WO2024065832A1

WO2024065832A1 - Information sending method and apparatus, information receiving method and apparatus, and communication apparatus and storage medium

Info

Publication number: WO2024065832A1
Application number: PCT/CN2022/123622
Authority: WO
Inventors: 高雪媛; 刘敏; 周华; 赵中原
Original assignee: 北京小米移动软件有限公司
Priority date: 2022-09-30
Filing date: 2022-09-30
Publication date: 2024-04-04

Abstract

The present disclosure relates to an information sending method and apparatus, an information receiving method and apparatus, and a communication apparatus and a storage medium. The information sending method comprises: preprocessing estimated full-channel information according to a first number of spatial-domain basis vectors and a second number of frequency-domain basis vectors, so as to obtain effective channel information; calculating a feature vector of the effective channel information; and inputting the feature vector into a model, so as to obtain CSI-related information, and sending the CSI-related information to a network device. According to the present disclosure, a feature vector of effective channel information can be further calculated, such that the dimension of the feature vector is unrelated to the number Nr of receiving antenna ports. Therefore, the feature vector is used as an input of a model, and it is not necessary to train different models by means of taking into account scenarios with different numbers of receiving antenna ports, thereby facilitating a reduction in the number of models that are required to be trained, that is, reducing the number of models that are required to be sent to a terminal and the number of models that are required to be stored in the terminal, and thus facilitating a reduction in signaling overheads and saving on storage space of the terminal.

Description

Information sending and receiving method and device, communication device and storage medium

Technical Field

The present disclosure relates to the field of communication technology, and in particular, to an information sending method, an information receiving method, an information sending device, an information receiving device, a communication device, and a computer-readable storage medium.

Background technique

The terminal can report channel state information (CSI, Channel State Information) to the network device so that the network device can determine the current channel status and make appropriate configurations to ensure good communication effects.

In order to reduce the overhead of reporting CSI and improve the accuracy of CSI reporting, the relevant technology proposes a bilateral model based on artificial intelligence (AI)/machine learning (ML) to determine the CSI generation part and the CSI recovery part to achieve the above purpose.

However, the input of the model in the related technology is data related to the number of antenna ports. Using this data as the input of the model, different models need to be trained when facing scenarios with different numbers of antenna ports, which results in a large number of models needing to be configured for the terminal, increasing signaling overhead and occupying too much storage space of the terminal.

Summary of the invention

In view of this, the embodiments of the present disclosure propose an information sending method, an information receiving method, an information sending device, an information receiving device, a communication device and a computer-readable storage medium to solve the technical problems in the related art.

According to a first aspect of an embodiment of the present disclosure, a method for sending information is proposed, which is executed by a terminal, and the method includes: preprocessing the estimated full channel information according to a first number of spatial domain basis vectors and a second number of frequency domain basis vectors to obtain effective channel information; calculating a feature vector of the effective channel information; inputting the feature vector into a first artificial intelligence and/or machine learning model to obtain CSI-related information, and sending the CSI-related information to a network device.

According to a second aspect of an embodiment of the present disclosure, an information receiving method is proposed, which is executed by a network device. The method includes: receiving CSI-related information sent by the above-mentioned information sending method of a terminal.

According to the third aspect of an embodiment of the present disclosure, an information sending device is proposed, comprising: a processing module, configured to pre-process the estimated full channel information according to a first number of spatial domain basis vectors and a second number of frequency domain basis vectors to obtain effective channel information; calculate a feature vector of the effective channel information; input the feature vector into a first artificial intelligence and/or machine learning model to obtain CSI-related information; and a sending module, configured to send the CSI-related information to a network device.

According to a fourth aspect of an embodiment of the present disclosure, an information receiving device is proposed, the device comprising: a receiving module configured to receive CSI-related information sent by the above-mentioned information sending method of a terminal.

According to a fifth aspect of an embodiment of the present disclosure, an information sending and receiving system is proposed, comprising a terminal and a network side device, wherein the terminal is configured to implement the above-mentioned information sending method, and the network device is configured to implement the above-mentioned information receiving method.

According to a sixth aspect of an embodiment of the present disclosure, a communication device is proposed, comprising: a processor; and a memory for storing a computer program; wherein when the computer program is executed by the processor, the above-mentioned information sending method is implemented.

According to a seventh aspect of an embodiment of the present disclosure, a communication device is proposed, comprising: a processor; and a memory for storing a computer program; wherein, when the computer program is executed by the processor, the above-mentioned information receiving method is implemented.

According to an eighth aspect of an embodiment of the present disclosure, a computer-readable storage medium is proposed for storing a computer program. When the computer program is executed by a processor, the above-mentioned information sending method is implemented.

According to a ninth aspect of an embodiment of the present disclosure, a computer-readable storage medium is proposed for storing a computer program. When the computer program is executed by a processor, the above-mentioned information receiving method is implemented.

According to the embodiments of the present disclosure, the eigenvector of the effective channel information can be further calculated, for example, by performing eigenvalue analysis on the effective channel information to obtain the eigenvector, then the dimension of the eigenvector is irrelevant to the number of receiving antenna ports Nr. Thus, by using the eigenvector as the input of the first artificial intelligence and/or machine learning model, there is no need to train different models considering different scenarios of the number of receiving antenna ports, which is conducive to reducing the number of models that need to be trained, thereby reducing the number of models that need to be sent to the terminal and the number of models that need to be saved by the terminal, which is conducive to saving signaling overhead and saving storage space of the terminal.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a schematic diagram showing an application scenario according to an embodiment of the present disclosure.

FIG2 is a schematic flow chart of an information sending method according to an embodiment of the present disclosure.

FIG3 is a schematic flow chart of another information sending method according to an embodiment of the present disclosure.

FIG. 4 is a schematic flow chart of yet another information sending method according to an embodiment of the present disclosure.

FIG5 is a schematic flowchart showing another information sending method according to an embodiment of the present disclosure.

FIG6 is a schematic flow chart of an information receiving method according to an embodiment of the present disclosure.

FIG. 7 is a schematic block diagram of an information sending device according to an embodiment of the present disclosure.

FIG8 is a schematic block diagram of an information receiving device according to an embodiment of the present disclosure.

FIG. 9 is a schematic block diagram of a device for receiving information according to an embodiment of the present disclosure.

FIG. 10 is a schematic block diagram of a device for sending information according to an embodiment of the present disclosure.

Detailed ways

The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

The terms used in the disclosed embodiments are only for the purpose of describing specific embodiments and are not intended to limit the disclosed embodiments. The singular forms of "a" and "the" used in the disclosed embodiments and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and/or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

For the purpose of brevity and ease of understanding, the terms used herein to characterize size relationships are "greater than" or "less than", "higher than" or "lower than". However, it is understood by those skilled in the art that the term "greater than" also covers the meaning of "greater than or equal to", and "less than" also covers the meaning of "less than or equal to", the term "higher than" covers the meaning of "higher than or equal to", and "lower than" also covers the meaning of "lower than or equal to".

As shown in FIG1 , a CSI generation partial model based on AI/ML is provided on the terminal side, and a CSI recovery partial model based on AI/ML is provided on the network device side.

The terminal determines the input data by detecting the downlink channel information sent by the network device, and inputs the input data into the CSI generation model. The CSI generation model can compress the input data and quantize the compressed data (for example, obtain a binary bit stream) and send it to the network device.

The network device inputs the quantized data received from the terminal into the CSI recovery partial model, and the CSI recovery partial model can recover the quantized data to obtain recovered input data, such as CSI-related information.

However, the dimension of the input data determined by the terminal is related to the port configuration of the transmitting antenna (network side antenna) of the network device and the number of frequency domain units. Different CSI generation partial models need to be trained for different transmitting antenna port configurations. The CSI generation partial model requires the network device to configure it to the terminal, and the terminal needs to store it. Too many CSI generation partial models will increase the signaling overhead and occupy the storage space of the terminal.

To address the above problems, the input data can be preprocessed using the spatial domain basis (SD basis) and frequency domain basis (FD basis) of DFT (Discrete Fourier Transform) to obtain the main characteristic information of the channel. The information obtained after preprocessing is independent of the transmitting antenna port configuration and the number of frequency domain units, which is beneficial to reducing the number of CSI generation models that need to be trained.

However, on the one hand, although the dimension of the information obtained by preprocessing with the SD basis and FD basis of DFT has nothing to do with the configuration of the transmitting antenna port, it is related to the number of receiving antenna (terminal side antenna) ports. Different CSI generation partial models still need to be trained for different numbers of receiving antenna ports, and there is still the problem of needing to train too many CSI generation partial models.

On the other hand, since both SD basis and FD basis are DFT basis (discrete Fourier transform basis vector), the information obtained after SD basis and FD basis preprocessing has the characteristics of DFT codebook. However, due to the quantization characteristics of the DFT codebook, there will be more information loss when the CSI recovery model recovers the quantized data, which affects the network equipment's determination of the downlink channel status.

FIG2 is a schematic flow chart of a method for sending information according to an embodiment of the present disclosure. The method for sending information shown in this embodiment can be executed by a terminal, and the terminal includes but is not limited to a communication device such as a mobile phone, a tablet computer, a wearable device, a sensor, an Internet of Things device, etc. The terminal can communicate with a network device, and the network device includes but is not limited to a network device in any generation of communication systems such as 4G, 5G, and 6G, such as a base station, a core network, etc.

As shown in FIG. 2 , the information sending method may include the following steps:

In step S201, the estimated full channel information is preprocessed according to a first number of spatial domain basis vectors and a second number of frequency domain basis vectors to obtain effective channel information;

In step S202, a characteristic vector of the effective channel information is calculated;

In step S203, the feature vector is input into a first artificial intelligence and/or machine learning model to obtain CSI-related information, and the CSI-related information is sent to a network device.

In one embodiment, the terminal can receive a downlink state information reference signal (CSI-RS, Channel State Information Reference Signal) sent by a network device, and determine the estimated downlink full channel information based on the CSI-RS, wherein the estimated downlink full channel information includes at least spatial domain channel information and frequency domain channel information.

Further, the spatial domain basis vectors and the frequency domain basis vectors may be determined according to the estimated full channel information. How to determine the spatial domain basis vectors and the frequency domain basis vectors will be described in subsequent embodiments.

Next, the estimated full channel information can be preprocessed according to the first number of spatial domain basis vectors and the second number of frequency domain basis vectors (the preprocessing method can refer to the relevant technology and is not described in detail in this disclosure) to obtain effective channel information, and the dimension of the effective channel information is determined based on the number of receiving antenna ports of the terminal, the first number and the second number.

For example, when a terminal communicates through a dual-polarized antenna, the first number is L, the second number is M, and the number of receiving antenna ports is Nr, then the dimension of the effective channel information is equal to twice the product of Nr and L and M, that is, Nr×2LM. It can be seen that the dimension of the effective channel information is related to the number of receiving antenna ports Nr.

According to the embodiments of the present disclosure, the eigenvector of the effective channel information can be further calculated, for example, by performing eigenvalue analysis on the effective channel information to obtain the eigenvector, then the dimension of the eigenvector is irrelevant to the number of receiving antenna ports Nr. Thus, by using the eigenvector as the input of the first artificial intelligence and/or machine learning model (such as the above-mentioned CSI generation part model), there is no need to train different models considering different scenarios of the number of receiving antenna ports, which is beneficial to reduce the number of models that need to be trained, thereby reducing the number of models that need to be sent to the terminal and the number of models that need to be saved by the terminal, which is beneficial to saving signaling overhead and saving storage space of the terminal. In all embodiments of the present disclosure, the first number L and the second number M may be the same or different, and this is not limited in the embodiments of the present disclosure.

FIG3 is a schematic flow chart of another information sending method according to an embodiment of the present disclosure. As shown in FIG3, the method further includes:

In step S301, current statistical downlink full channel information is determined according to current estimated downlink full channel information and historical statistical downlink full channel information;

In step S302, eigenvalue decomposition is performed according to the current statistical downlink full channel information to obtain the first number of spatial domain basis vectors and the second number of frequency domain basis vectors;

The types of the spatial domain basis vector and the frequency domain basis vector are eigenvectors.

In one embodiment, for example, the current is t, and the history is t-1, which refers to any time point before the current time. The current estimated downlink full channel information can be recorded as H _t , the historical statistical downlink full channel information can be recorded as H' _t-1 , and the current statistical downlink full channel information can be recorded as H' _t . Exemplarily, a filtering algorithm with α<1 can be used to calculate H' _t , for example, H' _t =αH _t +(1-α)H' _t-1 .

Further, eigenvalue decomposition is performed based on the statistical downlink full channel information at the current moment. For example, the transposed matrix (H' _t ) ^H of H' _t can be determined first, and then (H' _t ) ^H H' _t is subjected to eigenvalue decomposition to obtain multiple eigenvectors, from which the eigenvectors with the largest eigenvalues of the first number are selected as the first number of spatial basis vectors; similarly, H' _t (H' _t ) ^H can be subjected to eigenvalue decomposition to obtain multiple eigenvectors, from which the eigenvectors with the largest eigenvalues of the second number are selected as the second number of frequency domain basis vectors. The first number of spatial basis vectors and the second number of frequency domain basis vectors obtained in this way are both of the type of eigenvectors.

On this basis, the terminal can preprocess the current statistical downlink full channel information through the first number of spatial basis vectors and the second number of frequency domain basis vectors to obtain effective channel information.

The dimension is Nr×2LM.

Further eigenvalue decomposition, for example

or

Perform eigenvalue decomposition to obtain multiple eigenvectors, and the dimension of the obtained eigenvectors is independent of the number Nr of receiving antenna ports.

In addition, since the first number of spatial domain basis vectors and the second number of frequency domain basis vectors in this embodiment are both characteristic vectors rather than DFT basis vectors, the effective channel information obtained after preprocessing of the spatial domain basis vectors and the frequency domain basis vectors does not have the characteristics of the DFT codebook, and will not cause excessive information loss in the CSI recovery part model for recovering the quantized data due to the quantization characteristics of the DFT codebook. This is beneficial to ensure that the network equipment accurately recovers the information reported by the terminal so as to accurately determine the status of the downlink channel.

FIG4 is a schematic flow chart of another information sending method according to an embodiment of the present disclosure. As shown in FIG4, the method further includes:

In step S401, the first number of spatial domain basis vectors and the second number of frequency domain basis vectors are calculated according to the estimated downlink full channel information, wherein the types of the spatial domain basis vectors and the frequency domain basis vectors are discrete Fourier transform DFT basis vectors (DFT basis).

In one embodiment, the terminal calculates a first number of spatial basis vectors and a second number of frequency domain basis vectors of the DFT basis vector type according to the estimated downlink full channel information, and then pre-processes the statistical downlink full channel information at the current moment through the first number of spatial basis vectors and the second number of frequency domain basis vectors to obtain effective channel information.

The dimension is Nr×2LM.

Further eigenvalue decomposition, for example

or

FIG5 is a schematic flow chart of another information sending method according to an embodiment of the present disclosure. As shown in FIG5, the method further includes:

In step S501, the spatial domain basis vectors and the frequency domain basis vectors are reported to the network device.

In one embodiment, the terminal can quantize the CSI-related information and then report it, and the network device can input the quantized CSI-related information into a second artificial intelligence and/or machine learning model (e.g., a CSI recovery partial model) to obtain the recovery information of the estimated full channel information, and then based on the recovery information, the frequency domain basis vectors and the spatial domain basis vectors, construct the estimated full channel information, and/or channel information feature vectors, and/or precoding for downlink data transmission.

That is, the network device constructs (which can be called recovery) an estimate of the full channel information, which needs to be implemented based on the spatial domain basis vectors and the frequency domain basis vectors. Therefore, the terminal can report the spatial domain basis vectors and the frequency domain basis vectors to the network device for use by the network device.

In one embodiment, reporting the spatial domain basis vector and the frequency domain basis vector to the network device includes:

Reporting the spatial domain basis vector and the frequency domain basis vector to the network device respectively; and/or

The spatial domain basis vector and the frequency domain basis vector are jointly reported to the network device.

There are two ways to report spatial domain basis vectors and frequency domain basis vectors:

One is to report the spatial domain basis vectors and the frequency domain basis vectors separately, for example, report the spatial domain basis vectors and the frequency domain basis vectors as two independent values, or report the indexes corresponding to the spatial domain basis vectors and the frequency domain basis vectors respectively.

Another method is to report the spatial domain basis vector and the frequency domain basis vector jointly. For example, the spatial domain basis vector and the frequency domain basis vector pair can be reported. For example, they can be reported in the form of tensor product. For example, if the spatial domain basis vector is f and the frequency domain basis vector is s, then

Represents a tensor product.

When the type of the spatial basis vector is a feature vector, the real part and the imaginary part of the spatial basis vector are quantized respectively and then reported to the network device; and/or

When the type of the frequency domain basis vector is a feature vector, the real part and the imaginary part of the frequency domain basis vector are quantized respectively and then reported to the network device.

Since the spatial basis vector is of the type of eigenvector, the spatial basis vector can be represented in complex form, and the complex number includes a real part and an imaginary part. For the convenience of quantization, the real part and the imaginary part can be quantized separately and then reported to the network device. Similarly, when the frequency domain basis vector is of the type of eigenvector, the frequency domain basis vector can be represented in complex form, and the complex number includes a real part and an imaginary part. For the convenience of quantization, the real part and the imaginary part can be quantized separately and then reported to the network device.

Representing the spatial domain basis vectors and/or the frequency domain basis vectors as a linear combination of a plurality of orthogonal basis vectors and a plurality of coefficients corresponding to the orthogonal basis vectors;

The coefficients corresponding to the multiple orthogonal basis vectors are reported to the network device.

For spatial domain basis vectors and/or frequency domain basis vectors, they can be represented as a linear combination of multiple orthogonal basis vectors and multiple orthogonal basis vector corresponding coefficients, wherein the terminal and the network device can know the way of representing the linear combination, that is, the network device can determine how the terminal represents the spatial domain basis vectors and/or frequency domain basis vectors as a linear combination of multiple orthogonal basis vectors and multiple orthogonal basis vector corresponding coefficients. Since the orthogonal basis vectors are relatively fixed in the linear combination, it is only necessary to report the multiple orthogonal basis vector corresponding coefficients to the network device.

It should be noted that the processing method for spatial domain basis vectors and frequency domain basis vectors during the reporting process is not limited to the above-mentioned embodiments. For example, the amplitude value and phase value of each element in the spatial domain basis vector can also be determined, and then the amplitude value and phase value of each element in the spatial domain basis vector are quantized separately and reported to the network device; accordingly, the amplitude value and phase value of each element in the frequency domain basis vector can be determined, and then the amplitude value and phase value of each element in the frequency domain basis vector are quantized separately and reported to the network device.

In one embodiment, the effective channel information includes at least one of the following:

one or more feature vectors of data transmission layers among feature vectors of multiple data transmission layers obtained by preprocessing the estimated full channel information using the first number of spatial basis vectors and the second number of frequency domain basis vectors;

The estimated full channel information is preprocessed by using the first number of spatial basis vectors and the second number of frequency domain basis vectors to obtain channel information of one or more receiving antenna ports among the channel information of multiple receiving antenna ports.

The effective channel information obtained by preprocessing the estimated full channel information by using a first number of spatial domain basis vectors and a second number of frequency domain basis vectors may be feature vectors of one or more data transmission layers among feature vectors of multiple data transmission layers, such as feature vectors of rank=v layers, or may be channel information of one or more receiving antenna ports among channel information of multiple receiving antenna ports, such as channel information of the rth antenna port among Nr antenna ports, or channel information of all Nr antenna ports.

In one embodiment, the number of dimensions of the effective channel information is determined based on at least one of the following:

the first quantity and the second quantity;

The number of pairs of the spatial domain basis vectors and the frequency domain basis vectors;

Number of receive antenna ports.

For example, it may be twice the product of the number of receiving antenna ports and the first number and the second number.

In one embodiment, the first number and the second number are determined based on at least one of the following:

the first number of the network device configurations;

the second number of the network device configurations;

The sum of the first number and the second number of the network device configurations;

The product of the first number and the second number of the network device configurations;

Downlink channel information.

The network device can directly configure the first quantity and the second quantity for the terminal; it can also configure the sum or product of the first quantity and the second quantity for the terminal. The terminal can autonomously determine the first quantity or the second quantity, and then determine the second quantity or the first quantity based on the sum or product of the first quantity and the second quantity configured by the network device. For example, the network device is configured with the sum of the first quantity and the second quantity. After the terminal autonomously determines the first quantity, it can be determined that the second quantity is equal to the sum configured by the network device minus the first quantity; the terminal can also determine the first quantity and the second quantity by monitoring the downlink channel information. For example, if it is determined based on the downlink channel information that the downlink channel quality is relatively good, then the first quantity and/or the second quantity can be relatively small. For example, if it is determined based on the downlink channel information that the downlink channel quality is relatively poor, then the first quantity and/or the second quantity can be relatively large.

Those skilled in the art can understand that the aforementioned multiple embodiments executed by the terminal can be implemented separately or combined in any manner, and the embodiments of the present disclosure are not limited to this.

Figure 6 is a schematic flow chart of an information receiving method according to an embodiment of the present disclosure. The information receiving method shown in this embodiment can be executed by a network device, and the network device can communicate with a terminal, the network device includes but is not limited to a base station in a communication system such as a 4G base station, a 5G base station, and a 6G base station, and the terminal includes but is not limited to a mobile phone, a tablet computer, a wearable device, a sensor, an Internet of Things device, and other communication devices.

As shown in FIG6 , the information receiving method may include the following steps:

In step S601, a receiving terminal sends CSI-related information according to the method described in any one of the above embodiments.

In one embodiment, the method further comprises:

Inputting the CSI-related information into a second artificial intelligence and/or machine learning model to obtain recovered information of the estimated full channel information;

The estimated full channel information and/or channel information eigenvectors and/or precoding for downlink data transmission are constructed according to the recovered information, the frequency domain basis vectors and the spatial domain basis vectors.

For example, taking the case where the terminal communicates via a dual-polarized antenna, the first number L=4, the second number M=4, and the number of receiving antenna ports Nr=2, the dimension of the effective channel information is equal to twice the basis of Nr and L and M, that is, 64. Then, the eigenvector of the effective channel information can be calculated, and the eigenvector is input into the CSI generation model for compression to generate 20 codewords, and each codeword can be quantized by 2 bits to obtain a 40-bit data stream to be sent to the network device.

The network device can input the received 40-bit data stream into a second artificial intelligence and/or machine learning model, such as a CSI recovery partial model, to recover information similar to the eigenvector as the recovery information, and then construct the estimated full channel information based on the frequency domain basis vector and the spatial domain basis vector, thereby determining the downlink channel situation. Of course, channel information eigenvectors, precoding for downlink data transmission, etc. can also be constructed.

In one embodiment, the spatial domain basis vectors and the frequency domain basis vectors include at least one of the following:

The spatial domain basis vectors and the frequency domain basis vectors reported by the terminal when sending the CSI related information;

The spatial domain basis vectors and frequency domain basis vectors reported historically by the terminal.

When sending CSI-related information (quantized data stream), the terminal can also report the spatial domain basis vectors and frequency domain basis vectors to the network device. Then, when the network device constructs the estimated full channel information, it can use the spatial domain basis vectors and frequency domain basis vectors reported by the terminal.

If the terminal does not report the spatial domain basis vectors and frequency domain basis vectors to the network device when sending CSI-related information (quantized data stream), the network device can use the spatial domain basis vectors and frequency domain basis vectors reported by the terminal in the past when constructing the estimated full channel information.

Corresponding to the aforementioned embodiments of the information sending method and the information receiving method, the present disclosure also provides embodiments of an information sending device and an information receiving device.

FIG7 is a schematic block diagram of an information sending device according to an embodiment of the present disclosure. The information sending device shown in this embodiment may be a terminal, or a device composed of modules in a terminal, and the terminal includes but is not limited to a mobile phone, a tablet computer, a wearable device, a sensor, an Internet of Things device and other communication devices. The terminal may communicate with a network device, and the network device includes but is not limited to a network device in a 4G, 5G, 6G and other communication systems, such as a base station, a core network and the like.

As shown in FIG. 7 , the information sending device includes:

The processing module 701 is configured to pre-process the estimated full channel information according to a first number of spatial basis vectors and a second number of frequency domain basis vectors to obtain effective channel information; calculate a feature vector of the effective channel information; and input the feature vector into a first artificial intelligence and/or machine learning model to obtain CSI related information;

The sending module 702 is configured to send the CSI related information to a network device.

In one embodiment, the processing module is further configured to determine the current statistical downlink full channel information based on the current estimated downlink full channel information and the historical statistical downlink full channel information; perform eigenvalue decomposition based on the current statistical downlink full channel information to obtain the first number of spatial domain basis vectors and the second number of frequency domain basis vectors; wherein the type of the spatial domain basis vector and the frequency domain basis vector is eigenvector.

In one embodiment, the processing module is further configured to calculate the first number of spatial domain basis vectors and the second number of frequency domain basis vectors based on the estimated downlink full channel information, wherein the types of the spatial domain basis vectors and the frequency domain basis vectors are discrete Fourier transform DFT basis vectors.

In one embodiment, the sending module is further configured to report the spatial domain basis vectors and the frequency domain basis vectors to the network device.

In one embodiment, the sending module is configured to report the spatial domain basis vectors and the frequency domain basis vectors to the network device separately; and/or report the spatial domain basis vectors and the frequency domain basis vectors jointly to the network device.

In one embodiment, the sending module is configured to, when the type of the spatial domain basis vector is a eigenvector, quantize the real part and the imaginary part of the spatial domain basis vector separately and report them to the network device; and/or when the type of the frequency domain basis vector is a eigenvector, quantize the real part and the imaginary part of the frequency domain basis vector separately and report them to the network device.

In one embodiment, the processing module is configured to represent the spatial domain basis vectors and/or the frequency domain basis vectors as a linear combination of multiple orthogonal basis vectors and coefficients corresponding to multiple orthogonal basis vectors; the sending module is configured to report the coefficients corresponding to the multiple orthogonal basis vectors to the network device.

In one embodiment, the number of dimensions of the effective channel information is determined based on at least one of: the first number and the second number; the number of pairs of the spatial domain basis vectors and the frequency domain basis vectors; and the number of receiving antenna ports.

In one embodiment, the first number and the second number are determined based on at least one of: the first number configured by the network device; the second number configured by the network device; the sum of the first number and the second number configured by the network device; the product of the first number and the second number configured by the network device; downlink channel information.

FIG8 is a schematic block diagram of an information receiving device according to an embodiment of the present disclosure. The information receiving device shown in this embodiment may be a network device, or a device composed of modules in a network device, and the network device may communicate with a terminal. The terminal includes but is not limited to communication devices such as mobile phones, tablet computers, wearable devices, sensors, and Internet of Things devices. The network device includes but is not limited to network devices in 4G, 5G, 6G and other communication systems, such as base stations, core networks, etc.

As shown in FIG8 , the information receiving device includes:

The receiving module 801 is configured to receive CSI-related information sent by a terminal according to the apparatus described in any of the above embodiments.

In one embodiment, the device also includes: a processing module, configured to input the CSI-related information into a second artificial intelligence and/or machine learning model to obtain the recovery information of the estimated full channel information; based on the recovery information, the frequency domain basis vectors and the spatial domain basis vectors, construct the estimated full channel information, and/or channel information feature vectors, and/or precoding for downlink data transmission.

In one embodiment, the spatial domain basis vectors and the frequency domain basis vectors include at least one of the following: the spatial domain basis vectors and the frequency domain basis vectors reported by the terminal when sending the CSI-related information; the spatial domain basis vectors and the frequency domain basis vectors reported historically by the terminal.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the relevant method, and will not be elaborated here.

For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

An embodiment of the present disclosure further proposes an information sending and receiving system, comprising a terminal and a network side device, wherein the terminal is configured to implement the information sending method described in any of the above embodiments, and the network device is configured to implement the information receiving method described in any of the above embodiments.

An embodiment of the present disclosure further proposes a communication device, comprising: a processor; and a memory for storing a computer program; wherein when the computer program is executed by the processor, the information sending method described in any of the above embodiments is implemented.

An embodiment of the present disclosure further proposes a communication device, comprising: a processor; and a memory for storing a computer program; wherein when the computer program is executed by the processor, the information receiving method described in any of the above embodiments is implemented.

The embodiments of the present disclosure further provide a computer-readable storage medium for storing a computer program. When the computer program is executed by a processor, the information sending method described in any of the above embodiments is implemented.

An embodiment of the present disclosure further provides a computer-readable storage medium for storing a computer program. When the computer program is executed by a processor, the information receiving method described in any of the above embodiments is implemented.

As shown in FIG9 , FIG9 is a schematic block diagram of a device 900 for information reception according to an embodiment of the present disclosure. The device 900 may be provided as a base station. Referring to FIG9 , the device 900 includes a processing component 922, a wireless transmission/reception component 924, an antenna component 926, and a signal processing part specific to a wireless interface, and the processing component 922 may further include one or more processors. One of the processors in the processing component 922 may be configured to implement the information reception method described in any of the above embodiments.

Fig. 10 is a schematic block diagram of a device 1000 for sending information according to an embodiment of the present disclosure. For example, the device 1000 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

10 , device 1000 may include one or more of the following components: a processing component 1002 , a memory 1004 , a power component 1006 , a multimedia component 1008 , an audio component 1010 , an input/output (I/O) interface 1012 , a sensor component 1014 , and a communication component 1016 .

The processing component 1002 generally controls the overall operation of the device 1000, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1002 may include one or more processors 1020 to execute instructions to complete all or part of the steps of the above-mentioned information transmission method. In addition, the processing component 1002 may include one or more modules to facilitate the interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate the interaction between the multimedia component 1008 and the processing component 1002.

The memory 1004 is configured to store various types of data to support operations on the device 1000. Examples of such data include instructions for any application or method operating on the device 1000, contact data, phone book data, messages, pictures, videos, etc. The memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

The power supply component 1006 provides power to the various components of the device 1000. The power supply component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1000.

The multimedia component 1008 includes a screen that provides an output interface between the device 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1008 includes a front camera and/or a rear camera. When the device 1000 is in an operating mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 1010 is configured to output and/or input audio signals. For example, the audio component 1010 includes a microphone (MIC), and when the device 1000 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1004 or sent via the communication component 1016. In some embodiments, the audio component 1010 also includes a speaker for outputting audio signals.

I/O interface 1012 provides an interface between processing component 1002 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, a home button, a volume button, a start button, and a lock button.

The sensor assembly 1014 includes one or more sensors for providing various aspects of status assessment for the device 1000. For example, the sensor assembly 1014 can detect the open/closed state of the device 1000, the relative positioning of components, such as the display and keypad of the device 1000, the sensor assembly 1014 can also detect the position change of the device 1000 or a component of the device 1000, the presence or absence of user contact with the device 1000, the orientation or acceleration/deceleration of the device 1000, and the temperature change of the device 1000. The sensor assembly 1014 can include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1014 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 can also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1016 is configured to facilitate wired or wireless communication between the device 1000 and other devices. The device 1000 can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G LTE, 5G NR, or a combination thereof. In an exemplary embodiment, the communication component 1016 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned information sending method.

In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1004 including instructions, and the instructions can be executed by the processor 1020 of the device 1000 to complete the above-mentioned information sending method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprises a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

The method and device provided in the embodiments of the present disclosure are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method of the present disclosure and its core idea. At the same time, for those skilled in the art, according to the idea of the present disclosure, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present disclosure.

Claims

A method for sending information, characterized in that it is executed by a terminal, and the method comprises:

Preprocessing the estimated full channel information according to a first number of spatial domain basis vectors and a second number of frequency domain basis vectors to obtain effective channel information;

Calculating a characteristic vector of the effective channel information;

The feature vector is input into a first artificial intelligence and/or machine learning model to obtain CSI-related information, and the CSI-related information is sent to a network device.
The method according to claim 1, characterized in that the method further comprises:

Determine current statistical downlink full channel information according to the current estimated downlink full channel information and historical statistical downlink full channel information;

Performing eigenvalue decomposition according to current statistical downlink full channel information to obtain the first number of spatial domain basis vectors and the second number of frequency domain basis vectors;

The types of the spatial domain basis vector and the frequency domain basis vector are eigenvectors.
The method according to claim 1, characterized in that the method further comprises:

The first number of spatial domain basis vectors and the second number of frequency domain basis vectors are calculated according to the estimated downlink full channel information, wherein the types of the spatial domain basis vectors and the frequency domain basis vectors are discrete Fourier transform DFT basis vectors.
The method according to claim 1, characterized in that the method further comprises:

The spatial domain basis vectors and the frequency domain basis vectors are reported to the network device.
The method according to claim 4, characterized in that the reporting the spatial domain basis vector and the frequency domain basis vector to the network device comprises:

Reporting the spatial domain basis vector and the frequency domain basis vector to the network device respectively; and/or

The spatial domain basis vector and the frequency domain basis vector are jointly reported to the network device.
The method according to claim 4, characterized in that the reporting the spatial domain basis vector and the frequency domain basis vector to the network device comprises:

When the type of the spatial basis vector is a feature vector, the real part and the imaginary part of the spatial basis vector are quantized respectively and then reported to the network device; and/or

When the type of the frequency domain basis vector is a feature vector, the real part and the imaginary part of the frequency domain basis vector are quantized respectively and then reported to the network device.
The method according to claim 4, characterized in that the reporting the spatial domain basis vector and the frequency domain basis vector to the network device comprises:

Representing the spatial domain basis vectors and/or the frequency domain basis vectors as a linear combination of a plurality of orthogonal basis vectors and a plurality of coefficients corresponding to the orthogonal basis vectors;

The coefficients corresponding to the multiple orthogonal basis vectors are reported to the network device.
The method according to any one of claims 1 to 7, characterized in that the effective channel information includes at least one of the following:

one or more feature vectors of data transmission layers among feature vectors of multiple data transmission layers obtained by preprocessing the estimated full channel information using the first number of spatial basis vectors and the second number of frequency domain basis vectors;

The estimated full channel information is preprocessed by using the first number of spatial basis vectors and the second number of frequency domain basis vectors to obtain channel information of one or more receiving antenna ports among the channel information of multiple receiving antenna ports.
The method according to any one of claims 1 to 7, characterized in that the number of dimensions of the effective channel information is determined based on at least one of the following:

the first quantity and the second quantity;

The number of pairs of the spatial domain basis vectors and the frequency domain basis vectors;

Number of receive antenna ports.
The method according to any one of claims 1 to 7, characterized in that the first number and the second number are determined based on at least one of the following:

the first number of the network device configurations;

the second number of the network device configurations;

The sum of the first number and the second number of the network device configurations;

The product of the first number and the second number of the network device configurations;

Downlink channel information.
An information receiving method, characterized in that it is executed by a network device, and the method comprises:

A receiving terminal receives CSI-related information sent by the method according to any one of claims 1 to 10.
The method according to claim 11, characterized in that the method further comprises:

Inputting the CSI-related information into a second artificial intelligence and/or machine learning model to obtain recovered information of the estimated full channel information;

The estimated full channel information and/or channel information eigenvectors and/or precoding for downlink data transmission are constructed according to the recovered information, the frequency domain basis vectors and the spatial domain basis vectors.
The method according to claim 12, characterized in that the spatial domain basis vectors and the frequency domain basis vectors include at least one of the following:

The spatial domain basis vectors and frequency domain basis vectors reported by the terminal when sending the CSI related information;

The spatial domain basis vectors and frequency domain basis vectors reported historically by the terminal.
An information sending device, characterized in that the device comprises:

A processing module is configured to pre-process the estimated full channel information according to a first number of spatial basis vectors and a second number of frequency domain basis vectors to obtain effective channel information; calculate a feature vector of the effective channel information; and input the feature vector into a first artificial intelligence and/or machine learning model to obtain CSI related information;

The sending module is configured to send the CSI related information to the network device.
An information receiving device, characterized in that the device comprises:

The receiving module is configured to receive CSI-related information sent by a terminal according to any one of the methods of claims 1 to 10.
An information transceiving system, characterized in that it includes a terminal and a network side device, wherein the terminal is configured to implement the information sending method described in any one of claims 1 to 10, and the network device is configured to implement the information receiving method described in any one of claims 11 to 13.
A communication device, comprising:

processor;

memory for storing computer programs;

When the computer program is executed by a processor, the information sending method according to any one of claims 1 to 10 is implemented.
A communication device, comprising:

processor;

memory for storing computer programs;

Wherein, when the computer program is executed by a processor, the information receiving method described in any one of claims 11 to 13 is implemented.
A computer-readable storage medium for storing a computer program, characterized in that when the computer program is executed by a processor, the information sending method according to any one of claims 1 to 10 is implemented.
A computer-readable storage medium for storing a computer program, characterized in that when the computer program is executed by a processor, the information receiving method described in any one of claims 11 to 13 is implemented.