Communication method and related equipment

Abstract

The invention provides a communication method and related equipment, which are used for enabling the computing power of a communication node to be applied to the processing of an artificial intelligence (AI) task and reducing the processing time delay at the same time. In the method, a first communication device performs first processing on first data to obtain second data; wherein the first data is obtained based on artificial intelligence (AI) data, and the first processing comprises first neural network processing; and the first communication device sends third data, wherein the third data is obtained through first transform domain processing based on the second data.

Description

A communication method and related equipment Technical Field

[0001] The present application relates to the field of communications, and in particular to a communication method and related equipment. Background Art

[0002] Wireless communication can be the transmission communication between two or more communication nodes without propagating through conductors or cables. The communication nodes generally include network devices and terminal devices.

[0003] Currently, in wireless communication systems, communication nodes generally possess both signal transceiver capabilities and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (e.g., processing both sending and receiving signals), enabling communication between the network device and other communication nodes.

[0004] However, in communication networks, communication nodes may have excess computing power beyond just supporting the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical issue.

[0005] Summary of the Invention

[0006] The present application provides a communication method and related equipment for enabling the computing power of communication nodes to be applied to the processing of artificial intelligence (AI) tasks while also reducing processing latency.

[0007] In the first aspect of the present application, a communication method is provided, which is performed by a first communication device, or the method is performed by some components in the first communication device (such as a processor, a chip or a chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the functions of the first communication device. In the first aspect and its possible implementation, the method is described as being performed by a first communication device. For example, the first communication device can be a communication node such as a terminal device or a network device in a communication system. In this method, the first communication device performs a first processing on the first data to obtain second data; wherein the first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing; the first communication device sends third data, and the third data is obtained based on the second data after being processed in the first transform domain.

[0008] Based on the above technical solution, after the first communication device performs a first processing on the first data to obtain the second data, the first communication device performs a first transform domain processing on the second data to obtain the third data, and sends the third data. The first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing. In other words, the second data is the processing result obtained by the first communication device performing at least the first neural network processing on the first data, and the third data sent by the first communication device is the processing result obtained by the first transform domain processing of the second data, wherein the first transform domain processing is one of the processes of the physical layer processing. Thus, when the communication device in the communication system acts as a node participating in the AI ​​task, the computing power of the communication device can be applied to the processing of the AI ​​task.

[0009] In addition, compared to the implementation method in which the communication device obtains the processing results through neural network processing at the application layer, quantizes the results, and then processes the quantized results through the communication signal processing at the physical layer during the process of sending data, in the above technical solution, the first communication device can use the processing results obtained by the neural network processing as the input of the transform domain processing in the physical layer, so that the first communication device can realize AI data processing without performing quantization processing, which can enable the computing power of the communication device to be applied to AI tasks while reducing processing delays.

[0010] It should be understood that the terms AI, neural network, AI neural network, machine learning, AI processing, AI neural network processing, etc. can be used interchangeably.

[0011] It should be understood that the data involved in this application (such as the first data, the second data, the third data, and other data mentioned later, including the fourth data to the eighth data, etc.) can be replaced by information, signals, etc.

[0012] In a possible implementation manner of the first aspect, the first data is obtained based on AI data, including: the first data is obtained by subjecting the AI ​​data to resource mapping processing and / or second transform domain processing.

[0013] Based on the above technical solution, the first data can be obtained by subjecting AI data to resource mapping processing and / or second transform domain processing, wherein the first communication device can subject the AI ​​data to resource mapping processing and / or second transform domain processing to obtain the first data, and then use the first data as input to a first process that includes at least a first neural network to obtain the second data. In other words, the AI ​​data can be used as input to the resource mapping process and / or the second transform domain, so that the first communication device does not need to perform other physical layer processing (such as encoding, rate matching, scrambling, modulation, etc.) before the resource mapping process during the transmission link processing of the communication signal, which can further reduce processing latency.

[0014] It should be understood that when the first data is obtained by at least resource mapping processing of AI data, the resource mapping processing can map the AI ​​data to the physical layer transmission resources, so that subsequent transmission of AI data can be adapted to the physical layer transmission resources.

[0015] It should be understood that when the first data is obtained by processing the AI ​​data at least in the second transform domain, the second transform domain processing can sample and transform the AI ​​data to obtain data suitable for the input of the first neural network.

[0016] Optionally, the second data is a result of performing at least the first neural network processing on the first data, that is, the first data can be used as the input of the first neural network, and the first data may not be obtained by subjecting the AI ​​data to resource mapping processing and / or second transform domain processing. In other words, the function of the first neural network processing includes resource mapping processing and / or second transform domain processing, that is, the same or similar processing effect of resource mapping processing and / or second transform domain processing can be achieved through processing by the first neural network without the need for device processing corresponding to resource mapping processing and / or second transform domain processing.

[0017] In a possible implementation manner of the first aspect, the resource mapping process includes at least one of the following: dimensionality conversion processing, translation processing, rotation processing, and interleaving processing.

[0018] Based on the above technical solution, when AI data is used as input for resource mapping processing, the AI ​​data can undergo at least one of the above processing to enhance the flexibility of the solution implementation.

[0019] In a possible implementation of the first aspect, the first processing also includes filtering processing, such as root raised cosine filter (RRC) processing, or the filtering processing may include Bessel filtering, Butterworth filtering, Chebyshev filtering, elliptic filtering and other filtering processing.

[0020] Based on the above technical solution, the first processing may include, in addition to the first neural network processing, a filtering processing to filter the communication signal and reduce the peak to average power ratio (PAPR) of the communication signal.

[0021] Optionally, the second data is a result of performing at least the first neural network processing in the first processing on the first data. That is, the first data can serve as input to the first neural network, and the first processing may not include RRC filtering. In other words, the function of the first neural network processing includes filtering, that is, the same or similar processing effect as the filtering processing can be achieved through the processing of the first neural network without the need for processing by a device corresponding to the filtering processing.

[0022] In a possible implementation manner of the first aspect, the method further includes: the first communication device receiving fourth data, wherein the AI ​​data is obtained based on the fourth data.

[0023] Based on the above technical solution, the AI ​​data of the first communication device can be obtained by receiving the fourth data, so that when the first communication device participates in the AI ​​task, the first communication device can serve as an intermediate node for multiple nodes participating in the AI ​​task.

[0024] Optionally, when the AI ​​data is not obtained based on data received by the first communication device, the AI ​​data may be data generated locally by the first communication device (or preconfigured data). Accordingly, the first communication device may serve as the head node (or starting node) of multiple nodes participating in the AI ​​task.

[0025] In a possible implementation of the first aspect, the method further includes: the first communication device performs a second processing on the fourth data to obtain the AI ​​data; wherein the second processing includes a second neural network processing.

[0026] Based on the above technical solution, when the AI ​​data of the first communication device is obtained by receiving fourth data, the first communication device can perform second processing on the fourth data, including at least second neural network processing, to obtain the AI ​​data. In other words, after receiving the fourth data, the first communication device can at least perform second neural network processing on the fourth data to obtain AI data for the transmit link. As a result, on the receive link of the first communication device, the second neural network processing can be used to participate in AI tasks, allowing the first communication device to participate in AI tasks through the first and second neural networks.

[0027] In a possible implementation of the first aspect, the first communication device performs the second processing on the fourth data to obtain the AI ​​data, including: the first communication device performs the second processing on the fourth data to obtain fifth data; wherein, the AI ​​data is obtained by subjecting the fifth data to the first transform domain processing and / or resource demapping processing.

[0028] Based on the above technical solution, after the first communication device receives the fourth data, the first communication device can perform a second processing on the received fourth data to obtain the fifth data. In addition, the first communication device can perform the first transform domain processing and / or de-resource mapping processing on the fifth data to obtain the AI ​​data. In other words, the fifth data, as the processing result of the second neural network, can be used as the input of the first transform domain processing and / or de-resource mapping processing. Compared with the implementation method in which the communication device processes the received data through the physical layer, dequantizes the physical layer processing result to obtain application layer data, and then performs neural network processing on the de-quantized data, in the above technical solution, the first communication device can use the processing result obtained by the neural network processing of the received data as the input of the transform domain processing and / or de-resource mapping processing in the physical layer, so that the first communication device can implement the neural network processing without performing de-quantization processing on the received data, which can enable the computing power of the communication device to be applied to AI tasks while also reducing processing latency.

[0029] In addition, the AI ​​data may be data on the transmission link of the first communication device (for example, the AI ​​data may be input for resource mapping processing and / or second transform domain processing on the transmission link). In the above technical solution, the AI ​​data is obtained by subjecting the fifth data to the first transform domain processing and / or de-resource mapping processing, that is, the processing results of the first transform domain processing and / or de-resource mapping processing on the receiving link of the first communication device can be used as input for a certain processing on the transmission link. In this way, the first communication device can avoid performing other physical layer processing (for example, demodulation, descrambling, de-rate matching, channel decoding, etc.) after the de-resource mapping processing during the receiving link processing of the communication signal, thereby further reducing processing delay.

[0030] In a possible implementation of the first aspect, the first communication device performs second processing on the fourth data to obtain fifth data, including: the first communication device performs second transform domain processing on the fourth data to obtain sixth data; and the first communication device performs the second processing on the sixth data to obtain the fifth data.

[0031] Based on the above technical solution, the first communication device can perform second transform domain processing on the fourth data to obtain sixth data; thereafter, the first communication device can perform second processing on the sixth data to obtain fifth data. The sixth data serves as input to a second process that includes at least a second neural network. The second transform domain processing can sample and transform the AI ​​data to obtain sixth data that is suitable for input to the second neural network.

[0032] In a possible implementation manner of the first aspect, the resource demapping process includes at least one of the following: dimensionality conversion processing, translation processing, rotation processing, and interleaving processing.

[0033] Based on the above technical solution, when AI data is used as the output of the resource de-mapping process, the AI ​​data can be the fifth data obtained by processing at least one of the above items to enhance the flexibility of the solution implementation.

[0034] In a possible implementation of the first aspect, the second processing further includes filtering processing, such as RRC filtering processing, or the filtering processing may include Bessel filtering, Butterworth filtering, Chebyshev filtering, elliptic filtering, and other filtering processing.

[0035] Based on the above technical solution, the second processing may include filtering processing in addition to the second neural network processing, so as to filter the communication signal through the filtering processing and reduce the PAPR of the communication signal.

[0036] Optionally, the fifth data is a result of the first communication device performing at least the second neural network processing in the second processing on the fourth data. That is, the fourth data can serve as input to the second neural network, and the second processing may not include filtering. In other words, the function of the second neural network processing includes filtering, meaning that the same or similar processing effect as filtering can be achieved through the second neural network processing without the need for processing by a device corresponding to the filtering processing.

[0037] Optionally, the second transform domain processing includes any one of the following: Fourier transform processing, wavelet transform processing, wherein the Fourier transform processing may include fast Fourier transform (FFT), discrete Fourier transform (DFT), etc.

[0038] Optionally, the first transform domain processing includes any one of the following: inverse Fourier transform processing, inverse wavelet transform processing, wherein the inverse Fourier transform may include inverse fast Fourier transform (IFFT), inverse discrete Fourier transform (IDFT), etc.

[0039] In a possible implementation manner of the first aspect, the AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

[0040] Based on the above technical solution, the first communication device can participate in the AI ​​task. Accordingly, the AI ​​data processed by the first communication device may include the original data of the AI ​​task and / or the feature data of the AI ​​task to enhance the flexibility of the solution implementation.

[0041] In a possible implementation of the first aspect, the third data is obtained based on the second data processed by the first transform domain, including: the third data is obtained based on the processing result obtained by processing the second data by the first transform domain and the fourth data; or, the third data is obtained based on the processing result obtained by processing the second data by the first transform domain.

[0042] Based on the above technical solution, the third data sent by the first communication device may include any of the above implementations, so that the data sent by the first communication device can adapt to the processing requirements of different AI network architectures.

[0043] The second aspect of the present application provides a communication method, which is performed by a second communication device, or the method is performed by some components in the second communication device (such as a processor, chip or chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the functions of the second communication device. In the second aspect and its possible implementation, the method is described as being performed by the second communication device. For example, the second communication device can be a communication node such as a terminal device or a network device in a communication system. In this method, the second communication device receives third data; the second communication device performs a second transform domain processing on the third data to obtain seventh data; the second communication device performs a second processing on the seventh data to obtain AI data; wherein the second processing includes a second neural network processing.

[0044] Based on the above technical solution, the second communication device performs second transform domain processing on the received third data to obtain seventh data. Thereafter, the second communication device performs second processing on the seventh data to obtain AI data; wherein the second processing includes second neural network processing. In other words, the AI ​​data is the processing result obtained by the second communication device performing at least the second neural network processing on the seventh data, and the seventh data is the processing result obtained by performing second transform domain processing on the third data received by the second communication device, wherein the second transform domain processing is one of the processes of physical layer processing. Thus, when a communication device in a communication system serves as a node participating in an AI task, the computing power of the communication device can be applied to the processing of the AI ​​task.

[0045] In addition, compared to the implementation method in which the communication device processes the received data through the physical layer, dequantizes the physical layer processing results to obtain application layer data, and then performs neural network processing on the dequantized data, in the above technical solution, the second communication device can process the received data through the second transform domain in the physical layer, and use the processing results of the second transform domain processing as input for the neural network processing, so that the second communication device can implement neural network processing without performing dequantization processing on the received data, which can enable the computing power of the communication device to be applied to AI tasks while reducing processing delays.

[0046] In addition, the AI ​​data determined by the second communication device can be obtained by receiving the third data, so that when the second communication device participates in the AI ​​task, the second communication device can serve as an intermediate node or tail node (or termination node) of multiple nodes participating in the AI ​​task.

[0047] In a possible implementation of the second aspect, the second communication device performs a second processing on the seventh data to obtain AI data, including: the second communication device performs the second processing on the seventh data to obtain eighth data, wherein the AI ​​data is obtained by subjecting the eighth data to first transform domain processing and / or resource demapping processing.

[0048] Based on the above technical solution, the second communication device can perform a second process on the seventh data to obtain eighth data; thereafter, the second communication device can perform a first transform domain process and / or a de-resource mapping process on the eighth data to obtain AI data. The seventh data serves as input to a second process that includes at least a second neural network. The second transform domain process can sample and transform the AI ​​data to obtain seventh data that is suitable for input to the second neural network.

[0049] In addition, in the above technical solution, the AI ​​data is obtained by subjecting the eighth data to the first transform domain processing and / or de-resource mapping processing, that is, the first transform domain processing and / or de-resource mapping processing on the receiving link in the second communication device can obtain the AI ​​data. In this way, the second communication device can process the communication signal through the receiving link without performing other physical layer processing (such as demodulation, de-scrambling, rate matching, channel decoding, etc.) after the de-resource mapping processing, which can further reduce the processing delay.

[0050] In a possible implementation manner of the second aspect, the resource demapping process includes at least one of the following: dimensionality conversion processing, translation processing, rotation processing, and interleaving processing.

[0051] Based on the above technical solution, when AI data is used as the output of resource de-mapping processing, the AI ​​data can be the eighth data obtained by processing at least one of the above items to improve the flexibility of the solution implementation.

[0052] In a possible implementation manner of the second aspect, the second processing further includes filtering processing, such as RRC filtering processing.

[0053] Based on the above technical solution, the second processing may include filtering processing in addition to the second neural network processing, so as to filter the communication signal through the filtering processing and reduce the PAPR of the communication signal.

[0054] Optionally, the AI ​​data serves as a processing result obtained by the second communication device performing at least the second neural network processing in the second processing on the seventh data. That is, the seventh data may serve as input to the second neural network, and the second processing may not include filtering. In other words, the function of the second neural network processing includes filtering, meaning that the same or similar processing effect as filtering can be achieved through the second neural network processing without the need for processing by a device corresponding to the filtering processing.

[0055] Optionally, the second transform domain processing includes any one of the following: Fourier transform processing, wavelet transform processing.

[0056] Optionally, the first transform domain processing includes any one of the following: inverse Fourier transform processing, inverse wavelet transform processing.

[0057] In a possible implementation manner of the second aspect, the AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

[0058] Based on the above technical solution, the second communication device can participate in the AI ​​task. Accordingly, the AI ​​data processed by the second communication device may include the original data of the AI ​​task and / or the feature data of the AI ​​task to enhance the flexibility of the solution implementation.

[0059] In a third aspect of the present application, a communication device is provided, which is a first communication device, or a component (such as a processor, chip, or chip system) in the first communication device, or a logic module or software capable of implementing all or part of the functions of the first communication device. In the third aspect and its possible implementations, the communication device is described as a first communication device, and the first communication device can be a terminal device or a network device.

[0060] The device includes a processing unit and a transceiver unit; the processing unit is used to perform a first processing on the first data to obtain second data; wherein the first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing; the transceiver unit is used to send the third data, and the third data is obtained based on the second data after being processed in the first transform domain.

[0061] In a possible implementation manner of the third aspect, the first data is obtained based on AI data, including: the first data is obtained by subjecting the AI ​​data to resource mapping processing and / or second transform domain processing.

[0062] In a possible implementation manner of the third aspect, the resource mapping process includes at least one of the following: dimensionality conversion processing, translation processing, rotation processing, and interleaving processing.

[0063] In a possible implementation manner of the third aspect, the first processing further includes filtering processing, such as root raised cosine RRC filtering processing.

[0064] In a possible implementation manner of the third aspect, the transceiver unit is further configured to receive fourth data, wherein the AI ​​data is obtained based on the fourth data.

[0065] In a possible implementation of the third aspect, the processing unit is further used to perform a second processing on the fourth data to obtain the AI ​​data; wherein the second processing includes a second neural network processing.

[0066] In a possible implementation of the third aspect, the processing unit is used to perform the second processing on the fourth data to obtain the AI ​​data, including: the processing unit performs the second processing on the fourth data to obtain fifth data; wherein, the AI ​​data is obtained by subjecting the fifth data to the first transform domain processing and / or de-resource mapping processing.

[0067] In a possible implementation of the third aspect, the processing unit performs the second processing on the fourth data to obtain the fifth data, including: the processing unit performs the second transform domain processing on the fourth data to obtain the sixth data; and the processing unit performs the second processing on the sixth data to obtain the fifth data.

[0068] In a possible implementation manner of the third aspect, the resource demapping process includes at least one of the following: dimensionality conversion processing, translation processing, rotation processing, and interleaving processing.

[0069] In a possible implementation manner of the third aspect, the second processing further includes filtering processing, such as RRC filtering processing.

[0070] In a possible implementation manner of the third aspect, the second transform domain processing includes any one of the following: Fourier transform processing and wavelet transform processing.

[0071] In a possible implementation manner of the third aspect, the first transform domain processing includes any one of the following: inverse Fourier transform processing and inverse wavelet transform processing.

[0072] In a possible implementation manner of the third aspect, the AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

[0073] In a possible implementation of the third aspect, the third data is obtained based on the second data processed by the first transform domain, including: the third data is obtained based on the processing result obtained by processing the second data by the first transform domain and the fourth data; or, the third data is obtained based on the processing result obtained by processing the second data by the first transform domain.

[0074] In a fourth aspect of the present application, a communication device is provided, which is a second communication device, or the device is a partial component (such as a processor, chip, or chip system) in the second communication device, or the device can also be a logic module or software that can implement all or part of the functions of the second communication device. In the eighth aspect and its possible implementation, the communication device is described as an example of the second communication device, and the second communication device can be a terminal device or a network device.

[0075] The device includes a processing unit and a transceiver unit; the transceiver unit is used to receive third data; the processing unit is used to perform a second transform domain processing on the third data to obtain seventh data; the processing unit is also used to perform a second processing on the seventh data to obtain AI data; wherein the second processing includes a second neural network processing.

[0076] In a possible implementation of the fourth aspect, the processing unit is used to perform a second processing on the seventh data to obtain AI data, including: the processing unit performs the second processing on the seventh data to obtain eighth data, wherein the AI ​​data is obtained by subjecting the eighth data to first transform domain processing and / or de-resource mapping processing.

[0077] In a possible implementation manner of the fourth aspect, the resource demapping process includes at least one of the following: dimensionality conversion processing, translation processing, rotation processing, and interleaving processing.

[0078] In a possible implementation manner of the fourth aspect, the second processing further includes filtering processing, such as RRC filtering processing.

[0079] In a possible implementation manner of the fourth aspect, the second transform domain processing includes any one of the following: Fourier transform processing and wavelet transform processing.

[0080] In a possible implementation manner of the fourth aspect, the first transform domain processing includes any one of the following: inverse Fourier transform processing and inverse wavelet transform processing.

[0081] In a possible implementation manner of the fourth aspect, the AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

[0082] In a fifth aspect, the present application provides a communication device, comprising at least one processor, wherein the at least one processor is coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the program or instructions so that the device implements the method described in any possible implementation method of any one of the first to second aspects.

[0083] In a sixth aspect, the present application provides a communication device comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute the method described in any possible implementation of any one of the first to second aspects.

[0084] In a seventh aspect, the present application provides a communication system, which includes the above-mentioned first communication device and second communication device.

[0085] Optionally, the communication system further includes a first data sending device and a first data receiving device. The first data sending device may be the first communication device, the second communication device, or another communication device, and the first data receiving device may also be the first communication device, the second communication device, or another communication device.

[0086] In an eighth aspect, the present application provides a computer-readable storage medium for storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in any possible implementation of any one of the first to second aspects above.

[0087] In a ninth aspect, the present application provides a computer program product (or computer program). When the computer program in the computer program product is executed by the processor, the processor executes the method described in any possible implementation of any one of the first to second aspects above.

[0088] In a tenth aspect, the present application provides a chip system comprising at least one processor for supporting a communication device to implement the method described in any possible implementation of any one of the first to second aspects.

[0089] In one possible design, the chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of a chip or may include a chip and other discrete components. Optionally, the chip system may further include an interface circuit for providing program instructions and / or data to the at least one processor.

[0090] Among them, the technical effects brought about by any design method in the third to tenth aspects can refer to the technical effects brought about by the different design methods in the above-mentioned first to second aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] Figures 1a to 1c are schematic diagrams of a communication system provided by this application;

[0092] Figures 1d, 1e, and 2a to 2f are schematic diagrams of the AI ​​processing process involved in this application;

[0093] FIG3 is an interactive schematic diagram of the communication method provided by this application;

[0094] Figures 4a to 4c are schematic diagrams of the AI ​​processing process provided by this application;

[0095] FIG5 is another schematic diagram of the AI ​​processing process provided by this application;

[0096] FIG6 is another interactive schematic diagram of the communication method provided by this application;

[0097] FIG7 is another schematic diagram of the AI ​​processing process provided by this application;

[0098] FIG8 is a schematic diagram of a communication device provided by the present application;

[0099] FIG9 is another schematic diagram of a communication device provided by the present application;

[0100] FIG10 is another schematic diagram of the communication device provided by the present application;

[0101] FIG11 is another schematic diagram of a communication device provided by the present application;

[0102] FIG12 is another schematic diagram of the communication device provided in this application. DETAILED DESCRIPTION

[0103] First, some of the terms used in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0104] (1) Terminal device: It can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0105] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (also known as "cellular" phones, mobile phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted mobile devices that exchange voice and / or data with the radio access network. Examples include personal communication service (PCS) phones, cordless phones, Session Initiation Protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablet computers, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be called system, subscriber unit, subscriber station, mobile station, mobile station (MS), remote station, access point (AP), remote terminal equipment (remote terminal), access terminal equipment (access terminal), user terminal equipment (user terminal), user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), etc.

[0106] As an example and not a limitation, in the embodiments of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices or smart wearable devices, etc., which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, etc., as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets, smart helmets, and smart jewelry for vital sign monitoring.

[0107] The terminal may also be a drone, a robot, a terminal in device-to-device (D2D) communication, a terminal in vehicle-to-everything (V2X), a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc.

[0108] In addition, the terminal device may also be a terminal device in a communication system that has evolved after the fifth generation (5G) communication system (e.g., a sixth generation (6G) communication system) or a terminal device in a future public land mobile network (PLMN). For example, the 6G network can further expand the form and function of 5G communication terminals. 6G terminals include but are not limited to vehicles, cellular network terminals (with integrated satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0109] In an embodiment of the present application, the terminal device may also obtain AI services provided by the network device. Optionally, the terminal device may also have AI processing capabilities.

[0110] (2) Network equipment: It can be a device in a wireless network. For example, the network equipment can be a RAN node (or device) that connects a terminal device to a wireless network, which can also be called a base station. Currently, some examples of RAN equipment include: base station, evolved NodeB (eNodeB), gNB (gNodeB) in a 5G communication system, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point AP, etc. In addition, in a network structure, the network equipment can include a centralized unit (CU) node, a distributed unit (DU) node, or a RAN device including a CU node and a DU node.

[0111] Alternatively, a RAN node can be a macro base station, micro base station, indoor base station, relay node, donor node, or a wireless controller in a cloud radio access network (CRAN) scenario. A RAN node can also be a server, wearable device, vehicle, or vehicle-mounted device. For example, the access network device in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0112] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN node can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or they can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0113] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open access network (open RAN, O-RAN or ORAN) system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application takes CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of 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.

[0114] The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: 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. The user plane protocol layer may include at least one of the following: a service data adaptation protocol (SDAP) layer, a PDCP layer, an RLC layer, a MAC layer, or a physical layer.

[0115] For the correspondence between network elements in the ORAN system and their achievable protocol layer functions, please refer to Table 1 below.

[0116] Table 1

[0117] The network device may be any other device that provides wireless communication functionality to the terminal device. The embodiments of this application do not limit the specific technology and device form used by the network device. For ease of description, the embodiments of this application do not limit this.

[0118] The network equipment may also include core network equipment, which may include, for example, a mobility management entity (MME), a home subscriber server (HSS), a serving gateway (S-GW), a policy and charging rules function (PCRF), and a public data network gateway (PDN gateway, P-GW) in a fourth generation (4G) network; and network elements such as an access and mobility management function (AMF), a user plane function (UPF), or a session management function (SMF) in a 5G network. In addition, the core network equipment may also include other core network equipment in a 5G network and a next generation network of a 5G network.

[0119] In an embodiment of the present application, the above-mentioned network device may also have a network node with AI capabilities, which can provide AI services for terminals or other network devices. For example, it can be an AI node on the network side (access network or core network), a computing power node, a RAN node with AI capabilities, a core network element with AI capabilities, etc.

[0120] In the embodiments of the present application, the apparatus for implementing the function of the network device may be the network device, or may be a device capable of supporting the network device in implementing the function, such as a chip system, which may be installed in the network device. In the technical solutions provided in the embodiments of the present application, the technical solutions provided in the embodiments of the present application are described by taking the network device as an example.

[0121] (3) Configuration and pre-configuration: In this application, configuration and pre-configuration are used simultaneously. Configuration refers to the network device / server sending some parameter configuration information or parameter values ​​to the terminal through messages or signaling, so that the terminal can determine the communication parameters or resources during transmission based on these values ​​or information. Pre-configuration is similar to configuration, and can be parameter information or parameter values ​​pre-negotiated between the network device / server and the terminal device, or parameter information or parameter values ​​used by the base station / network device or terminal device as specified in the standard protocol, or parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0122] Furthermore, these values ​​and parameters can be changed or updated.

[0123] (4) The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "Multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. In addition, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects.

[0124] (5) “Sending” and “receiving” in the embodiments of the present application indicate the direction of signal transmission. For example, “sending information to XX” can be understood as the destination of the information being XX, which can include direct sending through the air interface, as well as indirect sending through the air interface by other units or modules. “Receiving information from YY” can be understood as the source of the information being YY, which can include direct receiving from YY through the air interface, as well as indirect receiving from YY through the air interface from other units or modules. “Sending” can also be understood as the “output” of the chip interface, and “receiving” can also be understood as the “input” of the chip interface.

[0125] In other words, sending and receiving can be performed between devices, for example, between a network device and a terminal device, or can be performed within a device, for example, sending or receiving between components, modules, chips, software modules or hardware modules within the device through a bus, wiring or interface.

[0126] It is understandable that information may be processed between the source and destination of information transmission, such as coding, modulation, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be repeated.

[0127] (6) In the embodiments of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the indication information described below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated may also be indirectly indicated by indicating other information, wherein the other information is associated with the information to be indicated; or only a part of the information to be indicated may be indicated, while the other part of the information to be indicated is known or agreed in advance. For example, the indication of specific information may be achieved by means of the arrangement order of each information agreed in advance (such as predefined by the protocol), thereby reducing the indication overhead to a certain extent. The present application does not limit the specific method of indication. It is understandable that for the sender of the indication information, the indication information can be used to indicate the information to be indicated, and for the receiver of the indication information, the indication information can be used to determine the information to be indicated.

[0128] In this application, unless otherwise specified, the same or similar parts between the various embodiments can refer to each other. In the various embodiments of this application, and the various methods / designs / implementations in each embodiment, if there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments and the various methods / designs / implementations in each embodiment are consistent and can be referenced to each other. The technical features in different embodiments and the various methods / designs / implementations in each embodiment can be combined to form new embodiments, methods, or implementations according to their inherent logical relationships. The following description of the implementation methods of this application does not constitute a limitation on the scope of protection of this application.

[0129] The present application can be applied to a long term evolution (LTE) system, a new radio (NR) system, or a communication system evolved after 5G (such as 6G, etc.). The communication system includes at least one network device and / or at least one terminal device.

[0130] Please refer to Figure 1a, which is a schematic diagram of a communication system in this application. Figure 1a exemplarily illustrates a network device and six terminal devices, namely terminal device 1, terminal device 2, terminal device 3, terminal device 4, terminal device 5, and terminal device 6. In the example shown in Figure 1a, terminal device 1 is a smart teacup, terminal device 2 is a smart air conditioner, terminal device 3 is a smart gas pump, terminal device 4 is a vehicle, terminal device 5 is a mobile phone, and terminal device 6 is a printer.

[0131] As shown in Figure 1a, the AI ​​configuration information sending entity can be a network device. The AI ​​configuration information receiving entity can be terminal devices 1-6. In this case, the network device and terminal devices 1-6 form a communication system. In this communication system, terminal devices 1-6 can send data to the network device, and the network device needs to receive data sent by terminal devices 1-6. At the same time, the network device can send configuration information to terminal devices 1-6.

[0132] For example, in Figure 1a, terminal devices 4 and 6 can also form a communication system. Terminal device 5 serves as a network device, i.e., the AI ​​configuration information sending entity; terminal devices 4 and 6 serve as terminal devices, i.e., the AI ​​configuration information receiving entities. For example, in a connected vehicle system, terminal device 5 sends AI configuration information to terminal devices 4 and 6, respectively, and receives data from them. Correspondingly, terminal devices 4 and 6 receive AI configuration information from terminal device 5 and send data to terminal device 5.

[0133] Taking the communication system shown in Figure 1a as an example, in addition to executing communication-related services, different devices (including between network devices, between network devices and terminal devices, and / or between terminal devices) may also execute AI-related services.

[0134] As shown in Figure 1b, taking the network device as a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services.

[0135] As shown in Figure 1c, taking the terminal devices including a TV and a mobile phone as an example, communication-related services and AI-related services can also be performed between the TV and the mobile phone.

[0136] The technical solution provided in this application can be applied to a wireless communication system (e.g., the system shown in FIG. 1a , FIG. 1b , or FIG. 1c ). For example, an AI network element can be introduced into the communication system provided in this application to implement some or all AI-related operations. The AI ​​network element can also be referred to as an AI node, AI device, AI entity, AI module, AI model, or AI unit, etc. The AI ​​network element can be a network element built into the communication system. For example, the AI ​​network element can be an AI module built into: an access network device, a core network device, a cloud server, or a network management (OAM) to implement AI-related functions. The OAM can be a network management device for a core network device and / or a network management device for an access network device. Alternatively, the AI ​​network element can also be an independently set network element in the communication system. Optionally, the terminal or the chip built into the terminal can also include an AI entity to implement AI-related functions.

[0137] The following is a brief introduction to artificial intelligence (AI) that may be involved in this application.

[0138] Artificial intelligence (AI) can imbue machines with human intelligence. For example, it can enable machines to simulate certain intelligent human behaviors using computer hardware and software. Machine learning methods can be used to achieve AI. In machine learning, a machine uses training data to learn (or train) a model. This model represents the mapping from input to output. The learned model can be used for inference (or prediction), meaning that the model can be used to predict the output corresponding to a given input. This output can also be called an inference result (or prediction result).

[0139] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Among them, unsupervised learning can also be called unsupervised learning.

[0140] Supervised learning uses machine learning algorithms to learn the mapping relationship between sample values ​​and sample labels based on collected sample values ​​and sample labels, and then expresses this learned mapping relationship using an AI model. The process of training a machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values. The model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). Once the mapping relationship is learned, the learned mapping can be used to predict new sample labels. The mapping relationship learned by supervised learning can include linear mappings or nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0141] Unsupervised learning uses algorithms to discover inherent patterns in collected sample values. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping from one sample to another. This is called self-supervised learning. During training, the model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used in signal compression and decompression recovery applications. Common algorithms include autoencoders and generative adversarial networks.

[0142] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems lack explicit label data for "correct" actions. Instead, the algorithm must interact with the environment to obtain reward signals from the environment, and then adjust its decision-making actions to maximize the reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmit power of each user based on the overall system throughput fed back by the wireless network, hoping to achieve higher system throughput. The goal of reinforcement learning is also to learn the mapping between environmental states and optimal (e.g., optimal) decision-making actions. However, because the labels for "correct actions" cannot be obtained in advance, network optimization cannot be achieved by calculating the error between actions and "correct actions." Reinforcement learning training is achieved through iterative interaction with the environment.

[0143] A neural network (NN) is a specific model in machine learning technology. According to the universal approximation theorem, NNs can theoretically approximate any continuous function, enabling them to learn arbitrary mappings. Traditional communication systems require extensive expert knowledge to design communication modules. However, deep learning communication systems based on neural networks can automatically discover implicit patterns in massive data sets and establish mapping relationships between data, achieving performance superior to traditional modeling methods.

[0144] The idea of ​​a neural network is derived from the neuronal structure of the brain. For example, each neuron performs a weighted sum operation on its input values ​​and outputs the result through an activation function.

[0145] As shown in Figure 1d, it is a schematic diagram of the neuron structure. Assume that the input of the neuron is x = [x0, x1, ..., xn], and the weights corresponding to each input are w = [w, w1, ..., wn], where n is a positive integer, and wi and xi can be various possible types such as decimals, integers (such as 0, positive integers or negative integers, etc.), or complex numbers. Wi is used as the weight of xi to weight xi. The bias for weighted summation of input values ​​according to the weights is, for example, b. The activation function can take many forms. Assuming that the activation function of a neuron is: y = f(z) = max(0, z), the output of the neuron is: For another example, if the activation function of a neuron is: y = f(z) = z, then the output of the neuron is: b can be a decimal, an integer (eg, 0, a positive integer, or a negative integer), or a complex number, etc. The activation functions of different neurons in a neural network can be the same or different.

[0146] Furthermore, neural networks generally include multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the input information received by the neural network through neurons, passing the processing results to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, a hidden layer, and an output layer. The input layer processes the input information received by the neural network through neurons, passing the processing results to an intermediate hidden layer. The hidden layer performs calculations on the received processing results to obtain a calculation result, which is then passed to the output layer or the next adjacent hidden layer, which ultimately obtains the output of the neural network. A neural network can include one hidden layer or multiple hidden layers connected in sequence, without limitation.

[0147] A neural network is, for example, a deep neural network (DNN). Depending on how the network is constructed, a DNN can include a feedforward neural network (FNN), a convolutional neural network (CNN), and a recurrent neural network (RNN).

[0148] Figure 1e is a schematic diagram of a FNN network. A characteristic of FNN networks is that neurons in adjacent layers are fully connected. This characteristic typically requires a large amount of storage space and results in high computational complexity.

[0149] CNN is a neural network specifically designed to process data with a grid-like structure. For example, time series data (discrete sampling along the time axis) and image data (discrete sampling along two dimensions) can both be considered grid-like data. CNNs do not utilize all input information at once for computation. Instead, they use a fixed-size window to intercept a portion of the information for convolution operations, significantly reducing the computational complexity of model parameters. Furthermore, depending on the type of information intercepted by the window (e.g., people and objects in an image represent different types of information), each window can use a different convolution kernel, enabling CNNs to better extract features from the input data.

[0150] RNNs are a type of DNN that utilizes feedback time series information. Their input consists of a new input value at the current moment and their own output value at the previous moment. RNNs are suitable for capturing temporally correlated sequence features and are particularly well-suited for applications such as speech recognition and channel coding.

[0151] During the machine learning model training process, a loss function can be defined. This function describes the gap or discrepancy between the model's output and the ideal target value. Loss functions can be expressed in various forms, and there are no restrictions on their specific form. The model training process can be viewed as adjusting some or all of the model's parameters to keep the loss function below a threshold or meet the target.

[0152] A model may also be referred to as an AI model, rule, or other name. An AI model can be considered a specific method for implementing an AI function. An AI model represents a mapping relationship or function between the input and output of a model. AI functions may include one or more of the following: data collection, model training (or model learning), model information release, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model verification, or inference result release, etc. AI functions may also be referred to as AI (related) operations, or AI-related functions.

[0153] The following is an exemplary description of the implementation process of the neural network with reference to the accompanying drawings.

[0154] 1. Fully connected neural network, also known as multilayer perceptron (MLP).

[0155] As shown in Figure 2a, an MLP consists of an input layer (left), an output layer (right), and multiple hidden layers (center). Each layer of the MLP contains several nodes, called neurons. Neurons in adjacent layers are connected to each other.

[0156] Optionally, considering neurons in two adjacent layers, the output h of a neuron in the next layer is the weighted sum of all neurons x connected to it in the previous layer and passes through an activation function, which can be expressed as: h=f(wx+b).

[0157] Among them, w is the weight matrix, b is the bias vector, and f is the activation function.

[0158] Alternatively, the output of the neural network can be recursively expressed as: y = f n (w n f n-1 (…)+b n ).

[0159] Where n is the index of the neural network layer, 1<=n<=N, where N is the total number of neural network layers.

[0160] In other words, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly, and the process of obtaining this mapping from random w and b using existing data is called neural network training.

[0161] Optionally, a specific training method is to use a loss function to evaluate the output results of the neural network.

[0162] As shown in Figure 2b, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized using gradient descent until the loss function reaches a minimum, which is the "better point (e.g., optimal point)" in Figure 2b. It is understood that the neural network parameters corresponding to the "better point (e.g., optimal point)" in Figure 2b can be used as the neural network parameters in the trained AI model information.

[0163] Alternatively, the gradient descent process can be expressed as:

[0164] Among them, θ is the parameter to be optimized (including w and b), L is the loss function, and η is the learning rate, which controls the step size of gradient descent. represents the derivative operation, represents the derivative of θ with respect to L.

[0165] Optionally, the backpropagation process utilizes the chain rule for partial derivatives.

[0166] As shown in Figure 2c, the gradient of the previous layer parameters can be recursively calculated from the gradient of the next layer parameters, which can be expressed as:

[0167] Among them, w ij is the weight of node j connecting to node i, s i is the weighted sum of the inputs to node i.

[0168] 2. Federated Learning (FL)

[0169] The concept of federated learning effectively solves the current difficulties faced by the development of artificial intelligence. On the premise of fully protecting user data privacy and security, it efficiently completes the model learning task by promoting the collaboration between various edge devices and central servers.

[0170] As shown in Figure 2d, the FL architecture is the most widely used training architecture in the current FL field. The FedAvg algorithm is the basic algorithm of FL. Its algorithm flow is roughly as follows:

[0171] (1) The center initializes the model to be trained And broadcast it to all client devices.

[0172] (2) In the round t∈[1,T], client k∈[1,K] based on the local dataset For the received global model Perform E epochs of training to obtain local training results Report it to the central node.

[0173] (3) The central node aggregates and collects the local training results from all (or some) clients. Assume that the client set that uploads the local model in round t is The center will use the number of samples of the corresponding client as the weight to perform weighted averaging to obtain a new global model. The specific update rule is: The center then sends the latest version of the global model Broadcast to all client devices for a new round of training.

[0174] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0175] In addition to reporting local models You can also use the local gradient of training After reporting, the central node averages the local gradients and updates the global model according to the direction of the average gradient.

[0176] As you can see, in the FL framework, datasets exist on distributed nodes. Distributed nodes collect local datasets, perform local training, and report the local training results (models or gradients) to the central node. The central node itself does not have a dataset; it is only responsible for fusing the training results of distributed nodes to obtain a global model and send it to the distributed nodes.

[0177] 3. Decentralized learning: Different from federated learning, decentralized learning is another distributed learning architecture.

[0178] As shown in Figure 2e, consider a fully distributed system without a central node. The design goal f(x) of a decentralized learning system is generally the goal f of each node. i The mean of (x), that is Where n is the number of distributed nodes, x is the parameter to be optimized. In machine learning, x is the parameter of the machine learning (such as neural network) model. Each node uses local data and local target f i (x) Calculate local gradient Then it is sent to the neighboring nodes that can be communicated with. After any node receives the gradient information sent by its neighbor, it can update the parameter x of the local model according to the following formula:

[0179] in, represents the parameters of the local model after the k+1th (k is a natural number) update in the i-th node, Represents the parameters of the local model after the kth update in the i-th node (if k is 0, it means is the parameter of the local model of the i-th node that does not participate in the update), α k Represents the tuning coefficient, N i is the set of neighbor nodes of node i, |N i | represents the number of elements in the neighbor node set of node i, that is, the number of neighbor nodes of node i. Through information interaction between nodes, the decentralized learning system will eventually learn a unified model.

[0180] The technical solutions provided in this application can be applied to wireless communication systems (e.g., the systems shown in Figures 1a and 1b). In wireless communication systems, communication nodes generally have both signal transceiver capabilities and computing capabilities. For example, network devices with computing capabilities primarily provide computing power to support signal transceiver capabilities (e.g., performing signal transmission and reception processing) to enable communication between the network device and other communication nodes.

[0181] In communication networks, communication nodes may have excess computing power beyond supporting the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical issue.

[0182] In one possible implementation, a communication node can act as a participating node in an AI learning system, applying its computing power to a specific component of the system. With the advent of the era of large models, deep learning models with massive parameters, such as bidirectional encoder representations from transformers (BERT) and generative pre-trained transformers (GPT-2), can accomplish increasingly complex tasks and achieve superior performance. However, for large models, even the inference process is limited by device capacity, so large models are typically stored on central cloud servers. Furthermore, each device in the network generates a massive amount of raw data daily, which requires multiple inference calls on the large model. Typically, a device (such as a communication node) sends data to a central server, which then performs inference using the data and returns the inference results to the device. This process consumes significant communication resources for data transmission and also risks the privacy of device data.

[0183] To better save communication costs and protect user data privacy, scholars have proposed distributed inference technology for deep neural networks. This approach distributes models to devices and uses the local computing power of the devices to infer the models, thereby reducing communication costs and ensuring data privacy.

[0184] For example, in the example shown in Figure 2f, the two communication nodes, node 1 and node 2, participate in the AI ​​learning system. Node 1 and node 2 can both be communication nodes, such as terminal devices or network devices. The neural network used by the AI ​​learning system can include at least two sub-neural networks, namely sub-neural network 1 deployed at node 1 and sub-neural network 2 deployed at node 2. In this example, the processing result of sub-neural network 1 in node 1 will be used as the processing input of sub-neural network 2 in node 2. Similarly, the neural network can be split into more parts, deployed on more devices, and each device can complete the reasoning of the entire neural network sequentially. Here, the neural network is split into at least two sub-neural networks as an example.

[0185] Generally, the neural network is split and deployed on different devices. The processing of the sub-neural network is usually completed at the application layer of the protocol stack, and the intermediate results (real number symbols) are converted into bit sequences after processing (quantization, source coding, etc.), and then sent to other devices through the physical layer communication link.

[0186] Taking the processing process of node 1 in Figure 2f as an example, during the data transmission process, node 1 obtains the processing result of the neural network through the processing of the sub-neural network 1 deployed in the application layer; thereafter, node 1 can obtain a bit stream by quantizing the processing result of the neural network in the application layer, and subsequently send the bit stream after encoding, modulation, FFT, filtering, IFFT and other processing at the physical layer.

[0187] Taking the processing process of node 2 in Figure 2f as an example, during the data reception process, the data received by node 2 through the wireless channel is processed by the physical layer's FFT, filtering, FFT, demodulation, decoding, etc., and then converted into data that can be recognized by the application layer through dequantization; thereafter, the sub-neural network 2 deployed in the application layer performs the next step of neural network processing.

[0188] Optionally, in Figure 2f, the physical layer processing involved in node 1 is only an implementation example. Other physical layer processing may be involved in the data transmission process, including but not limited to rate matching, scrambling, layer mapping, precoding, resource element (RE) mapping, digital beam mapping (beamforming, BF), and adding a cyclic prefix (CP). Similarly, the physical layer processing involved in node 2 may also involve other physical layer processing, including but not limited to one or more of rate matching, descrambling, layer demapping, channel equalization, RE demapping, digital beam mapping (beamforming, BF), and cyclic prefix (CP) removal.

[0189] From the implementation process shown in Figure 2f, it can be seen that calculation (for example, neural network processing, including training, inference, etc.) and communication (for example, the transmission of neural network processing results, including the transmission of training results, inference results and other data) are two independent operations, which are completed at different protocol layers, require more steps and have higher latency.

[0190] To address the above issues, this application provides a communication method and related equipment for enabling the computing power of communication nodes to be applied to artificial intelligence (AI) tasks while also reducing processing latency. This will be described in detail below with reference to the accompanying drawings.

[0191] Please refer to FIG3 , which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0192] It should be noted that, in FIG3 and FIG6 hereinafter, the first communication device and the second communication device are used as examples of the execution subjects of the interaction diagram to illustrate the method, but the present application does not limit the execution subjects of the interaction diagram. For example, in FIG3 and FIG6 hereinafter, the execution subject of the method can be replaced by a chip, a chip system, a processor, a logic module or software in a communication device. The first communication device can be a terminal device and the second communication device can be a network device, or the first communication device can be a network device and the second communication device can be a terminal device, or the first communication device and the second communication device can be both terminal devices (for example, the method can be applied to the communication process of different terminal devices in a side link communication scenario).

[0193] S301. A first communication device performs a first processing on first data to obtain second data, wherein the first data is obtained based on artificial intelligence (AI) data, and the first processing includes a first neural network processing.

[0194] S302: The first communication device sends third data, and correspondingly, the second communication device receives the third data, wherein the third data is obtained based on the second data through first transform domain processing.

[0195] It should be understood that the terms AI, neural network, AI neural network, machine learning, AI processing, AI neural network processing, etc. can be used interchangeably.

[0196] It should be understood that the data involved in this application (such as the first data, the second data, the third data, and other data mentioned later, including the fourth data to the eighth data, etc.) can be replaced by information, signals, etc.

[0197] Optionally, the AI ​​data includes raw data of the AI ​​task and / or characteristic data of the AI ​​task. Specifically, the first communication device may participate in the AI ​​task, and accordingly, the AI ​​data processed by the first communication device may include raw data of the AI ​​task and / or characteristic data of the AI ​​task, to enhance the flexibility of the solution implementation.

[0198] Optionally, in step S302, the first transform domain processing performed on the second data includes any one of the following: inverse Fourier transform processing, inverse wavelet transform processing. The inverse Fourier transform may include an inverse fast Fourier transform (IFFT), an inverse discrete Fourier transform (IDFT), etc. Exemplarily, the first transform domain processing may perform one-dimensional IFFT processing.

[0199] In a possible implementation, in step S301, the first data is obtained based on the AI ​​data, including: the first data may be obtained by subjecting the AI ​​data to resource mapping processing and / or second transform domain processing.

[0200] Specifically, the first data may be obtained by subjecting AI data to resource mapping processing and / or second transform domain processing, wherein the first communication device may subject the AI ​​data to resource mapping processing and / or second transform domain processing to obtain the first data, and then use the first data as input to a first process that includes at least a first neural network to obtain the second data. In other words, the AI ​​data may be used as input to the resource mapping process and / or the second transform domain, so that the first communication device does not need to perform other physical layer processing (such as encoding, rate matching, scrambling, modulation, etc.) before the resource mapping process during the transmission link processing of the communication signal, thereby further reducing processing latency.

[0201] Optionally, the second transform domain processing includes any one of the following: Fourier transform processing, wavelet transform processing. The Fourier transform processing may include fast Fourier transform (FFT), discrete Fourier transform (DFT), etc. Exemplarily, the second transform domain processing may perform one-dimensional IFFT processing.

[0202] For example, in the example shown in Figure 4a, the first data can be obtained by processing the AI ​​data through resource mapping and the second transform domain. During the processing of the AI ​​data, the first communication device can use the AI ​​data as the input of the resource mapping processing and obtain the first data through the second transform domain processing. In this way, the first communication device does not need to perform other physical layer processing (such as encoding, rate matching, scrambling, modulation, etc.) before the resource mapping processing during the transmission link processing of the communication signal, which can further reduce the processing delay.

[0203] It should be understood that when the first data is obtained by at least resource mapping processing of AI data, the resource mapping processing can map the AI ​​data to the physical layer transmission resources, so that subsequent transmission of AI data can be adapted to the physical layer transmission resources.

[0204] Optionally, the resource mapping process includes at least one of the following: dimensionality conversion, translation, rotation, and interleaving. In other words, when AI data is used as input for the resource mapping process, the AI ​​data may undergo at least one of the above processes to enhance the flexibility of the solution implementation.

[0205] As an implementation example, the resource mapping module maps a data symbol sequence or a data feature symbol sequence onto a physical layer transmission resource, namely, implementing the function f(k, l, ...) = f(c, h, w, ...), where k, l, ... are the indices of the physical layer transmission resource in each resource dimension, and c, h, w, ... are the indices of the data symbol in each dimension of the original data or data feature. For example, taking the physical layer transmission resource as a two-dimensional time-frequency resource and the original data as image data, k is the frequency domain resource index (e.g., the subcarrier index in an OFDM system), l is the time domain symbol index (e.g., the OFDM symbol index in an orthogonal frequency division multiplexing (OFDM) system), c is the channel index of the image data symbol (e.g., the channel index in a red, green, and blue (RGB) three-channel image), h is the height index of the image data symbol within the image, and w is the width index of the image data symbol within the image.

[0206] The resource mapping function f can be implemented by any one or more processes such as dimension conversion, translation, rotation, and interleaving. The following example uses image data as the input AI data for resource mapping processing:

[0207] Dimension Conversion: The resource mapping function can be k = 0, 1, 2, ..., c × h × w. This means that the three-dimensional tensor (or matrix) representing the image is first converted into a one-dimensional vector, and then mapped to subcarriers 0 to c × h × w in the zeroth (i.e., l = 0) OFDM symbol. For example, taking k as the frequency domain resource index and c = 3 / h = 10 / w = 20 (i.e., RGB three channels / height 10 / width 20), this formula means that the 10 * 20 pixels of the three channels in the image data are mapped to k subcarriers respectively, with k = 3 × 10 × 20.

[0208] Translation: c′=(c+M c )mod c,w′=(w+M w )mod w;(k,l)=f(c′,h′,w′). c is the channel dimension translation, M h is the height dimension translation, M w The width dimension translation is performed first, and then the resource mapping is performed.

[0209] Rotation: h′=w, w′=h; (k, l)=f(c, h′, w′). This means that image rotation is performed first, followed by resource mapping.

[0210] Interleaving: (c′, h′, w′) = perm(c, h, w); (k, l) = f(c′, h′, w′). Perm(·) is the interleaving function, meaning interleaving is performed first, followed by resource mapping.

[0211] Correspondingly, for the receiver of the third data (eg, the second communication device shown in FIG. 7 hereinafter), the resource mapping can be de-mapped using the inverse function of the given resource mapping function f.

[0212] It should be understood that when the first data is obtained by processing the AI ​​data at least in the second transform domain, the second transform domain processing can sample and transform the AI ​​data to obtain data suitable for the input of the first neural network.

[0213] Optionally, the second data is a result of performing at least the first neural network processing on the first data, that is, the first data can be used as the input of the first neural network, and the first data may not be obtained by subjecting the AI ​​data to resource mapping processing and / or second transform domain processing. In other words, the function of the first neural network processing includes resource mapping processing and / or second transform domain processing, that is, the same or similar processing effect of resource mapping processing and / or second transform domain processing can be achieved through processing by the first neural network without the need for device processing corresponding to resource mapping processing and / or second transform domain processing.

[0214] In one possible implementation, the first processing further includes filtering, such as a root raised cosine (RRC) filter. Specifically, in addition to the first neural network processing, the first processing may further include filtering to filter the communication signal and reduce the PAPR of the communication signal.

[0215] It can be understood that filtering can be used to reduce the PAPR of wireless signals.

[0216] For example, in the example shown in FIG4b, compared to the implementation shown in FIG4a, in the modular implementation of the "first processing" for processing the first data to obtain the second data, in addition to the first neural network, a filtering processing module may also be included. It should be noted that this implementation example does not limit the number of filtering processes included in the first processing, that is, the first processing may include one or more filtering processes. Moreover, in the first neural network processing and filtering processing included in the first processing, the order of these two processes is not limited. For example, the first neural network processing may be performed first and then the filtering processing, or the filtering processing may be performed first and then the first neural network processing. This is not limited here.

[0217] Optionally, the second data is a result of performing at least the first neural network processing in the first processing on the first data. That is, the first data can serve as input to the first neural network, and the first processing may not include filtering. In other words, the function of the first neural network processing includes filtering, that is, the same or similar processing effect as the filtering processing can be achieved through the processing of the first neural network without the need for processing by a device corresponding to the filtering processing.

[0218] It is understandable that, in the case where the first processing does not include filtering processing, the processing function of the first neural network may include filtering processing. Accordingly, during the training process of the first neural network in the first processing, the training goal of the first neural network may be to target the performance of the AI ​​task (e.g., the accuracy of AI reasoning) and the weighted PAPR of the wireless signal. In the case where the first processing includes filtering processing, the processing function of the first neural network may not include filtering processing. Accordingly, during the training process of the first neural network in the first processing, the training goal of the first neural network may be to target the performance of the AI ​​task (e.g., the accuracy of AI reasoning), that is, the PAPR reduction of the wireless signal is achieved by the filter used to implement the filtering processing.

[0219] Based on the technical solution shown in Figure 3, after the first communication device performs a first processing on the first data to obtain the second data in step S301, the first communication device performs a first transform domain processing on the second data to obtain the third data, and sends the third data in step S302. The first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing. In other words, the second data is the processing result obtained by the first communication device performing at least the first neural network processing on the first data, and the third data sent by the first communication device is the processing result obtained by the first transform domain processing of the second data, wherein the first transform domain processing is one of the processes of the physical layer processing. Therefore, when the communication device in the communication system acts as a node participating in the AI ​​task, the computing power of the communication device can be applied to the processing of the AI ​​task.

[0220] In addition, compared to the implementation method in which the communication device obtains the processing results through neural network processing at the application layer, quantizes the results, and then processes the quantized results through the communication signal processing at the physical layer during the process of sending data, in the above technical solution, the first communication device can use the processing results obtained by the neural network processing as the input of the transform domain processing in the physical layer, so that the first communication device can realize AI data processing without performing quantization processing, which can enable the computing power of the communication device to be applied to AI tasks while reducing processing delays.

[0221] In the technical solution shown in Figure 3, the first communication device can participate in the AI ​​learning system as a communication node. As shown in Figures 2d, 2e, and 2f above, the AI ​​learning system may require multiple communication nodes to participate in the first communication device.

[0222] In one possible implementation, the first communication device may be a head node (or starting node) of the multiple communication nodes. Accordingly, the AI ​​data in step S301 (e.g., the AI ​​data in Figures 4a and 4b) may be data locally generated (or preconfigured) by the first communication device.

[0223] In another possible implementation, the first communication device may be an intermediate node among the multiple communication nodes. Accordingly, the AI ​​data in step S301 (e.g., the AI ​​data in Figures 4a and 4b) may be obtained from data of the previous hop node received by the first communication device. That is, after receiving the data from the previous hop node, the first communication device may obtain the AI ​​data based on the data of the previous hop node.

[0224] For example, using FIG4c as an example, in addition to the processing on the transmit link (e.g., resource mapping processing, second transform domain processing, first processing, first transform domain processing, etc.) shown in FIG4a and FIG4b , the first communication device may also include processing on the receive link. The processing procedures that may be involved in the receive link are described below.

[0225] It should be noted that, when the first communication device is an intermediate node among the multiple communication nodes, the AI ​​data obtained by the first communication device in step S301 may be data obtained by processing the received fourth data at least through the second neural network (i.e., the implementation process of Figure 4c). Alternatively, the AI ​​data obtained by the first communication device in step S301 may also be data obtained by processing the received fourth data through a traditional receiving link (e.g., demodulation, descrambling, rate matching, channel decoding, etc.). In the following example, the implementation process of the former is taken as an example.

[0226] In one possible implementation, in the method shown in FIG. 3 , before step S301, the method further includes: receiving, by the first communication device, fourth data, wherein the AI ​​data is obtained based on the fourth data. Specifically, the AI ​​data transmitted by the first communication device may be obtained by receiving the fourth data, so that when the first communication device participates in an AI task, the first communication device can serve as an intermediate node for multiple nodes participating in the AI ​​task.

[0227] In one possible implementation, after the first communication device receives the fourth data, the method further includes: the first communication device performs a second processing on the fourth data to obtain the AI ​​data; wherein the second processing includes a second neural network processing. Specifically, in a case where the AI ​​data sent by the first communication device is obtained by receiving the fourth data, the first communication device may perform a second processing on the fourth data that at least includes a second neural network processing to obtain the AI ​​data. In other words, after receiving the fourth data, the first communication device may at least perform a second neural network processing on the fourth data to obtain the AI ​​data on the transmitting link. Thus, on the receiving link of the first communication device, the second neural network processing can be used to participate in the AI ​​task, so that the first communication device can participate in the AI ​​task through the first neural network and the second neural network.

[0228] In one possible implementation, the first communication device performs a second processing on the fourth data, and the process of obtaining the AI ​​data may include: the first communication device performs the second processing on the fourth data to obtain fifth data; wherein, the AI ​​data is obtained by subjecting the fifth data to the first transform domain processing and / or de-resource mapping processing. Specifically, after the first communication device receives the fourth data, the first communication device may perform a second processing on the received fourth data to obtain the fifth data. Furthermore, the first communication device may perform the first transform domain processing and / or de-resource mapping processing on the fifth data to obtain the AI ​​data. In other words, the fifth data, as the processing result of the second neural network, can be used as the input of the first transform domain processing and / or de-resource mapping processing. Compared with the implementation method in which the communication device processes the received data through the physical layer, dequantizes the physical layer processing results to obtain application layer data, and then performs neural network processing on the dequantized data, in the above technical solution, the first communication device can use the processing results obtained by neural network processing of the received data as input for transform domain processing and / or resource demapping processing in the physical layer, so that the first communication device can implement neural network processing without performing dequantization processing on the received data, which can enable the computing power of the communication device to be applied to AI tasks while reducing processing delays.

[0229] In addition, the AI ​​data may be data on the transmission link of the first communication device (for example, the AI ​​data may be input for resource mapping processing and / or second transform domain processing on the transmission link). In the above technical solution, the AI ​​data is obtained by subjecting the fifth data to the first transform domain processing and / or de-resource mapping processing, that is, the processing results of the first transform domain processing and / or de-resource mapping processing on the receiving link of the first communication device can be used as input for a certain processing on the transmission link. In this way, the first communication device can avoid performing other physical layer processing (for example, demodulation, descrambling, de-rate matching, channel decoding, etc.) after the de-resource mapping processing during the receiving link processing of the communication signal, thereby further reducing processing delay.

[0230] In one possible implementation, the first communication device performs a second processing on the fourth data to obtain the fifth data, including: the first communication device performs a second transform domain processing on the fourth data to obtain the sixth data; and the first communication device performs the second processing on the sixth data to obtain the fifth data. Specifically, the first communication device may perform a second transform domain processing on the fourth data to obtain the sixth data; thereafter, the first communication device may perform a second processing on the sixth data to obtain the fifth data. The sixth data serves as the input of the second processing including at least the second neural network, and the second transform domain processing process can sample and transform the AI ​​data to obtain the sixth data adapted to the input of the second neural network.

[0231] In one possible implementation, the resource demapping process includes at least one of the following: dimensionality conversion, translation, rotation, and interleaving. Specifically, when AI data is output from the resource demapping process, the AI ​​data may be obtained by subjecting the fifth data to at least one of the above processes, thereby increasing the flexibility of the solution implementation.

[0232] In one possible implementation, the second processing further includes filtering processing, such as RRC filtering processing. Specifically, in addition to the second neural network processing, the second processing may also include filtering processing to filter the communication signal and reduce the PAPR of the communication signal.

[0233] Optionally, the fifth data is a result of the first communication device performing at least the second neural network processing in the second processing on the fourth data. That is, the fourth data can serve as input to the second neural network, and the second processing may not include filtering. In other words, the function of the second neural network processing includes filtering, meaning that the same or similar processing effect as filtering can be achieved through the second neural network processing without the need for processing by a device corresponding to the filtering processing.

[0234] In one possible implementation, the third data is obtained based on the second data processed in the first transform domain, including: the third data is obtained based on the processing result obtained by processing the second data in the first transform domain and the fourth data; or the third data is obtained based on the processing result obtained by processing the second data in the first transform domain. Specifically, the third data sent by the first communication device may include any of the above implementations, so that the data sent by the first communication device can adapt to the processing requirements of different AI network architectures.

[0235] For example, when the third data is obtained based on the processing result obtained by processing the second data in the first transform domain and the fourth data, the first neural network and the second neural network can be part of the neural network in the residual network resNet or other residual connection network architecture.

[0236] For example, when the third data is a processing result obtained based on the second data processed in the first transform domain, the first neural network and the second neural network can be part of the neural network in a network architecture such as CNN, graph neural network (GNN), etc.

[0237] Exemplarily, the third data is obtained based on the processing result obtained by the first transform domain processing of the second data and the fourth data. For example, taking the dashed arrow below the fourth data shown in FIG4c as an example, after receiving the fourth data, the first communication device may copy the fourth data to obtain a copy of the fourth data, use the fourth data as the input of the receiving link, and obtain the processing result of the first transform domain processing on the transmitting link through the aforementioned implementation process. Subsequently, the first communication device processes the copy of the fourth data with the processing result of the first transform domain processing on the transmitting link (e.g., summation, weighted summation, weighted averaging, etc.) to obtain and transmit the third data in step S302. Alternatively, after receiving the fourth data, the first communication device may copy the fourth data to obtain a copy of the fourth data, use the copy of the fourth data as the input of the receiving link, and obtain the processing result of the first transform domain processing on the transmitting link through the aforementioned implementation process. Subsequently, the first communication device processes the fourth data with the processing result of the first transform domain processing on the transmitting link (e.g., summation) to obtain and transmit the third data in step S302.

[0238] As an implementation example, the first transform domain can transform the input data from the frequency domain to the time domain, and the second transform domain can transform the input data from the time domain to the frequency domain. Exemplarily, taking the schematic diagram shown in Figure 4c as an example, during the processing of data by the first communication device, the first data or sixth data obtained by the second transform domain processing (i.e., the processing result of the second transform domain) can be frequency domain data, and the third data or AI data obtained by the first transform domain processing (i.e., the processing result of the first transform domain) can be time domain data. In other words, the data processed by the first neural network or the second neural network can be frequency domain data, and the data transmitted on the wireless channel can be time domain data.

[0239] As an application example, in the example shown in FIG5 , an AI learning system includes five communication nodes as an example. The five communication nodes may include a camera, a car, a mobile phone, a watch, a bracelet, etc., and the five communication nodes may respectively deploy five neural network sub-modules, which are respectively recorded as module 1 (Block1), module 2 (Block2), module 3 (Block3), module 4 (Block4), and module 5 (Block5) in the figure. Among them, the first communication device may be a mobile phone (i.e., node 3). Accordingly, the first communication device may implement the neural network processing corresponding to Block3 in the "first processing" in the sending link (i.e., Block3 may be the first neural network processing). Alternatively, the first communication device may implement the neural network processing corresponding to Block3 in the "second processing" in the receiving link and the "first processing" in the sending link (i.e., Block3 may include two parts, one part being the first neural network processing in the first processing, and the other part being the second neural network processing in the second processing).

[0240] FIG3 and the related technical solutions describe the process of participating in AI learning in a communication node at least in the transmitting link. For example, in the examples shown in FIG4a and FIG4b, the first communication device can participate in AI learning through the first neural network deployed on the transmitting link; for another example, in the example shown in FIG4c, the first communication device can participate in AI learning through the second neural network deployed on the receiving link and the first neural network deployed on the transmitting link. As shown in the example of FIG4c, the processing result of the second neural network will be used as the input of the first neural network after one or more processing processes. In other words, within a communication node (such as the first communication device), the neural network deployed on the receiving link (such as the second neural network in FIG4c) and the neural network deployed on the transmitting link (such as the first neural network in FIG4c) can be neural networks that are executed serially or sequentially; or, the neural network deployed on the receiving link (such as the second neural network in FIG4c) and the neural network deployed on the transmitting link (such as the first neural network in FIG4c) can be two adjacent layers of a multi-layer neural network.

[0241] Similarly, in the example shown in Figure 5, taking the AI ​​learning process through the five nodes shown in Figure 5 as an example, the five neural network modules Block1, Block2, Block3, Block4, and Block5 are deployed on five different nodes, and each node deploys a neural network on its receiving link and / or sending link. Node 1 can be the head node among the five nodes, and the neural network deployed on the sending link in node 1 can be Block 1. Node 2 can deploy a part of Block 2 (denoted as Block 2-1) on the receiving link and another part of Block 2 (denoted as Block 2-2) on the sending link. Similarly, nodes 2, 3, and 4 are all intermediate nodes. Node 3 can deploy a part of Block 3 (denoted as Block 3-1) on the receiving link and another part of Block 3 (denoted as Block 3-2) on the sending link. Node 4 can deploy a part of Block 4 (denoted as Block 4-1) on the receiving link and another part of Block 4 (denoted as Block 4-2) on the sending link. In addition, node 5 can be used as the tail node among the five nodes, and the neural network deployed on the receiving link of node 5 can be Block 5. Accordingly, in the example shown in Figure 5, the processing flow of the five neural network modules can be expressed as follows:

[0242] Block1→Block2-1→Block2-2→Block3-1→Block3-2→Block4-1→Block4-2→Block5;

[0243] In this processing flow, two adjacent neural network modules can be neural networks executed serially or sequentially, or two adjacent layers of neural networks in a multi-layer neural network.

[0244] In addition, in actual application, it is possible that a communication node (such as node 5 in Figure 5) needs to participate in the AI ​​learning process at least in the receiving link, which will be introduced below with more drawings.

[0245] Please refer to FIG6 , which is another schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0246] S601. The first communication device sends third data, and correspondingly, the second communication device receives the third data.

[0247] S602. The second communication device performs second transform domain processing on the third data to obtain seventh data.

[0248] S603: The second communication device performs a second processing on the seventh data to obtain AI data, wherein the second processing includes a second neural network processing.

[0249] In one possible implementation, the second communication device performs a second processing on the seventh data to obtain AI data, including: the second communication device performs the second processing on the seventh data to obtain eighth data, wherein the AI ​​data is obtained by subjecting the eighth data to first transform domain processing and / or resource demapping processing.

[0250] Specifically, the second communication device may perform a second process on the seventh data to obtain eighth data; thereafter, the second communication device may perform a first transform domain process and / or a de-resource mapping process on the eighth data to obtain AI data. The seventh data serves as input to a second process that includes at least a second neural network, and the second transform domain process can sample and transform the AI ​​data to obtain seventh data that is adapted for input to the second neural network.

[0251] In addition, in the above technical solution, the AI ​​data is obtained by subjecting the eighth data to the first transform domain processing and / or de-resource mapping processing, that is, the first transform domain processing and / or de-resource mapping processing on the receiving link in the second communication device can obtain the AI ​​data. In this way, the second communication device can process the communication signal through the receiving link without performing other physical layer processing (such as demodulation, de-scrambling, rate matching, channel decoding, etc.) after the de-resource mapping processing, which can further reduce the processing delay.

[0252] In one possible implementation, the resource demapping process includes at least one of the following: dimensionality conversion, translation, rotation, and interleaving. Specifically, when AI data is output from the resource demapping process, the AI ​​data may be obtained by processing the eighth data using at least one of the above processes, thereby increasing the flexibility of the solution implementation.

[0253] In one possible implementation, the second processing further includes filtering processing, such as RRC filtering processing. Specifically, in addition to the second neural network processing, the second processing may also include filtering processing to filter the communication signal and reduce the PAPR of the communication signal.

[0254] For example, in the example shown in FIG7 , in the modular implementation of the “second processing” of processing the seventh data to obtain the eighth data, in addition to the second neural network, a filtering processing module may also be included. It should be noted that this implementation example does not limit the number of filtering processes included in the second processing, that is, the second processing may include one or more filtering processes. Moreover, in the second neural network processing and filtering processing included in the second processing, the order of these two processes is not limited. For example, the second neural network processing may be performed first and then the filtering processing, or the filtering processing may be performed first and then the second neural network processing. This is not limited here.

[0255] Optionally, the AI ​​data serves as a processing result obtained by the second communication device performing at least the second neural network processing in the second processing on the seventh data. That is, the seventh data may serve as input to the second neural network, and the second processing may not include filtering. In other words, the function of the second neural network processing includes filtering, meaning that the same or similar processing effect as filtering can be achieved through the second neural network processing without the need for processing by a device corresponding to the filtering processing.

[0256] Optionally, the second transform domain processing includes any one of the following: Fourier transform processing, wavelet transform processing.

[0257] Optionally, the first transform domain processing includes any one of the following: inverse Fourier transform processing, inverse wavelet transform processing.

[0258] It should be understood that the implementation process of each processing module shown in Figure 7 (for example, the second transform domain processing, the second processing, the first transform domain processing, the de-resource mapping processing, etc.) and the implementation process of each processing module on the receiving link shown in Figure 4c above (for example, the second transform domain processing, the second processing, the first transform domain processing, the de-resource mapping processing, etc.) can refer to each other.

[0259] In one possible implementation, the AI ​​data includes raw data of the AI ​​task and / or characteristic data of the AI ​​task. Specifically, the second communication device can participate in the AI ​​task, and accordingly, the AI ​​data processed by the second communication device can include the raw data of the AI ​​task and / or characteristic data of the AI ​​task, thereby improving the flexibility of the solution implementation.

[0260] It should be noted that the implementation process of the technical solution shown in FIG6 can refer to the implementation process of FIG3 and related solutions above.

[0261] Based on the technical solution shown in Figure 6, the second communication device performs second transform domain processing on the received third data to obtain seventh data. Thereafter, the second communication device performs second processing on the seventh data to obtain AI data; wherein the second processing includes second neural network processing. In other words, the AI ​​data is the processing result obtained by the second communication device performing at least the second neural network processing on the seventh data, and the seventh data is the processing result obtained by performing second transform domain processing on the third data received by the second communication device, wherein the second transform domain processing is one of the processes of physical layer processing. Thus, when a communication device in a communication system serves as a node participating in an AI task, the computing power of the communication device can be applied to the processing of the AI ​​task.

[0262] In addition, compared to the implementation method in which the communication device processes the received data through the physical layer, dequantizes the physical layer processing results to obtain application layer data, and then performs neural network processing on the dequantized data, in the above technical solution, the second communication device can process the received data through the second transform domain in the physical layer, and use the processing results of the second transform domain processing as input for the neural network processing, so that the second communication device can implement neural network processing without performing dequantization processing on the received data, which can enable the computing power of the communication device to be applied to AI tasks while reducing processing delays.

[0263] In addition, the AI ​​data determined by the second communication device can be obtained by receiving the third data, so that when the second communication device participates in the AI ​​task, the second communication device can serve as an intermediate node or tail node (or termination node) of multiple nodes participating in the AI ​​task.

[0264] It is understandable that, as can be seen from the implementation process of Figures 3 and 6 above, the third data sent by the first communication device can be the received data of the second communication device, that is, the second communication device can be understood as the next hop node of the first communication device, and correspondingly, the first communication device can be understood as the previous hop node of the second communication device. For example, when the AI ​​learning system is participated by multiple distributed nodes, the first communication device and the second communication device can be any two adjacent nodes among the multiple nodes.

[0265] Optionally, for any adjacent two-hop nodes, in order to improve the success rate of data processing of the adjacent two-hop nodes, the parameters of the first transform domain processing and the second transform domain processing deployed by the two-hop nodes can be matched with each other. For example, the first transform domain processing of the sending link of the previous hop node and the second transform domain processing of the receiving link of the next hop node are matched; for another example, the second transform domain processing of the sending link of the previous hop node and the first transform domain processing of the receiving link of the next hop node are matched. For example, taking the Fourier transform as an example, the two transform domain processings here are matched, which can be understood as the number of Fourier transform points (or length) of the two transform domain processings being the same. For example, the number of inverse Fourier transform points of the sending link of the previous hop node is equal to the number of Fourier transform points of the receiving link of the next hop node. For another example, the number of Fourier transform points of the sending link of the previous hop node is equal to the number of inverse Fourier transform points of the receiving link of the next hop node.

[0266] Referring to Figure 8 , an embodiment of the present application provides a communication device 800. This communication device 800 can implement the functions of the second communication device or the first communication device in the above-described method embodiment, thereby also achieving the beneficial effects of the above-described method embodiment. In this embodiment of the present application, the communication device 800 can be the first communication device (or second communication device), or it can be an integrated circuit or component, such as a chip, within the first communication device (or second communication device).

[0267] It should be noted that the transceiver unit 802 may include a sending unit and a receiving unit, which are respectively used to perform sending and receiving.

[0268] In one possible implementation, when the device 800 is used to execute the method executed by the first communication device in the aforementioned embodiment, the device 800 includes a processing unit 801 and a transceiver unit 802; the processing unit 801 is used to perform a first processing on the first data to obtain second data; wherein the first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing; the transceiver unit 802 is used to send the third data, and the third data is obtained based on the second data after first transform domain processing.

[0269] In one possible implementation, when the device 800 is used to execute the method executed by the second communication device in the aforementioned embodiment, the device 800 includes a processing unit 801 and a transceiver unit 802; the transceiver unit 802 is used to receive third data; the processing unit is used to perform a second transform domain processing on the third data to obtain seventh data; the processing unit 801 is also used to perform a second processing on the seventh data to obtain AI data; wherein the second processing includes a second neural network processing.

[0270] It should be noted that, for details on the information execution process of the units of the above-mentioned communication device 800, please refer to the description in the method embodiment shown above in this application, and no further details will be given here.

[0271] Please refer to Figure 9, which is another schematic structural diagram of a communication device 900 provided in this application. The communication device 900 includes a logic circuit 901 and an input / output interface 902. The communication device 900 may be a chip or an integrated circuit.

[0272] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the input / output interface 902 in FIG9 , which may include an input interface and an output interface. Alternatively, the communication interface may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0273] Optionally, the logic circuit 901 is used to perform a first processing on the first data to obtain second data; wherein, the first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing; the input and output interface 902 is used to send the third data, and the third data is obtained based on the second data after first transform domain processing.

[0274] Optionally, the input-output interface 902 is used to receive third data; the processing unit is used to perform a second transform domain processing on the third data to obtain seventh data; the logic circuit 901 is also used to perform a second processing on the seventh data to obtain AI data; wherein the second processing includes a second neural network processing.

[0275] The logic circuit 901 and the input / output interface 902 may also execute other steps executed by the first communication device or the second communication device in any embodiment and achieve corresponding beneficial effects, which will not be described in detail here.

[0276] In a possible implementation, the processing unit 801 shown in FIG. 8 may be the logic circuit 901 in FIG. 9 .

[0277] Optionally, the logic circuit 901 may be a processing device, and the functions of the processing device may be partially or entirely implemented by software. The functions of the processing device may be partially or entirely implemented by software.

[0278] Optionally, the processing device may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform corresponding processing and / or steps in any one of the method embodiments.

[0279] Alternatively, the processing device may include only a processor. A memory for storing the computer program is located outside the processing device, and the processor is connected to the memory via circuits / wires to read and execute the computer program stored in the memory. The memory and processor may be integrated or physically separate.

[0280] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), central processor units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0281] Please refer to Figure 10, which shows the communication device 1000 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1000 can specifically be a communication device serving as a terminal device in the above-mentioned embodiments. The example shown in Figure 10 is that the terminal device is implemented through the terminal device (or a component in the terminal device).

[0282] Herein, a possible logical structure diagram of the communication device 1000 is shown. The communication device 1000 may include but is not limited to at least one processor 1001 and a communication port 1002 .

[0283] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the communication port 1002 in FIG10 , which may include an input interface and an output interface. Alternatively, the communication port 1002 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0284] Further optionally, the device may also include at least one of a memory 1003 and a bus 1004. In an embodiment of the present application, the at least one processor 1001 is used to control and process the actions of the communication device 1000.

[0285] In addition, the processor 1001 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and so on. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0286] It should be noted that the communication device 1000 shown in Figure 10 can be specifically used to implement the steps implemented by the terminal device in the aforementioned method embodiment and achieve the corresponding technical effects of the terminal device. The specific implementation methods of the communication device shown in Figure 10 can refer to the description in the aforementioned method embodiment and will not be repeated here.

[0287] Please refer to Figure 11, which is a structural diagram of the communication device 1100 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1100 can specifically be a communication device as a network device in the above-mentioned embodiments. The example shown in Figure 11 is that the network device is implemented through the network device (or a component in the network device), wherein the structure of the communication device can refer to the structure shown in Figure 11.

[0288] The communication device 1100 includes at least one processor 1111 and at least one network interface 1114. Further optionally, the communication device also includes at least one memory 1112, at least one transceiver 1113 and one or more antennas 1115. The processor 1111, the memory 1112, the transceiver 1113 and the network interface 1114 are connected, for example, via a bus. In an embodiment of the present application, the connection may include various interfaces, transmission lines or buses, etc., which are not limited in this embodiment. The antenna 1115 is connected to the transceiver 1113. The network interface 1114 is used to enable the communication device to communicate with other communication devices through a communication link. For example, the network interface 1114 may include a network interface between the communication device and the core network device, such as an S1 interface, and the network interface may include a network interface between the communication device and other communication devices (such as other network devices or core network devices), such as an X2 or Xn interface.

[0289] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the network interface 1114 in FIG11 , which may include an input interface and an output interface. Alternatively, the network interface 1114 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0290] Processor 1111 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process software program data, for example, to support the communication device in performing the actions described in the embodiments. The communication device may include a baseband processor and a central processing unit. The baseband processor is primarily used to process communication protocols and communication data, while the central processing unit is primarily used to control the entire terminal device, execute software programs, and process software program data. Processor 1111 in Figure 11 may integrate the functions of both a baseband processor and a central processing unit. Those skilled in the art will appreciate that the baseband processor and the central processing unit may also be independent processors interconnected via a bus or other technology. Those skilled in the art will appreciate that a terminal device may include multiple baseband processors to accommodate different network standards, multiple central processing units to enhance its processing capabilities, and various components of the terminal device may be connected via various buses. The baseband processor may also be referred to as a baseband processing circuit or a baseband processing chip. The central processing unit may also be referred to as a central processing circuit or a central processing chip. The functionality for processing communication protocols and communication data may be built into the processor or stored in memory as a software program, which is executed by the processor to implement the baseband processing functionality.

[0291] The memory is primarily used to store software programs and data. Memory 1112 can exist independently and be connected to processor 1111. Alternatively, memory 1112 can be integrated with processor 1111, for example, within a single chip. Memory 1112 can store program code for executing the technical solutions of the embodiments of the present application, and execution is controlled by processor 1111. The various computer program codes executed can also be considered drivers for processor 1111.

[0292] Figure 11 shows only one memory and one processor. In an actual terminal device, there may be multiple processors and multiple memories. The memory may also be referred to as a storage medium or a storage device. The memory may be a storage element on the same chip as the processor, i.e., an on-chip storage element, or an independent storage element, which is not limited in the present embodiment.

[0293] The transceiver 1113 can be used to support the reception or transmission of radio frequency signals between the communication device and the terminal. The transceiver 1113 can be connected to the antenna 1115. The transceiver 1113 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1115 can receive radio frequency signals. The receiver Rx of the transceiver 1113 is used to receive the radio frequency signal from the antenna, convert the radio frequency signal into a digital baseband signal or a digital intermediate frequency signal, and provide the digital baseband signal or digital intermediate frequency signal to the processor 1111 so that the processor 1111 can further process the digital baseband signal or digital intermediate frequency signal, such as demodulation and decoding. In addition, the transmitter Tx in the transceiver 1113 is also used to receive a modulated digital baseband signal or digital intermediate frequency signal from the processor 1111, convert the modulated digital baseband signal or digital intermediate frequency signal into a radio frequency signal, and transmit the radio frequency signal through one or more antennas 1115. Specifically, the receiver Rx can selectively perform one or more stages of down-mixing and analog-to-digital conversion on the RF signal to obtain a digital baseband signal or a digital intermediate frequency signal. The order of the down-mixing and analog-to-digital conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of up-mixing and digital-to-analog conversion on the modulated digital baseband signal or digital intermediate frequency signal to obtain a RF signal. The order of the up-mixing and digital-to-analog conversion processes is adjustable. The digital baseband signal and the digital intermediate frequency signal may be collectively referred to as digital signals.

[0294] The transceiver 1113 may also be referred to as a transceiver unit, a transceiver, a transceiver device, etc. Optionally, a device in the transceiver unit that implements a receiving function may be referred to as a receiving unit, and a device in the transceiver unit that implements a transmitting function may be referred to as a transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit may also be referred to as a receiver, an input port, a receiving circuit, etc., and the transmitting unit may be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0295] It should be noted that the communication device 1100 shown in Figure 11 can be specifically used to implement the steps implemented by the network device in the aforementioned method embodiment, and to achieve the corresponding technical effects of the network device. The specific implementation methods of the communication device 1100 shown in Figure 11 can refer to the description in the aforementioned method embodiment, and will not be repeated here one by one.

[0296] Please refer to FIG12 , which is a schematic structural diagram of the communication device involved in the above-mentioned embodiment provided in an embodiment of the present application.

[0297] It can be understood that the communication device 120 includes, for example, modules, units, elements, circuits, or interfaces, which are appropriately configured together to implement the technical solutions provided in this application. The communication device 120 can be the terminal device or network device described above, or a component (such as a chip) in these devices, used to implement the method described in the following method embodiment. The communication device 120 includes one or more processors 121. The processor 121 can be a general-purpose processor or a dedicated processor. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (such as a RAN node, terminal, or chip, etc.), execute software programs, and process data of software programs.

[0298] Optionally, in one design, the processor 121 may include a program 123 (sometimes also referred to as code or instructions), which may be executed on the processor 121 to cause the communication device 120 to perform the methods described in the following embodiments. In yet another possible design, the communication device 120 includes circuitry (not shown in FIG12 ).

[0299] Optionally, the communication device 120 may include one or more memories 122 on which a program 124 (sometimes also referred to as code or instructions) is stored. The program 124 can be run on the processor 121, so that the communication device 120 executes the method described in the above method embodiment.

[0300] Optionally, the processor 121 and / or the memory 122 may include an AI module 127, 128, which is used to implement AI-related functions. The AI ​​module may be implemented through software, hardware, or a combination of software and hardware. For example, the AI ​​module may include a wireless intelligent control (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0301] Optionally, data may be stored in the processor 121 and / or the memory 122. The processor and the memory may be provided separately or integrated together.

[0302] Optionally, the communication device 120 may further include a transceiver 125 and / or an antenna 126. The processor 121 may also be sometimes referred to as a processing unit, and controls the communication device (e.g., a RAN node or terminal). The transceiver 125 may also be sometimes referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, and is configured to implement the transceiver functions of the communication device through the antenna 126.

[0303] The transceiver unit 802 shown in FIG8 may be a communication interface, which may be the transceiver 125 in FIG12 . The transceiver 125 may include an input interface and an output interface. Alternatively, the transceiver 125 may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0304] An embodiment of the present application further provides a computer-readable storage medium, which is used to store one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in the possible implementation methods of the first communication device or the second communication device in the aforementioned embodiment.

[0305] An embodiment of the present application also provides a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes the method that may be implemented by the above-mentioned first communication device or second communication device.

[0306] An embodiment of the present application also provides a chip system, which includes at least one processor for supporting a communication device to implement the functions involved in the possible implementation methods of the above-mentioned communication device. Optionally, the chip system also includes an interface circuit, which provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory, which is used to store the necessary program instructions and data for the communication device. The chip system can be composed of chips, or it can include chips and other discrete devices, wherein the communication device can specifically be the first communication device or the second communication device in the aforementioned method embodiment.

[0307] An embodiment of the present application further provides a communication system, wherein the network system architecture includes the first communication device and the second communication device in any of the above embodiments.

[0308] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0309] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0310] In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the contributing part or all or part of the technical solution can be embodied in the form of a software product, which 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 method described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A communication method, characterized in that: include: Performing a first processing on the first data to obtain second data; wherein the first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing; Send third data, where the third data is obtained based on the second data after being processed in the first transform domain.

2. The method according to claim 1, characterized in that: The first data is obtained based on AI data, including: The first data is obtained by subjecting the AI ​​data to resource mapping processing and / or second transform domain processing.

3. The method according to claim 2, characterized in that The resource mapping process includes at least one of the following: Dimension conversion processing, translation processing, rotation processing, and interleaving processing.

4. The method according to any one of claims 1 to 3, characterized in that: The first processing also includes a filtering process.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Fourth data is received, wherein the AI ​​data is obtained based on the fourth data.

6. The method according to claim 5, characterized in that The method further comprises: Perform a second processing on the fourth data to obtain the AI ​​data; wherein the second processing includes a second neural network processing.

7. The method according to claim 6, characterized in that The performing a second processing on the fourth data to obtain the AI ​​data comprises: The second processing is performed on the fourth data to obtain fifth data; wherein the AI ​​data is obtained by performing the first transform domain processing and / or de-resource mapping processing on the fifth data.

8. The method according to claim 7, characterized in that The performing a second processing on the fourth data to obtain fifth data comprises: Performing second transform domain processing on the fourth data to obtain sixth data; The second processing is performed on the sixth data to obtain the fifth data.

9. The method according to claim 7 or 8, characterized in that: The resource demapping process includes at least one of the following: Dimension conversion processing, translation processing, rotation processing, and interleaving processing.

10. The method according to any one of claims 6 to 8, characterized in that: The second process also includes a filtering process.

11. The method according to any one of claims 2 to 10, characterized in that: The second transform domain processing includes any one of the following: Fourier transform processing and wavelet transform processing.

12. The method according to any one of claims 1 to 11, characterized in that: The first transform domain processing includes any one of the following: Inverse Fourier transform processing and inverse wavelet transform processing.

13. The method according to any one of claims 1 to 12, characterized in that: The AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

14. The method according to any one of claims 5 to 13, characterized in that The third data is obtained based on the second data through first transform domain processing, and includes: The third data is obtained based on the processing result obtained by processing the second data in the first transform domain and the fourth data; or, The third data is a processing result obtained by processing the second data in the first transform domain.

15. A communication method, characterized in that: include: receiving third data; Performing second transform domain processing on the third data to obtain seventh data; Perform a second processing on the seventh data to obtain AI data; wherein the second processing includes a second neural network processing.

16. The method according to claim 15, characterized in that The performing the second processing on the seventh data to obtain AI data comprises: The second processing is performed on the seventh data to obtain eighth data, wherein the AI ​​data is obtained by performing first transform domain processing and / or de-resource mapping processing on the eighth data.

17. The method according to claim 16, characterized in that The resource de-mapping process includes at least one of the following: Dimension conversion processing, translation processing, rotation processing, and interleaving processing.

18. The method according to any one of claims 15 to 17, characterized in that The second process also includes a filtering process.

19. The method according to any one of claims 15 to 18, characterized in that The second transform domain processing includes any one of the following: Fourier transform processing and wavelet transform processing.

20. The method according to any one of claims 16 to 19, characterized in that The first transform domain processing includes any one of the following: Inverse Fourier transform processing and inverse wavelet transform processing.

21. The method according to any one of claims 15 to 20, characterized in that The AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

22. A communication device, characterized in that: including a processing unit and a transceiver unit; The processing unit is used to perform a first processing on the first data to obtain second data; wherein the first data is obtained based on artificial intelligence AI data, and the first processing includes a first neural network processing; The transceiver unit is used to send third data, where the third data is obtained based on the second data after being processed in the first transform domain.

23. The device according to claim 22, characterized in that The first data is obtained based on AI data, including: The first data is obtained by subjecting the AI ​​data to resource mapping processing and / or second transform domain processing.

24. The device according to claim 23, characterized in that The resource mapping process includes at least one of the following: Dimension conversion processing, translation processing, rotation processing, and interleaving processing.

25. The device according to any one of claims 22 to 24, characterized in that The first processing also includes a filtering process.

26. The device according to any one of claims 22 to 25, characterized in that The transceiver unit is further used to receive fourth data, wherein the AI ​​data is obtained based on the fourth data.

27. The device according to claim 26, characterized in that The processing unit is also used to perform a second processing on the fourth data to obtain the AI ​​data; wherein the second processing includes a second neural network processing.

28. The device according to claim 27, characterized in that The processing unit is configured to perform a second process on the fourth data to obtain the AI ​​data, comprising: The processing unit performs the second processing on the fourth data to obtain fifth data; wherein the AI ​​data is obtained by performing the first transform domain processing and / or de-resource mapping processing on the fifth data.

29. The device according to claim 28, characterized in that The processing unit performs the second processing on the fourth data to obtain fifth data, which includes: The processing unit performs second transform domain processing on the fourth data to obtain sixth data; The processing unit performs the second processing on the sixth data to obtain the fifth data.

30. The device according to claim 28 or 29, characterized in that The resource de-mapping process includes at least one of the following: Dimension conversion processing, translation processing, rotation processing, and interleaving processing.

31. The device according to any one of claims 27 to 30, characterized in that The second process also includes a filtering process.

32. The device according to any one of claims 23 to 31, characterized in that The second transform domain processing includes any one of the following: Fourier transform processing and wavelet transform processing.

33. The device according to any one of claims 22 to 32, characterized in that The first transform domain processing includes any one of the following: Inverse Fourier transform processing and inverse wavelet transform processing.

34. The device according to any one of claims 22 to 33, characterized in that The AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

35. The device according to any one of claims 26 to 34, characterized in that The third data is obtained based on the second data through first transform domain processing, and includes: The third data is obtained based on the processing result obtained by processing the second data in the first transform domain and the fourth data; or, The third data is a processing result obtained by processing the second data in the first transform domain.

36. A communication device, characterized in that: including a transceiver unit and a processing unit; The transceiver unit is used to receive third data; The processing unit is used for performing second transform domain processing on the third data to obtain seventh data; The processing unit is also used to perform a second processing on the seventh data to obtain AI data; wherein the second processing includes a second neural network processing.

37. The device according to claim 36, characterized in that The processing unit is used to perform a second process on the seventh data to obtain AI data, including: The processing unit performs the second processing on the seventh data to obtain eighth data, wherein the AI ​​data is obtained by performing the first transform domain processing and / or de-resource mapping processing on the eighth data.

38. The device according to claim 37, characterized in that The resource de-mapping process includes at least one of the following: Dimension conversion processing, translation processing, rotation processing, and interleaving processing.

39. The device according to any one of claims 36 to 38, characterized in that The second process also includes a filtering process.

40. The device according to any one of claims 36 to 39, characterized in that The second transform domain processing includes any one of the following: Fourier transform processing and wavelet transform processing.

41. The device according to any one of claims 37 to 40, characterized in that The first transform domain processing includes any one of the following: Inverse Fourier transform processing and inverse wavelet transform processing.

42. The device according to any one of claims 36 to 41, characterized in that The AI ​​data includes original data of the AI ​​task and / or feature data of the AI ​​task.

43. A communication device, characterized in that: The device comprises at least one processor configured to execute computer programs or instructions in the memory to implement the method according to any one of claims 1 to 14.

44. A communication device, characterized in that: The device comprises at least one processor configured to execute computer programs or instructions in the memory to implement the method according to any one of claims 15 to 21.

45. A communication system, characterized in that: The system comprises a communication device as claimed in any one of claims 22 to 35, and a communication device for executing any one of claims 36 to 42; or The system comprises the communication device as claimed in claim 43, and the communication device as claimed in claim 44.

46. ​​A computer-readable storage medium, characterized in that The medium stores instructions, and when the instructions are executed by a computer, the method according to any one of claims 1 to 21 is implemented.

47. A computer program product, characterized in that The method comprises instructions which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 21.

Images