Communication method, and apparatus

Abstract

The present application relates to the technical field of communications. Provided are a communication method and an apparatus. The method comprises: compressing first sensing information by means of an artificial intelligence (AI) model to obtain second sensing information, the first sensing information comprising power spectrum information, and the second sensing information comprising eigenvalue codebook information; and sending the second sensing information. The described solution uses the AI model to compress the first sensing information, and compared with the power spectrum information, the compressed eigenvalue codebook information has a smaller data volume or a smaller quantity of bits, thereby reducing transmission overheads, and improving transmission efficiency.

Description

A communication method and apparatus

[0001] Cross Reference to Related Applications

[0002] This application claims priority to the Chinese Patent Application No. 202411310714.2, filed on September 19, 2024, and entitled "A communication method and apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of communication, and in particular to a communication method and apparatus. BACKGROUND

[0004] In a communication sensing system, a base station can implement positioning, detection, imaging and identification of a target, and other sensing functions by sending a sensing signal to obtain surrounding physical environment information. In a scenario where the base station sends a sensing signal and a user equipment (UE) receives the sensing signal, the UE needs to feed back sensing imaging information to the base station, and the base station processes the sensing imaging information to implement the sensing function. However, in order to meet the sensing accuracy requirement, the sensing imaging information fed back by the UE has a large overhead.

[0005] Therefore, how to reduce the feedback overhead of the sensing imaging information is a technical problem to be solved. SUMMARY

[0006] To solve the above technical problem, the present application provides a communication method and apparatus, which can reduce the feedback overhead of the sensing imaging information. In the embodiments of the present application, the communication method and apparatus can also be regarded as a sensing method and apparatus, or a communication sensing integrated method and apparatus.

[0007] In a first aspect, a communication method is provided, which can be applied to a first apparatus. The first apparatus in the present application can be a network device or a terminal device, or a module (for example, a processor, a chip, or a chip system, etc.) in the network device or the terminal device, or a logic module or software capable of realizing all or part of the functions of the network device or the terminal device. For ease of description, the first apparatus is described below as an example.

[0008] The method comprises: compressing first sensing information by an artificial intelligence (AI) model to obtain second sensing information; the first sensing information comprises power spectrum information, and the second sensing information comprises feature value codebook information; and transmitting the second sensing information.

[0009] Through the above scheme, the AI model is used to compress the first sensing information, and the feature value codebook information after compression has a smaller data volume or bit number than the power spectrum information, which can reduce the transmission overhead and improve the transmission efficiency.

[0010] Optionally, the first information indicates an AI model, or a compression rate of the perception information.

[0011] Optionally, the compression rate is a bit ratio of the first perception information and the second perception information, a compression level, or a bit per pixel. Illustratively, the compression rate is a ratio of a bit number of the power spectrum information before compression and a bit number of the eigenvalue codebook after compression; the compression rate is a bit per pixel, or a bit number of each position point in the power spectrum; the higher the compression level, the higher the compression rate. The higher the compression rate, the stronger the compression capability of the data, and the smaller the bit number of the eigenvalue codebook after compression under the condition that the bit number of the power spectrum information is the same.

[0012] In some implementations, the first information indicates an AI model, and the AI model belongs to an AI model set, wherein network structures of different AI models in the AI model set are different, or compression rates of different AI models in the AI model set are different.

[0013] Optionally, the network structures of different AI models in the AI model set are different, including that a convolution layer channel number and / or a convolutional neural network number of the AI model are different. Illustratively, the more the convolution layer channel number, the lower the compression rate; the more the convolutional neural network number, the higher the compression rate.

[0014] Optionally, the network structure of the AI model or the compression rate corresponding to the network structure of the AI model is determined in the AI model set according to the first information.

[0015] In some implementations, the first information indicates a compression rate of the perception information.

[0016] Optionally, the first perception information is compressed by the AI model according to the compression rate to obtain the second perception information.

[0017] Through the above scheme, the specified AI model or the compression rate of the perception information can be determined according to the first information to compress the power spectrum information, so that the receiving end of the eigenvalue codebook information can be decompressed in a corresponding manner; through the first information, different AI models or compression rates can be flexibly selected to adapt to different application scenarios

[0018] Optionally, the power spectrum information includes a three-dimensional power spectrum, or a two-dimensional power spectrum; the three-dimensional power spectrum includes a subcarrier dimension, a horizontal direction dimension, and a vertical direction dimension; the two-dimensional power spectrum includes a horizontal direction dimension and a vertical direction dimension, a subcarrier dimension and a horizontal direction dimension, or a subcarrier dimension and a vertical direction dimension.

[0019] Optionally, the AI model comprises a plurality of three-dimensional convolution layers, or a plurality of two-dimensional convolution layers. For example, the three-dimensional power spectrum is compressed by the plurality of three-dimensional convolution layers, and the two-dimensional power spectrum is compressed by the plurality of two-dimensional convolution layers.

[0020] Optionally, a sensing signal is received, and the sensing signal is used to determine the first sensing information. For example, the sensing signal is a reference signal with a known initial amplitude and phase, a communication signal carrying data, or other wireless signals that can enable the receiving end to know the initial amplitude and phase information thereof.

[0021] In a second aspect, a communication method is provided, which can be applied to a second device. The second device in the present application can be a network device or a terminal device, or a module (for example, a processor, a chip, or a chip system, etc.) in the network device or the terminal device, or a logic module or software that can realize all or part of the functions of the network device or the terminal device. For ease of description, the second device is taken as an example in the following description.

[0022] The method comprises: receiving second sensing information, decompressing the second sensing information by using a first AI model to obtain first sensing information, wherein the first sensing information comprises power spectrum information, and the second sensing information comprises eigenvalue codebook information.

[0023] By using the above scheme, the second sensing information is decompressed by using the first AI model, and the decompressed power spectrum information has a larger data volume or bit number than the eigenvalue codebook information. This method of transmitting the second sensing information and decompressing and restoring can reduce the transmission overhead and improve the transmission efficiency.

[0024] Optionally, first information is transmitted, the first information indicating a second AI model or a compression rate of the sensing information, wherein the second sensing information is obtained by compressing the first sensing information by using the second AI model.

[0025] Optionally, the compression rate is a bit ratio of the first sensing information to the second sensing information, a compression level, or a bit per pixel. For example, the compression rate is a ratio of a bit number of the power spectrum information before compression to a bit number of the eigenvalue codebook after compression; the compression rate is a bit per pixel or a bit number of each position point in the power spectrum; the higher the compression level is, the higher the compression rate is. The higher the compression rate is, the stronger the compression capability of the data is, and the smaller the bit number of the eigenvalue codebook after compression is under the condition that the bit number of the power spectrum information is the same.

[0026] In some implementations, the first information indicates the second AI model, and the second AI model belongs to an AI model set, wherein the network structures of different AI models in the AI model set are different, or the compression rates of different AI models in the AI model set are different.

[0027] Optionally, the network structures of different AI models in the AI model set are different, including: different numbers of convolutional layers and / or different numbers of convolutional neural network layers of the AI models. For example, the more the number of convolutional layers, the lower the compression rate; the more the number of convolutional neural network layers, the higher the compression rate.

[0028] Optionally, the network structure of the second AI model is determined in the AI model set according to the first information, or the compression rate corresponding to the network structure of the second AI model.

[0029] In some implementations, the first information indicates the compression rate of the perception information.

[0030] Optionally, the first perception information and the first information are input into the second AI model for compression to obtain second perception information.

[0031] Through the above scheme, the specified AI model or the compression rate of the perception information can be determined according to the first information to compress the power spectrum information, so that the receiving end of the eigenvalue codebook information can be decompressed in a corresponding manner; through the first information, different AI models or compression rates can be flexibly selected to adapt to different application scenarios.

[0032] Optionally, the power spectrum information includes three-dimensional power spectrum or two-dimensional power spectrum; the three-dimensional power spectrum includes a subcarrier dimension, a horizontal direction dimension, and a vertical direction dimension; the two-dimensional power spectrum includes a horizontal direction dimension and a vertical direction dimension, a subcarrier dimension and a horizontal direction dimension, or a subcarrier dimension and a vertical direction dimension.

[0033] Optionally, the AI model includes a multi-level three-dimensional convolutional layer or a multi-level two-dimensional convolutional layer. For example, the three-dimensional power spectrum is compressed through the multi-level three-dimensional convolutional layer, and the two-dimensional power spectrum is compressed through the multi-level two-dimensional convolutional layer.

[0034] Optionally, a perception signal is sent, and the perception signal is used to determine the first perception information. For example, the perception signal is a reference signal with known initial amplitude and phase, a communication signal carrying data, or other wireless signals that can make the receiving end know the initial amplitude and phase information thereof.

[0035] Optionally, the first AI model includes a decompression model of a convolutional autoencoder, and the second AI model includes a compression model of the convolutional autoencoder, and the compression model of the convolutional autoencoder corresponds to the decompression model of the convolutional autoencoder in a one-to-one manner.

[0036] In a third aspect, a communication method is provided, which can be applied to a third device. The third device in the present application can be a network device or a terminal device, can also be a module (for example, a processor, a chip, or a chip system, etc.) in the network device or the terminal device, or can also be a logic module or software, etc. capable of realizing all or part of the functions of the network device or the terminal device. For ease of description, the third device is taken as an example for description below.

[0037] The method comprises: receiving first information, the first information indicating an AI model or a compression rate of perception information; compressing first perception information according to the AI model to obtain second perception information; and transmitting the second perception information.

[0038] Through the above scheme, the first perception information is compressed using the AI model indicated by the first information, and the second perception information after compression has a smaller data volume or bit number than the first perception information, which can reduce transmission overhead and improve transmission efficiency.

[0039] Optionally, the first perception information comprises power spectrum information, and the second perception information comprises eigenvalue codebook information.

[0040] Optionally, the compression rate is a bit ratio of the first perception information to the second perception information, a compression level, or a bit per pixel. For example, the compression rate is a ratio of a bit number of the power spectrum information before compression to a bit number of the eigenvalue codebook after compression; the compression rate is a bit per pixel or a bit number of each position point in the power spectrum; the higher the compression level, the higher the compression rate. The higher the compression rate, the stronger the compression capability of the data, and the smaller the bit number of the eigenvalue codebook after compression under the condition that the bit number of the power spectrum information is the same.

[0041] In some implementations, the first information indicates the AI model, and the AI model belongs to an AI model set, wherein network structures of different AI models in the AI model set are different, or compression rates of different AI models in the AI model set are different.

[0042] Optionally, the network structures of different AI models in the AI model set are different, comprising: the number of convolution layers and / or the number of convolution neural network layers of the AI model are different. For example, the more the number of convolution layers, the lower the compression rate; the more the number of convolution neural network layers, the higher the compression rate.

[0043] Optionally, the network structure of the AI model or the compression rate corresponding to the network structure of the AI model is determined according to the first information in the AI model set.

[0044] In some implementations, the first information indicates the compression rate of the perception information.

[0045] Optionally, the first perception information and the first information are input into an AI model for compression to obtain second perception information.

[0046] Through the above scheme, the specified AI model or the compression rate of the perception information can be determined according to the first information to compress the power spectrum information, so that the receiving end of the eigenvalue codebook information can be decompressed in a corresponding manner; different AI models or compression rates can be flexibly selected through the first information to adapt to different application scenarios

[0047] Optionally, the power spectrum information includes three-dimensional power spectrum, or two-dimensional power spectrum; the three-dimensional power spectrum includes a subcarrier dimension, a horizontal direction dimension and a vertical direction dimension; the two-dimensional power spectrum includes a horizontal direction dimension and a vertical direction dimension, a subcarrier dimension and a horizontal direction dimension, or a subcarrier dimension and a vertical direction dimension.

[0048] Optionally, the AI model includes a multi-stage three-dimensional convolution layer or a multi-stage two-dimensional convolution layer. For example, the three-dimensional power spectrum is compressed through the multi-stage three-dimensional convolution layer, and the two-dimensional power spectrum is compressed through the multi-stage two-dimensional convolution layer.

[0049] Optionally, a perception signal is received, and the perception signal is used to determine the first perception information. For example, the perception signal is a reference signal with known initial amplitude and phase, a communication signal carrying data, or other wireless signals that can enable the receiving end to know the initial amplitude and phase information.

[0050] In a fourth aspect, a communication method is provided, which can be applied to a fourth device. The fourth device in the present application can be a network device or a terminal device, or a module (for example, a processor, a chip, or a chip system, etc.) in the network device or the terminal device, or a logic module or software that can realize all or part of the functions of the network device or the terminal device. For ease of description, the fourth device is described below as an example.

[0051] The method includes: sending first information, the first information indicating a second AI model or a compression rate of perception information; and receiving second perception information, wherein the second perception information is obtained by compressing first perception information through the second AI model.

[0052] Through the above scheme, the first perception information is compressed using the second AI model, and the second perception information after compression has a smaller data volume or bit number than the first perception information. This method of transmitting the second perception information can reduce transmission overhead and improve transmission efficiency.

[0053] Optionally, the second perception information is decompressed through the first AI model to obtain the first perception information; the first perception information includes power spectrum information, and the second perception information includes eigenvalue codebook information.

[0054] Optionally, the compression rate is a bit ratio of the first perceptual information and the second perceptual information, a compression level, or a bit per pixel. Illustratively, the compression rate is a ratio of a bit number of the power spectrum information before compression and a bit number of the eigenvalue codebook after compression; the compression rate is a bit per pixel, or a bit number of each position point in the power spectrum; the higher the compression level, the higher the compression rate. The higher the compression rate, the stronger the compression ability of the data, and the smaller the bit number of the eigenvalue codebook after compression under the condition that the bit number of the power spectrum information is the same.

[0055] In some implementations, the first information indicates a second AI model, and the second AI model belongs to an AI model set, where network structures of different AI models in the AI model set are different, or compression rates of different AI models in the AI model set are different.

[0056] Optionally, the network structures of different AI models in the AI model set are different, including that a convolution layer channel number and / or a convolutional neural network layer number of the AI model are different. Illustratively, the more the convolution layer channel number, the lower the compression rate; the more the convolutional neural network layer number, the higher the compression rate.

[0057] Optionally, the network structure of the second AI model is determined according to the first information in the AI model set, or a compression rate corresponding to the network structure of the second AI model.

[0058] In some implementations, the first information indicates a compression rate of the perceptual information.

[0059] Optionally, the second perceptual information and the first information are input to the first AI model for decompression to obtain the first perceptual information.

[0060] Through the above scheme, the specified AI model or the compression rate of the perceptual information can be determined according to the first information to compress the power spectrum information, so that the receiving end of the eigenvalue codebook information can be decompressed in a corresponding manner; through the first information, different AI models or compression rates can be flexibly selected to adapt to different application scenarios.

[0061] Optionally, the power spectrum information includes a three-dimensional power spectrum, or a two-dimensional power spectrum; the three-dimensional power spectrum includes a subcarrier dimension, a horizontal direction dimension, and a vertical direction dimension; the two-dimensional power spectrum includes the horizontal direction dimension and the vertical direction dimension, the subcarrier dimension and the horizontal direction dimension, or the subcarrier dimension and the vertical direction dimension.

[0062] Optionally, the AI model includes a multi-level three-dimensional convolution layer, or a multi-level two-dimensional convolution layer. Illustratively, the three-dimensional power spectrum is compressed through the multi-level three-dimensional convolution layer, and the two-dimensional power spectrum is compressed through the multi-level two-dimensional convolution layer.

[0063] Optionally, a sensing signal is transmitted, and the sensing signal is used to determine the first sensing information. For example, the sensing signal is a reference signal with known initial amplitude and phase, a communication signal carrying data, or other wireless signals from which the receiving end can obtain the initial amplitude and phase information.

[0064] Optionally, the first AI model comprises a decompression model of a convolutional autoencoder, and the second AI model comprises a compression model of the convolutional autoencoder, and the compression model of the convolutional autoencoder corresponds to the decompression model of the convolutional autoencoder in a one-to-one manner.

[0065] In a fifth aspect, a communication apparatus is provided. The communication apparatus comprises a processor configured to perform the first aspect and any possible implementation of the first aspect, the processor configured to perform the second aspect and any possible implementation of the second aspect, the processor configured to perform the third aspect and any possible implementation of the third aspect, or the processor configured to perform the fourth aspect and any possible implementation of the fourth aspect.

[0066] In some implementations, the communication apparatus of the fifth aspect can further comprise a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be configured to enable the communication apparatus of the fifth aspect to communicate with other communication apparatuses.

[0067] In a possible implementation, the communication apparatus of the fifth aspect can further comprise a memory. The memory can be integrated with the processor or can be separately arranged. The memory can be configured to store computer programs and / or data related to the method of the first aspect or any implementation of the first aspect, the method of the second aspect or any implementation of the second aspect, the method of the third aspect or any implementation of the third aspect, or the method of the fourth aspect or any implementation of the fourth aspect.

[0068] In addition, the communication apparatus of the fifth aspect can have the technical effects of the first aspect or any implementation of the first aspect, the second aspect or any implementation of the second aspect, the third aspect or any implementation of the third aspect, or the fourth aspect or any implementation of the fourth aspect, which will not be repeated here.

[0069] In a sixth aspect, a communication apparatus is provided. The communication apparatus includes a processor coupled with a memory, the processor configured to execute computer programs or instructions stored in the memory to cause the communication apparatus to perform the method of the first aspect or any of the embodiments of the first aspect, to cause the communication apparatus to perform the method of the second aspect or any of the embodiments of the second aspect, to cause the communication apparatus to perform the method of the third aspect or any of the embodiments of the third aspect, or to cause the communication apparatus to perform the method of the fourth aspect or any of the embodiments of the fourth aspect.

[0070] In a possible implementation, the communication apparatus can further include a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be configured to enable the communication apparatus to communicate with other communication apparatuses.

[0071] In a possible implementation, the communication apparatus further includes the memory configured to store the computer programs or instructions. Optionally, the memory and the processor are integrated together.

[0072] In addition, the technical effects of the communication apparatus of the fourth aspect can refer to the technical effects of the first aspect or any of the embodiments of the first aspect, the technical effects of the second aspect or any of the embodiments of the second aspect, the technical effects of the third aspect or any of the embodiments of the third aspect, or the technical effects of the fourth aspect or any of the embodiments of the fourth aspect, which will not be repeated here.

[0073] In a seventh aspect, a chip is provided. The chip includes a processor configured to invoke computer programs or computer instructions in a memory to cause the processor to perform any of the embodiments of the first aspect, to cause the processor to perform any of the embodiments of the second aspect, to cause the processor to perform any of the embodiments of the third aspect, or to cause the processor to perform any of the embodiments of the fourth aspect.

[0074] In some embodiments, the processor is coupled with the memory through an interface.

[0075] In an eighth aspect, a communication system is provided. The communication system includes a first apparatus configured to perform the method of the first aspect or any of the embodiments of the first aspect, a second apparatus configured to perform the method of the second aspect or any of the embodiments of the second aspect, a third apparatus configured to perform the method of the third aspect or any of the embodiments of the third aspect, or a fourth apparatus configured to perform the method of the fourth aspect or any of the embodiments of the fourth aspect.

[0076] In a ninth aspect, a computer-readable storage medium is provided, including: a computer program or instructions; when the computer program or instructions are run, causing the method of the first aspect or any of the implementation forms of the first aspect to be implemented, causing the method of the second aspect or any of the implementation forms of the second aspect to be implemented, causing the method of the third aspect or any of the implementation forms of the third aspect to be implemented, or causing the method of the fourth aspect or any of the implementation forms of the fourth aspect to be implemented.

[0077] In a tenth aspect, a computer program product is provided, including: a computer program or instructions; when the computer program or instructions are run, causing the method of the first aspect or any of the implementation forms of the first aspect to be implemented, causing the method of the second aspect or any of the implementation forms of the second aspect to be implemented, causing the method of the third aspect or any of the implementation forms of the third aspect to be implemented, or causing the method of the fourth aspect or any of the implementation forms of the fourth aspect to be implemented. BRIEF DESCRIPTION OF DRAWINGS

[0078] FIG. 1 is a schematic diagram of a communication system;

[0079] FIG. 2 is an example diagram of an O-RAN system;

[0080] FIG. 3 is a network element function division and protocol layer structure diagram of an O-RAN device;

[0081] FIG. 4 is an example diagram of a common sensing network architecture;

[0082] FIG. 5 is an example diagram of a common sensing RAN architecture;

[0083] FIG. 6 is an example diagram of mesh division of an imaging area;

[0084] FIG. 7 is a schematic flow diagram of a communication method provided by an embodiment of the present application;

[0085] FIG. 8 is a schematic block diagram of a communication apparatus according to an embodiment of the present application;

[0086] FIG. 9 is a schematic block diagram of another communication apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0087] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0088] In order to facilitate understanding of the embodiments of the present application, the following points will be explained before introducing the present application.

[0089] In order to facilitate understanding of the embodiments of the present application, the following points will be explained before introducing the present application.

[0090] 1. In this application, the term "system" can be used interchangeably with "network". Various aspects, embodiments or features presented in this application can be presented in terms of systems that can include a number of devices, components, modules, and the like. It is to be understood and appreciated that the various systems can include additional devices, components, modules, etc. and / or can not include all of the devices, components, modules etc. discussed in connection with the figures. A combination of these approaches can also be used.

[0091] In this application, the words "example," "for example," and the like can be used to illustrate aspects of the present application. Any embodiment or design presented as an example in this application should not be interpreted as being more preferred or advantageous than other embodiments or designs. In fact, the use of the word example is intended to present concepts in a concrete manner.

[0092] In this application, for the convenience of description, when referring to numbering, it can be consecutively numbered from 1, or consecutively numbered from 0, or numbered from any one parameter. It should be understood that the above are settings provided by the technical solutions for describing the embodiments of the present application, and are not intended to limit the scope of the embodiments of the present application.

[0093] 2. In the embodiments of the present application, "indication" can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by a certain information is referred to as to-be-indicated information. In the implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol). Thus, to a certain extent, the indication overhead is reduced. At the same time, the common part of each information can be identified and indicated uniformly, so as to reduce the indication overhead caused by separately indicating the same information.

[0094] In addition, the specific indication manner can also be various existing indication manners, for example, but not limited to, the above-mentioned indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, which will not be described herein. As can be seen from the above, for example, when multiple information of the same type needs to be indicated, the indication manner of different information can not be the same. In the implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present application. In this way, the indication manner involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0095] 3. The "protocol" referred to in the embodiments of the present application can refer to a standard protocol in the communication field, which can include, for example, a long term evolution (LTE) protocol, a new radio (NR) protocol, and a related protocol applied in a future communication system, and the embodiments of the present application do not limit this.

[0096] 4. In the embodiments of the present application, "when", "in the case of", "if", and the like all refer to the fact that a device (such as a terminal device) will make a corresponding processing under certain objective circumstances, and are not limited in time, and do not require the device (such as a terminal device) to have a judgment action when implemented, nor does it mean that there are other limitations.

[0097] 5. In the description of the present application, unless otherwise specified, " / " represents an "or" relationship between the objects associated before and after, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the associated relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent: A alone, A and B exist at the same time, and B alone, of which A, B can be singular or plural. And in the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or the like refers to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, of which a, b, c can be single or multiple.

[0098] In addition, in order to clearly describe the technical solutions of the embodiments of the present application, "first", "second", and the like are used in the embodiments of the present application to distinguish the same or similar items with basically the same function and role. The skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different.

[0099] The network architecture and business scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. The skilled in the art can know that, with the evolution of network architecture and the appearance of new business scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0100] The technical solutions of the embodiments of the present application can be applied to various communication systems, including but not limited to: a fifth generation (5th generation, 5G) mobile communication system such as a LTE system, a LTE frequency division duplex (frequency division duplex, FDD) system, a LTE time division duplex (time division duplex, TDD) system, a NR system, a narrow band internet of things (narrow band internet of things, NB-IoT) system, an enhanced machine type communication (enhanced machine-type communication, eMTC) system, an enhanced mobile broadband (enhanced mobile broadband, eMBB) system, an ultra reliable low latency communication (ultra reliable low latency communications, URLLC) system, a non-terrestrial network (non-terrestrial network, NTN) communication system, an open access network (open RAN, O-RAN or ORAN), a cloud radio access network (cloud radio access network, CRAN), a LTE-machine-to-machine (LTE-machine-to-machine, LTE-M) system, or a future communication network.

[0101] In the embodiments of the present application, the term "communication" can also be described as "data transmission", "signal transmission", "information transmission" or "transmission" and the like. In the embodiments of the present application, the transmission can include sending or receiving. Exemplarily, the transmission can be uplink transmission, for example, the terminal device can send a signal to the network device; the transmission can also be downlink transmission, for example, the network device can send a signal to the terminal device; the transmission can also be sidelink transmission, for example, the terminal device can send a signal to another terminal device. Exemplarily, "transmission" can be air interface level transmission, or can refer to signal sending of a chip input (input, I) / output (output, O) interface, rather than air interface level transmission.

[0102] FIG. 1 is a schematic diagram of a communication system 100. As shown in FIG. 1, the communication system 100 includes a radio access network (radio access network, RAN) 110 and a core network (core network, CN) 120. Optionally, the communication system 100 can also include an Internet 130. Among them, the network device can include the RAN 110, or the network device can include the RAN 110 and the CN 120.

[0103] The RAN 110 can include at least one access network device (e.g., 111a and 111b in FIG. 1) and at least one terminal device (e.g., 112a-112j in FIG. 1). The terminal device is connected to the access network device in a wireless manner. The access network device is connected to the core network 120 in a wireless or wired manner. The core network 120 can include one or more core network devices. Among them, the core network device and the access network device can be independent and different physical devices, can be integrated into the same physical device, or can be a physical device integrated with part of the core network device function and part of the access network device function. The terminal device and the terminal device, and the access network device and the access network device can be connected to each other in a wired or wireless manner. The terminal device and the terminal device, the access network device and the access network device, and the terminal device and the access network device can communicate with each other in a wireless manner through air interface resources. Illustratively, the air interface resources can include at least one of time domain resources, frequency domain resources, code resources and space resources. It should be noted that FIG. 1 is only a schematic diagram, and the communication system 100 can also include other devices with wireless transceiver functions, such as wireless relay devices and wireless backhaul devices, which are not shown in FIG. 1.

[0104] The RAN 110 can be a 3rd generation partnership project (3GPP) related cellular system, such as a 4G, 5G mobile communication system, or a future communication network. The RAN 110 can also be an O-RAN, a CRAN, or a wireless fidelity (WiFi) system, and can also be a communication system integrating two or more of the above systems. In the present application, the RAN 110 can be an NTN system, and the RAN 110 can be a transparent mode or a regenerative mode.

[0105] The access network device can be any device with wireless transceiver function. For example, the access network device can be a base station for accessing the terminal device to the RAN. The access network device can also be referred to as an access network node. It can be understood that the name of the device with access function can be different in systems with different wireless access technologies. For convenience of description, the apparatuses providing wireless communication access function for terminal devices in the embodiments of the present application are collectively referred to as base stations. In the embodiments of the present application, the access network device includes, but is not limited to, various forms of macro base stations (such as 111a in FIG. 1), micro base stations or indoor stations (such as 111b in FIG. 1), pico base stations, small stations, balloon stations, relay stations, access points, etc. The access network device can include an evolved node B (eNB or eNodeB) in LTE, an access point (AP) in a wireless fidelity (WiFi) system, a wireless relay node, a wireless backhaul node, a transmission point (TP), or a transmission reception point (TRP), etc. It can also include a next generation NodeB (gNB) or a transmission point (TRP or TP) in a 5G system, one or a group (including multiple antenna panels) of antenna panels of a base station in a 5G system, a network node constituting a gNB or a transmission point, such as a baseband unit (BBU) or a distributed unit (DU), and can also include an access network device, a server or a vehicle-mounted device, etc. in a future communication network. The access network device can also be a module or unit that completes part of the function of the base station, for example, it can be a central unit (CU) or a DU.

[0106] Exemplarily, in a universal mobile telecommunications system (UMTS) or LTE wireless communication system, the access network device can be a macro base station eNB; in a heterogeneous network (HetNet) scenario, the access network device can be a micro base station eNB; in a distributed base station scenario, the access network device can include a BBU and a remote radio unit (RRU); in a cloud radio access network (CRAN) scenario, the access network device can be a BBU pool and an RRU; in a future wireless communication system, the access network device can be a gNB.

[0107] In an embodiment of the present application, the apparatus for implementing the function of the network device can be a network device, or an apparatus capable of supporting the network device to implement the function, such as a chip system, which can be installed in the network device. The chip system can be composed of a chip, or can include a chip and other discrete devices.

[0108] The communication between the access network device and the terminal device complies with a certain protocol layer structure. The protocol layer can include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer can include at least one of a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, a media access control (MAC) layer, or a physical (PHY) layer, etc. The user plane protocol layer can include at least one of a service data adaptation protocol (SDAP) layer, a PDCP layer, an RLC layer, a MAC layer, or a physical layer, etc.

[0109] In another possible scenario, multiple access network devices cooperate to assist the terminal to implement wireless access, and different access network devices respectively implement part of the functions of the base station. For example, the access network device can be a CU, a DU, a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU node and the DU node split the protocol layer of the base station, part of the functions of the protocol layer are placed in the CU for centralized control, and the remaining part or all of the functions of the protocol layer are distributed in the DU and controlled by the CU. As an implementation manner, the CU is deployed with an RRC layer, a PDCP layer, and an SDAP layer in the protocol stack; and the DU is deployed with an RLC layer, a MAC layer, and a physical layer in the protocol stack. Therefore, the CU has the processing capability of RRC, PDCP, and SDAP. The DU has the processing capability of RLC, MAC, and PHY. It can be understood that the above-mentioned splitting of functions is only an example and does not constitute a limitation on the CU and the DU. The CU and the DU can be separately arranged, or can be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, an active antenna processing unit (AAU), or a remote radio head (RRH).

[0110] The core network device refers to a device in a core network that provides service support for a terminal. Currently, some examples of the core network device are: an access and mobility management function (AMF) entity, a session management function (SMF) entity, a user plane function (UPF) entity, a policy control function (PCF) entity, a unified data management (UDM) entity, an application function (AF) entity, a network exposure function (NEF) entity, a network data analytics function (NWDAF) entity, a location management function (LMF) entity, and the like, which are not listed one by one here. Among them, the AMF entity can be responsible for access management and mobility management of the terminal, such as user location update, user registration network, user handover, etc.; the SMF entity can be responsible for session management, such as session establishment, modification, and release. Specific functions are, for example, allocating IP addresses for users, selecting UPFs that provide message forwarding functions, etc.; the UPF entity can be a functional entity of the user plane, mainly responsible for connecting external networks; the PCF is responsible for providing policies to the AMF and SMF, such as quality of service (QoS) policies, slice selection policies, etc.; the UDM is used to store user data, such as subscription information, authentication / authorization information; the AF is responsible for providing services to the 3GPP network, such as affecting service routing and interacting with the PCF for policy control; the NEF exposes the capabilities of each network function and is responsible for converting internal and external information; the LMF is mainly responsible for location management, for example, it can initiate a positioning process and perform positioning on a specific terminal; the NWDAF is used to collect, process, and analyze various data from the network, so as to help operators better understand network performance, optimize network configuration, and improve user experience. It should be noted that the entity in this application can also be referred to as a network element or a functional entity, for example, the AMF entity can also be referred to as an AMF network element or an AMF functional entity, and for another example, the SMF entity can also be referred to as an SMF network element or an SMF functional entity, etc.

[0111] The terminal device can be a device providing voice and / or data connectivity to users; the terminal device can also be a device having wireless connection function. The terminal device can be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; can also be deployed on water surface (such as ships, etc.); can also be deployed in the air (such as airplanes, balloons and satellites, etc.). The terminal device can also be referred to as user equipment (UE), access terminal, terminal, subscriber unit, subscriber station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, wireless network device, user agent or user apparatus. In the embodiments of the present application, the terminal device includes but is not limited to: cellular phone, mobile phone, wireless data card, wireless modem, pad, laptop computer, notebook computer, palm computer, mobile internet device (MID), computer with wireless transceiver function, cordless phone, session initiation protocol (SIP) phone, smart phone, wireless local loop (WLL) station, personal digital assistant (PDA), handset with wireless communication function, computing device or other device connected to wireless modem, vehicle-mounted device (such as automobile, bicycle, electric vehicle, airplane, ship, train, high-speed rail, etc.), wearable device (such as smart watch, smart bracelet, pedometer, smart glasses, etc.), satellite terminal, terminal device in Internet of Things or Internet of Vehicles, and any form of terminal in future network, relay user equipment or terminal in future evolved public land mobile network (PLMN), etc.The terminal device can also be a virtual reality (VR) device, an augmented reality (AR) device, a smart point of sale (POS) machine, a customer-premises equipment (CPE), a light UE, a reduced capability UE (REDCAP UE), a machine type communication (MTC) terminal, a terminal device in industrial control, a terminal device in self driving, a terminal device in remote medical treatment, a terminal device in a smart grid, a wireless terminal in transportation safety, a terminal device in a smart city, a terminal device in a smart home, a haptic terminal device, a smart home device (e.g., a refrigerator, a television, an air conditioner, an electricity meter, etc.), a smart robot, a mechanical arm, a plant device, a wireless terminal in self driving, or a flight device (e.g., a smart robot, a hot air balloon, a drone, an airplane), and the like. The terminal device can also be a vehicle device, such as a whole vehicle device, a vehicle-mounted module, a vehicle-mounted communication module, a vehicle-mounted chip, an on board unit (OBU), a telematics box (T-BOX), and the like. The terminal device can also be other devices with terminal functions, for example, the terminal device can also be a device in device to device (D2D) communication. The terminal device can also be other embedded communication modules. The embodiments of the present application are not limited thereto.

[0112] In the embodiments of the present application, the device for implementing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to implement the function, such as a chip or a chip system, which can be installed in the terminal device. The chip system can be composed of a chip, or can include a chip and other discrete devices. In the technical solutions of the embodiments of the present application, the device for implementing the function of the terminal device is a terminal device, which can also be referred to as a terminal. In the following, the terminal device can be taken as an example of a UE to describe the technical solutions provided by the embodiments of the present application.

[0113] The roles of base stations and terminals can be relative, for example, the helicopter or drone 112i in FIG. 1 can be configured as a mobile base station, and for those terminals 112j accessing the wireless access network 110 through 112i, the terminal 112i is a base station; but for the base station 111a, 112i is a terminal, that is, 111a and 112i communicate through a wireless air interface protocol. Of course, 111a and 112i can also communicate through a base station-to-base station interface protocol, in which case 112i is also a base station relative to 111a. Therefore, both base stations and terminals can be collectively referred to as communication devices, and 111a and 111b in FIG. 1 can be referred to as communication devices with base station functions, and 112a-112j in FIG. 1 can be referred to as communication devices with terminal functions.

[0114] The base station and the terminal device can communicate through a wireless link. The transmission link from the base station to the terminal device can be referred to as a downlink (DL) or downlink channel, for transmitting downlink signals. The transmission link from the terminal device to the base station can be referred to as an uplink (UL) or uplink channel, for transmitting uplink signals.

[0115] By way of example, consider the transmission of a UMTS terrestrial radio access network (UTRAN) to UE (Uu) interface, the two parties of the wireless communication can include a base station and a terminal device.

[0116] FIG. 2 is an example diagram of an O-RAN system, which can include other components than those shown in FIG. 2. As shown, the RAN communicates with the core network through a backhaul link and communicates with user equipment (UE) or terminal devices through an air interface. Specifically, the baseband unit (BBU) in the access network device communicates with the core network through a backhaul link, and the RU in the access network device communicates with at least one UE through an air interface. The BBU communicates with at least one RU through a fronthaul link, and the BBU and the RU can or can not be co-located. The BBU includes at least one CU and at least one DU, which can communicate through at least one midhaul link.

[0117] Figure 3 illustrates a network element function split and protocol layer structure of an O-RAN device. In some examples, the CU is a logical node that hosts the RRC layer, the SDAP layer, the PDCP layer, and other control functions of the access network device. The CU is connected to network nodes such as core network nodes through some interfaces, which can be E2 interface or other interfaces. Optionally, the CU can have part of the functions of the core network. The CU (e.g., the PDCP layer and higher layers) is connected to the DU (e.g., the RLC layer and lower layers) through some interfaces, which can be F1 interface or other interfaces. In some examples, these interfaces (e.g., the F1 interface) can provide control plane (CP) and user plane (UP) functions (e.g., interface management, system information management, UE context management, RRC message transmission, etc.). The F1 AP is an application protocol of the F1 interface, which defines the signaling procedures of the F1 in some examples. The F1 interface supports control plane F1-C and user plane F1-U.

[0118] In some examples, the CU can be split into a CU-CP (Control Unit-Control Plane) and a CU-UP (Control Unit-User Plane), where the CU-CP is a logical node that hosts the RRC layer and the PDCP-C (Control plane part of PDCP) layer, and is used to implement the control plane functions of the CU. The CU-CP can interact with network elements in the core network that are used to implement the control plane functions. The network elements in the core network that are used to implement the control plane functions can be access and mobility function network elements, such as the AMF in the 5G system. The CU-UP is a logical node that hosts the SDAP layer and the PDCP-U (User plane part of PDCP) layer, and is used to implement the user plane functions of the CU. The CU-UP can interact with network elements in the core network that are used to implement the user plane functions. The network elements in the core network that are used to implement the user plane functions can be UPFs in the 5G system. The above configuration of the CU and the DU is merely an example, and the CU and the DU can be configured to have other functions according to needs. For example, the CU or the DU can be configured to have more protocol layer functions, or the CU or the DU can be configured to have partial processing functions of the protocol layers. For example, part of the functions of the RLC layer and the functions of the protocol layers above the RLC layer can be set in the CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer can be set in the DU. For another example, the functions of the CU or the DU can be divided according to the service type or other system requirements, for example, according to the delay requirement. The functions that need to meet the delay requirement can be set in the DU, and the functions that do not need to meet the delay requirement can be set in the CU.

[0119] The CU (or CU-CP and CU-UP), DU or RU can also have different names in different systems, but those skilled in the art can understand their meanings. For example, in an O-RAN system, the CU can also be referred to as an O-CU (Open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module. The embodiments of this application do not limit the specific technology and specific device form adopted by the network device.

[0120] In some examples, the DU is a logical node that carries the RLC layer, the MAC layer, the Higher PHY layer and other functions. In some examples, the DU can control at least one RU. The DU is connected to the RU through some interfaces, which can be a front-haul interface.

[0121] In some examples, the CU can have no PDCP layer, i.e., only include the RRC layer. The CU-CP has no PDCP-C. The CU-UP can have no PDCP-U, or have no CU-UP at all. In some examples, the DU can have no RLC layer, only have the MAC and higher PHY layers. In addition, in some examples, there can be no CU only including the DU.

[0122] In some examples, the Higher PHY layer includes part of the PHY layer processing, such as forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc. In some examples, the RU is a logical node that carries the Lower Physical Layer (Lower PHY) and Radio Frequency (RF) processing. In some examples, the RU can be a 3GPP Transmission Reception Point (TRP) or a Remote Radio Head (RRH) or other similar functional entity. In some examples, the Low-PHY includes part of the PHY processing, such as fast Fourier transform (FFT), inverse fast Fourier transform (IFFT), digital beamforming and filtering, etc. The RU communicates with one or more UEs through a wireless link.

[0123] The DU and the RU can be co-located or not. The DU and the RU exchange control plane and user plane information over a front-haul link via a lower-layer split-control, user and synchronization (LLS-CUS) interface. The LLS-CUS can include a LLS-C interface and a LLS-U interface that provide a control plane (C-Plane) and a user plane (U-Plane), respectively. In some examples, the control plane (C-Plane) refers to real-time control between the DU and the RU. The DU and the RU exchange management information over a LLS-M interface of the front-haul link, and the management plane (M-Plane) refers to non-real-time management operations between the DU and the RU. The DU and the RU can cooperate to jointly implement the functions of the PHY layer. One DU can be connected to one or more RUs. The functions of the DU and the RU can be configured in multiple ways according to design. For example, the DU is configured to implement baseband functions, and the RU is configured to implement intermediate radio frequency functions. For another example, the DU is configured to implement high-layer functions in the PHY layer, and the RU is configured to implement low-layer functions in the PHY layer or implement the low-layer functions and radio frequency functions. The high-layer functions in the PHY layer can include a part of the functions of the PHY layer that are closer to the MAC layer, and the low-layer functions in the PHY layer can include another part of the functions of the PHY layer that are closer to the intermediate radio frequency side.

[0124] Meanwhile, the O-RAN system can also include the following functions / nodes:

[0125] Non-real time RAN intelligent controller (non-RT RIC or NRT RIC): used to implement non-real-time intelligent management of the RAN, capable of implementing AI / ML work flows including model training and model updating, and guiding applications / functions in the NRT RIC based on policies;

[0126] Near-real time RAN intelligent controller (near-RT RIC or nRT RIC): used to implement near-real-time intelligent management of the RAN, to implement near-real-time control and optimization of modules and resources of the O-RAN through data collection and related operations on the E2 interface.

[0127] 1、Communication sensing integration (Integrated sensing and communication, ISAC)

[0128] Communication and sensing integration aims to integrate wireless communication and sensing functions in the same system, and uses various propagation characteristics of wireless signals to realize target positioning, detection, imaging and identification, etc. to obtain surrounding physical environment information, improve communication performance and enhance user experience. In the communication and sensing integration technology, network devices perform sensing by sending sensing signals and receiving echo signals to obtain the position, speed and other information of targets in the environment. Among them, the sensing signal is a signal used for sensing, and the initial amplitude and phase of the sensing signal sent by the sending end are known to the receiving end. One way is that the initial amplitude and phase information of the sensing signal can be pre-configured to the receiving end through configuration sequence, such as channel state information-reference signal (CSI-RS) and other reference signals that can be used for sensing; in addition, the sensing signal can also be a communication signal carrying data, and the receiving end can calculate the initial amplitude and phase information of each data signal according to the data check result and the known modulation mode; or other wireless signals that can make the receiving end know the initial amplitude and phase information. The echo signal is a signal reflected by the target in the environment after the sensing signal is sent, or the echo signal can also be understood as the sensing signal. The time delay of the echo signal relative to the transmitted sensing signal reflects the distance of the target; the Doppler frequency shift of the echo signal relative to the transmitted sensing signal reflects the speed of the target.

[0129] The sensing mode can be divided into the following six modes: network device self-generation and self-reception, the sensing signal is sent by the network device, and after being reflected by the target in the environment, it is received by the network device again; network device A sends and network device B receives, the sensing signal is sent by network device A, and after being reflected by the target in the environment, it is received by network device B; network device sends and terminal receives, the sensing signal is sent by the network device, and after being reflected by the target in the environment, it is received by the terminal again; terminal sends and network device receives, the sensing signal is sent by the terminal, and after being reflected by the target in the environment, it is received by the network device again; terminal self-generation and self-reception, the sensing signal is sent by the terminal, and after being reflected by the target in the environment, it is received by the terminal again; terminal A sends and terminal B receives, the sensing signal is sent by terminal A, and after being reflected by the target in the environment, it is received by terminal B again.

[0130] 2、Network architecture for sensing

[0131] In order to meet the technical requirements of wireless network end-to-end implementation of sensing capability, a sensing network architecture is shown in FIG. 4. A sensing network element or sensing function (SF) is added in the core network, and interfaces between the SF and the AMF, UPF, RAN, etc. are added and interacted. The sensing control signaling between the SF and the RAN / UE can be transmitted through the AMF or directly, and the sensing measurement data obtained by the RAN / UE can be forwarded through the UPF or directly transmitted to the SF.

[0132] 3. Sensing RAN architecture

[0133] For the fusion sensing service scenario, a new module, such as a sensing unit (SU), is introduced at the RAN side, which is not limited in the name in this application, and can be any other name. As shown in FIG. 5, the SU can be a function or entity within the base station, or a function or entity outside the base station, responsible for performing sensing-related functions, and the base station can include a CU and a DU. The SU can be directly or indirectly connected to the SF in the core network for interaction of related sensing requirements; the SU can also be connected to the AMF / UPF, etc. in the core network or the CU / DU / RU for transmission of sensing-related information or data.

[0134] When the UE reports to the base station (which can be understood as the UE reporting sensing data to the SU in the base station), the sensing data can be transmitted by the UE to the DU, and then transmitted by the DU to the CU, the CU to the SU, or directly transmitted by the DU to the SU after being transmitted by the UE to the DU, or the sensing data can be directly transmitted by the UE to the SU through the s-Uu interface.

[0135] 4. UE-assisted sensing imaging based on network device transmission and UE reception mode

[0136] Sensing imaging of stationary targets such as high-rise buildings is an important application scenario of 5G-A communication and sensing integration. UE-assisted sensing in the network device transmission and UE reception mode utilizes the multi-view and ranging capabilities of the UE to make up for the lack of field of view and imaging accuracy of the network device self-transmission and self-reception mode. The UE-assisted sensing imaging technology based on the network device transmission and UE reception mode mainly includes the following three steps:

[0137] 1) Network device transmits sensing signal

[0138] The network device sends sensing signals using different antenna ports, and the UE receives the sensing signals after reflection / scattering by the sensing target. The sensing imaging information is obtained using algorithms such as back projection (BP) and discrete Fourier transform (DFT). Generally, the sensing imaging information is a three-dimensional power spectrum with the network device or the UE as the coordinate origin, distance, horizontal angle, and vertical angle. The three-dimensional power spectrum is composed of power values of all position points in the sensing range, wherein each position point corresponds to a certain distance, a certain horizontal angle, a certain vertical angle, and a unique sensing power value. The higher the power value of a certain position point, the stronger the reflection / scattering energy of the sensing signal at the point, and the more likely the point contains a sensing target; otherwise, when the power value of a certain position point is very low, it indicates that the point is likely to not contain a sensing target.

[0139] 2) UE feeds back sensing imaging information to the network device

[0140] The feedback sensing information requires power values of all position points in its coverage range, that is, the imaging area is divided into multiple position grids, each grid is indicated by the center point position or its position index, and the power value of each position point is quantized using multiple bits. To improve imaging resolution and accuracy, the grid is divided into smaller grids and the quantization bits are higher, and the data bit quantity of the sensing imaging information exceeds gigabits. FIG. 6 shows a grid division diagram of the imaging area.

[0141] The network device configures the number of subcarriers N0, the number of horizontal ports N1, the number of vertical ports N2, and the subcarrier oversampling factor O0, the horizontal oversampling factor O1, and the vertical oversampling factor O2 information. The sensing space includes N0O0 values in the distance dimension, N1O1 values in the horizontal angle dimension, and N2O2 values in the vertical angle dimension. Each position point is uniquely determined by the distance, the horizontal angle, and the vertical angle, and therefore contains N0O0N1O1N2O2 position points. Each position point of the sensing space has a unique power value P(s, m, n), s∈[0, N0O0], m∈[0, N1O1], and n∈[0, N2O2].

[0142] For example, the sensing space is a space range with the network device as the coordinate origin, in the subcarrier dimension, the horizontal direction dimension and the vertical direction dimension, which can be determined by the distance R(s) in the subcarrier dimension, the horizontal angle θ(m) in the horizontal direction dimension and the vertical angle θ(n) in the vertical direction dimension. Wherein, R(s) = cu / (2N00Δf), in the formula, c is the speed of light, Δf is the interval of adjacent subcarriers used for sending the sensing signal, s is the subcarrier index after oversampling, the value range of s can be s∈[0, N00]; θ(m) = arcsin(λm / (W10d1)), in the formula, λ is the subcarrier wavelength, d1 is the interval of antenna ports in the horizontal direction, m is the horizontal direction index after oversampling, the value range of m can be m∈[0, N10]; θ(n) = arcsin(λn / (W20d2)), in the formula, λ is the subcarrier wavelength, d2 is the interval of antenna ports in the vertical direction, n is the vertical direction index after oversampling, the value range of n can be n∈[0, N20].

[0143] 3) The network device receives the sensing imaging information fed back by the UE

[0144] The network device receives the sensing imaging information fed back by the UE, and fuses it with the sensing imaging information fed back by other UEs or obtained by the network device itself, so as to increase the power value of the position point where the sensing target exists, and further improve the imaging accuracy.

[0145] 5、AI neural network

[0146] The AI neural network can be used for compression of sensing information, and the network structure can be a convolutional autoencoder, etc., mainly including an AI compression model and an AI decompression model, both of which are composed of a multi-level convolutional neural network and a multi-level deconvolutional neural network, wherein the AI compression model is used to extract feature values of the sensing information to realize compression of the sensing information; and the AI decompression model is used to inversely transform the feature values into the sensing information. The sensing power spectrum is first compressed into feature values by the AI compression model and a quantization operation, and the feature values can be further compressed by arithmetic coding; and the feature values are obtained after the AI decompression model to obtain the restored power spectrum.

[0147] The AI compression model can realize different AI compression rates in two ways.

[0148] Manner one: using different network structures. The AI compression model is composed of multiple levels of convolutional neural networks, each of which includes a convolutional layer, an activation function layer, and a pooling layer. The convolutional layer can generate a set of parallel feature maps, which is composed of different convolutional kernels sliding on the input image and performing certain operations, where each feature map in each set is a channel. In addition, at each sliding position, an element-by-element multiplication and summation operation is performed between the convolutional kernel and the input image to project the information in the receptive field to an element in the feature map. The activation function layer is used to enhance the decision function and the non-linear characteristics of the entire neural network, and can use the linear rectifier (Rectified Linear Units, ReLU) function f(x) = max(0, x) and the like. The pooling layer is a kind of non-linear form of down-sampling, which divides the input image into several rectangular regions according to the pooling step, and outputs the maximum value of each sub-region. Correspondingly, the AI decompression model is composed of multiple levels of deconvolutional neural networks, each of which includes a deconvolutional layer, an activation function, and a depooling layer.

[0149] The compression rate of the convolutional neural network is proportional to the number of channels of the convolutional layer / deconvolutional layer, the stride of the pooling layer / depooling layer, and the number of levels of the convolutional neural network. For example, for the perceptual power spectrum P(s, m, n), s∈[0,N0O0], m∈[0,N1O1], n∈[0,N2O2], if the power value is quantized by 8 bits, the feedback overhead of the power spectrum is 8N0O0N1O1N2O2. The perceptual power spectrum is input into an AI compression model composed of 3 levels of convolutional neural networks, where the number of channels of the convolutional layer in each level of the convolutional neural network is 128, the stride of the pooling layer is 2, and if the feature values of the output feature map are also quantized by 8 bits, the feedback overhead of the compressed feature value codebook is 128*8*N0O0 / 2 3 *N1O1 / 2 3 *N2O2 / 2 3 =128*8 / 512N0O0N1O1N2O2=2N0O0N1O1N2O2, i.e. the compression rate of the AI compression model using this neural network structure is 4. In order to further improve the compression rate to 32, the number of channels of the convolutional layer can be changed from 128 to 16, or the convolutional neural network can be increased from 3 levels to 4 levels. Similarly, by adjusting the number of convolutional layer channels or the number of convolutional neural network levels, AI compression models and decompression models with network structures corresponding to different compression rates are obtained.

[0150] The second mode is that the compression rate is taken as input data to train the same AI compression model and AI decompression model applicable to different compression rates. The AI compression model and the AI decompression model are conditional convolutional neural network structures, each level of the conditional convolutional neural network includes a full connection layer, and the full connection layer takes the compression rate as input data. The AI compression model outputs a characteristic value codebook corresponding to the compression rate according to the input data and the compression rate; and the AI decompression model outputs the recovered input data according to the characteristic value codebook and the compression rate. Therefore, the data compression and recovery can be performed by inputting the compression rate to the AI compression model and the decompression model.

[0151] In the UE-assisted perception imaging scenario based on the network device receiving UE mode, the UE needs to feed back the power value quantized by multiple bits of all position points in the perception space to the network device. If referring to the power value reporting mode based on DFT oversampling in the NR standard, when the spatial network segmentation granularity reaches the decimeter level, the position points of the perception space are dense, and the feedback overhead is high. To solve this technical problem, in the embodiments of the present application, the feedback overhead can be reduced by using an AI-based perception information compression feedback method. Specifically, the UE uses an AI compression model to generate an AI characteristic value codebook with a low number of bits by taking the perception information as input; the UE feeds back the AI characteristic value codebook to realize low feedback overhead; and the network device receives the AI characteristic value codebook and recovers the perception information by using an AI decompression model.

[0152] FIG. 7 is a flowchart of a communication method provided by an embodiment of the present application. The communication method is applicable to the above-mentioned communication system, and mainly involves the interaction between a terminal device and a network device. The network device includes one or more of a perception network core network element, a SU, a gNB, a CU, or a DU. The embodiments of the present application include an information transmission method, the sending end of the information is a first device, and the receiving end of the information is a second device. The first device is a terminal device, and the second device is a network device. The first device and the second device in the present application can also be modules (for example, a processor, a chip, or a chip system, etc.) in the network device or the terminal device, or can also be logical modules or software that can realize all or part of the functions of the network device or the terminal device. For ease of description, the second device is taken as the network device, and the first device is taken as the terminal device in the following description.

[0153] S601, the first device compresses the first perception information by using a second AI model to obtain second perception information.

[0154] The first perception information includes power spectrum information, and the second perception information includes eigenvalue codebook information. In the present application, the power spectrum information can be understood as the power value of all three-dimensional position points of distance-horizontal angle-vertical angle in the perception range or perception information. The perception information can be understood as data obtained by processing received signals or original channel information, such as time delay, Doppler, angle, intensity of sampling points, and multi-dimensional combination representation thereof, such as time delay spread spectrum, Doppler spectrum, micro-Doppler spectrum, angle spectrum, signal intensity spectrum, and the like. The eigenvalue codebook information can be understood as information with a lower bit number after AI model compression processing of the power spectrum information.

[0155] For example, the power spectrum information indicates a three-dimensional power spectrum or a two-dimensional power spectrum. The three-dimensional power spectrum includes a subcarrier dimension, a horizontal direction dimension, and a vertical direction dimension, divides an imaging area into a plurality of position grids, each grid is indicated by a center point position or a position index thereof, and the power value of each position point is quantized using a plurality of bits. For the explanation of the three-dimensional power spectrum, reference can be made to the related description in the above-mentioned feedback of perception imaging information by the UE to the network device, which will not be repeated here. The two-dimensional power spectrum includes two dimensions in the three-dimensional power spectrum, for example, the horizontal direction dimension and the vertical direction dimension, the subcarrier dimension and the horizontal direction dimension, or the subcarrier dimension and the vertical direction dimension.

[0156] For example, the second AI model includes a multi-level three-dimensional convolution layer or a multi-level two-dimensional convolution layer. The power spectrum information is first compressed into an eigenvalue by the second AI model and a quantization operation, and the eigenvalue can be further compressed by arithmetic coding. When the perception power spectrum includes three dimensions, the AI model includes a three-dimensional convolution layer, that is, a three-dimensional convolution operation is performed on the perception power spectrum; when the perception power spectrum includes two dimensions, the AI model includes a two-dimensional convolution layer, that is, a two-dimensional convolution operation is performed on the perception power spectrum. For example, according to the above-mentioned description of the AI compression model, the AI model composed of a 3-level convolutional neural network compresses the three-dimensional power spectrum: if the number of channels of the convolution layer in each level of the convolutional neural network is 128, the stride of the pooling layer is 2, and the eigenvalue of the input and output feature map is quantized by 8 bits, the compression rate of the AI compression model is 4; if the number of channels of the convolution layer in each level of the convolutional neural network is 16, the stride of the pooling layer is 2, and the eigenvalue of the input and output feature map is quantized by 8 bits, the compression rate of the AI compression model is 32.

[0157] It can be understood that the first device reduces the overhead of feedback perception information or power spectrum by sending the second perception information compressed by the second AI model, and improves the perception and transmission performance.

[0158] S602, the first device sends the second perception information, and correspondingly, the second device receives the second perception information.

[0159] Exemplarily, the first device can send the second perception information through an uplink channel, which can be a Physical Uplink Control Channel (PUCCH) or a Physical Uplink Shared Channel (PUSCH), and the present embodiment is not limited in this regard.

[0160] S603, the second device decompresses the second perception information through the first AI model to obtain the first perception information.

[0161] In the present application, the first AI model is a decompression model, and the second AI model is a compression model, which corresponds to the decompression model. It can be understood that the first AI model is deployed in the second device, and the second AI model is deployed in the first device, so as to realize compression of the first perception information in the first device to obtain the second perception information, and decompression of the second perception information in the second device to obtain the first perception information.

[0162] Exemplarily, the first AI model includes a multi-level three-dimensional deconvolution layer or a multi-level two-dimensional deconvolution layer. When the perception power spectrum includes three dimensions, the first AI model includes a three-dimensional deconvolution layer, i.e., a three-dimensional deconvolution operation is performed on the perception power spectrum; when the perception power spectrum includes two dimensions, the first AI model includes a two-dimensional deconvolution layer, i.e., a two-dimensional deconvolution operation is performed on the perception power spectrum. For example, according to the above description of the AI decompression model, the AI decompression model composed of a 3-level deconvolution neural network can decompress a three-dimensional power spectrum: if the number of channels of the deconvolution layer in each deconvolution neural network is 128, the stride of the deconvolution layer is 2, and the feature values of the input and output feature maps are quantized by 8 bits, then the AI compression model with a compression ratio of 4 can be decompressed; if the number of channels of the deconvolution layer in each deconvolution neural network is 16, the stride of the deconvolution layer is 2, and the feature values of the input and output feature maps are quantized by 8 bits, then the AI compression model with a compression ratio of 32 can be decompressed. At this time, the AI decompression model and the AI compression model in S601 are corresponding, and the compression and decompression recovery of the data can be realized.

[0163] It can be understood that the second device can accurately recover the compressed second perception information to obtain the first perception information by using the first AI model corresponding to the second AI model of the first device, so as to realize correct transmission of the perception information with low overhead.

[0164] Optionally, the method further includes S604 before S601. S604, the second device sends the first information, and correspondingly, the first device receives the first information, the first information indicating the second AI model or the compression ratio of the perception information.

[0165] The compression rate is a bit ratio of the first perceptual information to the second perceptual information, a compression level, or a bit per pixel. In this application, the compression rate can be understood as a ratio of the number of bits of the power spectrum information before compression to the number of bits of the eigenvalue codebook after compression, indicating the compression capability of the compression method on the data; or the compression rate can be understood as a bit per pixel (bpp), indicating the number of bits of each position point in the power spectrum; or the compression rate can be understood as a compression level, indicating the compression degree of the first perceptual information, and the higher the compression level, the higher the compression rate. The higher the compression rate, the stronger the compression capability on the data, and the smaller the number of bits of the eigenvalue codebook after compression under the condition that the number of bits of the power spectrum information is the same.

[0166] In a possible implementation, the first information indicates a second AI model, and the second AI model belongs to an AI model set, where different AI models in the AI model set have different network structures or different compression rates. In this application, the different network structures of different AI models in the AI model set can be understood as that different AI models in the AI model set have different numbers of convolution layer channels and / or different numbers of convolution neural network layers. Different numbers of convolution layer channels or different numbers of convolution neural network layers can be considered as different network structures of different AI models. The network structure of a specific AI model is the same as that in the above manner one, which will not be described here. It can be understood that different network structures can also be understood as different compression rates. For example, the more the number of convolution layer channels, the lower the compression rate; the more the number of convolution neural network layers, the higher the compression rate. The first device determines the network structure of the second AI model or the compression rate corresponding to the network structure of the second AI model in the AI model set according to the first information.

[0167] In another possible implementation, the first information indicates a compression rate of the perceptual information. According to the method for implementing different compression rates of different AI models in the above manner two, the compression rate can be used as input data to obtain the same AI compression model and AI decompression model suitable for different compression rates. It can be understood that according to the first information, the AI compression model and the AI decompression model can compress and restore data based on the same compression rate. The first device can use the AI compression model to output the eigenvalue codebook corresponding to the compression rate according to the compression rate and the data; and the second device can use the AI decompression model to output the restored data according to the compression rate and the eigenvalue codebook.

[0168] It can be understood that the second device can indicate the first device to use the second AI model or the compression rate indicated in the first information by sending the first information, so that the second device can use the corresponding first AI model or compression rate to restore the perceptual information. In addition, by sending the first information, the second device can flexibly select different AI models or compression rates to adapt to different application scenarios.

[0169] Optionally, the method further includes S605 before S601. S605, the second device sends a sensing signal, and correspondingly, the first device receives the sensing signal, and the sensing signal is used to determine the first sensing information.

[0170] In the embodiments of the present application, the sensing signal is a reference signal with known initial amplitude and phase for the first device and the second device, a communication signal carrying data, or other wireless signals that can enable the receiving end to know the initial amplitude and phase information. The sensing signal is used by the first device to determine the first sensing information.

[0171] The reception of the sensing signal by the first device can be understood as the reception of a return signal of the sensing signal reflected by the target in the environment. The time delay of the return signal relative to the transmitted sensing signal reflects the distance of the target. The Doppler frequency shift of the return signal relative to the transmitted sensing signal reflects the speed of the target. The power value of the return signal indicates the reflection / scattering energy of the sensing signal at that point.

[0172] Through the above scheme, the first device uses the second AI model to compress the sensing information and sends the compressed feature value codebook information to the second device. The second device uses the first AI model to decompress the feature value codebook information to obtain the sensing information. This sensing information transmission mode of feeding back the feature value codebook information reduces the transmission overhead and improves the sensing and transmission performance. The second device realizes flexible configuration of the AI model or compression rate by sending the first information.

[0173] The device embodiments corresponding to the method embodiments of the present application are introduced below. Only a brief introduction to the device is given below, and the specific implementation steps and details of the scheme can be referred to the method embodiments described above.

[0174] To implement the functions in the methods provided in the present application, the communication device can include hardware structures and / or software modules to implement the above functions in the form of hardware structures, software modules, or hardware structures plus software modules. Whether a certain function in the above functions is executed in the form of hardware structure, software module, or hardware structure plus software module depends on the specific application of the technical solution and the design constraint conditions.

[0175] The communication device for executing the communication method provided in the embodiments of the present application is described in detail below in combination with FIG. 8 and FIG. 9.

[0176] FIG. 8 is a schematic block diagram of a communication device 1000 according to an embodiment of the present application. The communication device 1000 includes a processor 1010 and a communication interface 1020. Optionally, the processor 1010 and the communication interface 1020 can be connected to each other through a bus. The communication device 1000 can be the first device or the second device.

[0177] Optionally, the communication apparatus 1000 can further include a memory 1040. The memory 1040 includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a cache, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a synchronous dynamic random access memory (SDRAM), a hard disk drive (HDD), a register, a solid-state drive (SSD), or a compact disc read-only memory (CD-ROM). The memory 1040 is configured to store relevant instructions and / or data. The memory 1040 can be integrated with the processor 1010 or separately arranged.

[0178] The processor 1010 can be a general purpose processor or a dedicated processor. The processor 1010 can include one or more central processing units (CPUs), application processors, modem processors, graphics processors, image signal processors, digital signal processors (DSPs), video coding processors, controllers, or neural network processors. In the case of the processor 1010 being a CPU, the CPU can be a single core CPU or a multi-core CPU. The processor 1010 can be a signal processor, a chip, or other integrated circuits that can implement the method of the present application, or a part of the foregoing processor, chip, or integrated circuit for processing functions. The processor in the embodiments of the present application can be an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. The general purpose processor can be a microprocessor, or any conventional processor.

[0179] The communication interface 1020 can be an input / output interface or an antenna, which is configured to input or output signals or data, and can also be an input / output circuit.

[0180] Exemplarily, the communication apparatus 1000 is a first device, and the communication apparatus 1000 is configured to perform the following operations: compressing first perception information by using an AI model to obtain second perception information; the first perception information comprises power spectrum information, and the second perception information comprises eigenvalue codebook information; and transmitting the second perception information.

[0181] Exemplarily, the communication apparatus 1000 is a second device, and the communication apparatus 1000 is configured to perform the following operations: receiving second perception information; decompressing the second perception information by using a first AI model to obtain first perception information; the first perception information comprises power spectrum information, and the second perception information comprises eigenvalue codebook information.

[0182] The above description is only exemplary. The communication apparatus 1000 is configured to perform the method or steps related to the first device or the second device in the foregoing method embodiments.

[0183] In a possible implementation, the communication interface 1020 can be a transceiver. The transceiver can include a transmitter configured to perform the transmitting operation and a receiver configured to perform the receiving operation. For example, the processor 1010 is configured to control the transceiver to receive and / or transmit signals.

[0184] In a possible implementation, the communication interface 1020 can also be a communication circuit, a pin, an input / output interface, a bus, or the like.

[0185] The communication apparatus 1000 can include a transmitter but not a receiver. Alternatively, the communication apparatus 1000 can include a receiver but not a transmitter. Whether the communication apparatus 1000 includes the transmitter and the receiver can depend on whether the communication apparatus 1000 performs the transmitting operation and the receiving operation in the foregoing scheme.

[0186] The above description is only exemplary. The specific content can be referred to the content shown in the foregoing method embodiments. The implementation of each operation in FIG. 8 can also correspond to the description of the corresponding method embodiment shown in FIG. 6. For example, the communication apparatus 1000 can be configured to perform the scheme shown in FIG. 7.

[0187] Exemplarily, the communication apparatus 1000 is a first device, and the processor 1010 is configured to compress first perception information by using a second AI model to obtain second perception information, and the communication interface 1020 is configured to transmit the second perception information.

[0188] Exemplarily, the communication apparatus 1000 is a second device, and the communication interface 1020 can be configured to receive second perception information, and the processor 1010 is configured to decompress the second perception information by using a first AI model to obtain first perception information.

[0189] For other implementation manners, refer to the detailed description of the embodiment shown in FIG. 7, which will not be repeated here. It should be understood that the specific process of each component performing the corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0190] FIG. 9 is a schematic block diagram of another communication apparatus 1100 according to an embodiment of the present application. The communication apparatus 1100 can be the first apparatus, or the second apparatus, or a chip or module of the first apparatus or the second apparatus, and is configured to implement the method according to the embodiment shown in FIG. 7. For details, refer to the related description in the method embodiment.

[0191] The communication apparatus 1100 includes a transceiver unit 1110. The transceiver unit 1110 is exemplarily described as follows.

[0192] The transceiver unit 1110 can include a sending unit and a receiving unit. The sending unit is configured to perform the sending action of the communication apparatus, and the receiving unit is configured to perform the receiving action of the communication apparatus. For the sake of description, the sending unit and the receiving unit are combined into one transceiver unit in the embodiments of the present application. This is uniformly described here, and will not be repeated hereinafter. The transceiver unit 1110 can implement the corresponding communication function. The transceiver unit 1110 can also be referred to as a communication interface or a communication module.

[0193] The communication apparatus 1100 can include the sending unit and not include the receiving unit. Alternatively, the communication apparatus 1100 can include the receiving unit and not include the sending unit. Specifically, whether the sending action and the receiving action are included in the above-mentioned scheme performed by the communication apparatus 1100.

[0194] Exemplarily, the transceiver unit 1110 is configured to send or receive the first information, etc.

[0195] Optionally, the communication apparatus 1100 can further include a processing unit 1120, which is configured to perform the processing, coordination, etc. related to the communication apparatus 1100.

[0196] Optionally, the communication apparatus 1100 can further include a processing unit 1120, which is configured to perform the processing, coordination, etc. related to the communication apparatus 1100.

[0197] The above-mentioned content is only exemplarily described. The communication apparatus 1100 will be responsible for performing the related method or step in the above-mentioned method embodiment.

[0198] Optionally, the communication apparatus 1100 further includes a storage unit 1130 configured to store programs or codes for implementing the foregoing method. Alternatively, the storage unit 1130 can be configured to store instructions and / or data, and the processing unit 1120 can read the instructions and / or data in the storage unit 1130, so that the communication apparatus 1100 implements the foregoing method embodiments.

[0199] For implementation, reference can be made to the detailed description of the embodiment shown in FIG. 7. It should be understood that the specific processes of the components performing the corresponding processes have been described in the foregoing method embodiments, and thus will not be described here for brevity.

[0200] When the communication apparatus 1000 in FIG. 8 is a chip, the communication interface 1020 can be a transceiver, an input / output circuit or a communication interface of the chip. The processor 1010 can be an integrated processor on the chip, or a microprocessor, or an integrated circuit. The sending operation of the first device or the second device in the foregoing method embodiments can be understood as the output of the chip, and the receiving operation of the first device or the second device in the foregoing method embodiments can be understood as the input of the chip.

[0201] When the communication apparatus 1100 in FIG. 9 is a chip, the transceiver unit 1110 can be a transceiver, an input / output circuit or a communication interface of the chip. The processing unit 1120 can be an integrated processor on the chip, or a microprocessor, or an integrated circuit. The sending operation of the first device or the second device in the foregoing method embodiments can be understood as the output of the chip, and the receiving operation of the first device or the second device in the foregoing method embodiments can be understood as the input of the chip.

[0202] The present application also provides a chip including a processor configured to call and run instructions stored in a memory, so that a communication apparatus installed with the chip performs the method in any of the examples.

[0203] The present application also provides another chip including an input interface, an output interface and a processor, which are connected through internal connection paths. The processor is configured to execute codes in a memory, and when the codes are executed, the processor is configured to perform the method in any of the examples. Optionally, the chip further includes a memory configured to store computer programs or codes.

[0204] The present application also provides a processor configured to be coupled with a memory, and configured to perform the method and functions of the communication apparatus in any of the embodiments, or configured to perform the method and functions of the first device or the second device in any of the embodiments.

[0205] In another embodiment of the present application, a computer program product containing computer programs or instructions is provided, when the computer program product is run, the method of the foregoing embodiment is implemented.

[0206] The present application also provides a computer program, when the computer program is run, the method of the foregoing embodiment is implemented.

[0207] In another embodiment of the present application, a computer readable storage medium is provided, the computer readable storage medium stores a computer program, when the computer program is run, the method of the foregoing embodiment is implemented.

[0208] The present application also provides a communication system, the communication system comprises a first device and a second device. The first device and the second device are respectively used for executing the method executed by the first device and the second device in the foregoing embodiment.

[0209] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software mode depends on the specific application of the technical solution and the design constraints. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0210] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0211] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0212] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0213] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0214] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially contribute to or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as U disk, mobile hard disk, ROM, RAM, magnetic disk, or optical disk.

Claims

1. A communication method characterized by comprising: The method comprises: compressing first sensing information by an artificial intelligence (AI) model to obtain second sensing information, wherein the first sensing information comprises power spectrum information, and the second sensing information comprises eigenvalue codebook information; and transmitting the second sensing information.

2. The method of claim 1, wherein, The method further comprises: receiving first information, wherein the first information indicates the AI model or a compression rate of sensing information.

3. The method of claim 2, wherein: the first information indicates that the AI model belongs to a set of AI models; and different AI models in the set of AI models have different network structures or different compression rates.

4. The method of claim 3, wherein: different AI models in the set of AI models have different network structures, including: the AI model has different numbers of convolutional layers or different numbers of convolutional neural network layers.

5. The method according to claim 1 or 2, characterized in that, the first information indicates a compression rate of sensing information, the compression of the first sensing information by the AI model to obtain the second sensing information comprises: inputting the first sensing information and the first information into the AI model for compression to obtain the second sensing information.

6. The method of claim 2 or 5, wherein: the compression rate is a bit ratio of the first sensing information to the second sensing information, a compression level, or a bit per pixel.

7. The method of any one of claims 1-6, wherein: the power spectrum information indicates a three-dimensional power spectrum or a two-dimensional power spectrum; the three-dimensional power spectrum comprises a subcarrier dimension, a horizontal direction dimension, and a vertical direction dimension; and the two-dimensional power spectrum comprises a horizontal direction dimension and a vertical direction dimension.

8. The method of any one of claims 1-7, wherein: the AI model comprises a multi-stage three-dimensional convolutional layer or a multi-stage two-dimensional convolutional layer.

9. The method of any one of claims 1-8, wherein: a sensing signal is received, wherein the sensing signal is used to determine the first sensing information.

10. A communication method characterized by comprising: The method comprises: receiving second sensing information, decompressing the second sensing information by a first artificial intelligence (AI) model to obtain first sensing information, wherein the first sensing information comprises power spectrum information, and the second sensing information comprises eigenvalue codebook information.

11. The method of claim 10, wherein, The method further comprises: transmitting first information, wherein the first information indicates a second AI model or a compression rate of sensing information; the second sensing information is information compressed by the second AI model.

12. The method of claim 11, wherein: the first information indicates that the second AI model belongs to a set of AI models; and different AI models in the set of AI models have different network structures or different compression rates.

13. The method of claim 12, wherein: different AI models in the set of AI models have different network structures, including: the AI model has different numbers of convolutional layers or different numbers of convolutional neural network layers.

14. The method of claim 10 or 11, wherein, The first information indicates a compression rate of the perception information, The second perception information is decompressed by the first AI model to obtain the first perception information, including: The second perception information and the first information are input into the AI model for decompression to obtain the first perception information.

15. The method of claim 11 or 14, wherein, The compression rate is a bit ratio of the first perception information and the second perception information, a compression level, or a bit per pixel.

16. The method of any one of claims 10-15, wherein, The power spectrum information indicates a three-dimensional power spectrum or a two-dimensional power spectrum; the three-dimensional power spectrum includes a subcarrier dimension, a horizontal direction dimension, and a vertical direction dimension; and the two-dimensional power spectrum includes a horizontal direction dimension and a vertical direction dimension.

17. The method of any one of claims 10-16, wherein, The first AI model and the second AI model include a multi-level three-dimensional convolution layer or a multi-level two-dimensional convolution layer.

18. The method of any one of claims 10-17, wherein, The first AI model includes a decompression model of a convolutional autoencoder, and the second AI model includes a compression model of the convolutional autoencoder, the compression model of the convolutional autoencoder corresponding one-to-one to the decompression model of the convolutional autoencoder.

19. The method of any one of claims 10-18, wherein, A perception signal is transmitted, the perception signal being used to determine the first perception information.

20. A communications device, characterized by A method as claimed in any one of claims 1 to 9.

21. The communication apparatus according to claim 20, wherein, The communication device is a terminal device or a chip.

22. A communications device, characterized by A method as claimed in any one of claims 10 to 19.

23. The communication apparatus according to claim 22, wherein, The communication device is a network device or a chip.

24. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program or instructions, when the computer program or the instructions are executed, causing a method as claimed in any one of claims 1 to 9 to be implemented, or causing a method as claimed in any one of claims 10 to 19 to be implemented.

25. A computer program product, characterised in that, The computer readable storage medium stores a computer program or instructions, when the computer program or the instructions are executed, causing a method as claimed in any one of claims 1 to 9 to be implemented, or causing a method as claimed in any one of claims 10 to 19 to be implemented.

26. A communication system, characterized by The communication system includes a first device and a second device, wherein, The first device is configured to perform a method as claimed in any one of claims 1 to 9; The second device is configured to perform a method as claimed in any one of claims 10 to 19.

27. The communication system of claim 26, wherein, The first device is a terminal device, and the second device is a network device, the network device including a perception function module.

Images