introduction of AI into physical layer algorithms has attracted more and more attention.

As a typical application, AI can be introduced into CSI feedback. In the scenario where AI is introduced into CSI feedback, the terminal can directly feed back (or report) the precoding matrix or channel matrix through the AI neural network (referred to as the AI model), that is, the terminal directly feeds back the precoding matrix or channel matrix to the CSI feedback framework (Including the overall feedback mechanism of CQI, PMI, RI, CRI (or SSBRI), etc.). AI models can include convolutional neural networks, deep neural networks, and more.

In some scenarios, the direct feedback precoding matrix or channel matrix has more information than the codebook-based feedback, such as amplitude information (the eigenvector has no amplitude information), and is more suitable for multi-user multi-input and multi-output (multi-user multi-output) -input multi-output, MU-MIMO), etc.

In the process of directly feeding back the precoding matrix or channel matrix to the CSI feedback architecture through the AI model, on the terminal side, the precoding matrix or channel matrix is processed, then input into the AI model for compression, and then quantized and encoded to obtain encoding information;

On the network device side, the coded information is decoded and dequantized, then input into the AI model for decompression, and then processed to obtain the precoding matrix or channel matrix.

In addition, the precoding matrix or channel matrix in the embodiment of the present application may be the precoding matrix or channel matrix before compression, or the precoding matrix or channel matrix after decompression, which is not specifically limited.

Since most AI models are used for image processing, and a pixel in an image is one or a set of gray values, the image input to the AI model is a real number greater than or equal to zero. However, when the terminal estimates the precoding matrix or channel matrix by referring to the signal, each element in the precoding matrix or channel matrix may be a complex value, even if the precoding matrix or channel matrix is divided into a real part and an imaginary part , the real or imaginary part may still be positive or negative. Therefore, in the process of directly feeding back the precoding matrix or channel matrix to the CSI feedback architecture through the AI model, in order to adapt the AI model for image processing, it is necessary to process the precoding matrix or channel matrix to be fed back (or reported) .

The channel data processing and inverse processing methods of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

As shown in Figure 2, it is a schematic flow chart of a channel data processing and inverse processing method according to an embodiment of the present application, which includes the following steps:

S210. The terminal acquires the first channel data.

It should be noted that the channel data in the embodiment of the present application may be the precoding matrix or the channel matrix itself, or the processed data of the channel matrix or the precoding matrix, such as the sorted data of the channel matrix or the precoding matrix wait.

S220. The terminal processes the first channel data to obtain the second channel data.

S230. The network device acquires the second channel data.

S240. The network device performs inverse processing on the second channel data to obtain the first channel data.

It should be noted that the embodiment of the present application needs to analyze the scenario where AI is introduced into the CSI feedback. Therefore, the terminal can directly feed back (or report) the precoding matrix or the channel matrix through the AI model, instead of the feedback based on the codebook.

Since most AI models are used for image processing, and a pixel in an image is one or a set of gray values, the image input to the AI model is a real number greater than or equal to zero. However, when the terminal uses the channel data estimated by the reference signal, each element in the channel data may be a complex value.

One way is that the channel data can be divided into real part data and imaginary part data, and elements in the real part data or imaginary part data may still be positive or negative.

Alternatively, the channel data can be divided into amplitude data and phase data, and elements within the amplitude data or phase data may still be positive or negative.

In the process of directly feeding back (or reporting) channel data to the CSI feedback architecture through the AI model, in order to adapt the AI model used for image processing, avoid AI due to out-of-range elements in the channel data input to the AI model. The model cannot process the channel data or the AI model processing efficiency is low. The terminal in the embodiment of the present application needs to process the channel data (that is, the first channel data) to be fed back (or reported), so that the processed channel data (that is, the second channel data) channel data) meet the requirements of the AI model adapted to image processing, which is beneficial to ensure that the AI model can successfully process the input processed channel data or achieve higher processing efficiency.

For example, the possible process for the terminal to directly feed back (or report) channel data through the AI model is as follows:

First, the terminal can perform downlink channel estimation/measurement through downlink signals (such as CSI-RS, SSB or PBCH DMRS, etc.) to obtain the first channel data, and then process the first channel data to obtain the second channel data;

Secondly, the terminal inputs the second channel data into the AI model to obtain the compression information corresponding to the second channel data;

Then, the terminal sends the compressed information to the quantizer and encoder, and after the quantization and encoding is completed, it is fed back (or reported) on the physical uplink channel (such as the physical uplink shared channel (PUSCH), physical uplink control channel (PUCCH)) through CSI ) process is sent to the network device;

Finally, the network device decodes, dequantizes, and inputs the AI model through the reverse process to obtain the second channel data, and then performs inverse processing on the second channel data to obtain the first channel data, so that the network device can execute through the first channel data. Relevant operations, for example, the network device calculates the CQI through the first channel data, calculates the corresponding SINR and the corresponding MCS through the first channel data so as to schedule the terminal through the MCS, and the like.

To sum up, in the process of directly feeding back channel data to the CSI feedback architecture through the AI model, the terminal needs to process the channel data to be fed back (or reported), and the network device needs to inversely process the acquired processed channel data . How to process the first channel data and how to inversely process the second channel data will be specifically described below.

method one:

Because at least one of the elements in the first channel data, the real part of the elements in the first channel data, and the imaginary part of the elements in the first channel data may be less than or equal to a preset value (such as zero) , so in the embodiment of the present application, the real part and/or the imaginary part of the element, the amplitude of the element and/or the phase of the element can be shifted so that it is greater than or equal to a preset value (such as zero), so as to facilitate Guarantees successful processing by the AI model when input to the AI model for processing.

For the terminal, the terminal needs to check the elements in the first channel data, the real part of the elements in the first channel data, the imaginary part of the elements in the first channel data, the amplitude of the elements in the first channel data, the first A shift amount is subtracted from at least one of the phases of the elements within the channel data.

It can be understood that the following methods can exist for the terminal:

1) The terminal subtracts the translation amount from the elements in the first channel data; where the translation amount is used to perform translation processing on the elements in the first channel data so that it is greater than or equal to a preset value;

2) The terminal subtracts the translation amount from the real part of the element in the first channel data; where the translation amount is used to perform translation processing on the real part of the element in the first channel data so that it is greater than or equal to a preset value;

3) The terminal subtracts a translation amount from the imaginary part of the element in the first channel data; where the translation amount is used to perform translation processing on the imaginary part of the element in the first channel data so that it is greater than or equal to a preset value;

4) The terminal subtracts the translation amount from the real part and the imaginary part of the elements in the first channel data; where the translation amount is used to perform translation processing on the real part and the imaginary part of the elements in the first channel data so that it is greater than or equal to a preset value;

5) The terminal subtracts the translation amount from the amplitude of the element in the first channel data; wherein, the translation amount is used to perform translation processing on the amplitude of the element in the first channel data so that it is greater than or equal to a preset value;

6) The terminal subtracts the shift amount from the phase of the elements in the first channel data; where the shift amount is used to shift the phase of the elements in the first channel data so that it is greater than or equal to a preset value;

7) The terminal subtracts a shift amount from the real part and the imaginary part of the elements in the first channel data; where the shift amount is used to shift the amplitude and phase of the elements in the first channel data so that it is greater than or equal to one default value;

etc.; there is no specific limitation thereon.

For the network device, the network device needs to analyze the elements in the second channel data, the real part of the elements in the second channel data, the imaginary part of the elements in the second channel data, the amplitude of the elements in the second channel data, A shift amount is added to at least one of the phases of the elements within the second channel data.

It can be understood that the following modes may exist for network devices:

1) The network device adds a translation amount to the elements in the second channel data; wherein, the translation amount is used to perform translation processing on the elements in the first channel data so that it is greater than or equal to a preset value;

2) The network device adds a translation amount to the real part of the element in the second channel data; wherein, the translation amount is used to perform translation processing on the real part of the element in the first channel data so that it is greater than or equal to a preset value ;

3) The network device adds a translation amount to the imaginary part of the element in the second channel data; wherein, the translation amount is used to perform translation processing on the imaginary part of the element in the first channel data so that it is greater than or equal to a preset value ;

4) The network device adds a translation amount to the real part and the imaginary part of the elements in the second channel data; wherein, the translation amount is used to perform translation processing on the real part and the imaginary part of the elements in the first channel data so that it is greater than or equal to a preset value;

5) The network device adds a translation amount to the amplitude of the elements in the second channel data; wherein, the translation amount is used to perform translation processing on the amplitude of the elements in the first channel data so that it is greater than or equal to a preset value;

6) The network device adds a shift amount to the phase of the elements in the second channel data; wherein, the shift amount is used to shift the phase of the elements in the first channel data so that it is greater than or equal to a preset value;

7) The network device adds a translation amount to the amplitude and phase of the elements in the second channel data; wherein, the translation amount is used to perform translation processing on the real part and the imaginary part of the elements in the first channel data so that it is greater than or equal to a preset value;

etc.; there is no specific limitation thereon.

In addition, for the amount of translation, the embodiment of the present application may exist as follows:

1) The translation amount can be m;

Wherein, the m can be used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the imaginary part of all the elements in the first channel data The minimum value of at least one of the component, the amplitude of all elements in the first channel data, and the phase of all elements in the first channel data.

For example, the terminal may subtract the minimum value of all elements in the first channel rectangle from the element to make it greater than or equal to a preset value. For the network device, the network device needs to add the minimum value among all the elements in the first channel rectangle to the elements of the second channel data, so as to ensure that the first channel data is recovered.

Similarly, the terminal may subtract the minimum value of the modulus of all the elements in the first channel rectangle from the element to make it greater than or equal to a preset value.

As for the network device, the network device needs to add the minimum value of the modulus of all elements in the first channel rectangle to the elements of the second channel data, so as to ensure that the first channel data is recovered. Among them, the modulus of an element is a measure of an element, including amplitude value, phase value, power value, maximum absolute value of real part and imaginary part, absolute value of real part plus imaginary part, etc., but not limited to the listed values .

Similarly, the terminal may subtract the minimum value among the real parts of all elements in the first channel rectangle from the real part of the element, so that it is greater than or equal to a preset value. For the network device, the network device needs to add the minimum value among the real parts of all elements in the first channel rectangle to the real part of the elements of the second channel data, so as to ensure recovery of the first channel data.

Similarly, the terminal may subtract the minimum value of the imaginary parts of all elements in the first channel rectangle from the imaginary part of the element to make it greater than or equal to a preset value. For the network device, the network device needs to add the minimum value of the imaginary parts of all elements in the first channel rectangle to the imaginary part of the elements of the second channel data, so as to ensure that the first channel data is recovered.

Similarly, the terminal may subtract the minimum value of the amplitudes of all elements in the first channel rectangle from the real part of the element to make it greater than or equal to a preset value. For the network device, the network device needs to add the minimum value of the amplitudes of all elements in the first channel rectangle to the amplitude of the elements of the second channel data, so as to ensure that the first channel data is restored.

Similarly, the terminal may subtract the minimum value of the phases of all elements in the first channel rectangle from the imaginary part of the element to make it greater than or equal to a preset value. For the network device, the network device needs to add the minimum value of the phases of all elements in the first channel rectangle to the phase of the elements of the second channel data, so as to ensure the restoration of the first channel data.

2) The translation amount can be a quantized value of m;

It should be noted that, based on the above description, since the first channel data obtained by the terminal may be quantized before being input into the AI model, the elements in the first channel data, the real parts of the elements in the first channel data and/or Or the imaginary part of the element in the first channel data, the amplitude of the element in the first channel data and/or the phase of the element in the first channel data have been quantized, so when performing translation processing on the first channel data, the The obtained translation amount needs to be quantized in order to improve the processing accuracy.

In addition, for the terminal, in order to realize that the terminal uses the translation amount to process the first channel data to obtain the second channel data, the terminal performs downlink channel estimation/measurement according to the downlink signal (such as CSI-RS, SSB or PBCH DMRS, etc.) In the case of obtaining the first channel data, the terminal can directly obtain all elements in the first channel data, the modulus of all elements, the real part of all elements, the imaginary part of all elements, the amplitude of all elements, and the phase of all elements The minimum value of at least one of obtains the translation amount.

For the network device, in order to realize that the network device performs inverse processing on the second channel data by using the translation amount to obtain the first channel data, the terminal can report (or feed back) the second signal matrix to the network device while reporting the translation amount to network equipment. For example, the terminal reports the second channel data and translation amount through a CSI feedback (or reporting) process.

Method 2:

Since the element in the first channel data, the real part of the element in the first channel data, the imaginary part of the element in the first channel data, the magnitude of the element in the first channel data, the phase of the element in the first channel data At least one of them may have some situations greater than or equal to a preset threshold (these may be after the above-mentioned translation processing, may not be the above-mentioned translation processing), so the embodiment of the present application can combine the real part of the element and /or the imaginary part of the element, the amplitude of the element and/or the phase of the element are stretched to make it greater than or equal to a preset threshold, so as to improve the processing efficiency of the AI model when it is input to the AI model for processing.

Wherein, the preset threshold may be configured by the network device, pre-configured, stipulated by a protocol, etc., and there is no specific limitation on this. For example, the preset threshold can be 1.

For the terminal, for the elements in the first channel data, the real part of the elements in the first channel data, the imaginary part of the elements in the first channel data, the amplitude of the elements in the first channel data, the first channel data At least one of the phases of the elements within is divided by the stretch amount.

It can be understood that the following methods can exist for the terminal:

1) The terminal divides the elements in the first channel data by the scaling amount; where the scaling amount is used to perform scaling processing on the elements in the first channel data so that the value is less than a preset threshold;

2) The terminal divides the real part of the element in the first channel data by the stretching amount; wherein, the stretching amount is used to perform stretching processing on the real part of the element in the first channel data so that it is less than or equal to a preset threshold;

3) The terminal divides the imaginary part of the element in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the imaginary part of the element in the first channel data so that it is less than or equal to a preset threshold;

4) The terminal divides the real part and the imaginary part of the elements in the first channel data by the stretching amount; wherein, the stretching amount is used to perform stretching processing on the real part and the imaginary part of the elements in the first channel data so that it is less than or equal to a preset threshold;

5) The terminal divides the amplitude of the element in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the amplitude of the element in the first channel data so that it is less than or equal to a preset threshold;

6) The terminal divides the phase of the elements in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the phases of the elements in the first channel data so that it is less than or equal to a preset threshold;

7) The terminal divides the amplitude and phase of the elements in the first channel data by the scaling amount; where the scaling amount is used to perform scaling processing on the amplitude and phase of the elements in the first channel data so that it is less than or equal to a preset threshold;

etc.; there is no specific limitation thereon.

For the network device, the network device needs to analyze the elements in the second channel data, the real part of the elements in the second channel data, the imaginary part of the elements in the second channel data, the amplitude of the elements in the second channel data, At least one of the phases of the elements in the second channel data is multiplied by the scaling amount.

It can be understood that the following methods can exist for the terminal:

1) The network device multiplies the elements in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the elements in the first channel data so as to be less than or equal to a preset threshold;

2) The network device multiplies the real part of the element in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the real part of the element in the first channel data so that it is less than or equal to a preset threshold ;

3) The network device multiplies the imaginary part of the element in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the imaginary part of the element in the first channel data so that it is less than or equal to a preset threshold ;

4) The network device multiplies the real part and the imaginary part of the element in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the real part and the imaginary part of the element in the first channel data so that it is less than or equal to a preset threshold;

5) The network device multiplies the amplitude of the elements in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the amplitude of the elements in the first channel data so that it is less than or equal to a preset threshold;

6) The network device multiplies the phase of the elements in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the phases of the elements in the first channel data so that it is less than or equal to a preset threshold;

7) The network device multiplies the amplitude and phase of the elements in the first channel data by the scaling amount; wherein, the scaling amount is used to perform scaling processing on the amplitude and phase of the elements in the first channel data so that it is less than or equal to a preset set threshold;

etc.; there is no specific limitation thereon.

For the amount of scaling, the embodiment of this application may exist as follows:

1) The stretching amount can be the difference between M and m.

Wherein, the M can be used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the imaginary part of all the elements in the first channel data part, the amplitude of all elements in the first channel data, and the maximum value of at least one of the phases of all elements in the first channel data; the m can be used to represent all elements in the first channel data, the first channel Modulus of all elements in the data, real part of all elements in the first channel data, imaginary part of all elements in the first channel data, magnitude of all elements in the first channel data, all elements in the first channel data The minimum value of at least one of the phases of the elements.

For example, the terminal may divide the element by the difference between the maximum value and the minimum value of all elements in the first channel rectangle, so that it is less than or equal to a preset threshold. For the network device, the network device needs to multiply the elements of the second channel data by the difference between the maximum value and the minimum value of all elements in the first channel rectangle, so as to ensure that the first channel data is restored.

Similarly, the terminal may divide the element by the difference between the maximum value and the minimum value of the modulus of all elements in the first channel rectangle, so that it is less than or equal to a preset threshold. For the network equipment, the network equipment needs to multiply the elements of the corresponding second channel data by the difference between the maximum value and the minimum value of the modulus of all elements in the first channel rectangle, so as to ensure that the first channel data.

Similarly, the terminal may divide the real part of the element by the difference between the maximum value and the minimum value of the real parts of all elements in the first channel rectangle, so that it is less than or equal to a preset threshold. For the network device, the network device needs to multiply the real part of the element of the corresponding second channel data by the difference between the maximum value and the minimum value of the real part of all elements in the first channel rectangle to ensure Recover the first channel data.

Similarly, the terminal may divide the imaginary part of the element by the difference between the maximum value and the minimum value of the imaginary parts of all elements in the first channel rectangle, so that it is less than or equal to a preset threshold. For the network device, the network device needs to multiply the imaginary part of the element of the corresponding second channel data by the difference between the maximum value and the minimum value of the imaginary part of all elements in the first channel rectangle to ensure Recover the first channel data.

Similarly, the terminal may divide the amplitude of the element by the difference between the maximum value and the minimum value among the amplitudes of all elements in the first channel rectangle, so that it is less than or equal to a preset threshold. For the network device, the network device needs to multiply the amplitude of the elements of the second channel data by the difference between the maximum value and the minimum value of the amplitudes of all elements in the first channel rectangle to ensure that the first channel data.

Similarly, the terminal may divide the phase of the element by the difference between the maximum value and the minimum value of the phases of all elements in the first channel rectangle, so that it is less than or equal to a preset threshold. For the network device, the network device needs to multiply the phase of the elements of the second channel data by the difference between the maximum value and the minimum value of the phases of all elements in the first channel rectangle to ensure that the first channel data.

2) The scaling amount can be a quantized value of the difference between M and m.

It should be noted that, based on the above description, since the first channel data obtained by the terminal may be quantized before being input into the AI model, the elements in the first channel data, the real parts of the elements in the first channel data and/or Or the imaginary part of the element in the first channel data, the amplitude of the element in the first channel data and/or the phase of the element in the first channel data have been quantized, so the The obtained translation amount needs to be quantized in order to improve the processing accuracy.

3) The stretching amount can be one of the norm of the first channel data, the average value of the power of all elements in the first channel data, and the average value of the square of the modulus of all elements in the first channel data.

For example, the terminal may divide the element by the norm of the first channel data, so that the value thereof is smaller than the preset threshold. For the network device, the network device needs to multiply the elements of the second channel matrix by the norm of the first channel data to ensure that the first channel data is recovered.

Similarly, the terminal may divide the element by the average power of all elements in the first channel data, so that the value is smaller than the preset threshold. For the network device, the network device needs to multiply the elements of the second channel data by the average power of all elements in the first channel data, so as to ensure that the first channel data is recovered.

Similarly, the terminal may divide the element by the average value of the squares of the moduli of all elements in the first channel data, so that the amplitude thereof is smaller than the preset threshold. For the network device, the network device needs to multiply the elements of the second channel data by the average value of the squares of the moduli of all elements in the first channel data, so as to ensure that the first channel data is recovered.

4) The scale amount is one of the reference signal received power RSRP, the reference signal received quality RSRQ, and the reference signal strength indicator RSSI.

It should be noted that one of RSRP, RSRQ and RSSI may be obtained by the terminal through downlink channel estimation/measurement from a downlink reference signal (such as CSI-RS).

In addition, for the terminal, in order to realize that the terminal processes the first channel data by using the scaling amount to obtain the second channel data, the terminal performs downlink channel estimation/measurement according to the downlink reference signal (such as CSI-RS) to obtain the first channel In the case of data, the terminal can directly obtain the maximum value and minimum value of at least one of all elements in the first channel data, the real part of all elements, the imaginary part of all elements, the amplitude of all elements, and the phase The stretching amount is obtained from the value, or from the norm of the first channel data, the average value of the power of all elements in the first channel data, and the average value of the square of the modulus of all elements in the first channel data Once the scaling amount is acquired, or the scaling amount is acquired from one of RSRP, RSRQ, and RSSI obtained by performing downlink channel estimation/measurement on the downlink reference signal.

For the network device, in order to achieve the reverse processing of the second channel data by the network device using the scaling amount to obtain the first channel data, the terminal can report (or feed back) the second signal matrix to the network device and at the same time report the translation amount to network equipment. For example, the terminal reports the second channel data and translation amount through a CSI feedback (or reporting) process.

Method 3:

Combining the above "mode 1" and "mode 2", it can be seen that due to the elements in the first channel data, the real part of the elements in the first channel data, the imaginary part of the elements in the first channel data, the At least one of the amplitude of the element and the phase of the element in the first channel data may be less than or equal to a preset value (such as zero), so the embodiment of the present application can first set the real part of the element and/or The imaginary part of the element, the amplitude of the element and/or the phase of the element are shifted to make it greater than or equal to a preset value, and then stretched to make it smaller than or equal to a preset threshold, which is beneficial to the input to When the AI model is processed, ensuring the successful processing of the AI model is also conducive to improving the processing efficiency of the AI model.

For the terminal, for the elements in the first channel data, the real part of the elements in the first channel data, the imaginary part of the elements in the first channel data, the amplitude of the elements in the first channel data, the first channel data At least one of the phases of the elements within minus the translation amount, divided by the stretch amount.

It can be understood that the following methods can exist for the terminal:

1) The terminal subtracts the translation amount from the elements in the first channel data, and then divides by the scaling amount; wherein, the translation amount is used to perform translation processing on the elements in the first channel data so that it is greater than or equal to a preset value; The scaling amount is used to perform scaling processing on elements in the first channel data so as to be less than or equal to a preset threshold;

2) The terminal subtracts the translation amount from the real part of the element in the first channel data, and then divides it by the stretching amount; wherein, the translation amount is used to perform translation processing on the real part of the element in the first channel data so that it is greater than or Equal to a preset value; the scaling amount is used to scale the real part of the elements in the first channel data so that it is less than or equal to a preset threshold;

3) The terminal subtracts the translation amount from the imaginary part of the elements in the first channel data, and then divides it by the scaling amount; wherein, the translation amount is used to translate at least one of the imaginary parts of the elements in the first channel data Processing so that it is greater than or equal to a preset value; the scaling amount is used to perform scaling processing on the imaginary part of the element in the first channel data so that it is less than or equal to a preset threshold;

4) The terminal subtracts the translation amount from the real part and the imaginary part of the elements in the first channel data, and then divides by the stretching amount; wherein, the translation amount is used to carry out the real part and the imaginary part of the elements in the first channel data translation processing so that it is greater than or equal to a preset value; the scaling amount is used to perform scaling processing on the real part and the imaginary part of the elements in the first channel data so that it is less than or equal to a preset threshold;

5) The terminal subtracts the translation amount from the amplitude of the elements in the first channel data, and then divides it by the stretching amount; wherein, the translation amount is used to perform translation processing on the amplitude of the elements in the first channel data so that it is greater than or equal to one A preset value; the scaling amount is used to scale and scale the amplitude of elements in the first channel data so as to be less than or equal to a preset threshold;

6) The terminal subtracts the translation amount from the phase of the elements in the first channel data, and then divides by the scaling amount; wherein, the translation amount is used to perform translation processing on at least one of the phases of the elements in the first channel data to Make it greater than or equal to a preset value; the stretching amount is used to stretch the phase of the elements in the first channel data so that it is less than or equal to a preset threshold;

7) The terminal subtracts the translation amount from the amplitude and phase of the elements in the first channel data, and then divides by the scaling amount; wherein, the translation amount is used to perform translation processing on the amplitude and phase of the elements in the first channel data so that greater than or equal to a preset value; the scaling amount is used to scale and scale the amplitude and phase of elements in the first channel data so as to be less than or equal to a preset threshold;

etc.; there is no specific limitation thereon.

For the network device, for the elements in the second channel data, the real part of the elements in the second channel data, the imaginary part of the elements in the second channel data, the amplitude of the elements in the second channel data, the second channel At least one of the phases of the elements within the data is multiplied by the stretch amount, plus the translation amount.

It can be understood that the following modes may exist for network devices:

1) The network device multiplies the elements in the second channel data by the scaling amount, and then adds the translation amount; wherein, the scaling amount is used to perform scaling processing on the elements in the first channel data so that it is less than or equal to a preset threshold ; The translation amount is used to perform translation processing on the elements in the first channel data so that it is greater than or equal to a preset value;

2) The network device multiplies the real part of the element in the second channel data by the stretching amount, and adds the translation amount; wherein, the stretching amount is used to perform stretching processing on the real part of the element in the first channel data so that it is less than or equal to a preset threshold; the shift amount is used to shift the real part of the elements in the first channel data so that it is greater than or equal to a preset value;

3) The network device multiplies the imaginary part of the element in the second channel data by the stretching amount, and adds the translation amount; wherein, the stretching amount is used to stretch the imaginary part of the element in the first channel data so that it is less than or equal to a preset threshold; the shift amount is used to shift at least one of the imaginary parts of the elements in the first channel data so that it is greater than or equal to a preset value;

4) The network device multiplies the real part and the imaginary part of the elements in the second channel data by the scaling amount, and adds the translation amount; wherein, the scaling amount is used to adjust the real part and the imaginary part of the elements in the first channel data Perform scaling processing so that it is less than or equal to a preset threshold; the translation amount is used to perform translation processing on the real part and the imaginary part of the elements in the first channel data so that it is greater than or equal to a preset value;

5) The network device multiplies the amplitude of the elements in the second channel data by the scaling amount, and adds the translation amount; wherein, the scaling amount is used to scale the amplitude of the elements in the first channel data so that it is less than or equal to A preset threshold; the shift amount is used to shift the amplitude of the element in the first channel data so that it is greater than or equal to a preset value;

6) The network device multiplies the phase of the elements in the second channel data by the stretching amount, and then adds the translation amount; wherein, the stretching amount is used to stretch the phases of the elements in the first channel data so that it is less than or equal to A preset threshold; the shift amount is used to shift at least one of the phases of the elements in the first channel data so that it is greater than or equal to a preset value;

7) The network device multiplies the amplitude and phase of the elements in the second channel data by the scaling amount, and then adds the translation amount; wherein, the scaling amount is used to perform scaling processing on the amplitude and phase of the elements in the first channel data to Make it less than or equal to a preset threshold; the shift amount is used to shift the amplitude and phase of the elements in the first channel data so that it is greater than or equal to a preset value;

etc.; there is no specific limitation thereon.

Wherein, the description about the "translation amount" is consistent with that in the above-mentioned "method 1" and will not be repeated here; the description about the "stretching amount" is consistent with that in the above-mentioned "method 2" and will not be repeated here.

Method 4:

Combining the above "Mode 1", "Mode 2" and "Mode 3", it can be seen that due to the elements in the first channel data, the real part of the elements in the first channel data, the imaginary part of the elements in the first channel data, the At least one of the amplitude of the element in the first channel data and the phase of the element in the first channel data may be less than or equal to a preset value (such as zero), so the embodiment of the present application can first set the element’s The real part and/or the imaginary part of the element, the amplitude of the element and/or the phase of the element are shifted to make it greater than or equal to a preset value, and then stretched to make it smaller than or equal to a preset threshold, so that both It is conducive to ensuring the successful processing of the AI model when it is input to the AI model for processing, and is also conducive to improving the processing efficiency of the AI model.

The above processing is to perform overall processing on the first channel data, such as translation and/or scaling. There is another manner (namely "mode 4") that may be to partially process the data of the first channel. In this way, only a part of data can be affected, and no corresponding counter-processing is required on the network device side.

Part of the processing may include puncturing, that is, discarding data whose modulus, real part, imaginary part, amplitude or phase is less than or equal to a preset value as a low bit (least significant bit, LSB). In this way, smaller data can be set to zero or close to zero, reducing the amount of unimportant information.

Part of the processing may include saturation, that is, data whose modulus, real part, imaginary part, amplitude or phase is greater than or equal to a preset threshold is discarded as a most significant bit (MSB). In this way, larger data can be reduced to avoid excessive fluctuations in data. For the terminal, for the elements in the first channel data, the real part of the elements in the first channel data, the imaginary part of the elements in the first channel data, the amplitude of the elements in the first channel data, the first channel data At least one of the phases of the elements within is truncated and/or saturated.

It can be understood that the following methods can exist for the terminal:

1) The terminal truncates and/or saturates elements in the first channel data;

2) The terminal truncates and/or saturates the real part of the elements in the first channel data;

3) The terminal truncates and/or saturates the imaginary part of the elements in the first channel data;

4) The terminal truncates and/or saturates the real part and the imaginary part of the elements in the first channel data;

5) The terminal truncates and/or saturates the amplitude of elements in the first channel data;

6) The terminal truncates and/or saturates the phases of the elements in the first channel data;

7) The terminal truncates and/or saturates the amplitude and phase of elements in the first channel data;

etc.; there is no specific limitation thereon.

The specific implementation manner can be known in combination with the manners in the above "mode 1", "mode 2" and "mode 3", and will not be repeated here.

Way five:

The above processing is to perform overall processing on the first channel data, such as translation and/or scaling. There is another manner (namely "mode 5") that may be to partially process the data of the first channel. This can only affect a part of the data.

Part of the processing can include data deletion, that is, data whose modulus, real part, imaginary part, amplitude or phase is less than or equal to a preset value is deleted (not input to the AI model for compression), which is equivalent to reducing the input to the AI model The size of the data being compressed. In this way, small data can not be input to the AI model for compression, reducing the amount of unimportant information. A typical example is that there may be unimportant transmission paths in the channel matrix. These transmission paths can be deleted before being input to the AI model for compression.

For the terminal, for the elements in the first channel data, the real part of the elements in the first channel data, the imaginary part of the elements in the first channel data, the amplitude of the elements in the first channel data, the first channel data At least one of the phases of the elements within is deleted.

It can be understood that the following methods can exist for the terminal:

1) The terminal deletes elements (according to their modulus) in the first channel data;

2) The terminal deletes the real part (according to the size of the real part) of the elements in the first channel data;

3) The terminal deletes the imaginary part (according to the size of the imaginary part) of the element in the first channel data;

4) The terminal deletes the real part and the imaginary part (according to the size of the real part and the imaginary part) of the elements in the first channel data;

5) The terminal deletes the amplitude (according to the amplitude) of the elements in the first channel data;

6) The terminal deletes the phase (according to the phase size) of the elements in the first channel data;

7) The terminal deletes the amplitude and phase (according to the amplitude and phase) of the elements in the first channel data;

etc.; there is no specific limitation thereon.

Since the terminal has created data, the terminal needs to inform the network device of the location of the deleted data (element location). That is to say, the terminal feeds back (or reports) the location of the deleted data (element location).

For the network device, for the elements in the second channel data, the real part of the elements in the second channel data, the imaginary part of the elements in the second channel data, the amplitude of the elements in the second channel data, the second channel At least one of the phases of the elements within the data is restored.

It can be understood that the following modes may exist for network devices:

1) The network device restores the elements (according to their modulus) in the second channel data;

2) The network device restores the real part (according to the size of the real part) of the elements in the second channel data;

3) The network device restores the imaginary part (according to the size of the imaginary part) of the element in the second channel data;

4) The network device restores the real part and the imaginary part (according to the size of the real part and the imaginary part) of the elements in the second channel data;

5) The network device restores the amplitude (according to its amplitude) of the elements in the second channel data;

6) The network device restores the phase (according to its phase size) of the elements in the second channel data;

7) The network device restores the amplitude and phase of the elements in the second channel data (according to their amplitude and phase size);

etc.; there is no specific limitation thereon.

The network device restores the position of the deleted data according to the position (element position) of the deleted data fed back (or reported) by the terminal.

The specific implementation manner can be known by combining the manners in the above "mode 1", "mode 2", "mode 3" and "mode 4", and will not be repeated here.

The foregoing mainly introduces the solutions of the embodiments of the present application from the perspective of the method side. It can be understood that, in order to realize the above-mentioned functions, the terminal or network device includes corresponding hardware structures and/or software modules for performing various functions. Those skilled in the art should easily realize that the present application can be implemented in the form of hardware or a combination of hardware and computer software in combination with the units and algorithm steps of each example described in the embodiments disclosed herein. Whether a certain function is executed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may implement the described functionality using different methods for each particular application, but such implementation should not be considered as exceeding the scope of the present application.

In this embodiment of the present application, the terminal or network device may be divided into functional units according to the foregoing method examples. For example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The above-mentioned integrated units can be implemented not only in the form of hardware, but also in the form of software program modules. It should be noted that the division of units in the embodiment of the present application is schematic, and is only a logical function division, and there may be another division manner in actual implementation.

In the case of using integrated units, FIG. 3 is a block diagram of functional units of a channel data processing device according to an embodiment of the present application. The channel data processing apparatus 300 includes: a processing unit 302 and a communication unit 303 . The processing unit 302 is used to control and manage the actions of the channel data processing device 300 . For example, the processing unit 302 is configured to support the channel data processing apparatus 300 to execute the steps executed by the terminal in FIG. 2 and other processes used in the technical solutions described in this application. The communication unit 303 is used to support communication between the channel data processing apparatus 300 and other devices in the wireless communication system. The channel data processing device 300 may further include a storage unit 301 for storing computer programs or instructions executed by the channel data processing device 300 .

It should be noted that the channel data processing device 300 may be a chip or a chip module.

Wherein, the processing unit 302 may be a processor or a controller, such as a central processing unit (central processing unit, CPU), a general purpose processor, a digital signal processor (digital signal processor, DSP), an application-specific integrated circuit (application-specific integrated circuit, ASIC), field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various illustrative logical blocks, modules and circuits described in connection with the present disclosure. The processing unit 302 may also be a combination that implements computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication unit 303 may be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit 301 may be a memory. When the processing unit 302 is a processor, the communication unit 303 is a communication interface, and the storage unit 301 is a memory, the channel data processing apparatus 300 involved in this embodiment of the present application may be the terminal shown in FIG. 5 .

During specific implementation, the processing unit 302 is configured to perform any step performed by the terminal in the above method embodiments, and when performing data transmission such as sending, the communication unit 303 may be called to complete corresponding operations. Detailed description will be given below.

The processing unit 302 is configured to: acquire first channel data; process the first channel data to obtain second channel data.

It can be seen that in the process of directly feeding back (or reporting) channel data to the CSI feedback architecture through the AI model, in order to adapt the AI model used for image processing, it is necessary to avoid the out-of-range number of elements in the input channel data of the AI model. As a result, the AI model cannot process the channel data or the AI model processing efficiency is low. The channel data processing device 300 in the embodiment of the present application needs to process the channel data to be fed back (or reported), that is, the first channel data, so that the processed The channel data (that is, the second channel data) satisfies the requirements of the AI model adapted to image processing, which is beneficial to ensure that the AI model can successfully process the input processed channel data or achieve higher processing efficiency.

It should be noted that, for the specific implementation of each operation in the embodiment shown in FIG. 3 , refer to the description in the method embodiment shown in FIG. 2 above, and details are not repeated here.

In some possible implementations, in terms of processing the first channel data, the processing unit 302 is configured to:

The translation amount is subtracted from at least one of the element in the first channel data, the real part of the element in the first channel data, and the imaginary part of the element in the first channel data.

Dividing at least one of the elements in the first channel data, the real parts of the elements in the first channel data, and the imaginary parts of the elements in the first channel data by the scaling amount.

In some possible implementations, when processing the first channel data, the processing unit 302 is configured to:

Subtracting the translation amount from at least one of the elements in the first channel data, the real part of the elements in the first channel data, and the imaginary parts of the elements in the first channel data, and then dividing by the stretching amount.

In some possible implementations, the translation is m;

m is used to represent at least one of all elements in the first channel data, moduli of all elements in the first channel data, real parts of all elements in the first channel data, and imaginary parts of all elements in the first channel data one of the minimum values.

In some possible implementations, the translation amount is a quantized value of m;

m is used to represent at least all elements in the first channel data, moduli of all elements in the first channel data, real parts of all elements in the first channel data, and all imaginary parts of elements in the first channel data one of the minimum values.

In some possible implementations, the amount of scaling is the difference between M and m;

M is used to represent at least one of all elements in the first channel data, moduli of all elements in the first channel data, real parts of all elements in the first channel data, and imaginary parts of all elements in the first channel data one of the maximum value;

In some possible implementations, the amount of scaling is a quantized value of the difference between M and m;

M is used to represent at least one of all elements in the first channel data, moduli of all elements in the first channel data, real parts of all elements in the first channel data, and imaginary parts of all elements in the first channel data One of the maximum values.

In some possible implementations, the scaling amount is one of the norm of the first channel data, the average value of the power of all elements in the first channel data, and the average value of the squares of the amplitudes of all elements in the first channel data one.

In some possible implementations, the scaling amount is one of Reference Signal Received Power RSRP, Reference Signal Received Quality RSRQ, and Reference Signal Strength Indicator RSSI.

In some possible implementations, the processing unit 302 is further configured to: report a translation amount or a scaling amount.

In some possible implementations, in terms of reporting the amount of translation or scaling, the processing unit 302 is configured to:

Report the translation amount or scaling amount through the channel state information CSI feedback process.

In the case of using integrated units, FIG. 4 is a block diagram of functional units of a channel data inverse processing device according to an embodiment of the present application. The channel data reverse processing apparatus 400 includes: a processing unit 402 and a communication unit 403 . The processing unit 402 is used to control and manage the actions of the channel data inverse processing device 400, for example, the processing unit 402 is used to support the channel data inverse processing device 400 to execute the steps performed by the network equipment in FIG. Other processes of the technical plan. The communication unit 403 is used to support communication between the channel data reverse processing apparatus 400 and other devices in the wireless communication system. The channel data inverse processing device 400 may further include a storage unit 401 for storing computer programs or instructions executed by the channel data inverse processing device 400 .

It should be noted that the channel data reverse processing device 400 may be a chip or a chip module.

Wherein, the processing unit 402 may be a processor or a controller, such as a CPU, DSP, ASIC, FPGA or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute the various illustrative logical blocks, modules and circuits described in connection with the present disclosure. The processing unit 402 may also be a combination that implements computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication unit 403 may be a communication interface, a transceiver, a transceiver circuit, etc., and the storage unit 401 may be a memory. When the processing unit 402 is a processor, the communication unit 403 is a communication interface, and the storage unit 401 is a memory, the channel data reverse processing apparatus 400 involved in this embodiment of the present application may be the network device shown in FIG. 6 .

During specific implementation, the processing unit 402 is configured to perform any step performed by the network device in the above method embodiments, and when performing data transmission such as sending, it may optionally call the communication unit 403 to complete corresponding operations. Detailed description will be given below.

The processing unit 402 is configured to: acquire the second channel data; perform inverse processing on the second channel data to obtain the first channel data.

It can be seen that in the process of directly feeding back channel data to the CSI feedback architecture through the AI model, in order to adapt the AI model used for image processing, the terminal needs to process the fed back (or reported) channel data before performing feedback (or report), therefore, when the channel data inverse processing device 400 obtains the processed channel data (that is, the second channel data), the channel data inverse processing device 400 needs to perform inverse processing on the processed channel data to obtain the first channel data , so that the channel data inverse processing device 400 performs related operations through the first channel data, for example, the network device calculates the CQI through the first channel data, calculates the corresponding SINR and the corresponding MCS through the first channel data, so as to schedule the terminal through the MCS, etc. .

It should be noted that, for the specific implementation of each operation in the embodiment shown in FIG. 4 , refer to the description in the method embodiment shown in FIG. 3 above, and details are not repeated here.

In some possible implementations, in terms of performing inverse processing on the second channel data, the processing unit 402 is configured to:

A shift amount is added to at least one of the elements in the second channel data, the real parts of the elements in the second channel data, and the imaginary parts of the elements in the second channel data.

Multiplying at least one of the elements in the second channel data, the real parts of the elements in the second channel data, and the imaginary parts of the elements in the second channel data by the scaling amount.

At least one of the element in the second channel data, the real part of the element in the second channel data, and the imaginary part of the element in the second channel data is multiplied by a scaling amount, and then a translation amount is added.

In some possible implementations, the translation is m;

m is used to represent at least one of the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, and the imaginary part of the elements in the first channel data min.

A quantized value shifted by m in some possible implementations;

M is used to represent at least one of the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, and the imaginary part of the elements in the first channel data maximum value.

m is used to represent the minimum value of at least one of the elements in the first channel data, the real part of the elements in the first channel data, and the imaginary parts of the elements in the first channel data.

m is used to represent at least one of the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, and the imaginary parts of the elements in the first channel data min.

In some possible implementations, the scaling amount is one of the norm of the first channel data, the average power of elements in the first channel data, and the average squared magnitude of elements in the first channel data.

In some possible implementations, the translation amount is reported.

In some possible implementations, translations are reported by:

The translation amount is reported through the channel state information (CSI) feedback process.

In some possible implementations, the scaling amount is reported.

In some possible implementations, the scaling amount is reported, including:

The scaling amount is reported through the CSI feedback process.

Referring to FIG. 5 , FIG. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application. Wherein, the terminal 500 includes a processor 510 , a memory 520 and a communication bus for connecting the processor 510 and the memory 520 .

Memory 520 includes, but is not limited to, random access memory (random access memory, RAM), read-only memory (read-only memory, ROM), erasable programmable read-only memory (erasable programmable read-only memory, EPROM) or A portable read-only memory (compact disc read-only memory, CD-ROM), the memory 520 is used to store program codes executed by the terminal 500 and transmitted data.

Terminal 500 may also include a communication interface for receiving and sending data.

The processor 510 may be one or more CPUs. In the case where the processor 510 is one CPU, the CPU may be a single-core CPU or a multi-core CPU.

The processor 510 in the terminal 500 is configured to execute the computer program or instruction 521 stored in the memory 520 to realize the following steps: acquire the first channel data; process the first channel data to obtain the second channel data.

It can be seen that in the process of directly feeding back (or reporting) channel data to the CSI feedback architecture through the AI model, in order to adapt the AI model used for image processing, it is necessary to avoid the out-of-range number of elements in the input channel data of the AI model. As a result, the AI model cannot process the channel data or the AI model processing efficiency is low. The terminal 500 in the embodiment of the present application needs to process the channel data to be fed back (or reported) (that is, the first channel data), so that the processed channel data ( That is, the second channel data) meet the requirements of the AI model adapted to image processing, which is beneficial to ensure that the AI model can successfully process the input processed channel data or achieve higher processing efficiency. It should be noted that the specific implementation of each operation can use the corresponding description of the method embodiment shown in FIG. 2 above, and the terminal 500 can be used to execute the method on the terminal side of the above method embodiment of the present application, which will not be described in detail here.

In some possible implementations, in terms of processing the first channel data, the processor 510 is configured to execute a computer program or an instruction 521 stored in the memory 520 to implement the following steps:

In some possible implementations, when processing the first channel data, the processor 510 is configured to execute the computer program or instruction 521 stored in the memory 520 to implement the following steps:

In some possible implementations, the translation is m;

In some possible implementations, the processor 510 is further configured to execute a computer program or an instruction 521 stored in the memory 520 to implement the following steps: report the translation amount or the scaling amount.

In some possible implementations, in terms of reporting the amount of translation or scaling, the processor 510 is configured to execute a computer program or instruction 521 stored in the memory 520 to implement the following steps:

Referring to FIG. 6, FIG. 6 is a schematic structural diagram of a network device according to an embodiment of the present application. Wherein, the network device 600 includes a processor 610 , a memory 620 and a communication bus for connecting the processor 610 and the memory 620 .

The memory 620 includes but not limited to RAM, ROM, EPROM or CD-ROM, and the memory 620 is used to store relevant instructions and data.

Network device 600 may also include a communication interface for receiving and sending data.

The processor 610 may be one or more CPUs. In the case where the processor 610 is one CPU, the CPU may be a single-core CPU or a multi-core CPU.

The processor 610 in the network device 600 is configured to execute the computer program or instruction 621 stored in the memory 620 to implement the following steps: acquire the second channel data; perform inverse processing on the second channel data to obtain the first channel data.

It can be seen that in the process of directly feeding back channel data to the CSI feedback architecture through the AI model, in order to adapt the AI model used for image processing, the terminal needs to process the fed back (or reported) channel data before performing feedback (or report), so when the network device 600 obtains the processed channel data (that is, the second channel data), the network device 600 needs to inversely process the processed channel data to obtain the first channel data, so that the network device 600 Perform related operations through the first channel data, for example, the network device 600 calculates a CQI through the first channel data, calculates a corresponding SINR and a corresponding MCS through the first channel data so as to schedule terminals through the MCS, and the like.

It should be noted that the specific implementation of each operation can use the corresponding description of the method embodiment shown in FIG. 2 above, and the network device 600 can be used to execute the method on the network device side of the above method embodiment of the present application, which will not be detailed here. repeat.

In some possible implementations, in terms of reverse processing the second channel data, the processor 610 is configured to execute a computer program or instructions 621 stored in the memory 620 to implement the following steps:

At least one of the element in the second channel data, the real part of the element in the second channel data, and the imaginary part of the element in the second channel data is multiplied by the scaling amount, and then the translation amount is added.

In some possible implementations, the translation is m;

A quantized value shifted by m in some possible implementations;

In some possible implementations, the translation amount is reported.

In some possible implementations, translations are reported by:

In some possible implementations, the scaling amount is reported.

In some possible implementations, the scaling amount is reported, including:

The scaling amount is reported through the CSI feedback process.

An embodiment of the present application also provides a chip, including a processor, a memory, and a computer program or instruction stored on the memory, wherein the processor executes the computer program or instruction to implement the steps described in the above method embodiments.

The embodiment of the present application also provides a chip module, including a transceiver component and a chip. The chip includes a processor, a memory, and a computer program or instruction stored on the memory, wherein the processor executes the computer program or instruction to The steps described in the above method embodiments are implemented.

The embodiment of the present application also provides a computer-readable storage medium, on which a computer program or instruction is stored, wherein, when the computer program or instruction is executed by a processor, the steps described in the foregoing method embodiments are implemented.

An embodiment of the present application further provides a computer program product, including a computer program or an instruction, wherein, when the computer program or instruction is executed by a processor, the steps described in the foregoing method embodiments are implemented. The computer program product may be a software installation package.

It should be noted that, for the above-mentioned embodiments, for the sake of simple description, they are expressed as a series of action combinations. Those skilled in the art should know that the present application is not limited by the sequence of actions described, because some steps in the embodiments of the present application may be performed in other orders or simultaneously. In addition, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions, steps, modules or units involved are not necessarily required by the embodiments of the present application.

In the above-mentioned embodiments, the embodiments of the present application have different emphases in the description of each embodiment, and for the parts not described in detail in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art should know that the methods, steps or functions of related modules/units described in the embodiments of the present application may be realized in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it may be implemented in whole or in part in the form of a computer program product, or may be implemented in a manner in which a processor executes computer program instructions. Wherein, the computer program product includes at least one computer program instruction, and the computer program instruction can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, mobile hard disk, CD-ROM (CD-ROM) or any other form of storage medium known in the art. The computer program instructions may be stored in, or transmitted from, one computer-readable storage medium to another computer-readable storage medium. For example, the computer program instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium, or a semiconductor medium (such as an SSD).

Each module/unit contained in each device or product described in the above embodiments may be a software module/unit, may be a hardware module/unit, or may be a part of a software module/unit while the other part is a hardware module/unit. For example, for each device or product that is applied to or integrated in a chip, each module/unit included in it may be implemented by hardware such as a circuit; or, a part of the modules/units included in it may be implemented by a software program. The software program runs on the processor integrated in the chip, and some modules/units of the other part (if any) can be realized by hardware such as circuits. The same can be understood for each device or product applied to or integrated in a chip module, or each device or product applied to or integrated in a terminal.

The specific implementation manners described above further describe the purpose, technical solutions and beneficial effects of the embodiments of the present application in detail. The scope of protection of the embodiments of the present application is limited. All modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application shall be included in the protection scope of the embodiments of the present application.

Claims

A channel data processing method, characterized in that, comprising:

Obtain the first channel data;

Process the first channel data to obtain second channel data.
The method according to claim 1, wherein said processing said first channel data comprises:

Subtracting a translation amount from at least one of an element in the first channel data, a real part of an element in the first channel data, and an imaginary part of an element in the first channel data.
The method according to claim 1, wherein said processing said first channel data comprises:

Dividing at least one of the elements in the first channel data, the real parts of the elements in the first channel data, and the imaginary parts of the elements in the first channel data by a scaling amount.
The method according to claim 1, wherein said processing said first channel data comprises:

Subtracting the translation amount from at least one of the elements in the first channel data, the real part of the elements in the first channel data, and the imaginary parts of the elements in the first channel data, and then dividing by the scaling quantity.
The method according to claim 2 or 4, wherein the translation amount is m;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of the imaginary parts of all elements in .
The method according to claim 2 or 4, wherein the translation amount is a quantized value of m;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of all imaginary parts of the elements in .
The method according to claim 3 or 4, wherein the stretching amount is the difference between M and m;

The M is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The maximum value of at least one of the imaginary parts of all elements in ;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of the imaginary parts of all elements in .
The method according to claim 3 or 4, wherein the stretching amount is a quantized value of the difference between M and m;

The M is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The maximum value of at least one of the imaginary parts of all elements in ;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of the imaginary parts of all elements in .
The method according to claim 3 or 4, wherein the scaling amount is the norm of the first channel data, the average power of all elements in the first channel data, the first One of the averages of the squared magnitudes of all elements within the channel data.
The method according to claim 3 or 4, wherein the scaling amount is one of Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Reference Signal Strength Indicator (RSSI).
The method according to claim 2 or 3, further comprising:

Report the translation amount or the stretching amount.
The method according to claim 11, wherein the reporting of the translation amount or the expansion and contraction amount comprises:

The translation amount or the scaling amount is reported through a channel state information (CSI) feedback process.
A channel data deprocessing method, characterized in that, comprising:

Obtain second channel data;

Reverse processing is performed on the second channel data to obtain the first channel data.
The method according to claim 13, wherein said performing reverse processing on said second channel data comprises:

Adding a translation amount to at least one of the elements in the second channel data, the real parts of the elements in the second channel data, and the imaginary parts of the elements in the second channel data.
The method according to claim 13, wherein said performing reverse processing on said second channel data comprises:

Multiplying at least one of the elements in the second channel data, the real parts of the elements in the second channel data, and the imaginary parts of the elements in the second channel data by a scaling amount.
The method according to claim 13, wherein said performing reverse processing on said second channel data comprises:

Multiplying at least one of the elements in the second channel data, the real part of the elements in the second channel data, and the imaginary parts of the elements in the second channel data by the scaling amount, plus translation quantity.
The method according to claim 14 or 16, wherein the translation amount is m;

The m is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the The minimum value of at least one of the imaginary parts of the elements.
The method according to claim 14 or 16, wherein the translation amount is a quantized value of m;

The m is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the The minimum value of at least one of the imaginary parts of the elements.
The method according to claim 15 or 16, wherein the stretching amount is the difference between M and m;

The M is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the the maximum value of at least one of the imaginary parts of the elements;

The m is used to represent the minimum value of at least one of the elements in the first channel data, the real parts of the elements in the first channel data, and the imaginary parts of the elements in the first channel data.
The method according to claim 15 or 16, wherein the stretching amount is a quantized value of the difference between M and m;

The M is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the the maximum value of at least one of the imaginary parts of the elements;

The m is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the The minimum value of at least one of the imaginary parts of the elements.
The method according to claim 15 or 16, wherein the stretching amount is the norm of the first channel data, the average power of elements in the first channel data, the power of the first channel data One of the averages of the squared magnitudes of the elements within.
The method according to claim 15 or 16, wherein the scaling amount is one of Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Reference Signal Strength Indicator (RSSI).
The method according to any one of claims 14, 16-18, characterized in that the translation amount is obtained by reporting.
The method according to claim 23, wherein the translation amount is obtained by reporting, including:

The translation amount is reported through the channel state information (CSI) feedback process.
The method according to any one of claims 15, 16, 19-22, characterized in that the expansion and contraction amount is obtained by reporting.
The method according to claim 25, wherein the amount of expansion and contraction is obtained by reporting, including:

The scaling amount is reported through the CSI feedback process.
A channel data processing device, characterized in that the device includes a processing unit, and the processing unit is used for:

Obtain the first channel data;

Process the first channel data to obtain second channel data.
The device according to claim 27, wherein, in terms of processing the first channel data, the processing unit is configured to:

Subtracting a translation amount from at least one of an element in the first channel data, a real part of an element in the first channel data, and an imaginary part of an element in the first channel data.
The device according to claim 27, wherein, in terms of processing the first channel data, the processing unit is configured to:

Dividing at least one of the elements in the first channel data, the real parts of the elements in the first channel data, and the imaginary parts of the elements in the first channel data by a scaling amount.
The device according to claim 27, wherein, in terms of processing the first channel data, the processing unit is configured to:

Subtracting the translation amount from at least one of the elements in the first channel data, the real part of the elements in the first channel data, and the imaginary parts of the elements in the first channel data, and then dividing by the scaling quantity.
The device according to claim 28 or 30, wherein the translation amount is m;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of the imaginary parts of all elements in .
The device according to claim 28 or 30, wherein the translation amount is a quantized value of m;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of all imaginary parts of the elements in .
The device according to claim 29 or 30, wherein the stretching amount is the difference between M and m;

The M is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The maximum value of at least one of the imaginary parts of all elements in ;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of the imaginary parts of all elements in .
The device according to claim 29 or 30, wherein the stretching amount is a quantized value of the difference between M and m;

The M is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The maximum value of at least one of the imaginary parts of all elements in ;

The m is used to represent all the elements in the first channel data, the modulus of all the elements in the first channel data, the real part of all the elements in the first channel data, the The minimum value of at least one of the imaginary parts of all elements in .
The device according to claim 29 or 30, wherein the scaling amount is the norm of the first channel data, the average power of all elements in the first channel data, the first One of the averages of the squared magnitudes of all elements within the channel data.
The device according to claim 29 or 30, wherein the scaling amount is one of Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Reference Signal Strength Indicator (RSSI).
The device according to claim 28 or 29, wherein the processing unit is also used for:

Report the translation amount or the stretching amount.
The device according to claim 37, wherein the reporting of the translation amount or the expansion and contraction amount includes:

The translation amount or the scaling amount is reported through a channel state information (CSI) feedback process.
A channel data inverse processing device, characterized in that the device includes a processing unit, the processing unit is used for:

Obtain second channel data;

Reverse processing is performed on the second channel data to obtain the first channel data.
The device according to claim 39, wherein, in terms of performing inverse processing on the second channel data, the processing unit is configured to:

Adding a translation amount to at least one of the elements in the second channel data, the real parts of the elements in the second channel data, and the imaginary parts of the elements in the second channel data.
The device according to claim 39, wherein, in terms of performing inverse processing on the second channel data, the processing unit is configured to:

Multiplying at least one of the elements in the second channel data, the real parts of the elements in the second channel data, and the imaginary parts of the elements in the second channel data by a scaling amount.
The device according to claim 39, wherein, in terms of performing inverse processing on the second channel data, the processing unit is configured to:

Multiplying at least one of the elements in the second channel data, the real part of the elements in the second channel data, and the imaginary parts of the elements in the second channel data by the scaling amount, plus translation quantity.
The device according to claim 40 or 42, wherein the translation amount is m;

The m is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the The minimum value of at least one of the imaginary parts of the elements.
The device according to claim 40 or 42, wherein the translation amount is a quantized value of m;

The m is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the The minimum value of at least one of the imaginary parts of the elements.
The device according to claim 41 or 42, wherein the stretching amount is the difference between M and m;

The M is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the the maximum value of at least one of the imaginary parts of the elements;

The m is used to represent the minimum value of at least one of the elements in the first channel data, the real parts of the elements in the first channel data, and the imaginary parts of the elements in the first channel data.
The device according to claim 41 or 42, wherein the stretching amount is a quantized value of the difference between M and m;

The M is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the the maximum value of at least one of the imaginary parts of the elements;

The m is used to represent the elements in the first channel data, the modulus of all elements in the first channel data, the real part of the elements in the first channel data, the The minimum value of at least one of the imaginary parts of the elements.
The device according to claim 41 or 42, wherein the stretching amount is the norm of the first channel data, the average power of elements in the first channel data, the power of the first channel data One of the averages of the squared magnitudes of the elements within.
The device according to claim 41 or 42, wherein the scaling amount is one of Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Reference Signal Strength Indicator (RSSI).
The device according to any one of claims 40, 42-44, wherein the translation amount is obtained by reporting.
The device according to claim 49, wherein the translation amount is obtained by reporting, including:

The translation amount is reported through the channel state information (CSI) feedback process.
The device according to any one of claims 41, 42, 45-48, wherein the stretching amount is obtained by reporting.
The device according to claim 51, wherein the expansion and contraction amount is obtained by reporting, including:

The scaling amount is reported through the CSI feedback process.
A terminal, comprising a processor, a memory, and a computer program or instruction stored on the memory, wherein the processor executes the computer program or instruction to implement any one of claims 1-12 method steps.
A network device, comprising a processor, a memory, and a computer program or instruction stored on the memory, wherein the processor executes the computer program or instruction to implement any one of claims 13-26 steps of the method described above.
A computer-readable storage medium, characterized in that computer programs or instructions are stored on the computer-readable storage medium, and when the computer programs or instructions are executed by a processor, any one of claims 1-26 is implemented. method steps.
A chip, comprising a processor, wherein the processor executes the steps of the method according to any one of claims 1-26.