CN116941198A

CN116941198A - Feedback method of channel information, receiving end equipment and transmitting end equipment

Info

Publication number: CN116941198A
Application number: CN202180094787.0A
Authority: CN
Inventors: 刘文东; 田文强; 肖寒
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2021-05-13
Filing date: 2021-05-13
Publication date: 2023-10-24
Also published as: WO2022236785A1

Abstract

The embodiment of the application provides a channel information feedback method, receiving end equipment and transmitting end equipment, which utilize the CSI time domain correlation and/or the CSI frequency domain correlation among different CSI feedback periods in N CSI feedback periods to carry out CSI feedback, can improve the CSI feedback precision and reduce the CSI feedback expenditure. The feedback method of the channel information comprises the following steps: the receiving end equipment acquires target channel vectors of the N CSI feedback periods according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.

Description

Feedback method of channel information, receiving end equipment and transmitting end equipment

Technical Field

The embodiment of the application relates to the field of communication, and more particularly relates to a feedback method of channel information, receiving end equipment and transmitting end equipment.

Background

In a New Radio, NR, system, channel state information (Channel State Information, CSI) may be fed back based on a codebook, specifically, according to a higher layer signaling configuration, periodically, aperiodically, or semi-continuously, an estimated channel is used to select an optimal feedback matrix and a corresponding feedback coefficient from the codebook. However, since the codebook itself is a preset limited set, i.e., the mapping process from the estimated channels to the channels in the codebook is quantization-lossy. Meanwhile, the fixed codebook design cannot be dynamically adjusted according to the change of the channel, so that the accuracy of the fed-back channel information is reduced, and the precoding performance is further reduced.

Disclosure of Invention

The embodiment of the application provides a channel information feedback method, receiving end equipment and transmitting end equipment, which utilize the CSI time domain correlation and/or the CSI frequency domain correlation among different CSI feedback periods in N CSI feedback periods to carry out CSI feedback, can improve the CSI feedback precision and reduce the CSI feedback expenditure.

In a first aspect, a method for feeding back channel information is provided, where the method includes:

the receiving end equipment acquires target channel vectors of the N CSI feedback periods according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.

In a second aspect, a feedback method of channel information is provided, where the method includes:

the transmitting device performs the CSI feedback according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.

In a third aspect, a terminating device is provided for performing the method in the first aspect.

Specifically, the sink device comprises a functional module for performing the method in the first aspect.

In a fourth aspect, an originating device is provided for performing the method of the second aspect described above.

In particular, the originating device comprises functional modules for performing the method in the second aspect described above.

In a fifth aspect, a terminating device is provided that includes a processor and a memory. The memory is used for storing a computer program, and the processor is used for calling and running the computer program stored in the memory to execute the method in the first aspect.

In a sixth aspect, an originating device is provided that includes a processor and a memory. The memory is for storing a computer program and the processor is for calling and running the computer program stored in the memory for performing the method of the second aspect described above.

In a seventh aspect, there is provided an apparatus for implementing the method of any one of the first to second aspects.

Specifically, the device comprises: a processor for calling and running a computer program from a memory, causing a device in which the apparatus is installed to perform the method of any of the first to second aspects as described above.

In an eighth aspect, a computer-readable storage medium is provided for storing a computer program that causes a computer to execute the method of any one of the first to second aspects.

In a ninth aspect, there is provided a computer program product comprising computer program instructions for causing a computer to perform the method of any one of the first to second aspects above.

In a tenth aspect, there is provided a computer program which, when run on a computer, causes the computer to perform the method of any of the first to second aspects described above.

Through the technical scheme, the transmitting device can perform CSI feedback according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods, and the receiving device can acquire the target channel vectors of the N CSI feedback periods according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods. That is, the embodiment of the application can utilize the CSI time domain correlation and/or the CSI frequency domain correlation among different CSI feedback periods in N CSI feedback periods to carry out CSI feedback, thereby improving the feedback precision of the CSI and reducing the CSI feedback overhead.

Drawings

Fig. 1 is a schematic diagram of a communication system architecture to which embodiments of the present application apply.

Fig. 2 is a schematic diagram of a neuron provided by the present application.

Fig. 3 is a schematic diagram of a neural network provided by the present application.

Fig. 4 is a schematic diagram of a convolutional neural network provided by the present application.

Fig. 5 is a schematic diagram of an LSTM cell provided by the present application.

Fig. 6 is a schematic diagram of channel information feedback provided by the present application.

Fig. 7 is a schematic diagram of another channel information feedback provided by the present application.

Fig. 8 is a schematic flow chart of a feedback method of channel information according to an embodiment of the present application.

Fig. 9 is a schematic diagram of a flow of CSI periodic feedback provided according to an embodiment of the present application.

Fig. 10 is a schematic diagram of CSI periodic feedback provided according to an embodiment of the present application.

Fig. 11 is a schematic diagram of an alternate configuration of primary and secondary feedback subbands provided in accordance with an embodiment of the present application.

Fig. 12 is a schematic diagram of a flow of another CSI periodic feedback provided according to an embodiment of the present application.

Fig. 13 is a schematic block diagram of CSI periodic feedback provided according to an embodiment of the present application.

Fig. 14 is a schematic diagram of a primary CSI feedback period and a secondary CSI feedback period according to an embodiment of the present application.

Fig. 15 is a schematic diagram of another CSI periodic feedback provided in accordance with an embodiment of the present application.

Fig. 16 is a schematic diagram of another primary CSI feedback period and a secondary CSI feedback period provided according to an embodiment of the present application.

Fig. 17 is a schematic block diagram of another CSI periodic feedback provided according to an embodiment of the present application.

Fig. 18 is a schematic flowchart of another feedback method of channel information according to an embodiment of the present application.

Fig. 19 is a schematic block diagram of a sink device according to an embodiment of the present application.

Fig. 20 is a schematic block diagram of an originating device provided according to an embodiment of the present application.

Fig. 21 is a schematic block diagram of a communication device provided according to an embodiment of the present application.

Fig. 22 is a schematic block diagram of an apparatus provided in accordance with an embodiment of the present application.

Fig. 23 is a schematic block diagram of a communication system provided according to an embodiment of the present application.

Detailed Description

The following description of the technical solutions according to the embodiments of the present application will be given with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art to which the application pertains without inventive faculty, are intended to fall within the scope of the application.

The technical scheme of the embodiment of the application can be applied to various communication systems, such as: global system for mobile communications (Global System of Mobile communication, GSM), code division multiple access (Code Division Multiple Access, CDMA) system, wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA) system, universal packet Radio service (General Packet Radio Service, GPRS), long term evolution (Long Term Evolution, LTE) system, advanced long term evolution (Advanced long term evolution, LTE-a) system, new Radio, NR system evolution system, LTE-based access to unlicensed spectrum, LTE-U system on unlicensed spectrum, NR-based access to unlicensed spectrum, NR-U system on unlicensed spectrum, non-terrestrial communication network (Non-Terrestrial Networks, NTN) system, universal mobile communication system (Universal Mobile Telecommunication System, UMTS), wireless local area network (Wireless Local Area Networks, WLAN), wireless fidelity (Wireless Fidelity, wiFi), fifth Generation communication (5 th-Generation, 5G) system, sixth Generation communication (6 th-Generation, 6G) system, or other subsequently evolved communication systems, etc.

Generally, the number of connections supported by the conventional communication system is limited and easy to implement, however, as the communication technology advances, the mobile communication system will support not only conventional communication but also, for example, 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, or internet of vehicles (Vehicle to everything, V2X) communication, etc., to which the embodiments of the present application can also be applied.

In some embodiments, the communication system in the embodiments of the present application may be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, a dual connectivity (Dual Connectivity, DC) scenario, or a Stand Alone (SA) networking scenario.

In some embodiments, the communication system in the embodiments of the present application may be applied to unlicensed spectrum, where unlicensed spectrum may also be considered as shared spectrum; alternatively, the communication system in the embodiment of the present application may also be applied to licensed spectrum, where licensed spectrum may also be considered as non-shared spectrum.

Embodiments of the present application are described in connection with a network device and a terminal device, where the terminal device may also be referred to as a User Equipment (UE), an access terminal, a subscriber unit, a subscriber station, a mobile station, a remote terminal, a mobile device, a User terminal, a wireless communication device, a User agent, a User Equipment, or the like.

The terminal device may be a STATION (ST) in a WLAN, may be a cellular telephone, a cordless telephone, a session initiation protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) STATION, a personal digital assistant (Personal Digital Assistant, PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle mounted device, a wearable device, a terminal device in a next generation communication system such as an NR network, or a terminal device in a future evolved public land mobile network (Public Land Mobile Network, PLMN) network, etc.

In the embodiment of the application, the terminal equipment can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; can also be deployed on the water surface (such as ships, etc.); but may also be deployed in the air (e.g., on aircraft, balloon, satellite, etc.).

In the embodiment of the present application, the terminal device may be a Mobile Phone (Mobile Phone), a tablet computer (Pad), a computer with a wireless transceiving function, a Virtual Reality (VR) terminal device, an augmented Reality (Augmented Reality, AR) terminal device, a wireless terminal device in industrial control (industrial control), a wireless terminal device in unmanned driving (self driving), a wireless terminal device in remote medical (remote medical), a wireless terminal device in smart grid (smart grid), a wireless terminal device in transportation security (transportation safety), a wireless terminal device in smart city (smart city), or a wireless terminal device in smart home (smart home), and the like.

By way of example, and not limitation, in embodiments of the present application, the terminal device may also be a wearable device. The wearable device can also be called as a wearable intelligent device, and is a generic name for intelligently designing daily wear by applying wearable technology and developing wearable devices, such as glasses, gloves, watches, clothes, shoes and the like. The wearable device is a portable device that is worn directly on the body or integrated into the clothing or accessories of the user. The wearable device is not only a hardware device, but also can realize a powerful function through software support, data interaction and cloud interaction. The generalized wearable intelligent device includes full functionality, large size, and may not rely on the smart phone to implement complete or partial functionality, such as: smart watches or smart glasses, etc., and focus on only certain types of application functions, and need to be used in combination with other devices, such as smart phones, for example, various smart bracelets, smart jewelry, etc. for physical sign monitoring.

In the embodiment of the present application, the network device may be a device for communicating with a mobile device, where the network device may be an Access Point (AP) in a WLAN, a base station (Base Transceiver Station, BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, a relay station or an Access Point, a vehicle device, a wearable device, a network device or a base station (gNB) in an NR network, a network device in a PLMN network evolved in the future, or a network device in an NTN network, etc.

By way of example, and not limitation, in embodiments of the present application, a network device may have a mobile nature, e.g., the network device may be a mobile device. In some embodiments, the network device may be a satellite, a balloon station. For example, the satellite may be a Low Earth Orbit (LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geosynchronous orbit (geostationary earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite, or the like. In some embodiments, the network device may also be a base station located on land, in water, etc.

In the embodiment of the present application, a network device may provide services for a cell, where a terminal device communicates with the network device through a transmission resource (e.g., a frequency domain resource, or a spectrum resource) used by the cell, where the cell may be a cell corresponding to the network device (e.g., a base station), and the cell may belong to a macro base station, or may belong to a base station corresponding to a Small cell (Small cell), where the Small cell may include: urban cells (Metro cells), micro cells (Micro cells), pico cells (Pico cells), femto cells (Femto cells) and the like, and the small cells have the characteristics of small coverage area and low transmitting power and are suitable for providing high-rate data transmission services.

An exemplary communication system to which embodiments of the present application may be applied is shown in fig. 1. As shown in fig. 1, the communication system 100 may include a network device 110, and the network device 110 may be a device that communicates with a terminal device 120 (or referred to as a communication terminal, terminal). Network device 110 may provide communication coverage for a particular geographic area and may communicate with terminal devices located within the coverage area.

Fig. 1 illustrates one network device and two terminal devices, and in some embodiments, the communication system 100 may include multiple network devices and may include other numbers of terminal devices within the coverage area of each network device, which is not limited by the embodiments of the present application.

In some embodiments, the communication system 100 may further include a network controller, a mobility management entity, and other network entities, which are not limited in this embodiment of the present application.

It should be understood that a device having a communication function in a network/system according to an embodiment of the present application may be referred to as a communication device. Taking the communication system 100 shown in fig. 1 as an example, the communication device may include a network device 110 and a terminal device 120 with communication functions, where the network device 110 and the terminal device 120 may be specific devices described above, and are not described herein again; the communication device may also include other devices in the communication system 100, such as a network controller, a mobility management entity, and other network entities, which are not limited in this embodiment of the present application.

It should be understood that the terms "system" and "network" are used interchangeably herein. The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

The terminology used in the description of the embodiments of the application herein is for the purpose of describing particular embodiments of the application only and is not intended to be limiting of the application. The terms "first," "second," "third," and "fourth" and the like in the description and in the claims and drawings are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.

It should be understood that the "indication" mentioned in the embodiments of the present application may be a direct indication, an indirect indication, or an indication having an association relationship. For example, a indicates B, which may mean that a indicates B directly, e.g., B may be obtained by a; it may also indicate that a indicates B indirectly, e.g. a indicates C, B may be obtained by C; it may also be indicated that there is an association between a and B.

In the description of the embodiments of the present application, the term "corresponding" may indicate that there is a direct correspondence or an indirect correspondence between the two, or may indicate that there is an association between the two, or may indicate a relationship between the two and the indicated, configured, etc.

In the embodiment of the present application, the "pre-defining" or "pre-configuring" may be implemented by pre-storing corresponding codes, tables or other manners that may be used to indicate relevant information in devices (including, for example, terminal devices and network devices), and the present application is not limited to the specific implementation manner thereof. Such as predefined may refer to what is defined in the protocol.

In the embodiment of the present application, the "protocol" may refer to a standard protocol in the communication field, for example, may include an LTE protocol, an NR protocol, and related protocols applied in a future communication system, which is not limited in the present application.

In order to better understand the embodiments of the present application, a CSI feedback scheme and a reporting configuration in an NR system related to the present application are described.

In the NR system, for the CSI feedback scheme, a codebook-based eigenvector feedback is generally adopted to enable a base station to acquire downlink CSI. Specifically, the base station sends a downlink channel state information reference signal (Channel State Information Reference Signal, CSI-RS) to the terminal, the terminal estimates CSI of the downlink channel by using the CSI-RS, and performs eigenvalue decomposition on the estimated downlink channel to obtain an eigenvector corresponding to the downlink channel. And the terminal calculates codeword coefficients corresponding to the feature vector in a preset codebook according to a certain rule, carries out quantization feedback, and the base station recovers the feature vector according to quantized CSI fed back by the terminal. And for the CSI reporting configuration, reporting types comprise periodic reporting, aperiodic reporting and semi-continuous reporting. For periodic CSI reporting and semi-persistent reporting on the physical uplink control channel (Physical Uplink Control Channel, PUCCH), the period is configured by radio resource control (Radio Resource Control, RRC) parameters such as slot configuration report (reportSlotConfig) through PUCCH feedback; for semi-persistent and aperiodic reporting on the physical uplink shared channel (Physical Uplink Shared Channel, PUSCH), the allowed slot offset is configured by RRC parameters such as slot offset list report (reportSlotOffsetList), triggered by the reception of downlink control information (Downlink Control Information, DCI).

In order to facilitate a better understanding of the embodiments of the present application, the neural network and deep learning related to the present application will be described.

A neural network is an operational model composed of a plurality of neuronal nodes connected to each other, wherein the connections between the nodes represent weight values from an input signal to an output signal, called weights; each node performs a weighted Summation (SUM) of the different input signals and outputs through a specific activation function (f). The neuron structure is shown, for example, in fig. 2. A simple neural network is shown in FIG. 3, and comprises an input layer, a hidden layer and an output layer, wherein different outputs can be generated through different connection modes, weights and activation functions of a plurality of neurons, and then the mapping relation from the input to the output is fitted.

The deep learning adopts a deep neural network with multiple hidden layers, greatly improves the capability of the network to learn characteristics, and can fit complex nonlinear mapping from input to output, so that the method is widely applied to the fields of voice and image processing. In addition to deep neural networks, facing different tasks, deep learning also includes common basic structures such as convolutional neural networks (Convolutional Neural Network, CNN), recurrent neural networks (Recurrent Neural Network, RNN), and the like.

The basic structure of a convolutional neural network comprises: input layer, multiple convolution layers, multiple pooling layers, full connection layer, and output layer, as shown in fig. 4. Each neuron of the convolution kernel in the convolution layer is locally connected with the input of the neuron, and a pooling layer is introduced to extract the local maximum value or average value characteristic of a certain layer, so that the parameters of the network are effectively reduced, the local characteristic is mined, the convolution neural network can be quickly converged, and excellent performance is obtained.

RNNs are a type of neural network modeling sequence data with significant performance in the field of natural language processing, such as machine translation, speech recognition, etc. The method is characterized in that the network memorizes information at the past moment and is used for calculating the current output, namely, nodes between hidden layers are not connectionless but connected, and the input of the hidden layers comprises not only the input layer but also the output of the hidden layer at the last moment. Common RNNs include Long Short-Term Memory (LSTM) and gated loop units (gated recurrent unit, GRU) structures. FIG. 5 shows a basic LSTM cell structure that may contain tanh activation functions, unlike RNNs that only consider the most recent states, LSTM cell states determine which states should be left and which should be forgotten, solving the deficiencies of conventional RNNs in long-term memory.

In order to better understand the embodiment of the application, the channel information feedback method based on deep learning related to the application is described.

In view of the great success of artificial intelligence (Artificial Intelligence, AI) technology, especially deep learning, in terms of computer vision, natural language processing, etc., the communication field has begun to try to solve technical problems that are difficult to solve by conventional communication methods, such as deep learning, using deep learning. The neural network architecture commonly used in deep learning is nonlinear and data-driven, can perform feature extraction on actual channel matrix data and restore channel matrix information fed back by the terminal side compression as much as possible at the base station side, and provides possibility for reducing CSI feedback overhead at the terminal side while ensuring restoring the channel information. Channel information is regarded as an image to be compressed based on the CSI feedback of the deep learning, the channel information is compressed and fed back by a deep learning self-encoder, and the compressed channel image is reconstructed at a transmitting end, so that the channel information can be reserved to a greater extent, as shown in fig. 6.

A typical channel information feedback system is shown in fig. 7. The whole feedback system is divided into an encoder part and a decoder part which are respectively arranged at a transmitting end and a receiving end. After the transmitting end obtains the channel information through channel estimation, the channel information matrix is compressed and encoded through a neural network of the encoder, the compressed bit stream is fed back to the receiving end through an air interface feedback link, and the receiving end recovers the channel information through the decoder according to the feedback bit stream, so that complete feedback channel information is obtained. The encoder shown in fig. 7 uses a superposition of multiple fully-connected layers and the decoder uses a design of convolutional layers and residual structures. With the codec framework unchanged, the network model structure inside the encoder and decoder can be flexibly designed.

In order to facilitate better understanding of the embodiments of the present application, the technology related to the present application and the problems that exist will be described.

CSI feedback in the 5G NR standard is a codebook-based feedback scheme configured according to high-layer signaling, periodically, aperiodically, or semi-continuously, and an estimated channel is used to select an optimal feedback matrix and a corresponding feedback coefficient from the codebook. However, since the codebook itself is a preset limited set, i.e., the mapping process from the estimated channels to the channels in the codebook is quantization-lossy. Meanwhile, the fixed codebook design cannot be dynamically adjusted according to the change of the channel, so that the accuracy of the fed-back channel information is reduced, and the precoding performance is further reduced.

Furthermore, the channel information feedback scheme based on deep learning utilizes a Deep Neural Network (DNN), a Convolutional Neural Network (CNN) and the like to directly encode and compress the channel information obtained after channel estimation, and compared with the traditional channel information feedback based on a codebook, the feedback precision is remarkably improved. However, the feedback method is still in a one-to-one mode, that is, the channel vector obtained by estimating the nth sub-band at the t moment is input into the encoder, and is compressed into a bit stream through quantization and fed back to the decoding end; the decoder outputs a channel vector corresponding to the nth sub-band at time t. However, in an actual communication environment, channels with different feedback periods have different degrees of time domain correlation, for example, the time domain correlation of the channels is higher in a low-speed mobile scene of the terminal; meanwhile, channels among different sub-bands have different degrees of frequency domain correlation, such as higher channel frequency domain correlation in a scene with weak multipath influence. Therefore, under the fixed feedback bit overhead, the one-to-one channel compression feedback and recovery accuracy is limited; in addition, for the CSI feedback process adopted by NR, the periodic, aperiodic and semi-persistent feedback methods adopted do not utilize the correlation of the channel in the time domain and the frequency domain, so when a certain channel recovery precision is reached, there are more redundant feedback bits, and thus the feedback bit overhead is also higher. Therefore, how to effectively utilize the correlation of the channel in the time domain and the frequency domain under different channel scenes, and effectively reduce the CSI feedback overhead while ensuring the accuracy of channel vector compression feedback and recovery is a technical problem to be solved.

Based on the above problems, the application provides a CSI feedback scheme, which can utilize CSI time domain correlation and/or CSI frequency domain correlation among different CSI feedback periods in N CSI feedback periods to perform CSI feedback, so as to improve CSI feedback accuracy and reduce CSI feedback overhead.

The technical scheme of the application is described in detail below through specific embodiments.

Fig. 8 is a schematic flowchart of a channel information feedback method 200 according to an embodiment of the present application, and as shown in fig. 8, the channel information feedback method 200 may include at least some of the following:

s210, receiving end equipment acquires target channel vectors of N CSI feedback periods according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.

In the embodiment of the application, the transmitting device can perform the CSI feedback according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods.

In some embodiments, the CSI correlation comprises a CSI time domain correlation and/or a CSI frequency domain correlation.

Considering that when the user speed is low (for example, the typical user moving speed is less than 3km/h scene), the channel change is low, the correlation degree of the CSI of different time slots is high, and redundancy exists in periodically reporting the CSI. Therefore, the embodiment of the application can utilize the CSI time domain correlation and/or the CSI frequency domain correlation among different CSI feedback periods in the N CSI feedback periods to carry out the CSI feedback, can improve the CSI feedback precision and reduce the CSI feedback overhead.

In some embodiments, the flow of CSI periodic feedback may be as shown in fig. 9, for example; the period T indicates that the CSI-RS may be sent at intervals of T slots, and the same CSI reporting is also performed at intervals of T slots, where the period T is configured by RRC signaling. Assuming that the number of feedback bits of each CSI is M, the downlink CSI-RS is sent in the 0 th slot and CSI reporting is performed, and for n×t slots that follow-up consecutive, n×m feedback bits are required for N CSI reporting.

In some embodiments, the receiving device obtains the target channel vectors of the N CSI feedback periods through the neural network according to CSI time domain correlation and/or CSI frequency domain correlation between different CSI feedback periods in the N CSI feedback periods.

In some embodiments, the terminating device is a terminal device and the originating device is a network device; alternatively, the sink device is a network device and the originating device is a terminal device.

In still other embodiments, the terminating device is one terminal device and the originating device is another terminal device. The embodiment of the application is applied to Side Link (SL) communication.

In still other embodiments, the originating device is a network device and the receiving device is another network device. The embodiment of the application is applied to backhaul link (backhaul link) communication.

In some embodiments, the downlink CSI-RS transmission and CSI reporting are performed in K CSI feedback periods of the N CSI feedback periods, where CSI of the CSI feedback periods other than the K CSI feedback periods is obtained by prediction through a neural network, K is a positive integer, and K is less than N.

In some implementations, the receiving device receives K bit streams sent by the sending device, where the K bit streams are obtained after encoding channel vectors of K CSI feedback periods in the N CSI feedback periods respectively; the receiving end equipment decodes the K bit streams respectively to obtain K target channel vectors of the K CSI feedback periods; the receiving end device predicts the K target channel vectors through a first receiving end neural network to obtain N-K target channel vectors of the CSI feedback periods except the K CSI feedback periods in the N CSI feedback periods.

That is, the originating device may encode the channel vectors of K CSI feedback periods in the N CSI feedback periods, respectively, to obtain the K bit streams. For example, for each CSI feedback period of the K CSI feedback periods, the originating device performs channel estimation according to the CSI-RS to obtain channel information between the originating device and the receiving device; performing characteristic decomposition on the channel information to obtain a channel vector; and then encoding the channel vector to obtain a bit stream.

In some implementations, the first receiving neural network extracts CSI time domain correlations of different CSI feedback periods, and uses sequence input and sequence output, so the first receiving neural network may be, for example, RNN with LSTM and GRU, or other neural networks with better prediction performance, which is not limited in the present application.

For example, the first terminating neural network includes, but is not limited to, a structural implementation based on one or more of a full connection layer, a convolution layer, a recurrent neural network layer, an activation function layer, and the like.

In some implementations, the K CSI feedback periods are the first K consecutive CSI feedback periods of the N CSI feedback periods.

In some implementations, the receiving device decodes the K bit streams through a second receiving neural network, respectively, to obtain the K target channel vectors.

In some implementations, the second receiving neural network may be a neural network for image processing, for example, may be CNN or DNN, or other neural networks with better image processing performance, which is not limited by the present application.

For example, the second terminating neural network includes, but is not limited to, a structural implementation based on one or more of a fully connected layer, a convolutional layer, a recurrent neural network layer, an activation function layer, and the like.

In some implementations, a bit stream of the K bit streams includes information of S subbands, S is a positive integer, S > 1; specifically, the receiving end equipment decodes the bit stream from the j sub-band of the i-L CSI feedback period to the bit stream on the j sub-band of the i-L CSI feedback period through the second receiving end neural network, and decodes the bit stream from the first sub-band to the S sub-band in the i-L CSI feedback period through the second receiving end neural network to obtain a target channel vector on the j sub-band of the i-L CSI feedback period, wherein i, j and L are positive integers, i is more than or equal to 1 and less than or equal to K, j is more than or equal to 1 and less than or equal to S, and L is less than or equal to i; and the receiving end equipment acquires the K target channel vectors according to the target channel vectors on the j sub-band of the ith CSI feedback period.

That is, for each CSI feedback period of the K CSI feedback periods, the bit stream that the originating device needs to feed back includes information of S subbands. In this case, the second receiving neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback period to the j-th subband of the i-th CSI feedback period, and the second receiving neural network extracts the CSI frequency-domain correlation from the first subband to the S-th subband in the i-th CSI feedback period, and performs joint recovery on the CSI on the j-th subband of the i-th CSI feedback period (i.e., determines the target channel vector on the j-th subband of the i-th CSI feedback period).

In this case, since the second receiving neural network extracts the CSI time domain correlation of L CSI feedback periods and the CSI frequency domain correlation of S subbands, the second receiving neural network adopts sequence input and sequence output, and thus, the second receiving neural network may be, for example, LSTM,The application is not limited to RNNs, for example, GRUs, or other neural networks with superior predictive performance. As shown in particular in fig. 10. Bit stream (b) on the j th subband from the i-L th CSI feedback period _i-L,j ) Bit stream (b) on the jth subband to the ith CSI feedback period _i,j ) Respectively inputting the time domain LSTM units in the second receiving neural network, and the bit stream (b) from the first sub-band in the ith CSI feedback period _i,1 ) Bit stream (b) to the S th sub-band _i,S ) Respectively inputting the frequency domain LSTM units in the second receiving end neural network, and outputting the time domain LSTM units and the frequency domain LSTM units through a full connection layer to finally obtain the target channel vector on the j sub-band of the i-th CSI feedback period

It should be noted that the serial structure of L time-domain LSTM units as shown in fig. 10 does not represent that the actual structure includes L different time-domain LSTM units, but is an expanded representation of the L-order column input of the same time-domain LSTM unit, and in fact, only one time-domain LSTM unit is included in the system. Similarly, the serial structure of the S frequency domain LSTM units does not represent that the actual structure includes S different frequency domain LSTM units, but is an expanded representation of the S-order column input of the same frequency domain LSTM unit, and in fact, the system includes only one frequency domain LSTM unit.

In some implementations, the S subbands include at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by information of the secondary feedback subbands in the at least one secondary feedback subband is less than the number of bits occupied by information of the primary feedback subbands in the at least one primary feedback subband. For example, s=4, and the primary feedback subbands and the secondary feedback subbands of the adjacent CSI feedback period are alternately arranged as shown in fig. 11.

It should be noted that, the present embodiment is not limited to the configuration method of the main feedback sub-band and the auxiliary feedback sub-band in each CSI feedback period, nor to the configuration method of the main feedback sub-band and the auxiliary feedback sub-band in different CSI feedback periods, and the present embodiment may support other flexible configuration methods of the main feedback sub-band and the auxiliary feedback sub-band with a certain periodicity principle, and perform configuration through RRC or DCI signaling, so as to reduce the overhead of CSI periodic feedback.

In some implementations, the primary and secondary feedback subbands in the S subbands are configured by the network device through RRC signaling and/or DCI signaling.

For example, the network device configures the primary feedback subband and the secondary feedback subband of the S subbands through RRC signaling.

For another example, the network device configures the primary feedback subband and the secondary feedback subband of the S subbands through DCI signaling.

For another example, the network device configures the primary feedback subband and the secondary feedback subband in the S subbands jointly through RRC signaling and DCI signaling.

In some implementations, the values of K and N are determined from the G group { K, N }, G is a positive integer, and G.gtoreq.2.

For example, g=3, i.e. configured with 3 sets { K, N }, respectively denoted as { K } ₁ ，N ₁ }、{K ₂ ，N ₂ Sum { K } ₃ ，N ₃ In this case, the values of K and N may be K ₁ And N ₁ Alternatively, the values of K and N may be K ₂ And N ₂ Alternatively, the values of K and N may be K ₃ And N ₃ 。

In some implementations, the values of K and N are determined from the G group { K, N } according to the channel scenario.

For example, g=3, i.e. configured with 3 sets { K, N }, respectively denoted as { K } ₁ ，N ₁ }、{K ₂ ，N ₂ Sum { K } ₃ ，N ₃ In this case, for channel scenario A (e.g., user movement velocity v ₁ The scene of (c), the values of K and N can be K respectively ₁ And N ₁ The method comprises the steps of carrying out a first treatment on the surface of the For channel scenario B (e.g., user movement velocity v ₂ Scene of (c) K and NThe values can be K respectively ₂ And N ₂ For channel scenario C (e.g., user movement speed v ₃ The scene of (c), the values of K and N can be K respectively ₃ And N ₃ 。

In some implementations, the G group { K, N } is configured by the network device through RRC signaling and/or DCI signaling. For example, the network device configures the G group { K, N } jointly by RRC signaling and DCI signaling.

In some implementations, the G group { K, N } is in RRC signaling and/or DCI signaling by the network deviceA bit configuration, wherein,representing an upward rounding. For example, as shown in fig. 12, the network device configures { K, N } for the terminal device through RRC signaling or DCI signaling.

For example, the network device needs to configure 2 sets { K, N }, in which case the network device configures the 2 sets { K, N }, by 1 bit in RRC signaling or DCI signaling.

As another example, the network device needs to configure 3 sets { K, N }, in which case the network device configures the 3 sets { K, N }, by 2 bits in RRC signaling or DCI signaling.

In some implementations, specifically, it is assumed that the first K CSI feedback periods of the N CSI feedback periods perform downlink CSI-RS transmission and CSI reporting, and CSI of the latter N-K CSI feedback periods is obtained by prediction through a neural network, and the structure thereof may be shown in fig. 13. The input of the encoder is channel vectors of the first K CSI feedback periods respectively, and the channel vectors are output as bit streams and fed back to a network side through CSI reporting; the input of the decoder at the network side is the feedback bit stream of the first K CSI feedback periods, and the output is the estimated channel vector (namely the target channel vector). Further, the estimated channel vectors of the K CSI feedback periods are combined as input to the predictor, and output as predicted channel vectors (i.e., target channel vectors) of the following N-K CSI feedback periods. The predictor in fig. 13 extracts the time domain correlation of CSI of different periods, and adopts sequence input and sequence output, and may adopt RNN, for example LSTM and GRU, which corresponds to the first receiving neural network; the decoder may adopt a neural network such as DNN, CNN, etc., which corresponds to the second receiving neural network; encoders typically employ neural networks such as DNN, CNN, etc. The embodiment does not limit the specific implementation scheme of the neural network in each neural network, so as to design different functions according to different communication scenes.

In some implementations, the training method of the encoder, decoder, and calibrator in fig. 13 described above is as follows:

joint training of encoder and decoder: the training data and the labels input in this step are channel vectors w, and the loss function includes but is not limited to estimating channel vectors(i.e., target channel vector) and the mean square error (Mean Squared Error, MSE) or cosine similarity (GCS) of the channel vector w,wherein the output of the encoder and the input of the decoder are required to be bit streams with a fixed length of M, wherein M is the bit overhead for channel vector compression feedback on the air interface.

Predictor training: the predictor is trained by optimizing the loss function, fixing the network model and parameters of the encoder and decoder. Setting the input of the predictive neural network as the sequence of the recovered target channel vectors of the first K CSI feedback periods, and outputting the predicted channel vectors (namely the target channel vectors) of the last N-K CSI feedback periodsThe label is the channel vector w= [ w ] of the last N-K CSI feedback periods _K+1 …w _N ]By optimizingAnd the loss function of w, and the training of the predictor is completed.

The above training method requires that the network parameters of the encoder and decoder are already fixed when the predictor is trained, so as to ensure that the output of the decoder in the training process is matched with the inferred output of the decoder in actual deployment. In this embodiment, the encoder, decoder and predictor may employ offline and online deployment training.

In this embodiment, in N continuous CSI feedback periods, only the first K CSI feedback periods need to perform CSI-RS transmission and CSI reporting, and CSI of the latter N-K CSI feedback periods can be obtained by using CSI time domain correlation and a neural network with reasonable design, so that feedback overhead is reduced to K/N of a periodic feedback scheme in the current NR system, and CSI feedback overhead is reduced. Further, depending on the different channel scenarios, different { K, N } combinations should be employed to achieve a tradeoff of feedback bit overhead and predicted CSI accuracy.

In some embodiments, the N CSI feedback periods are staged to obtain P primary CSI feedback periods and Q secondary CSI feedback periods. And respectively designing different neural networks to recover the CSI of the main CSI feedback period and the auxiliary CSI feedback period by extracting the time domain correlation between the main CSI feedback period and the auxiliary CSI feedback period.

In some implementations, the receiving end device receives P bit streams and Q bit streams sent by the sending end device; the P bit streams are obtained after the channel vectors of the P primary CSI feedback periods in the N CSI feedback periods are encoded, the Q bit streams are obtained after the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods are encoded, or the Q bit streams are obtained after the difference values of the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods and the channel vectors of the corresponding primary CSI feedback periods are encoded, P and Q are positive integers, and p+q=n; the receiving end equipment decodes the P bit streams respectively to obtain P target channel vectors of the P main CSI feedback periods; the receiving end equipment respectively decodes a first bit stream in the Q bit streams and a second bit stream in the P bit streams through a third receiving end neural network to obtain Q target channel vectors of the Q auxiliary CSI feedback periods; the secondary CSI feedback period corresponding to the first bit stream is a secondary CSI feedback period accompanying the primary CSI feedback period corresponding to the second bit stream.

That is, the originating device may encode the channel vectors of the P primary CSI feedback periods, respectively, to obtain P bit streams. For example, for each of the P primary CSI feedback periods, the originating device performs channel estimation according to the CSI-RS to obtain channel information between the originating device and the receiving device; performing characteristic decomposition on the channel information to obtain a channel vector; and then encoding the channel vector to obtain a bit stream.

The originating device may encode the channel vectors of the Q secondary CSI feedback periods, respectively, to obtain Q bit streams. Or, the transmitting device may encode differences between the channel vectors of the Q auxiliary CSI feedback periods in the N CSI feedback periods and the channel vectors of the corresponding main CSI feedback periods, respectively, to obtain Q bit streams.

In some implementations, the third receiving neural network extracts CSI time domain correlations of different CSI feedback periods, and uses sequence input and sequence output, so the third receiving neural network may be, for example, RNN with LSTM and GRU, or other neural networks with better prediction performance, which is not limited in the present application.

For example, the third terminating neural network includes, but is not limited to, a construction implementation based on one or more of a full connection layer, a convolution layer, a recurrent neural network layer, an activation function layer, and the like.

In some implementations, one of the Q bitstreams occupies a smaller number of bits than one of the P bitstreams. That is, the number of bits occupied by the bit stream fed back by the secondary CSI feedback period is smaller than the number of bits occupied by the bit stream fed back by the primary CSI feedback period.

In some implementations, different ones of the Q bitstreams occupy different numbers of bits, or different ones of the Q bitstreams occupy the same number of bits.

In some implementations, one primary CSI feedback period of the N CSI feedback periods is accompanied by one or more secondary CSI feedback periods.

For example, as shown in fig. 14, in N consecutive CSI feedback periods, the configuration is classified into a configuration in which one primary CSI feedback period is accompanied by N-1 secondary CSI feedback periods, in which one primary CSI feedback period feeds back M bits, and N-1 secondary CSI feedback periods feed back respectively different { M } ₁ ,m ₂ ,…,m _N-1 A number of bits. In this case, in N CSI feedback periods, the transmitting device feeds back the bit stream b to the receiving device in the primary CSI feedback period ₀ And the originating device feeds back b in N-1 auxiliary CSI feedback periods respectively ₁ ,b ₂ ,…,b _N-1 . As shown in fig. 15, bit stream b ₀ And b ₁ Inputting the LSTM unit in the third receiving end neural network to obtain a target channel vectorBit stream b ₀ And b ₂ Inputting the LSTM unit in the third receiving end neural network to obtain a target channel vectorBit stream b ₀ And b _N-1 Inputting the LSTM unit in the third receiving end neural network to obtain a target channel vector

It should be noted that the serial structure of N-1 LSTM cells as shown in fig. 15 does not represent that the actual structure contains N-1 different LSTM cells, but rather an expanded representation of the N-1 sequential column input of the same LSTM cell, and in fact, the system contains only one LSTM cell.

For another example, in a continuous N CSI feedback periods, a configuration may be classified into a plurality of primary CSI feedback periods accompanied by a plurality of secondary CSI feedback periods, where the plurality of primary CSI feedback periods may support an adjacent or spaced configuration, as shown in fig. 16, where in the configuration of n=5, 2 primary CSI feedback periods are accompanied by 3 secondary CSI feedback periods, and 2 primary CSI feedback periods are spaced by 2 secondary CSI feedback periods.

In some implementations, the number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is the same, or the number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is different.

In some implementations, the primary CSI feedback period and the secondary CSI feedback period of the N CSI feedback periods are configured by the network device through RRC signaling and/or DCI signaling. For example, the network device configures the primary CSI feedback period and the secondary CSI feedback period of the N CSI feedback periods through RRC signaling and DCI signaling in combination.

In some implementations, the receiving device decodes the P bit streams through a fourth receiving neural network, respectively, to obtain P target channel vectors of the P primary CSI feedback periods.

In some implementations, the fourth receiving neural network may be a neural network for image processing, for example, may be CNN or DNN, or other neural networks with better image processing performance, which is not limited by the present application.

For example, the fourth terminating neural network includes, but is not limited to, a structural implementation based on one or more of a full connection layer, a convolution layer, a recurrent neural network layer, an activation function layer, and the like.

In some implementations, a bit stream of the P bit streams includes information of S subbands, S is a positive integer, S > 1; specifically, the receiving end equipment decodes the bit stream from the j sub-band of the i-L CSI feedback period to the bit stream on the j sub-band of the i-L CSI feedback period through the fourth receiving end neural network, and decodes the bit stream from the first sub-band to the S sub-band in the i-L CSI feedback period through the fourth receiving end neural network to obtain a target channel vector on the j sub-band of the i-L CSI feedback period, wherein i, j and L are positive integers, i is more than or equal to 1 and less than or equal to P, j is more than or equal to 1 and less than or equal to S, and L is less than or equal to i; and the receiving end equipment acquires P target channel vectors of the P main CSI feedback periods according to the target channel vectors on the j sub-bands of the i CSI feedback periods.

That is, for each of the P primary CSI feedback periods, the bit stream that the originating device needs to feed back includes information of S subbands. In this case, the fourth receiving neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback period to the j-th subband of the i-th CSI feedback period, and the fourth receiving neural network extracts the CSI frequency-domain correlation from the first subband to the S-th subband in the i-th CSI feedback period, and performs joint recovery on the CSI on the j-th subband of the i-th CSI feedback period (i.e., determines the target channel vector on the j-th subband of the i-th CSI feedback period).

In this case, since the fourth receiving neural network extracts CSI time-domain correlations of L main CSI feedback periods and CSI frequency-domain correlations of S subbands, and uses sequence input and sequence output, the fourth receiving neural network may be, for example, RNN with LSTM and GRU, or another neural network with better prediction performance, which is not limited in the present application. Specifically, bit stream (b) on the j th subband from the i-L th CSI feedback period _i-L,j ) Bit stream (b) on the jth subband to the ith CSI feedback period _i,j ) Respectively inputting the time domain LSTM units in the fourth receiving neural network, and the bit stream (b) from the first sub-band in the ith main CSI feedback period _i,1 ) Bit stream (b) to the S th sub-band _i,S ) Respectively input into the fourth receiving-end neural networkThe frequency domain LSTM unit, and the outputs of the time domain LSTM unit and the frequency domain LSTM unit pass through a full connection layer to finally obtain the target channel vector on the jth subband of the ith CSI feedback periodReference may be made specifically to the description of fig. 10 in the above embodiment, and for brevity, the description is omitted here.

In some implementations, in particular, in the 1 st CSI feedback period, the number of bits of CSI feedback of the originating device is M, and when the channel changes not fast, there is a strong time-domain correlation between channels in adjacent CSI feedback periods, so that in the 2 nd CSI feedback period, a smaller number of bits M can be fed back, where M<And M, extracting the CSI time domain correlation with the 1 st CSI feedback period by using a third receiving end neural network and recovering the CSI of the 2 nd CSI feedback period. By analogy, in this embodiment, a CSI feedback period in which a complete M bits are used for reporting during CSI feedback is referred to as a primary CSI feedback period, a CSI feedback period in which fewer M bits are used for reporting during CSI feedback is referred to as a secondary CSI feedback period, and CSI of the primary CSI feedback period and the secondary CSI feedback period are respectively designed by extracting time domain correlations between the primary CSI feedback period and the secondary CSI feedback period, and different neural networks are respectively designed to recover CSI of the primary CSI feedback period and the secondary CSI feedback period. Taking the 1 st CSI feedback period as the main CSI feedback period and the 2 nd CSI feedback period as the auxiliary CSI feedback period as an example, the specific architecture can be shown in fig. 17. The input of the main CSI feedback period decoder (corresponding to the fourth receiving neural network) is b ₁ The input of the auxiliary CSI feedback period decoder (corresponding to the third receiving neural network) is [ b ] ₁ ,b ₂ ]The secondary CSI feedback period decoder may also employ similar DNN, CNN, etc. structures as the primary CSI feedback period decoder. In practice, for a secondary periodic encoder, its input is not limited to the channel vector w ₂ May also be a channel vector w ₂ And w is equal to ₁ Or other characteristic that characterizes the difference between channels.

It should be noted that, in this embodiment, reference may be made to the description of the foregoing embodiments for the training of the encoder and decoder, which is not repeated herein for brevity.

In some embodiments, periodic feedback based on CSI time-frequency domain joint correlation.

In some implementations, the receiving end device receives N bit streams sent by the sending end device; wherein, the bit stream in the N bit streams comprises information of S sub-bands, S is a positive integer, and S is more than 1; the receiving end equipment decodes bit streams from a j-th sub-band of an i-L CSI feedback period to a j-th sub-band of the i-th CSI feedback period through a fifth receiving end neural network, and decodes bit streams from a first sub-band to an S-th sub-band in the i-th CSI feedback period through the fifth receiving end neural network to obtain target channel vectors on the j-th sub-band of the i-th CSI feedback period, wherein i, j and L are positive integers, i is more than or equal to 1 and less than or equal to N, j is more than or equal to 1 and less than or equal to S, and L is less than or equal to i; and the receiving end equipment acquires the target channel vectors of the N CSI feedback periods according to the target channel vectors of the j sub-bands of the ith CSI feedback period.

That is, for each CSI feedback period of the N CSI feedback periods, the bit stream that the originating device needs to feed back includes information of S subbands. In this case, the fifth receiving neural network extracts the CSI time-domain correlation from the j-th subband of the i-L CSI feedback period to the j-th subband of the i-th CSI feedback period, and the fifth receiving neural network extracts the CSI frequency-domain correlation from the first subband to the S-th subband in the i-th CSI feedback period, and performs joint recovery on the CSI on the j-th subband of the i-th CSI feedback period (i.e., determines the target channel vector on the j-th subband of the i-th CSI feedback period).

In this case, since the fifth receiving-end neural network extracts CSI time-domain correlations of L CSI feedback periods and CSI frequency-domain correlations of S subbands, and uses sequence input and sequence output, the fifth receiving-end neural network may be, for example, RNN with LSTM and GRU, or another neural network with better prediction performance, which is not limited in the present application. Specifically, bit stream (b) on the j th subband from the i-L th CSI feedback period _i-L,j ) Bit stream (b) on the jth subband to the ith CSI feedback period _i,j ) Respectively inputting the time domain LSTM unit in the fifth receiving neural network and the bit stream (b) from the first sub-band in the ith CSI feedback period _i,1 ) Bit stream (b) to the S th sub-band _i,S ) Respectively inputting the frequency domain LSTM units in the fifth receiving end neural network, and outputting the time domain LSTM units and the frequency domain LSTM units through a full connection layer to finally obtain the target channel vector on the j sub-band of the i-th CSI feedback periodReference may be made specifically to the description of fig. 10 in the above embodiment, and for brevity, the description is omitted here.

In some implementations, the CSI of the jth subband of the ith feedback period may be obtained by extracting the joint correlation of the time domain and the frequency domain using a neural network by CSI of the jth-1 subband and the (j+1) th subband adjacent to each other in the ith feedback period and CSI of the jth subband of the ith-1 feedback period.

Therefore, in the embodiment of the present application, the transmitting device may perform CSI feedback according to CSI correlations between different CSI feedback periods in the N CSI feedback periods, and the receiving device may obtain target channel vectors of the N CSI feedback periods according to CSI correlations between different CSI feedback periods in the N CSI feedback periods. That is, the embodiment of the application can utilize the CSI time domain correlation and/or the CSI frequency domain correlation among different CSI feedback periods in N CSI feedback periods to carry out CSI feedback, thereby improving the feedback precision of the CSI and reducing the CSI feedback overhead.

The present application includes, but is not limited to, the technical solutions provided in the above embodiments, for example, the specific structural design inside each neural network, and the configuration parameters of N, K, L, etc. may be adaptively adjusted according to the different communication scenarios, such as the terminal moving speed, the channel delay expansion, etc. to optimize the transmission performance. And, the embodiments of the present application are not limited to channel vector compression and feedback between base stations and terminals, and the embodiments of the present application may also be applicable to CSI feedback overhead reduction requirements that may exist between terminals (e.g., sip link) and between base stations (e.g., backhaul link). The embodiment of the application focuses on the method for reducing the periodic feedback overhead of the CSI based on the AI.

The embodiments of the sink device side of the present application are described in detail above with reference to fig. 8 to 17, and the embodiments of the source device side of the present application are described in detail below with reference to fig. 18, it being understood that the embodiments of the source device side and the embodiments of the sink device side correspond to each other, and similar descriptions can refer to the embodiments of the sink device side.

Fig. 18 is a schematic flowchart of a channel information feedback method 300 according to an embodiment of the present application, and as shown in fig. 18, the channel information feedback method 300 may include at least some of the following:

S310, the transmitting device performs CSI feedback according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.

In some embodiments, the receiving device obtains the target channel vectors of the N CSI feedback periods according to CSI correlations between different CSI feedback periods of the N CSI feedback periods.

In some embodiments, the step S310 may specifically include:

the transmitting device respectively codes channel vectors of K CSI feedback periods in the N CSI feedback periods through a first transmitting neural network to obtain K bit streams; and the originating device does not encode channel vectors of CSI feedback periods other than the K CSI feedback periods of the N CSI feedback periods; the originating device sends the K bit streams to the receiving device, respectively.

In some embodiments, the bit stream of the K bit streams includes information of S subbands, the S subbands include at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by the information of the secondary feedback subbands in the at least one secondary feedback subband is smaller than the number of bits occupied by the information of the primary feedback subbands in the at least one primary feedback subband, S is a positive integer, and S > 1.

In some embodiments, the K CSI feedback periods are the first K consecutive CSI feedback periods of the N CSI feedback periods.

In some embodiments, the values of K and N are determined from the G group { K, N }, G is a positive integer, and G.gtoreq.2.

In some embodiments, the values of K and N are determined from the G group { K, N } according to the channel scene.

In some embodiments, the G group { K, N } is configured by the network device through RRC signaling or DCI signaling.

In some embodiments, the G group { K, N } is in RRC signaling and/or DCI signaling by the network deviceA bit configuration, wherein,representing an upward rounding.

In some embodiments, the step S310 may specifically include:

the originating equipment respectively codes channel vectors of P main CSI feedback periods in the N CSI feedback periods through a second originating neural network to obtain P bit streams;

the originating equipment respectively codes channel vectors of Q auxiliary CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain Q bit streams;

the originating device sends the P bit streams and the Q bit streams to the receiving device respectively; wherein P and Q are both positive integers, and p+q=n.

In some embodiments, the bit stream of the P bit streams includes information of S subbands, the S subbands include at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by the information of the secondary feedback subbands in the at least one secondary feedback subband is smaller than the number of bits occupied by the information of the primary feedback subbands in the at least one primary feedback subband, S is a positive integer, and S > 1.

In some embodiments, one of the Q bitstreams occupies a smaller number of bits than one of the P bitstreams.

In some embodiments, the number of bits occupied by different ones of the Q bitstreams is different, or the number of bits occupied by different ones of the Q bitstreams is the same.

In some embodiments, one primary CSI feedback period of the N CSI feedback periods is accompanied by one or more secondary CSI feedback periods.

In some embodiments, the number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is the same, or the number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is different.

In some embodiments, the primary CSI feedback period and the secondary CSI feedback period of the N CSI feedback periods are configured by the network device through RRC signaling and/or DCI signaling.

In some embodiments, the step S310 may specifically include:

the originating equipment respectively encodes the channel vectors of the N CSI feedback periods through a third originating neural network to obtain N bit streams;

the originating device sends the N bit streams to the receiving device, respectively.

In some embodiments, the bit stream of the N bit streams includes information of S subbands, the S subbands include at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by the information of the secondary feedback subbands in the at least one secondary feedback subband is less than the number of bits occupied by the information of the primary feedback subbands in the at least one primary feedback subband, S is a positive integer, and S > 1.

In some embodiments, the primary and secondary feedback subbands in the S subbands are configured by the network device through RRC signaling and/or DCI signaling.

The method embodiment of the present application is described in detail above with reference to fig. 8 to 18, and the apparatus embodiment of the present application is described in detail below with reference to fig. 19 to 23, it being understood that the apparatus embodiment and the method embodiment correspond to each other, and similar descriptions can be made with reference to the method embodiment.

Fig. 19 shows a schematic block diagram of a sink device 400 according to an embodiment of the application. As shown in fig. 19, the sink device 400 includes:

a processing unit 410, configured to obtain target channel vectors of the N CSI feedback periods according to CSI correlations among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.

In some embodiments, the sink device 400 includes a communication unit 420, wherein,

the communication unit 420 is configured to receive K bit streams sent by an originating device, where the K bit streams are obtained by encoding channel vectors of K CSI feedback periods in the N CSI feedback periods, K is a positive integer, and K is less than N;

the processing unit 410 is configured to decode the K bit streams respectively to obtain K target channel vectors of the K CSI feedback periods;

The processing unit 410 is configured to predict the K target channel vectors through a first receiving neural network, so as to obtain N-K target channel vectors of the CSI feedback periods except for the K CSI feedback periods in the N CSI feedback periods.

In some embodiments, the processing unit 410 is specifically configured to:

and respectively decoding the K bit streams through a second receiving end neural network to obtain K target channel vectors.

In some embodiments, a bit stream of the K bit streams includes information of S subbands, S is a positive integer, S > 1; the processing unit 410 is specifically configured to:

decoding bit streams from a jth sub-band of an ith-L CSI feedback period to the jth sub-band of the ith CSI feedback period through the second receiving end neural network, and decoding bit streams from a first sub-band to an S sub-band in the ith CSI feedback period through the second receiving end neural network to obtain target channel vectors on the jth sub-band of the ith CSI feedback period, wherein i, j and L are positive integers, i is not less than 1 and not more than K, j is not less than 1 and not more than S, and L is not more than i;

and obtaining the K target channel vectors according to the target channel vectors on the jth sub-band of the ith CSI feedback period.

In some embodiments, the G group { K, N } is configured by the network device through radio resource control, RRC, signaling and/or downlink control information, DCI, signaling.

In some embodiments, the G group { K, N } is in RRC signaling or DCI signaling by the network deviceThe configuration of the bits is such that,wherein,representing an upward rounding.

the communication unit 420 is configured to receive P bit streams and Q bit streams sent by an originating device; the P bit streams are obtained after the channel vectors of the P primary CSI feedback periods in the N CSI feedback periods are encoded, the Q bit streams are obtained after the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods are encoded, or the Q bit streams are obtained after the difference values of the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods and the channel vectors of the corresponding primary CSI feedback periods are encoded, P and Q are positive integers, and p+q=n;

The processing unit 410 is configured to decode the P bit streams respectively to obtain P target channel vectors of the P primary CSI feedback periods;

the processing unit 410 is configured to decode a first bit stream of the Q bit streams and a second bit stream of the P bit streams through a third receiving neural network, so as to obtain Q target channel vectors of the Q auxiliary CSI feedback periods; the secondary CSI feedback period corresponding to the first bit stream is a secondary CSI feedback period accompanying the primary CSI feedback period corresponding to the second bit stream.

In some embodiments, the processing unit 410 is specifically configured to:

and decoding the P bit streams through a fourth receiving end neural network respectively to obtain P target channel vectors of the P main CSI feedback periods.

In some embodiments, the bit stream of the P bit streams includes information of S subbands, S is a positive integer, S > 1; the processing unit 410 is specifically configured to:

decoding bit streams from a jth sub-band of an ith-L CSI feedback period to the jth sub-band of the ith CSI feedback period through the fourth receiving end neural network, and decoding bit streams from a first sub-band to an S sub-band in the ith CSI feedback period through the fourth receiving end neural network to obtain target channel vectors on the jth sub-band of the ith CSI feedback period, wherein i, j and L are positive integers, i is not less than 1 and not more than P, j is not less than 1 and not more than S, and L is not more than i;

And obtaining P target channel vectors of the P main CSI feedback periods according to the target channel vectors on the j sub-bands of the i CSI feedback periods.

the communication unit 420 is configured to receive N bit streams sent by an originating device; wherein, the bit stream in the N bit streams comprises information of S sub-bands, S is a positive integer, and S is more than 1;

The processing unit 410 is configured to decode, by using a fifth receiving neural network, a bit stream from a j-th subband of an i-L CSI feedback period to a bit stream on a j-th subband of the i-th CSI feedback period, and decode, by using the fifth receiving neural network, a bit stream from a first subband to an S-th subband in the i-th CSI feedback period to obtain a target channel vector on the j-th subband of the i-th CSI feedback period, where i, j, and L are positive integers, i is 1-N, j is 1-S, and L is less than i;

the processing unit 410 is configured to obtain the target channel vectors of the N CSI feedback periods according to the target channel vector on the j-th subband of the i-th CSI feedback period.

In some embodiments, the S subbands include at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by information of the secondary feedback subbands in the at least one secondary feedback subband is less than the number of bits occupied by information of the primary feedback subbands in the at least one primary feedback subband.

In some embodiments, the communication unit may be a communication interface or transceiver, or an input/output interface of a communication chip or a system on a chip. The processing unit may be one or more processors.

It should be understood that the sink device 400 according to the embodiment of the present application may correspond to the sink device in the embodiment of the method of the present application, and the foregoing and other operations and/or functions of each unit in the sink device 300 are respectively for implementing the corresponding flow of the sink device in the method 200 shown in fig. 8, and are not repeated herein for brevity.

Fig. 20 shows a schematic block diagram of an originating device 500 according to an embodiment of the application. As shown in fig. 20, the originating device 500 includes:

a processing unit 510, configured to perform CSI feedback according to CSI correlations between different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.

In some embodiments, the originating device 500 further comprises a communication unit 520, wherein,

the processing unit 510 is configured to encode channel vectors of K CSI feedback periods in the N CSI feedback periods through a first sender neural network, respectively, to obtain K bit streams; and the processing unit does not encode channel vectors of CSI feedback periods other than the K CSI feedback periods out of the N CSI feedback periods;

The communication unit 520 is configured to send the K bit streams to a sink device.

In some embodiments, the G group { K, N } is configured by the network device through radio resource control, RRC, signaling or downlink control information, DCI, signaling.

In some embodiments, the G group { K, N } is in RRC signaling and/or DCI signaling by the network deviceA bit configuration.

The processing unit 510 is configured to encode channel vectors of P primary CSI feedback periods in the N CSI feedback periods through a second originating neural network, respectively, to obtain P bit streams;

the processing unit 510 is configured to encode channel vectors of Q auxiliary CSI feedback periods in the N CSI feedback periods through the second originating neural network, respectively, to obtain Q bit streams;

the communication unit 520 is configured to send the P bit streams and the Q bit streams to a receiving device respectively; wherein P and Q are both positive integers, and p+q=n.

the processing unit 510 is configured to encode the channel vectors of the N CSI feedback periods through a third originating neural network, to obtain N bit streams;

the communication unit 520 is configured to send the N bit streams to a sink device.

It should be understood that the originating device 500 according to the embodiment of the present application may correspond to the originating device in the embodiment of the method of the present application, and the foregoing and other operations and/or functions of each unit in the originating device 500 are respectively for implementing the corresponding flow of the originating device in the method 300 shown in fig. 18, and are not repeated herein for brevity.

Fig. 21 is a schematic block diagram of a communication device 600 according to an embodiment of the present application. The communication device 600 shown in fig. 21 comprises a processor 610, from which the processor 610 may call and run a computer program to implement the method in an embodiment of the application.

In some embodiments, as shown in fig. 21, the communication device 600 may also include a memory 620. Wherein the processor 610 may call and run a computer program from the memory 620 to implement the method in an embodiment of the application.

The memory 620 may be a separate device from the processor 610 or may be integrated into the processor 610.

In some embodiments, as shown in fig. 21, the communication device 600 may further include a transceiver 630, and the processor 610 may control the transceiver 630 to communicate with other devices, and in particular, may transmit information or data to other devices, or receive information or data transmitted by other devices.

The transceiver 630 may include a transmitter and a receiver, among others. Transceiver 630 may further include antennas, the number of which may be one or more.

In some embodiments, the communication device 600 may be an originating device in the embodiments of the present application, and the communication device 600 may implement corresponding flows implemented by the originating device in the methods in the embodiments of the present application, which are not described herein for brevity.

In some embodiments, the communication device 600 may be a sink device in the embodiments of the present application, and the communication device 600 may implement corresponding flows implemented by the sink device in the methods in the embodiments of the present application, which are not described herein for brevity.

Fig. 22 is a schematic structural view of an apparatus of an embodiment of the present application. The apparatus 700 shown in fig. 22 includes a processor 710, and the processor 710 may call and execute a computer program from a memory to implement the method in an embodiment of the present application.

In some embodiments, as shown in fig. 22, the apparatus 700 may further include a memory 720. Wherein the processor 710 may call and run a computer program from the memory 720 to implement the method in an embodiment of the application.

Wherein the memory 720 may be a separate device from the processor 710 or may be integrated into the processor 710.

In some embodiments, the apparatus 700 may further include an input interface 730. The processor 710 may control the input interface 730 to communicate with other devices or chips, and in particular, may obtain information or data sent by other devices or chips.

In some embodiments, the apparatus 700 may further comprise an output interface 740. The processor 710 may control the output interface 740 to communicate with other devices or chips, and in particular, may output information or data to other devices or chips.

In some embodiments, the apparatus may be applied to an originating device in the embodiments of the present application, and the apparatus may implement corresponding flows implemented by the originating device in each method in the embodiments of the present application, which are not described herein for brevity.

In some embodiments, the apparatus may be applied to a receiving device in the embodiments of the present application, and the apparatus may implement corresponding flows implemented by the receiving device in each method in the embodiments of the present application, which are not described herein for brevity.

In some embodiments, the device according to the embodiments of the present application may also be a chip. For example, a system-on-chip or a system-on-chip, etc.

Fig. 23 is a schematic block diagram of a communication system 800 provided by an embodiment of the present application. As shown in fig. 23, the communication system 800 includes an originating device 810 and a receiving device 820.

The originating device 810 may be used to implement the corresponding functions implemented by the originating device in the above method, and the receiving device 820 may be used to implement the corresponding functions implemented by the receiving device in the above method, which are not described herein for brevity.

It should be appreciated that the processor of an embodiment of the present application may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The processor may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

It will be appreciated that the memory in embodiments of the application may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

It should be understood that the above memory is illustrative but not restrictive, and for example, the memory in the embodiments of the present application may be Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), direct RAM (DR RAM), and the like. That is, the memory in embodiments of the present application is intended to comprise, without being limited to, these and any other suitable types of memory.

The embodiment of the application also provides a computer readable storage medium for storing a computer program.

In some embodiments, the computer readable storage medium may be applied to the originating device in the embodiments of the present application, and the computer program causes a computer to execute corresponding processes implemented by the originating device in the methods in the embodiments of the present application, which are not described herein for brevity.

In some embodiments, the computer readable storage medium may be applied to the sink device in the embodiments of the present application, and the computer program causes a computer to execute corresponding processes implemented by the sink device in the methods in the embodiments of the present application, which are not described herein for brevity.

The embodiment of the application also provides a computer program product comprising computer program instructions.

In some embodiments, the computer program product may be applied to an originating device in the embodiments of the present application, and the computer program instructions cause the computer to execute corresponding processes implemented by the originating device in the methods in the embodiments of the present application, which are not described herein for brevity.

In some embodiments, the computer program product may be applied to the sink device in the embodiments of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the sink device in the methods in the embodiments of the present application, which are not described herein for brevity.

The embodiment of the application also provides a computer program.

In some embodiments, the computer program may be applied to an originating device in the embodiments of the present application, and when the computer program runs on a computer, the computer is caused to execute corresponding processes implemented by the originating device in the methods in the embodiments of the present application, which are not described herein for brevity.

In some embodiments, the computer program may be applied to the receiving device in the embodiments of the present application, and when the computer program runs on a computer, the computer is caused to execute corresponding processes implemented by the receiving device in the methods in the embodiments of the present application, which are not described herein for brevity.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. For such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

A method for feeding back channel information, comprising:

the receiving end equipment acquires target channel vectors of N CSI feedback periods according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.
The method of claim 1, in which the CSI correlation comprises a CSI time domain correlation and/or a CSI frequency domain correlation.
The method of claim 1 or 2, wherein the receiving device obtains the target channel vectors of the N CSI feedback periods according to CSI correlations between different CSI feedback periods of the N CSI feedback periods, including:

the receiving end equipment receives K bit streams sent by the transmitting end equipment, wherein the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback periods in the N CSI feedback periods, K is a positive integer, and K is smaller than N;

The receiving end equipment decodes the K bit streams respectively to obtain K target channel vectors of the K CSI feedback periods;

and the receiving device predicts the K target channel vectors through a first receiving neural network to obtain N-K target channel vectors of the CSI feedback periods except the K CSI feedback periods in the N CSI feedback periods.
The method of claim 3, wherein the receiving device decodes the K bit streams to obtain K target channel vectors for the K CSI feedback periods, respectively, comprising:

and the receiving end equipment decodes the K bit streams through a second receiving end neural network respectively to obtain the K target channel vectors.
The method of claim 4, wherein a bit stream of the K bit streams includes information of S subbands, S being a positive integer, S > 1;

the receiving device decodes the K bit streams through a second receiving neural network to obtain K target channel vectors, including:

the receiving end equipment decodes the bit stream from the j sub-band of the ith-L CSI feedback period to the bit stream on the j sub-band of the ith CSI feedback period through the second receiving end neural network, and decodes the bit stream from the first sub-band to the S sub-band in the ith CSI feedback period through the second receiving end neural network to obtain a target channel vector on the j sub-band of the ith CSI feedback period, wherein i, j and L are positive integers, i is more than or equal to 1 and less than or equal to K, j is more than or equal to 1 and less than or equal to S, and L is less than or equal to i;

And the receiving end equipment acquires the K target channel vectors according to the target channel vectors on the jth sub-band of the ith CSI feedback period.
The method of any of claims 3 to 5, wherein the K CSI feedback periods are first K consecutive CSI feedback periods of the N CSI feedback periods.
The method according to claim 3 to 6,

the values of K and N are determined from G groups { K, N }, G is a positive integer, and G is more than or equal to 2.
The method of claim 7, wherein,

the values of K and N are determined from the G groups { K, N } according to the channel scene.
The method of claim 7 or 8, wherein the G group { K, N } is configured by a network device via radio resource control, RRC, signaling and/or downlink control information, DCI, signaling.
The method of any one of claims 7 to 9, wherein the G group { K, N } is in RRC signaling or DCI signaling by a network deviceA bit configuration, wherein,representing an upward rounding.
The method of claim 1 or 2, wherein the receiving device obtains the target channel vectors of the N CSI feedback periods according to CSI correlations between different CSI feedback periods of the N CSI feedback periods, including:

The receiving end equipment receives P bit streams and Q bit streams sent by the transmitting end equipment; the P bit streams are obtained after the channel vectors of the P primary CSI feedback periods in the N CSI feedback periods are encoded, the Q bit streams are obtained after the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods are encoded, or the Q bit streams are obtained after the difference values of the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods and the channel vectors of the corresponding primary CSI feedback periods are encoded, P and Q are positive integers, and p+q=n;

the receiving end equipment decodes the P bit streams respectively to obtain P target channel vectors of the P main CSI feedback periods;

the receiving end equipment decodes a first bit stream in the Q bit streams and a second bit stream in the P bit streams through a third receiving end neural network respectively to obtain Q target channel vectors of the Q auxiliary CSI feedback periods; the secondary CSI feedback period corresponding to the first bit stream is a secondary CSI feedback period accompanying the primary CSI feedback period corresponding to the second bit stream.
The method of claim 11, wherein the receiving device decodes the P bit streams, respectively, to obtain P target channel vectors for the P primary CSI feedback periods, comprising:

and the receiving end equipment decodes the P bit streams through a fourth receiving end neural network respectively to obtain P target channel vectors of the P main CSI feedback periods.
The method of claim 12, wherein a bit stream of the P bit streams includes information of S subbands, S being a positive integer, S > 1;

the receiving device decodes the P bit streams through a fourth receiving neural network to obtain P target channel vectors of the P main CSI feedback periods, including:

the receiving end equipment decodes the bit stream from the j sub-band of the i-L CSI feedback period to the bit stream on the j sub-band of the i-L CSI feedback period through the fourth receiving end neural network, and decodes the bit stream from the first sub-band to the S sub-band in the i-L CSI feedback period through the fourth receiving end neural network to obtain a target channel vector on the j sub-band of the i-L CSI feedback period, wherein i, j and L are positive integers, i is more than or equal to 1 and less than or equal to P, j is more than or equal to 1 and less than or equal to S, and L is less than or equal to i;

And the receiving end equipment acquires P target channel vectors of the P main CSI feedback periods according to the target channel vectors on the j sub-bands of the i CSI feedback periods.
The method according to any one of claim 11 to 13, wherein,

the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
The method of claim 14, wherein different ones of the Q bitstreams occupy different numbers of bits or wherein different ones of the Q bitstreams occupy the same number of bits.
The method of any of claims 11-15, wherein one primary CSI feedback period of the N CSI feedback periods is accompanied by one or more secondary CSI feedback periods.
The method of any of claims 11-16, wherein a number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is the same or a number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is different.
The method according to any of claims 11 to 17, wherein the primary CSI feedback period and the secondary CSI feedback period of the N CSI feedback periods are configured by a network device through RRC signaling and/or DCI signaling.
The method of claim 1 or 2, wherein the receiving device obtains the target channel vectors of the N CSI feedback periods according to CSI correlations between different CSI feedback periods of the N CSI feedback periods, including:

the receiving end equipment receives N bit streams sent by the transmitting end equipment; wherein, the bit stream in the N bit streams comprises information of S sub-bands, S is a positive integer, and S is more than 1;

the receiving end equipment decodes the bit stream from the j sub-band of the ith-L CSI feedback period to the bit stream on the j sub-band of the ith CSI feedback period through a fifth receiving end neural network, and decodes the bit stream from the first sub-band to the S sub-band in the ith CSI feedback period through the fifth receiving end neural network to obtain a target channel vector on the j sub-band of the ith CSI feedback period, wherein i, j and L are positive integers, i is not less than 1 and not more than N, j is not less than 1 and not more than S, and L is not more than i;

and the receiving end equipment acquires the target channel vectors of the N CSI feedback periods according to the target channel vectors on the j sub-bands of the i CSI feedback periods.
The method of claim 5, 13 or 19, wherein,

The S subbands include at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by information of the secondary feedback subbands in the at least one secondary feedback subband is less than the number of bits occupied by information of the primary feedback subbands in the at least one primary feedback subband.
The method of claim 20, wherein a primary feedback subband and a secondary feedback subband of the S subbands are configured by a network device through RRC signaling and/or DCI signaling.
A method for feeding back channel information, comprising:

the transmitting device performs the CSI feedback according to the CSI correlation among different CSI feedback periods in the N channel state information CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.
The method of claim 22, in which the CSI correlation comprises a CSI time domain correlation and/or a CSI frequency domain correlation.
The method of claim 22 or 23, wherein the originating device performs CSI feedback according to CSI correlation between different CSI feedback periods of the N CSI feedback periods, comprising:

the transmitting device respectively codes channel vectors of K CSI feedback periods in the N CSI feedback periods through a first transmitting neural network to obtain K bit streams; and the originating device does not encode channel vectors of CSI feedback periods other than the K CSI feedback periods of the N CSI feedback periods;

And the transmitting device respectively transmits the K bit streams to the receiving device.
The method of claim 24, wherein a bit stream of the K bit streams comprises information for S subbands, the S subbands comprising at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by the information for the secondary feedback subband in the at least one secondary feedback subband is less than the number of bits occupied by the information for the primary feedback subband in the at least one primary feedback subband, S is a positive integer, and S > 1.
The method of claim 24 or 25, wherein the K CSI feedback periods are first K consecutive CSI feedback periods of the N CSI feedback periods.
The method of any one of claim 24 to 26,

the values of K and N are determined from G groups { K, N }, G is a positive integer, and G is more than or equal to 2.
The method of claim 27, wherein,

the values of K and N are determined from the G groups { K, N } according to the channel scene.
The method of claim 27 or 28, wherein the G group { K, N } is configured by a network device through radio resource control, RRC, signaling or downlink control information, DCI, signaling.
The method of any one of claims 27 to 29, wherein the G group { K, N } is in RRC signaling and/or DCI signaling by a network deviceA bit configuration, wherein,representing an upward rounding.
The method of claim 22 or 23, wherein the originating device performs CSI feedback according to CSI correlation between different CSI feedback periods of the N CSI feedback periods, comprising:

the originating equipment respectively codes channel vectors of P main CSI feedback periods in the N CSI feedback periods through a second originating neural network to obtain P bit streams;

the originating equipment respectively codes channel vectors of Q auxiliary CSI feedback periods in the N CSI feedback periods through the second originating neural network to obtain Q bit streams;

the originating device sends the P bit streams and the Q bit streams to a receiving device respectively; wherein P and Q are both positive integers, and p+q=n.
The method of claim 31, wherein a bit stream of the P bit streams comprises information for S subbands, the S subbands comprising at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by the information for the secondary feedback subband in the at least one secondary feedback subband is less than the number of bits occupied by the information for the primary feedback subband in the at least one primary feedback subband, S is a positive integer, and S > 1.
The method of claim 31 or 32, wherein,

the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
The method of claim 33, wherein different ones of the Q bitstreams occupy different numbers of bits or wherein different ones of the Q bitstreams occupy the same number of bits.
The method of any of claims 31-34, wherein one primary CSI feedback period of the N CSI feedback periods is accompanied by one or more secondary CSI feedback periods.
The method of any of claims 31-35, wherein a number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is the same or a number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is different.
The method of any of claims 31 to 36, wherein the primary CSI feedback period and the secondary CSI feedback period of the N CSI feedback periods are configured by a network device through RRC signaling and/or DCI signaling.
The method of claim 22 or 23, wherein the originating device performs CSI feedback according to CSI correlation between different CSI feedback periods of the N CSI feedback periods, comprising:

the originating equipment respectively encodes the channel vectors of the N CSI feedback periods through a third originating neural network to obtain N bit streams;

and the transmitting device respectively transmits the N bit streams to the receiving device.
The method of claim 38, wherein a bit stream of the N bit streams comprises information for S subbands, the S subbands comprising at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by the information for the secondary feedback subband in the at least one secondary feedback subband is less than the number of bits occupied by the information for the primary feedback subband in the at least one primary feedback subband, S is a positive integer, and S > 1.
The method of claim 25, 31 or 39, wherein the primary and secondary feedback subbands of the S subbands are configured by a network device through RRC signaling and/or DCI signaling.
A sink device, comprising:

the processing unit is used for acquiring target channel vectors of the N CSI feedback periods according to the CSI correlation among different CSI feedback periods in the N CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.
The sink device of claim 41, wherein the CSI correlation comprises a CSI time domain correlation and/or a CSI frequency domain correlation.
The sink device of claim 41 or 42,

the sink device comprises a communication unit, wherein,

the communication unit is used for receiving K bit streams sent by the originating equipment, wherein the K bit streams are respectively obtained by encoding channel vectors of K CSI feedback periods in the N CSI feedback periods, K is a positive integer, and K is smaller than N;

the processing unit is used for respectively decoding the K bit streams to obtain K target channel vectors of the K CSI feedback periods;

the processing unit is used for predicting the K target channel vectors through a first receiving neural network to obtain N-K target channel vectors of the CSI feedback periods except the K CSI feedback periods in the N CSI feedback periods.
The sink device of claim 43, wherein the processing unit is specifically configured to:

and respectively decoding the K bit streams through a second receiving end neural network to obtain the K target channel vectors.
The sink device of claim 44, wherein the bit stream of the K bit streams includes information of S sub-bands, S is a positive integer, and S > 1;

The processing unit is specifically configured to:

decoding bit streams from a j-th sub-band of an i-L-th CSI feedback period to a j-th sub-band of the i-th CSI feedback period through the second receiving neural network, and decoding bit streams from a first sub-band to an S-th sub-band in the i-th CSI feedback period through the second receiving neural network to obtain target channel vectors on the j-th sub-band of the i-th CSI feedback period, wherein i, j and L are positive integers, i is more than or equal to 1 and less than or equal to K, j is more than or equal to 1 and less than or equal to S, and L is less than or equal to i;

and obtaining the K target channel vectors according to the target channel vectors on the jth sub-band of the ith CSI feedback period.
The sink device of any of claims 43-45, wherein the K CSI feedback periods are first K consecutive CSI feedback periods of the N CSI feedback periods.
The sink device of any one of claims 43 to 46,

the values of K and N are determined from G groups { K, N }, G is a positive integer, and G is more than or equal to 2.
The sink device of claim 47,

the values of K and N are determined from the G groups { K, N } according to the channel scene.
The sink device of claim 47 or 48, wherein the G group { K, N } is configured by a network device through radio resource control, RRC, signaling and/or downlink control information, DCI, signaling.
The sink device of any one of claims 47 to 49, wherein the G group { K, N } is in RRC signaling or DCI signaling by a network deviceA bit configuration, wherein,representing an upward rounding.
The sink device of claim 41 or 42,

the sink device comprises a communication unit, wherein,

the communication unit is used for receiving P bit streams and Q bit streams sent by the originating equipment; the P bit streams are obtained after the channel vectors of the P primary CSI feedback periods in the N CSI feedback periods are encoded, the Q bit streams are obtained after the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods are encoded, or the Q bit streams are obtained after the difference values of the channel vectors of the Q secondary CSI feedback periods in the N CSI feedback periods and the channel vectors of the corresponding primary CSI feedback periods are encoded, P and Q are positive integers, and p+q=n;

The processing unit is used for respectively decoding the P bit streams to obtain P target channel vectors of the P main CSI feedback periods;

the processing unit is configured to decode a first bit stream of the Q bit streams and a second bit stream of the P bit streams through a third receiving neural network, so as to obtain Q target channel vectors of the Q auxiliary CSI feedback periods; the secondary CSI feedback period corresponding to the first bit stream is a secondary CSI feedback period accompanying the primary CSI feedback period corresponding to the second bit stream.
The sink device of claim 51, wherein the processing unit is specifically configured to:

and decoding the P bit streams through a fourth receiving end neural network respectively to obtain P target channel vectors of the P main CSI feedback periods.
The sink device of claim 52, wherein the bit stream of the P bit streams includes information of S sub-bands, S is a positive integer, S > 1;

the processing unit is specifically configured to:

decoding bit streams from a j-th sub-band of an i-L-th CSI feedback period to a j-th sub-band of the i-th CSI feedback period through the fourth receiving neural network, and decoding bit streams from a first sub-band to an S-th sub-band in the i-th CSI feedback period through the fourth receiving neural network to obtain target channel vectors on the j-th sub-band of the i-th CSI feedback period, wherein i, j and L are positive integers, i is more than or equal to 1 and less than or equal to P, j is more than or equal to 1 and less than or equal to S, and L is less than or equal to i; and obtaining P target channel vectors of the P main CSI feedback periods according to the target channel vectors on the j sub-bands of the i CSI feedback periods.
The sink device of any one of claims 51 to 53,

the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
The sink device of claim 54, wherein different ones of the Q bit streams occupy different numbers of bits or wherein different ones of the Q bit streams occupy the same number of bits.
The sink device of any one of claims 51 to 55, wherein one primary CSI feedback period of the N CSI feedback periods is accompanied by one or more secondary CSI feedback periods.
The sink device of any one of claims 51 to 56, wherein the number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is the same or the number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is different.
The sink device of any of claims 51 to 57, wherein the primary CSI feedback period and the secondary CSI feedback period of the N CSI feedback periods are configured by a network device through RRC signaling and/or DCI signaling.
The sink device of claim 41 or 42,

the sink device comprises a communication unit, wherein,

the communication unit is used for receiving N bit streams sent by the originating equipment; wherein, the bit stream in the N bit streams comprises information of S sub-bands, S is a positive integer, and S is more than 1;

the processing unit is used for decoding bit streams from a j-th sub-band of an i-L-th CSI feedback period to a j-th sub-band of the i-th CSI feedback period through a fifth receiving end neural network, and decoding bit streams from a first sub-band to an S-th sub-band in the i-th CSI feedback period through the fifth receiving end neural network to obtain target channel vectors on the j-th sub-band of the i-th CSI feedback period, wherein i, j and L are positive integers, i is not less than 1 and not more than N, j is not less than 1 and not more than S, and L is not more than i;

the processing unit is configured to obtain the target channel vectors of the N CSI feedback periods according to the target channel vector on the j-th subband of the i-th CSI feedback period.
The sink device of claim 45, 53 or 59,

the S subbands include at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by information of the secondary feedback subbands in the at least one secondary feedback subband is less than the number of bits occupied by information of the primary feedback subbands in the at least one primary feedback subband.
The sink device of claim 60, wherein the primary feedback subbands and the secondary feedback subbands in the S subbands are configured by a network device through RRC signaling and/or DCI signaling.
An originating device, comprising:

the processing unit is used for carrying out CSI feedback according to the CSI correlation among different CSI feedback periods in the N channel state information CSI feedback periods; wherein N is a positive integer, and N is more than or equal to 2.
The originating device of claim 62, wherein the CSI correlation comprises a CSI time domain correlation and/or a CSI frequency domain correlation.
The originating device of claim 62 or 63,

the originating device further comprises a communication unit, wherein,

the processing unit is used for respectively encoding channel vectors of K CSI feedback periods in the N CSI feedback periods through a first sender neural network to obtain K bit streams; and the processing unit does not encode channel vectors of CSI feedback periods other than the K CSI feedback periods out of the N CSI feedback periods;

the communication unit is used for respectively sending the K bit streams to the receiving end equipment.
The originating device of claim 64, wherein a bit stream of the K bit streams comprises information for S subbands, the S subbands comprising at least one primary feedback subband and at least one secondary feedback subband, wherein the number of bits occupied by the information for the secondary feedback subband in the at least one secondary feedback subband is less than the number of bits occupied by the information for the primary feedback subband in the at least one primary feedback subband, S is a positive integer, and S > 1.
The originating device of claim 64 or 65, wherein the K CSI feedback periods are first K consecutive CSI feedback periods of the N CSI feedback periods.
The originating device of any one of claims 64-66,

the values of K and N are determined from G groups { K, N }, G is a positive integer, and G is more than or equal to 2.
The originating device of claim 67,

the values of K and N are determined from the G groups { K, N } according to the channel scene.
The originating device of claim 67 or 68, wherein the G group { K, N } is configured by a network device via radio resource control, RRC, signaling or downlink control information, DCI, signaling.
The originating device of any one of claims 67-69, wherein the G group { K, N } is in RRC signaling and/or DCI signaling by a network deviceA bit configuration, wherein,representing an upward rounding.
The originating device of claim 62 or 63,

the originating device further comprises a communication unit, wherein,

the processing unit is used for respectively encoding channel vectors of P main CSI feedback periods in the N CSI feedback periods through a second originating neural network to obtain P bit streams;

The processing unit is configured to encode channel vectors of Q auxiliary CSI feedback periods in the N CSI feedback periods through the second originating neural network, respectively, to obtain Q bit streams;

the communication unit is used for respectively sending the P bit streams and the Q bit streams to the receiving end equipment; wherein P and Q are both positive integers, and p+q=n.
The originating device of claim 71, wherein a bit stream of the P bit streams comprises information for S subbands, the S subbands comprising at least one primary feedback subband and at least one secondary feedback subband, wherein the information for the secondary feedback subband in the at least one secondary feedback subband occupies fewer bits than the information for the primary feedback subband in the at least one primary feedback subband, S is a positive integer, and S > 1.
The originating device of claim 71 or 72,

the number of bits occupied by one of the Q bit streams is smaller than the number of bits occupied by one of the P bit streams.
The originating device of claim 73, wherein different ones of the Q bitstreams occupy different numbers of bits or wherein different ones of the Q bitstreams occupy the same number of bits.
The originating device of any one of claims 71-74, wherein one primary CSI feedback period of the N CSI feedback periods is accompanied by one or more secondary CSI feedback periods.
The originating device of any of claims 71-75, wherein a number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is the same or a number of secondary CSI feedback periods accompanying different primary CSI feedback periods in the N CSI feedback periods is different.
The originating device of any of claims 71-76, wherein the primary CSI feedback period and the secondary CSI feedback period of the N CSI feedback periods are configured by a network device through RRC signaling and/or DCI signaling.
The originating device of claim 62 or 63,

the originating device further comprises a communication unit, wherein,

the processing unit is used for respectively encoding the channel vectors of the N CSI feedback periods through a third originating neural network to obtain N bit streams;

the communication unit is used for respectively sending the N bit streams to the receiving end equipment.
The originating device of claim 78, wherein a bit stream of the N bit streams comprises information for S subbands, the S subbands comprising at least one primary feedback subband and at least one secondary feedback subband, wherein the information for the secondary feedback subband in the at least one secondary feedback subband occupies fewer bits than the information for the primary feedback subband in the at least one primary feedback subband, S is a positive integer, and S > 1.
The originating device of claim 65, 71 or 79, wherein a primary feedback subband and a secondary feedback subband of the S subbands are configured by a network device through RRC signaling and/or DCI signaling.
A sink device, comprising: a processor and a memory for storing a computer program, the processor being adapted to invoke and run the computer program stored in the memory to perform the method of any of claims 1 to 21.
An originating device, comprising: a processor and a memory for storing a computer program, the processor being for invoking and running the computer program stored in the memory, performing the method of any of claims 22 to 40.
A chip, comprising: a processor for calling and running a computer program from a memory, causing a device on which the chip is mounted to perform the method of any one of claims 1 to 21.
A chip, comprising: a processor for calling and running a computer program from a memory, causing a device on which the chip is mounted to perform the method of any of claims 22 to 40.
A computer readable storage medium storing a computer program for causing a computer to perform the method of any one of claims 1 to 21.
A computer readable storage medium storing a computer program for causing a computer to perform the method of any one of claims 22 to 40.
A computer program product comprising computer program instructions for causing a computer to perform the method of any one of claims 1 to 21.
A computer program product comprising computer program instructions for causing a computer to perform the method of any one of claims 22 to 40.
A computer program, characterized in that the computer program causes a computer to perform the method of any one of claims 1 to 21.
A computer program, characterized in that the computer program causes a computer to perform the method of any one of claims 22 to 40.