Data processing method and related device

Abstract

A data processing method. By means of the method, artificial intelligence technology can be applied to the field of communications. The method comprises: a control node determining a first mode used when a plurality of first sending ends and a first receiving end perform over-the-air computing, wherein the first mode is one of at least two over-the-air computing modes, the first mode is determined on the basis of first information of each first sending end and second information of the first receiving end, the first information of each first sending end indicates a channel information acquisition capability of the first sending end, and the second information of the first receiving end indicates a channel information acquisition capability of the first receiving end; and determining instruction information, wherein the instruction information instructs the first sending ends and the first receiving end to use the first mode to perform over-the-air computing. A used over-the-air computing mode matches the capabilities of sending ends and the capability of a receiving end, thereby helping to increase the probability of success for first sending ends and a first receiving end when using a first mode to perform over-the-air computing, and significantly reducing the probability of execution failure.

Description

A data processing method and related equipment Technical Field

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

[0002] Over-the-air computing (OTA) technology involves superimposing the signals transmitted by multiple transmitters over the air to the same receiver. The resulting signal is a signal that has undergone this superposition. However, since each transmitter's signal is affected by the channel as it passes through the air, and different transmitters reach the receiver through different channels, the receiver cannot obtain the data carried in the superimposed signal, significantly reducing the performance of over-the-air computing.

[0003] To solve the above problems, in one mode, each transmitter can perform a pre-equalization operation on the transmitted signal based on the channel information of the transmitter and the receiver; in another mode, multiple transmitters can send the same pilot signal to the receiver, and the receiver estimates the sum of the channel gains based on the received pilot signal. After obtaining the superimposed signal, the receiver can process the received superimposed signal based on the sum of the channel gains, etc. However, the first mode requires the transmitter to be able to obtain the channel information, and the second mode requires the receiver to be able to obtain the channel information. Not all devices have this capability, resulting in execution failure on some devices.

[0004] Summary of the Invention

[0005] An embodiment of the present application provides a data processing method and related equipment, in which a control node determines a first mode to be adopted when multiple first transmitting ends and first receiving ends perform over-the-air computing. The first mode is determined based on the channel information acquisition capability of the first transmitting end and the channel information acquisition capability of the first receiving end. That is, the specific over-the-air computing mode adopted is adapted to the capabilities of the transmitting end and the receiving end. This is beneficial to increasing the probability that the first transmitting end and the first receiving end can successfully adopt the first mode to perform over-the-air computing when performing over-the-air computing, thereby greatly reducing the probability of execution failure.

[0006] To solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a data processing method that can apply artificial intelligence technology to the field of communications. The method includes: a control node determines a first mode to be adopted when multiple first transmitters and a first receiver perform air computing, wherein the first mode is one of at least two air computing modes, and the first mode is determined based on the first information of each first transmitter among the multiple first transmitters and the second information of the first receiver, the first information of the first transmitter indicates the channel information acquisition capability of the first transmitter, and the second information of the first receiver indicates the channel information acquisition capability of the first receiver; the control node determines indication information, and the indication information instructs the first transmitter and the first receiver to adopt the first mode for air computing. Exemplarily, in one application scenario, the control node and the first receiver are integrated into the same device, and the aforementioned indication information includes the first indication information. The method also includes: the control node sends the first indication information to each of the multiple first transmitters, and the first indication information is used to inform each first transmitter to adopt the first mode for air computing. In another application scenario, the control node and the first receiving end are located in different devices, then the indication information may include first indication information and second indication information, the control node may send the first indication information to each of the multiple first transmitting ends, and send the second indication information to the first receiving end, the first indication information is used to inform each first transmitting end to use the first mode for air calculation, and the second indication information is used to inform the first receiving end to use the first mode for air calculation.

[0008] In this implementation, the control node determines a first mode to be adopted by multiple first transmitting ends and first receiving ends when performing over-the-air computing, and then determines indication information, where the indication information is used to instruct the first transmitting end and the first receiving end to adopt the first mode for over-the-air computing. Since the first mode is one of at least two over-the-air computing modes, and the first mode is determined based on the channel information acquisition capability of the first transmitting end and the channel information acquisition capability of the first receiving end, that is, which specific over-the-air computing mode is adapted to the capabilities of the transmitting end and the receiving end, this is conducive to increasing the probability that the first transmitting end and the first receiving end can successfully adopt the first mode for over-the-air computing when performing over-the-air computing, thereby greatly reducing the probability of execution failure.

[0009] In one possible implementation, the indication information may be present as identification information indicating the first mode. For example, the indication information may be present as an index value indicating the first mode, with different index values ​​indicating different over-the-air computing modes. Alternatively, the indication information may also inform the first transmitting end and the first receiving end of which over-the-air computing mode to adopt by indicating the steps that each first transmitting end and the first receiving end needs to perform.

[0010] In one possible implementation, the first information of the first transmitting end also includes the first number of transmitting antennas of each of the multiple first transmitting ends, and the second information of the first receiving end also includes the second number of receiving antennas of the first receiving end. In this implementation, because the number of transmitting antennas of the transmitting end and the number of antennas of the receiving end will affect the performance of certain air computing modes, the control node will also consider the number of transmitting antennas of the multiple first transmitting ends and the number of receiving antennas of the first receiving end when determining which air computing mode to adopt for the multiple first transmitting ends and the first receiving end. The ultimately determined first mode not only matches the channel information acquisition capabilities of the first transmitting end and the first receiving end, but also matches the number of antennas of the first transmitting end and the first receiving end, thereby facilitating the first receiving end to obtain valid information from the results of the air computing, thereby improving the performance of the air computing.

[0011] In one possible implementation, when multiple first transmitters and first receivers are capable of acquiring channel information, the first mode may be specifically expressed as a performance mode. The "performance mode" means that the first transmitter performs a pre-equalization operation on the transmitted signal, and the first receiver performs denoising on the received signal based on the channel information. Exemplarily, "the first transmitter has the ability to acquire channel information" may be understood as the first transmitter being able to acquire channel state information from the first transmitter to the first receiver through channel prediction, channel reciprocity, or other methods. Exemplarily, in this case, "the first receiver has the ability to acquire channel information" may be understood as the first receiver being able to acquire channel state information from each first transmitter to the first receiver through channel prediction, channel estimation, or other methods.

[0012] Alternatively, when multiple first transmitting ends can obtain channel information, the first receiving end cannot obtain channel information, and the first number is greater than or equal to the second number, the first mode can be specifically expressed as a pre-equalization mode. The "pre-equalization mode" means that the first transmitting end performs a pre-equalization operation on the transmitted signal, and the first receiving end no longer performs denoising processing on the received signal.

[0013] Alternatively, when multiple first transmitting ends are unable to obtain channel information, the first receiving end is able to obtain channel information, and the first number is less than the second number, the first mode can be specifically manifested as a channel hardening mode. The "channel hardening mode" represents that the first receiving end estimates the sum channel based on the pilot signal sent by the first transmitting end, and processes the received signal based on the sum channel; in this case, "the first receiving end has the ability to obtain channel information" can be understood as the first receiving end being able to estimate the sum channel based on the pilot signals sent by multiple first transmitting ends.

[0014] Alternatively, when multiple first transmitting ends can obtain channel information, the first receiving end cannot obtain channel information, and the first number is less than the second number; or, when multiple first transmitting ends cannot obtain channel information, the first receiving end can obtain channel information, and the first number is greater than or equal to the second number; or, when multiple first transmitting ends and the first receiving end cannot obtain channel information, that is, when the triggering conditions of the above-mentioned "performance mode", "pre-equalization mode" and "channel hardening mode" are not met, the first mode can be specifically expressed as an incoherent mode, and the "incoherent mode" represents that the first transmitting end performs binarization processing on the transmitted signal.

[0015] In this implementation, a specific scheme is provided for the first mode adopted by multiple first transmitting ends and first receiving ends when performing air computing in various situations. That is, in various situations, there are matching air computing modes, which is conducive to expanding the application scenarios of this scheme and improving the implementation flexibility of this scheme. In addition, there are matching air computing modes in various situations, which is conducive to using the most suitable air computing mode in various situations, and is conducive to assisting the first receiving end to obtain more valid data.

[0016] In one possible implementation, the method further includes: a control node receiving first information from each of a plurality of transmitters, the plurality of transmitters including a plurality of first transmitters; and a control node receiving second information from each of at least one receiver, the at least one receiver including the first receiver. The control node determining a first mode to be used when the plurality of first transmitters and the first receiver perform over-the-air computation, including: the control node determining the first mode to be used when the plurality of first transmitters and the first receiver perform over-the-air computation based on the first information from each transmitter and the second information from each receiver.

[0017] In this implementation, based on the first information of multiple transmitters and the second information of at least one receiver, multiple first transmitters and one first receiver are selected from the multiple transmitters and at least one receiver for air calculation, and an air calculation mode adapted to the selected "multiple first transmitters and one first receiver" is determined, which is beneficial to improving the adaptability between the finally determined first mode and the "multiple first transmitters and one first receiver", and is beneficial for the first receiver to obtain more valid data.

[0018] In one possible implementation, the control node is the first receiving end, the first receiving end and multiple first transmitting ends are used to perform federated learning, the first receiving end is the central node of federated learning, and the multiple first transmitting ends are distributed nodes of federated learning. In this implementation, the control node is the first receiving end, the first receiving end and multiple first transmitting ends are used to perform federated learning, the first receiving end is the central node of federated learning, and the multiple first transmitting ends are distributed nodes of federated learning. For the meaning of "federated learning", please refer to the above description and will not be elaborated here. In an embodiment of the present application, a specific application scenario is provided when multiple first transmitting ends and the first receiving end perform air computing, and in this application scenario, the control node and the first receiving end are integrated into the same device, that is, a specific combination scheme for combining federated learning with air computing is provided, which reduces the difficulty of implementing this scheme.

[0019] In one possible implementation, the first information of each transmitting end further includes the encoding scheme and / or quantization scheme of each transmitting end, and the second information of each receiving end further includes the decoding scheme and / or dequantization scheme of each receiving end. Exemplarily, the encoding schemes that can be adopted by a transmitting end include: Huffman coding, arithmetic coding, dictionary coding, or other encoding schemes, etc.; the decoding schemes that can be adopted by a receiving end include: Huffman decoding, arithmetic decoding, dictionary decoding, or other decoding schemes, etc. The quantization schemes that can be adopted by a transmitting end include: uniform quantization, non-uniform quantization, vector quantization, scalar quantization, or other quantization schemes, etc.; the dequantization schemes that can be adopted by a receiving end include: deuniform quantization, de-non-uniform quantization, de-vector quantization, de-scalar quantization, or other dequantization schemes, etc. In this implementation, the control node will consider more information when determining which air computing mode to adopt between multiple first transmitting ends and the first receiving end, which is conducive to more accurate grouping of multiple transmitting ends, that is, it is conducive to the same coding scheme and / or quantization scheme among the multiple first transmitting ends after grouping. After the transmission signals of the multiple first transmitting ends are superimposed in the air, the reception signal of the first receiving end can be obtained, so the first receiving end can more easily obtain valid data from the received signal, which is conducive to improving the performance of air computing between multiple first transmitting ends and the first receiving end.

[0020] In one possible implementation, multiple first transmitters use the same encoding scheme; the decoding scheme used by the first receiver matches the encoding scheme used by the multiple first transmitters. For example, when the encoding scheme used by the multiple first transmitters is Huffman encoding, the matching decoding scheme is Huffman decoding, meaning that the decoding scheme used by the first receiver may be Huffman decoding; for another example, when the encoding scheme used by the multiple first transmitters is arithmetic coding, the matching decoding scheme is arithmetic decoding, meaning that the decoding scheme used by the first receiver may be arithmetic decoding, and so on. When the encoding scheme used by the multiple first transmitters is other encoding schemes, the first receiver may also use other decoding schemes. In this implementation, if the multiple first transmitters use the same encoding scheme, it is easier for the transmission signals of the multiple first transmitters to be superimposed in the air, and if the decoding scheme used by the first receiver matches the encoding schemes of the multiple first transmitters, it is more conducive for the first receiver to obtain valid data from the received signals.

[0021] In one possible implementation, multiple first transmitting ends use the same quantization scheme; the dequantization scheme used by the first receiving end matches the quantization schemes used by the multiple first transmitting ends. For example, when the quantization scheme used by the multiple first transmitting ends is uniform quantization, the matching dequantization scheme is deuniform quantization, meaning that the dequantization scheme used by the first receiving end may be deuniform quantization. For another example, when the quantization scheme used by the multiple first transmitting ends is non-uniform quantization, the matching dequantization scheme is de-nonuniform quantization, meaning that the dequantization scheme used by the first receiving end may be de-nonuniform quantization. When the quantization scheme used by the multiple first transmitting ends is other quantization schemes, the first receiving end may also use other dequantization schemes. In this implementation, the multiple first transmitting ends use the same quantization scheme, making it easier for the signals transmitted by the multiple first transmitting ends to be superimposed in the air. Furthermore, the matching dequantization scheme used by the first receiving end with the quantization schemes of the multiple first transmitting ends further facilitates the first receiving end in obtaining valid data from the received signals.

[0022] In a second aspect, an embodiment of the present application provides a data processing method, which can apply artificial intelligence technology to the field of communications, and the method includes: a first transmitting end receives first indication information; the first transmitting end determines, based on the first indication information, that the first transmitting end and the first receiving end adopt a first mode when performing air computing, the first mode being one of at least two air computing modes, and the first mode is determined based on the first information of the first transmitting end and the second information of the first receiving end, the first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

[0023] In a possible implementation manner, the method further includes: the first sending end sending first information of the first sending end to the control node.

[0024] The meanings of the terms in each possible implementation of the second aspect of this application and the beneficial effects brought about can be referred to the first aspect and will not be repeated here.

[0025] In a third aspect, an embodiment of the present application provides a data processing method, which can apply artificial intelligence technology to the field of communications, and the method includes: a first receiving end receives second indication information; the first receiving end determines, based on the second indication information, that a first transmitting end and the first receiving end use a first mode when performing air computing, the first mode being one of at least two air computing modes, and the first mode being determined based on the first information of the first transmitting end and the second information of the first receiving end, the first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

[0026] In a possible implementation manner, the method further includes: the first sending end sending the second information of the first receiving end to the control node.

[0027] The meanings of the terms in each possible implementation of the third aspect of this application and the beneficial effects brought about can be referred to the first aspect and will not be repeated here.

[0028] In a fourth aspect, an embodiment of the present application provides a data processing device, which can apply artificial intelligence technology to the field of communications. The data processing device is applied to a control node, and the data processing device includes: a determination module, used to determine a first mode adopted by multiple first transmitting ends and a first receiving end when performing air computing, wherein the first mode is one of at least two air computing modes, and the first mode is determined based on the first information of each first transmitting end and the second information of the first receiving end in the multiple first transmitting ends, the first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end; the determination module is also used to determine indication information, and the indication information instructs the first transmitting end and the first receiving end to adopt the first mode for air computing.

[0029] The data processing device in the fourth aspect is also used to execute other steps performed by the control node in the first aspect. The specific implementation methods, meanings of terms and beneficial effects brought about by the steps in each possible implementation method of the fourth aspect of this application can all be referred to the first aspect and will not be repeated here.

[0030] In a fifth aspect, an embodiment of the present application provides a data processing device, which can apply artificial intelligence technology to the field of communications. The data processing device is applied to a first transmitting end, and the data processing device includes: a receiving module for receiving first indication information; a determination module for determining, based on the first indication information, that the first transmitting end and the first receiving end adopt a first mode when performing air calculations. The first mode is one of at least two air calculation modes. The first mode is determined based on the first information of the first transmitting end and the second information of the first receiving end. The first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

[0031] The data processing device in the fifth aspect is also used to execute other steps performed by the first sending end in the second aspect. The specific implementation methods, meanings of terms and beneficial effects brought about by the steps in each possible implementation method of the fifth aspect of this application can all be referred to the second aspect and will not be repeated here.

[0032] In a sixth aspect, an embodiment of the present application provides a data processing device, which can apply artificial intelligence technology to the field of communications. The data processing device is applied to a first receiving end, and the data processing device includes: a receiving module for receiving second indication information; a determination module for determining, based on the second indication information, that the first transmitting end and the first receiving end adopt a first mode when performing air calculations. The first mode is one of at least two air calculation modes. The first mode is determined based on the first information of the first transmitting end and the second information of the first receiving end. The first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

[0033] The data processing device in the sixth aspect is also used to execute other steps performed by the first receiving end in the third aspect. The specific implementation methods, meanings of terms and beneficial effects brought about by the steps in each possible implementation method of the sixth aspect of this application can all be referred to the third aspect and will not be repeated here.

[0034] In the seventh aspect, an embodiment of the present application provides a device including a processor and a memory, where the processor is coupled to the memory, the memory is used to store programs, and the processor is used to execute the programs in the memory, so that the device executes the data processing method of the first aspect, the second aspect or the third aspect mentioned above.

[0035] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the data processing method of the first aspect, the second aspect or the third aspect mentioned above.

[0036] In a ninth aspect, an embodiment of the present application provides a computer program product, which includes a program. When the program runs on a computer, it enables the computer to execute the data processing method of the first aspect, the second aspect or the third aspect mentioned above.

[0037] In a tenth aspect, the present application provides a chip system, which includes a processor for supporting the implementation of the functions involved in the above aspects, such as sending or processing the data and / or information involved in the above methods. In one possible design, the chip system also includes a memory, which is used to store program instructions and data necessary for the terminal device or communication device. The chip system can be composed of a chip or can include a chip and other discrete devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] FIG1 is a schematic diagram of an architecture of a wireless communication system provided in an embodiment of the present application;

[0039] FIG2 is a schematic diagram of federated learning provided in an embodiment of the present application;

[0040] FIG3 is a flow chart of a data processing method provided by the present application;

[0041] FIG4 is another schematic diagram of a data processing method provided in an embodiment of the present application;

[0042] FIG5 is a flow chart of a data processing method when the first mode is the “performance mode” according to an embodiment of the present application;

[0043] FIG6 is a flow chart of a data processing method when the first mode is the “pre-equalization mode” according to an embodiment of the present application;

[0044] FIG7 is a flow chart of a data processing method when the first mode is the “channel hardening mode” according to an embodiment of the present application;

[0045] FIG8 is a schematic structural diagram of a data processing device provided in an embodiment of the present application;

[0046] FIG9 is another structural diagram of a data processing device provided in an embodiment of the present application;

[0047] FIG10 is another structural diagram of a data processing device provided in an embodiment of the present application;

[0048] FIG11 is a schematic structural diagram of a device provided in an embodiment of the present application;

[0049] FIG12 is another schematic diagram of the structure of the device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0051] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0052] In the embodiments of the present application, "sending" and "receiving" indicate the direction of signal transmission. For example, "sending information to XX device" can be understood as the destination of the information being XX device, 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 device" can be understood as the source of the information being YY device, which can include direct receiving from YY device through the air interface, as well as indirect receiving from YY device 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. In other words, sending and receiving can be performed between devices or within a device, for example, between components, modules, chips, software modules or hardware modules within the device through a bus, trace or interface. It is understandable that information may undergo necessary processing, such as encoding, modulation, etc., between the source and destination of the information, 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.

[0053] 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, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated; it is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance, for example, the indication of specific information can be achieved with the help 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.

[0054] The present application can be applied in the field of communications, optionally, in the application scenario of over-the-air computing (OTA). Before describing in detail the method provided by the present application, the scenario in which the method provided by the embodiment of the present application is applied is first introduced. Please refer to Figure 1, which is a schematic diagram of the architecture of the wireless communication system provided by the embodiment of the present application. The method provided by the present application can be applied to a wireless communication system. As shown in Figure 1, the wireless communication system includes a network device 101 and a terminal device (mobile station, MS) 102. Among them, a wireless connection can be established between the network device 101 and each terminal device 102, and a wireless connection can also be established between each terminal device 102.

[0055] Network device 101 may refer to a device that provides wireless access services in a wireless network. For example, network device 101 may be a device that connects terminal device 102 to a wireless network, and may also be referred to as a base station. The aforementioned base station may be various forms of macro base stations, micro base stations, relay stations, or access points. In wireless communication systems that utilize different wireless access technologies, the name of network device 101 that has base station functionality may vary. For example, a base station may be referred to as an evolved Node B (eNB), a Node B (NB), the next generation Node B (gNB) in a fifth generation (5G) communication system, a home base station (e.g., a home evolved Node B or HNB), a baseband unit (BBU), a wireless fidelity (Wi-Fi) access point (AP), a transmission reception point (TRP), or a radio network controller (RNC). In another possible scenario, multiple network nodes collaborate to facilitate wireless access, with different network nodes each implementing portions of the base station's functionality. For example, a network node may 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 may be separately configured or included in the same network element, such as a baseband unit (BBU). The RU may 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). In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meanings. For example, in the ORAN system, CU may also be called open CU (O-CU), DU may also be called open DU (O-DU), CU-CP may also be called open CU-CP (O-CU-CP), CU-UP may also be called open CU-UP (O-CU-UP), and RU may also be called open RU (O-RU).Among them, any unit among CU (or CU-CP, CU-UP), DU and RU can be implemented by software module, hardware module, or a combination of software module and hardware module. The embodiment of the present application does not limit the specific device form of network device 101.

[0056] Terminal device 102 refers to a wireless terminal device capable of receiving scheduling information and indication information sent by network device 101. Terminal device 102 may be a handheld device with wireless communication capabilities, a vehicle-mounted device, a wearable device, a computing device, or other processing device, etc., which are not exhaustive here.

[0057] The terminal device 102 can communicate with one or more core networks or the Internet via a wireless access network (RAN). For example, the terminal device 102 can be a portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted mobile device that exchanges voice and / or data with the wireless access network. Exemplarily, the terminal device 102 can be a user agent, a cellular phone, a smart phone, a personal digital assistant (PDA), a tablet personal computer (Tablet PC), a wireless modem, a handset, a laptop computer, a personal communication service (PCS) phone, a remote station, an access point (AP), a remote terminal, an access terminal, customer premises equipment (CPE), a terminal, user equipment (UE), or a mobile terminal (MT), etc.

[0058] For another example, the terminal device 102 may also be a wearable device, which is 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 just 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, 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.

[0059] For another example, the terminal device 102 may also be a drone, a robot, a terminal device in device-to-device (D2D) communication, a terminal device in vehicle to everything (V2X), a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a terminal device in self-driving, a terminal device in remote medical, a terminal device in a smart grid, a wireless terminal in a smart city, a terminal device in a smart home, etc.

[0060] In addition, the terminal device 102 may also be a terminal device in a communication system after the 5G communication system (for example, a sixth generation (6G) communication system, etc.) or a terminal device in a future evolved public land mobile network (PLMN), etc. The embodiment of the present application does not limit the device form of the terminal device 102.

[0061] In some application scenarios, multiple terminal devices 102 and network device 101 can perform over-the-air computing. That is, when multiple terminal devices 102 send signals to network device 102, the signals transmitted by multiple terminal devices 102 are superimposed over-the-air, and the received signal obtained by network device 101 is the signal that has undergone the aforementioned superposition operation. Optionally, network device 101 and multiple terminal devices 102 can be used to perform federated learning (FL), where network device 101 can serve as the central node of FL and multiple terminal devices 102 can serve as distributed nodes of FL.

[0062] For a more intuitive understanding of this solution, please refer to Figure 2, which is a schematic diagram of federated learning provided in an embodiment of the present application. As shown in Figure 2, the central node can initialize the machine learning model to be trained and send the aforementioned machine learning model to all distributed nodes to perform multiple rounds of training operations on the machine learning model through the distributed nodes. The aforementioned machine learning model can be expressed as a neural network or an algorithm in the form of a non-neural network; illustratively, the aforementioned machine learning model can be expressed as a fully connected neural network, a convolutional neural network, a recurrent neural network, a residual neural network or other types of neural networks, etc., which are not exhaustive in the embodiments of the present application.

[0063] For the convenience of description, any round of training operations in multiple rounds of training operations is called the t-th round of training operations. In the t-th round of training operations, any distributed node among multiple distributed nodes (hereinafter referred to as the "target distributed node" for the convenience of description) obtains the machine learning model sent by the central node (that is, the machine learning model obtained in the t-1th round of training operations). ) After that, the local training data can be used to train the machine learning model obtained in the t-1 round of training operation. Perform training and obtain local training results Exemplarily, the target distributed node trains the machine learning model by evaluating the output of the machine learning model using a loss function, backpropagating the error between the output and the true value, and updating the weight parameters in the machine learning model using a gradient descent method. The target distributed node reports the local training results to the central node; all or some of the multiple distributed nodes execute the steps executed by the target distributed node.

[0064] The central node aggregates the local training results from all (or part) distributed nodes. Assume that the distributed nodes that upload local training results in round t constitute a set The central node can The weighted average of the local training results uploaded by all distributed nodes in the training process is used to obtain the machine learning model in the tth round of training operation. The weight corresponding to each distributed node in is determined based on the number of training samples on each distributed node, that is, the more training samples on each distributed node, the greater the weight corresponding to the local training result reported by the distributed node. in, represent The local training result reported by the kth distributed node to the central node, Dk represents the number of training samples on the kth distributed node, represent The total number of training samples on all distributed nodes in the . For example, multiple distributed nodes can send Thus, multiple distributed nodes send It can perform air calculation, that is, superposition in the air, and the central node can obtain the superimposed signal

[0065] After obtaining the machine learning model in the tth round of training operation, the central node can send the machine learning model obtained in the tth round of training operation to all distributed nodes again to start the t+1th round of training operation for the machine learning model. It should be understood that the example in Figure 2 is only for the convenience of understanding the concept of "federated learning" and is not used to limit this solution.

[0066] In addition to the scenarios described in Figures 1 and 2 above, the method provided in the embodiments of the present application can also be applied to other communication system scenarios. The embodiments of the present application do not limit the specific scenarios in which the data processing method is applied.

[0067] It should be noted that the wireless communication systems mentioned in the embodiments of the present application include but are not limited to: fifth generation mobile communication technology (5G) communication system, 6G communication system, satellite communication system, short-range communication system, narrowband Internet of Things system (NB-IoT), global system for mobile communications (GSM), enhanced data rate for GSM evolution system (EDGE), wideband code division multiple access system (WCDMA), code division multiple access 2000 system (CDMA2000), time division synchronous code division multiple access system (TD-SCDMA) and long term evolution system (LTE). The embodiments of the present application do not limit the specific architecture of the wireless communication system.

[0068] In the above application scenarios, since the transmission signal of each terminal device 102 in the multiple terminal devices 102 is affected by the channel when passing through the air, and different terminal devices 102 reach the network device 101 through different channels, the network device 101 cannot directly obtain the data carried in the superimposed signal. In order to solve the above problem, the present application provides a data processing method, please refer to Figure 3, which is a flow chart of the data processing method provided by the present application. Among them,

[0069] 301. A control node determines a first mode to be adopted when multiple first transmitting ends and first receiving ends perform over-the-air computing, wherein the first mode is one of at least two over-the-air computing modes, and the first mode is determined based on first information of each first transmitting end and second information of the first receiving end among the multiple first transmitting ends, the first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

[0070] In the embodiment of the present application, the control node can be implemented by a base station device, a core network device, a terminal device or other devices. The specific devices that implement the control node can be determined in combination with the actual application scenario, and are not limited in the embodiment of the present application.

[0071] Optionally, the control node is a first receiving end, and the first receiving end and multiple first transmitting ends are used to perform federated learning. The first receiving end is the central node of federated learning, and the multiple first transmitting ends are distributed nodes of federated learning. For the meaning of "federated learning", please refer to the above description and will not be repeated here. In an embodiment of the present application, a specific application scenario is provided when multiple first transmitting ends and a first receiving end perform air computing, and in this application scenario, the control node and the first receiving end are integrated into the same device, that is, a specific combination scheme for combining federated learning and air computing is provided, which reduces the difficulty of implementing this scheme.

[0072] Exemplarily, the control node may determine multiple first transmitters and one first receiver participating in the air calculation from at least one transmitter and at least one receiver. Specifically, in some application scenarios, there are multiple transmitters and one receiver (i.e., the first receiver) participating in the air calculation. Before executing step 301, the control node also receives the first information of each of the multiple transmitters and the second information of the first receiver. Then, in step 301, based on the first information of each of the multiple transmitters and the second information of the first receiver, a group of first transmitters is determined from the aforementioned multiple transmitters; the meaning of "the first information of each transmitter" is similar to that of "the first information of the first transmitter", which can be understood by reference.

[0073] In other application scenarios, there are multiple transmitters and multiple receivers participating in air computing. Before executing step 301, the control node also receives the first information of each of the multiple transmitters and the second information of each of the multiple receivers. Then, in step 301, the control node determines multiple first transmitters and one first receiver from the aforementioned "multiple transmitters and multiple receivers" based on the first information of each of the multiple transmitters and the second information of each receiver. The meaning of "the second information of each receiver" is similar to that of "the second information of the first receiver", which can be referred to for understanding and will not be repeated in the embodiments of the present application.

[0074] Exemplarily, in the process of the control node determining multiple first transmitters and one first receiver based on the first information of each transmitter and the second information of each receiver, the channel information acquisition capability of each transmitter is considered. The multiple first transmitters need to have the same channel information acquisition capability, that is, the multiple first transmitters can all obtain channel information, or the multiple first transmitters cannot obtain channel information.

[0075] Optionally, the first information of each transmitting end (including the first transmitting end) also includes the coding scheme and / or quantization scheme adopted by each transmitting end, and the second information of each receiving end (including the first receiving end) also includes the decoding scheme and / or dequantization scheme of each receiving end. In an embodiment of the present application, the control node will consider more information in the process of determining which air computing mode to adopt between multiple first transmitting ends and the first receiving end, which is conducive to more accurate grouping of multiple transmitting ends, that is, it is conducive to the same coding scheme and / or quantization scheme between the multiple first transmitting ends after grouping, and the transmission signals of the multiple first transmitting ends can obtain the reception signal of the first receiving end after superposition in the air, so that the first receiving end can more easily obtain valid data from the received signal, which is conducive to improving the performance of air computing between the multiple first transmitting ends and the first receiving end.

[0076] Exemplarily, the encoding schemes that can be adopted by a transmitting end include: Huffman coding, arithmetic coding, dictionary coding or other encoding schemes, etc.; the decoding schemes that can be adopted by a receiving end include: Huffman decoding, arithmetic decoding, dictionary decoding or other decoding schemes, etc. It should be understood that the examples here are only for the convenience of understanding this scheme and are not used to limit this scheme.

[0077] Exemplarily, the quantization schemes that can be adopted by a transmitting end include: uniform quantization, non-uniform quantization, vector quantization, scalar quantization or other quantization schemes, etc.; the dequantization schemes that can be adopted by a receiving end include: deuniform quantization, de-non-uniform quantization, de-vector quantization, de-scalar quantization or other dequantization schemes, etc. It should be understood that the examples here are only for the convenience of understanding this scheme and are not used to limit this scheme.

[0078] Optionally, when the control node determines multiple first transmitters and one first receiver based on the first information of each transmitter and the second information of each receiver, the coding scheme adopted by each transmitter and the decoding scheme adopted by each receiver may also be considered. Multiple first transmitters adopt the same coding scheme; the decoding scheme used by the first receiver matches the coding scheme used by the multiple first transmitters. For example, when the coding scheme adopted by the multiple first transmitters is Huffman coding, the decoding scheme matched therewith is Huffman decoding, that is, the decoding scheme adopted by the first receiver may be Huffman decoding; for another example, when the coding scheme adopted by the multiple first transmitters is arithmetic coding, the decoding scheme matched therewith is arithmetic decoding, that is, the decoding scheme adopted by the first receiver may be arithmetic decoding, and so on. When the coding scheme adopted by the multiple first transmitters is other coding schemes, the first receiver may also adopt other decoding schemes. The examples here are only for the convenience of understanding this solution and are not used to limit this solution.

[0079] In an embodiment of the present application, multiple first transmitting ends adopt the same encoding scheme, so it is easier for the transmission signals of multiple first transmitting ends to be superimposed in the air, and the decoding scheme adopted by the first receiving end matches the encoding schemes of multiple first transmitting ends, which is more conducive to the first receiving end obtaining valid data from the received signal.

[0080] Optionally, when the control node determines multiple first transmitters and one first receiver based on the first information of each transmitter and the second information of each receiver, the quantization scheme used by each transmitter and the dequantization scheme used by each receiver may also be considered. Multiple first transmitters use the same quantization scheme; the dequantization scheme used by the first receiver matches the quantization schemes used by the multiple first transmitters. For example, when the quantization scheme used by the multiple first transmitters is uniform quantization, the dequantization scheme that matches it is deuniform quantization, that is, the dequantization scheme used by the first receiver may be deuniform quantization; for another example, when the quantization scheme used by the multiple first transmitters is non-uniform quantization, the dequantization scheme that matches it is de-nonuniform quantization, that is, the dequantization scheme used by the first receiver may be de-nonuniform quantization, and so on. When the quantization scheme used by the multiple first transmitters is other quantization schemes, the first receiver may also use other dequantization schemes. The examples here are only for the convenience of understanding this solution and are not used to limit this solution.

[0081] In an embodiment of the present application, multiple first transmitting ends adopt the same quantization scheme, so it is easier for the transmission signals of the multiple first transmitting ends to be superimposed in the air, and the dequantization scheme adopted by the first receiving end matches the quantization schemes of the multiple first transmitting ends, which is more conducive to the first receiving end obtaining valid data from the received signal.

[0082] Optionally, the first information of each of the multiple transmitting ends (including the first transmitting end) further includes the first number of transmitting antennas of each transmitting end, and the second information of each receiving end (including the first receiving end) further includes the second number of receiving antennas of each first receiving end; when the control node determines which air computing mode to adopt between the multiple first transmitting ends and the first receiving end (i.e., determining the first mode), the number of transmitting antennas of each first transmitting end and the number of receiving antennas of the first receiving end may also be considered. Exemplarily, the relationship between the number of transmitting antennas of each of the multiple first transmitting ends and the number of receiving antennas of the first receiving end is consistent; that is, the number of transmitting antennas of each of the multiple first transmitting ends is greater than or equal to the number of receiving antennas of the first receiving end, or the number of transmitting antennas of each of the multiple first transmitting ends is less than the number of receiving antennas of the first receiving end.

[0083] In an embodiment of the present application, since the number of transmitting antennas of the transmitting end and the number of antennas of the receiving end will affect the performance of certain air computing modes, the control node will also consider the number of transmitting antennas of the multiple first transmitting ends and the number of receiving antennas of the first receiving end when determining which air computing mode to adopt for multiple first transmitting ends and the first receiving end. The first mode finally determined not only matches the channel information acquisition capability of the first transmitting end and the first receiving end, but also matches the number of antennas of the first transmitting end and the first receiving end, thereby facilitating the first receiving end to obtain valid information from the results of the air computing, thereby improving the performance of the air computing.

[0084] Based on the first information of multiple transmitters and the second information of at least one receiver, multiple first transmitters and one first receiver are selected from the multiple transmitters and at least one receiver for air calculation, and an air calculation mode adapted to the selected "multiple first transmitters and one first receiver" is determined, which is beneficial to improving the adaptability between the finally determined first mode and the "multiple first transmitters and one first receiver", and is beneficial for the first receiver to obtain more valid data.

[0085] Optionally, in one case, multiple first transmitting ends and first receiving ends can obtain channel information, and the first mode represents that the first transmitting end performs a pre-equalization operation on the transmitted signal, and the first receiving end performs denoising on the received signal according to the channel information.

[0086] Exemplarily, "the first transmitting end has the ability to obtain channel information" can be understood as the first transmitting end being able to obtain the channel state information from the first transmitting end to the first receiving end through channel prediction, channel reciprocity or other methods. It should be noted that the first transmitting end can also use other methods to obtain the channel state information from the first transmitting end to the first receiving end, which is not exhaustive in the embodiments of this application.

[0087] For example, in this case, "the first receiving end has the ability to obtain channel information" can be understood as the first receiving end being able to obtain the channel state information from each first transmitting end to the first receiving end through channel prediction, channel estimation or other methods. It should be noted that the first receiving end can also use other methods to obtain the channel state information from each first transmitting end to the first receiving end, which is not enumerated in the embodiments of the present application.

[0088] In step 301, after the control node determines that multiple first transmitting ends and first receiving ends all have the ability to obtain channel information, it can be determined that the first mode adopted by the multiple first transmitting ends and the first receiving ends when performing air calculations is the performance mode. The performance mode represents that each of the multiple first transmitting ends performs a pre-equalization operation on the transmitted signal, and the first receiving end performs denoising processing on the received signal based on the channel.

[0089] To further understand the “pre-equalization operation”, for example, there are K first transmitting ends, where K is an integer greater than or equal to 2, and the data that the kth first transmitting end needs to send is s k , the kth first transmitter needs to send data s k After performing the pre-equalization operation, we get in, Represents the data s that the kth first transmitter needs to send k The pre-equalization operation performed by the K first transmitting ends is performed by each of the K first transmitting ends. That is, the K first transmitting ends perform the pre-equalization operation on the data to be sent. After performing the pre-equalization operation on the data to be sent, each of the K first transmitting ends sends it out. The signals sent by the K first transmitting ends are superimposed in the air, and the signal received by the first receiving end is Among them, P k represents the transmission power of the kth first transmitter, H k Represents the signal x transmitted in the channel between the kth first transmitter and the first receiver k Therefore, it is necessary to design a pre-equalization operation make When I is a unit matrix or the upper half of I is a unit matrix, the influence of the channel on the signal transmission process can be eliminated. Then, the k-th first transmitting end needs to be able to obtain the channel state information between the k-th first transmitting end and the first receiving end, and then determine the influence of the channel between the k-th first transmitting end and the first receiving end on the signal transmitted in the channel (that is, H k ), and then according to H k right Make a design.

[0090] For example, when the first number of transmitting antennas of the kth first transmitting end is equal to the second number of receiving antennas of the first receiving end, I is a guideline, and it is necessary to design is a unit matrix; when the first number of transmitting antennas of the kth first transmitting end is greater than the second number of receiving antennas of the first receiving end, the number of rows of I is greater than the number of columns, then it is necessary to design Because the top is a unit matrix, and there are several rows of other elements below, for example, I is M rows and N columns, you need to design The upper N rows are unit matrices, and the lower (MN) rows are other elements; illustratively, the other elements can be any real numbers, which are not limited in the embodiments of the present application.

[0091] In another scenario, multiple first transmitting ends are able to obtain channel information, the first receiving end is unable to obtain channel information, and the first number of transmitting antennas of each of the multiple first transmitting ends is greater than or equal to the second number of receiving antennas of the first receiving end. The first mode may represent that the first transmitting end performs a pre-equalization operation on the transmitted signal. That is, in step 301, after determining that the multiple first transmitting ends are all able to obtain channel information, the first receiving end is unable to obtain channel information, and the first number of the multiple first transmitting ends is greater than or equal to the second number, the control node may determine that the first mode used by the multiple first transmitting ends and the first receiving end for over-the-air calculation is a pre-equalization mode. The pre-equalization mode represents that each first transmitting end performs a pre-equalization operation on the transmitted signal, and the first receiving end does not perform denoising processing.

[0092] In another scenario, multiple first transmitting ends are unable to obtain channel information, the first receiving end is able to obtain channel information, and the first number of transmitting antennas of each of the multiple first transmitting ends is less than the second number of receiving antennas of the first receiving end. The first mode represents that the first receiving end estimates the sum channel based on the pilot signal sent by the first transmitting end and processes the received signal based on the sum channel. Optionally, the first number of each of the multiple first transmitting ends needs to be much smaller than the second number of first receiving ends, that is, the first number of each first transmitting end and the second number of first receiving ends can meet the first condition. Exemplarily, the first condition can be that the result of dividing the second number by the first number is T, and T can be greater than or equal to 10. In this case, "the first receiving end has the ability to obtain channel information" can be understood as the first receiving end being able to estimate the sum channel based on the pilot signals sent by the multiple first transmitting ends.

[0093] In step 301, when the control node determines that multiple first transmitting ends cannot obtain channel information, the first receiving end can obtain channel information, and the first number of each first transmitting end in the multiple first transmitting ends and the second number of the first receiving ends meet the first condition, the control device can determine the first mode as the channel hardening mode. The channel hardening mode means that each first transmitting end does not need to preprocess the data to be transmitted, but multiple first transmitting ends need to send the same pilot signal to the first receiving end. The first receiving end estimates the sum channel based on the pilot signal sent by the first transmitting end, and processes the received signal based on the sum channel.

[0094] To further understand this solution, the specific steps of the first transmitting end and the first receiving end in the channel hardening mode are described below. In the channel hardening mode, the multiple first transmitting ends include K first transmitting ends, where K represents an integer greater than or equal to 2. The K first transmitting ends send data s k Previously, all first transmitting ends sent the same pilot signal s to the first receiving end. Since the pilot signals sent by multiple first transmitting ends to the first receiving end are superimposed in the air before reaching the first receiving end (i.e., they are calculated in the air), the signal received by the first receiving end is Among them, s represents the pilot signal, H k represents the impact of the channel between the kth first transmitting end and the first receiving end on the pilot signal s, n s represents noise. Since the first receiving end knows the pilot signal s, the first receiving end can s Sum pilot signal s, estimate the sum channel (um of the channel gains) U corresponding to the plurality of first transmitting ends, for example, sum channel

[0095] Let the data that the kth first transmitter needs to send be s k , since the kth first transmitter does not need to k Perform pre-equalization operation, then the data x carried in the signal sent by the kth first transmitting end to the first receiving end k =s k The signals sent by the K first transmitting ends are superimposed in the air before reaching the first receiving end, and the received signal obtained by the first receiving end is Among them, H k represents the impact of the channel between the kth first transmitting end and the first receiving end on the signal transmitted in the channel, and n represents noise.

[0096] The first receiving end may process the received signal according to the sum channel to estimate the K signals that the first transmitting end wants to send. For example, Among them, U H represents the conjugate transpose of U, y represents the received signal obtained by the first receiving end (that is, the signal obtained by superimposing the signals sent by the K first transmitting ends in the air), represents the signals that the K first transmitting ends actually want to send estimated by the first receiving end, that is, the signals after the influence of the channel is eliminated; it should be noted that when the first number of each first transmitting end and the second number of the first receiving end both meet the first condition, the influence of interference in the process of "estimating the signals that the K first transmitting ends want to send based on the sum channel" can be ignored, that is, when the first number of each first transmitting end and the second number of the first receiving end both meet the first condition, the received signal y is estimated based on the sum channel U It can be considered as a signal obtained by superimposing the signals that the K first transmitting ends want to send, that is, the influence of the channel on the signal is eliminated.

[0097] In another case, when multiple first transmitting ends can obtain channel information, the first receiving end cannot obtain channel information, and the first number is less than the second number; or, when multiple first transmitting ends cannot obtain channel information, the first receiving end can obtain channel information, and the first number is greater than or equal to the second number; or, when multiple first transmitting ends and first receiving ends cannot obtain channel information, that is, when the triggering conditions of the above-mentioned "performance mode", "pre-equalization mode" and "channel hardening mode" are not met, the control node can determine that the first mode adopted by multiple first transmitting ends and the first receiving end when performing air calculations is a non-coherent mode, and the non-coherent mode represents that the first transmitting end performs binarization processing on the transmitted signal.

[0098] Exemplarily, when the "incoherent mode" is adopted, each of the multiple first transmitting ends can perform binary quantization on the data to be sent, for example, quantize each data to be sent to -1 or +1. Then, for each data to be sent (hereinafter referred to as "target data" for the convenience of description), the first receiving end can obtain K quantized values ​​sent by K first transmitting ends. The first receiving end counts the K quantized values ​​and uses majority voting to determine the final value of the target data.

[0099] For example, the K first transmitting ends include a total of 5 first transmitting ends, and the 5 first transmitting ends are respectively the first transmitting end 1, the first transmitting end 2, the first transmitting end 3, the first transmitting end 4 and the first transmitting end 5. The first transmitting end 1 quantizes the target data to +1, the first transmitting end 2 quantizes the target data to +1, the first transmitting end 3 quantizes the target data to +1, the first transmitting end 4 quantizes the target data to -1, and the first transmitting end 5 quantizes the target data to -1. Then, the first receiving end can obtain 5 quantized values ​​corresponding to the target data. The 5 quantized values ​​are +1, +1, +1, -1 and -1 respectively. Then, the final result of the target data is +1. It should be understood that the example here is only for the convenience of understanding the specific steps performed by the first transmitting end and the first receiving end in the "incoherent mode" and is not used to limit this solution.

[0100] In an embodiment of the present application, a specific scheme is provided for the first mode adopted when multiple first transmitting ends and first receiving ends perform air computing in various situations. That is, in various situations, there are matching air computing modes, which is conducive to expanding the application scenarios of this scheme and improving the implementation flexibility of this scheme. In addition, there are matching air computing modes in various situations, which is conducive to using the most suitable air computing mode in various situations, and is conducive to assisting the first receiving end to obtain more valid data.

[0101] 302. The control node determines instruction information, where the instruction information instructs the first transmitting end and the first receiving end to perform over-the-air computing in a first mode.

[0102] In an embodiment of the present application, after determining multiple first transmitting ends, one first receiving end, and a first mode, the control node may determine indication information, where the indication information instructs the first transmitting end and the first receiving end to perform over-the-air calculations using the first mode.

[0103] In an application scenario, the control node and the first receiving end are integrated into the same device, and the indication information may include first indication information. After determining the indication information, the control node may send the first indication information to each of the multiple first transmitting ends. The first indication information is used to inform each first transmitting end to use the first mode for air computing.

[0104] In another application scenario, the control node and the first receiving end are located in different devices, and the indication information may include first indication information and second indication information. After determining the indication information, the control node can send the first indication information to each of the multiple first transmitting ends and send the second indication information to the first receiving end. The first indication information is used to inform each first transmitting end to use the first mode for air calculation, and the second indication information is used to inform the first receiving end to use the first mode for air calculation.

[0105] For example, in one scenario, the indication information may be present as identification information for indicating the first mode. For example, the indication information may be present as an index value for indicating the first mode, with different index values ​​indicating different over-the-air computing modes. For a more intuitive understanding of this solution, please refer to the following Table 1, which shows the relationship between index values ​​and different over-the-air computing modes.

[0106] Table 1

[0107] Among them, when the index value carried in the indication information is 0, it means that the first mode adopts the "performance mode", and the first transmitting end and the first receiving end determine to adopt the performance mode for air calculation; when the index value carried in the indication information is 1, it means that the first mode adopts the "pre-equalization mode", and the first transmitting end and the first receiving end determine to adopt the pre-equalization mode for air calculation; when the index value carried in the indication information is 2, it means that the first mode adopts the "channel hardening mode", and the first transmitting end and the first receiving end determine to adopt the channel hardening mode for air calculation; when the index value carried in the indication information is 3, it means that the first mode adopts the "incoherent mode", and the first transmitting end and the first receiving end determine to adopt the incoherent mode for air calculation. It should be understood that the examples here are only for the convenience of understanding this scheme and are not used to limit this scheme.

[0108] In another case, since the steps that the first transmitting end and the first receiving end need to perform are also different when the first mode is specifically manifested as different air computing modes, the indication information can also inform the first transmitting end and the first receiving end which air computing mode to adopt by indicating the steps that each first transmitting end and the first receiving end need to perform. For example, when the first mode is determined to be a "performance mode", the first indication information is used to instruct each first transmitting end to send a pilot signal to the first receiving end, and perform a pre-equalization operation on the signal to be sent, and the first receiving end needs to perform denoising processing on the received signal obtained based on the channel.

[0109] When the first mode is determined to be the "pre-equalization mode", the first indication information is used to instruct each first transmitting end to perform a pre-equalization operation on the signal to be sent. When the first mode is determined to be the "channel hardening mode", the first indication information is used to instruct each first transmitting end to send a pilot signal to the first receiving end, and the first receiving end needs to process the received signal obtained according to the channel. When the first mode is determined to be the "incoherent mode", the first indication information is used to instruct each first transmitting end to perform a binarization process on each data to be sent, and the first receiving end determines the result of each received data based on the majority voting principle.

[0110] It should be understood that the "indication information" can also carry other specific information, etc., to indicate which air computing mode each first transmitting end and first receiving end should adopt when performing air computing. The example of "indication information" here is only for the convenience of understanding this solution and is not used to limit this solution.

[0111] In this implementation, the control node determines a first mode to be adopted by multiple first transmitting ends and first receiving ends when performing over-the-air computing, and then determines indication information, where the indication information is used to instruct the first transmitting end and the first receiving end to adopt the first mode for over-the-air computing. Since the first mode is one of at least two over-the-air computing modes, and the first mode is determined based on the channel information acquisition capability of the first transmitting end and the channel information acquisition capability of the first receiving end, that is, which specific over-the-air computing mode is adapted to the capabilities of the transmitting end and the receiving end, this is conducive to increasing the probability that the first transmitting end and the first receiving end can successfully adopt the first mode for over-the-air computing when performing over-the-air computing, thereby greatly reducing the probability of execution failure.

[0112] In conjunction with the above description, the following describes the detailed implementation process of the data processing method provided by this application, taking multiple transmitters and one receiver (i.e., a first receiver) participating in air computing, using the method provided by this application to determine multiple first transmitters from multiple transmitters, and determining the first mode adopted between multiple first transmitters and a first receiver as an example. Specifically, please refer to Figure 4, which is another schematic diagram of the data processing method provided by the embodiment of this application. As shown in Figure 4, the data processing method provided by this application may include:

[0113] 401. A control node obtains first information of each of multiple sending ends.

[0114] In an embodiment of the present application, after determining that there are multiple transmitters and one receiver participating in the air calculation, each of the multiple transmitters can send the first information of the transmitter to the control node. Correspondingly, the control node can obtain the first information of each of the multiple transmitters. The meaning of "the first information of each transmitter" is similar to the meaning of "the first information of the first transmitter". Please refer to the description in the corresponding embodiment of Figure 3 above, and no further details will be given here.

[0115] 402. The control node obtains second information of the first receiving end.

[0116] In an embodiment of the present application, in some application scenarios, the control node and the first receiving end are respectively located in different devices. In this case, in step 402, the first receiving end can send the second information of the first receiving end to the control node; in other application scenarios, the control node and the first receiving end can be integrated into the same device. In this case, in step 402, the control node can directly obtain the second information of the first receiving end. The meaning of the "second information of the first receiving end" can be found in the description of the embodiment corresponding to Figure 3 above, and will not be repeated here.

[0117] 403. The control node determines a first mode to be adopted when multiple first transmitting ends and first receiving ends perform over-the-air computing, wherein the first mode is one of at least two over-the-air computing modes, and the first mode is determined based on first information of each first transmitting end and second information of the first receiving end in the multiple first transmitting ends, the first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

[0118] In an embodiment of the present application, after obtaining the second information of the first receiving end, the control node can determine the channel information acquisition capability of the first receiving end; optionally, the second information of the first receiving end also includes the second number of receiving antennas of the first receiving end.

[0119] The control node can group the multiple transmitters according to the first information of each of the multiple transmitters, that is, divide the multiple transmitters into at least one group, each of the at least one group includes multiple first transmitters, and the multiple first transmitters in the same group have the same channel information acquisition capability.

[0120] Optionally, the first information of each transmitting end also includes the first number of transmitting antennas of each transmitting end, and the second information of the first receiving end also includes the second number of receiving antennas of the first receiving end. The relationship between the first number and the second number of each first transmitting end included in the multiple first transmitting ends in the same group is consistent, that is, the first number of each first transmitting end included in the multiple first transmitting ends in the same group is greater than or equal to the second number, or, the first number of each first transmitting end included in the multiple first transmitting ends in the same group is less than the second number.

[0121] Optionally, the first information of each transmitting end further includes a coding scheme used by each transmitting end, and the coding scheme used by multiple first transmitting ends in the same group is the same. Optionally, the first information of each transmitting end further includes a quantization scheme used by each transmitting end, and the quantization scheme used by multiple first transmitting ends in the same group is the same.

[0122] For the convenience of description, any one group in at least one group is referred to as a "target group". In one case, if the first receiving end and multiple first transmitting ends in the target group can obtain channel information, the control node can determine that the first mode used for air calculation between the multiple first transmitting ends and the first receiving end in the target group is a "performance mode".

[0123] In another case, if the first receiving end cannot obtain channel information, and multiple first transmitting ends in the target group can obtain channel information, the control node also needs to determine whether the first number of each first transmitting end included in the multiple first transmitting ends in the target group is greater than or equal to the second number. If the judgment result is yes, the first mode adopted when the multiple first transmitting ends in the target group perform air calculations with the first receiving end is determined to be the "pre-equalization mode"; if the judgment result is no, the first mode can be determined to be the "incoherent mode".

[0124] In another case, if the first receiving end can obtain channel information and multiple first transmitting ends in the target group cannot obtain the channel, the control node also needs to determine whether the relationship between the first quantity and the second quantity of each first transmitting end in the target group meets the first condition. If the judgment result is yes, it can be determined that the first mode used for air calculation between the multiple first transmitting ends and the first receiving end in the target group is the "channel hardening mode"; if the judgment result is no, it can be determined that the first mode is the "incoherent mode".

[0125] In another case, if the first receiving end and multiple first transmitting ends in the target group are unable to acquire the channel, it can be determined that the first mode used for air calculation between the multiple first transmitting ends in the target group and the first receiving end is the "incoherent mode".

[0126] 404. The control node determines instruction information, where the instruction information is used to instruct the first transmitting end and the first receiving end to perform over-the-air computing in the first mode.

[0127] In the embodiment of the present application, the specific meaning of "indication information" can be found in the description of the embodiment corresponding to Figure 3 above, and will not be repeated here.

[0128] 405. The control node sends first indication information to each first transmitting end in the target group, where the indication information includes first indication information, and the first indication information is used to instruct each first transmitting end in the target group to adopt the first mode when performing over-the-air computing.

[0129] 406. The control node sends second indication information to the first receiving end, where the indication information includes second indication information, and the second indication information is used to instruct the first receiving end to adopt the first mode when performing over-the-air computing.

[0130] In the embodiment of the present application, step 406 is an optional step. If the control node and the first receiving end are integrated into the same device, step 406 may not be performed.

[0131] In an embodiment of the present application, after determining which mode to use for air calculation, each first transmitting end and first receiving end in the target group can use the determined first mode to transmit information between each first transmitting end and first receiving end in the target group. To understand this solution more intuitively, please refer to Figures 5 to 7, which respectively show the flow charts of the data processing method provided by this application when the first mode is "performance mode", "pre-equalization mode" and "channel hardening mode". First refer to Figure 5, which is a flow chart of the data processing method provided by the embodiment of the present application when the first mode is "performance mode".

[0132] 501. A first sending end sends first information to a control node.

[0133] 502. The first receiving end sends second information to the control node.

[0134] 503. The control node determines a first mode to be adopted by multiple first transmitting ends and the first receiving end when performing over-the-air calculations based on the first information of each transmitting end and the second information of the first receiving end, wherein the first mode is determined based on the first information of each first transmitting end and the second information of the first receiving end among the multiple first transmitting ends, the first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

[0135] 504. The control node sends first indication information to the first transmitting end, where the first indication information is used to instruct each first transmitting end in the target group to adopt the first mode when performing over-the-air calculation.

[0136] 505. The control node sends second indication information to the first receiving end, where the second indication information is used to instruct the first receiving end to adopt the first mode when performing over-the-air computing.

[0137] In the embodiment of the present application, the specific implementation method of steps 501 to 505 and the meaning of the terms in steps 501 to 505 can be found in the description of the corresponding embodiment of Figure 4, and will not be repeated here.

[0138] 506. The first transmitting end obtains channel information between the first transmitting end and the first receiving end.

[0139] 507. The first receiving end obtains channel information between each first transmitting end and the first receiving end.

[0140] 508. The first transmitting end performs a pre-equalization operation on the data to be transmitted according to the acquired channel information to obtain a transmission signal.

[0141] 509. The first receiving end obtains a received signal corresponding to the transmission signals of the multiple first transmitting ends. Both the transmission signal and the received signal carry data to be sent.

[0142] 510. The first receiving end performs denoising processing on a received signal according to channel information from each first transmitting end to the first receiving end.

[0143] Referring again to FIG6 , FIG6 is a flow chart of a data processing method when the first mode is the “pre-equalization mode” provided in an embodiment of the present application. Steps 601 to 605 are the same as steps 501 to 505 above and will not be repeated here. The difference is that:

[0144] 606. The first transmitting end obtains channel information.

[0145] 607. The first transmitting end performs a pre-equalization operation on the data to be transmitted according to the acquired channel information to obtain a transmission signal.

[0146] 608. The first receiving end obtains a received signal corresponding to the transmit signals of the multiple first transmitting ends, where both the transmit signal and the received signal carry data to be transmitted. Exemplarily, the transmit signals of the multiple first transmitting ends are superimposed in the air before reaching the first receiving end. The received signal obtained by the first receiving end includes the data carried in the transmit signals of the multiple first transmitting ends. After obtaining the received signal, the first receiving end may no longer perform denoising on the received signal, but may directly obtain the data carried in the received signal from it.

[0147] It should be noted that when the first mode is the "pre-equalization mode", each of the multiple first transmitting ends needs to obtain the channel information between the first transmitting end and the first receiving end, and then each first transmitting end performs a pre-equalization operation on the data to be sent according to the obtained channel information, and the first receiving end no longer needs to perform a denoising operation on the received signal.

[0148] Referring again to FIG7 , FIG7 is a flow chart of a data processing method when the first mode is the "channel hardening mode" provided by an embodiment of the present application. Steps 701 to 705 are the same as steps 501 to 505 above and will not be repeated here. The difference is:

[0149] 706. The first transmitting end sends a pilot signal to the first receiving end.

[0150] 707. The first receiving end determines the channel according to the received pilot signal.

[0151] 708. The first receiving end obtains a received signal corresponding to the transmission signals of the multiple first transmitting ends, where both the transmission signal and the received signal carry data to be sent.

[0152] 709. The first receiving end performs denoising processing on the received signal according to the sum channel.

[0153] It should be noted that when the first mode is the "channel hardening mode", each first transmitting end no longer needs to obtain channel information, but each first transmitting end needs to send the same pilot signal to the first receiving end, so that the first receiving end can determine the sum channel based on the received pilot signal, and then denoise the received signal based on the estimated sum channel.

[0154] It should be understood that since in step 403, the control node divides the multiple transmitters participating in the air calculation into at least one group, if the aforementioned at least one group includes at least two groups, the multiple first transmitters and the first receiver included in each of the at least two groups can be allowed to transmit information in sequence; for example, if the at least two groups include the first group and the second group, the multiple first transmitters in the first group can be allowed to use air calculation to transmit information with the first receiver, and then the multiple first transmitters in the second group can be allowed to use air calculation to transmit information with the first receiver. If the at least two groups include more groups, then the same process will apply, and examples will not be given one by one here.

[0155] On the basis of the embodiments corresponding to Figures 1 to 7, in order to better implement the above-mentioned scheme of the embodiments of the present application, the following also provides related equipment for implementing the above-mentioned scheme. Please refer to Figure 8 in detail. Figure 8 is a structural diagram of a data processing device provided in the embodiment of the present application. The data processing device 800 is applied to the control node. The data processing device 800 includes: a determination module 801, which is used to determine the first mode adopted by multiple first transmitting ends and the first receiving end when performing air calculations, wherein the first mode is one of at least two air calculation modes, and the first mode is determined based on the first information of each first transmitting end in the multiple first transmitting ends and the second information of the first receiving end. The first information of the first transmitting end indicates the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates the channel information acquisition capability of the first receiving end; the determination module 801 is also used to determine the indication information, and the indication information indicates that the first transmitting end and the first receiving end adopt the first mode for air calculations.

[0156] Optionally, the first information of the first transmitting end further includes a first number of transmitting antennas of the first transmitting end, and the second information of the first receiving end further includes a second number of receiving antennas of the first receiving end.

[0157] Optionally, when multiple first transmitting ends and first receiving ends can obtain channel information, the first mode represents the first transmitting end performing a pre-equalization operation on the transmitted signal, and the first receiving end performs denoising on the received signal according to the channel information; or, when multiple first transmitting ends can obtain channel information, the first receiving end cannot obtain channel information, and the first number is greater than or equal to the second number, the first mode represents the first transmitting end performing a pre-equalization operation on the transmitted signal; or, when multiple first transmitting ends cannot obtain channel information, the first receiving end can obtain channel information, and the first number is less than the second number, the first mode represents the first receiving end estimating the sum channel according to the pilot signal sent by the first transmitting end, and processing the received signal according to the sum channel; or, the first mode represents the first transmitting end performing binarization processing on the transmitted signal.

[0158] Optionally, the data processing device 800 also includes: a receiving module 802, which is used to receive first information from each of multiple transmitting ends, and the multiple transmitting ends include multiple first transmitting ends; the receiving module 802 is also used to receive second information from each of at least one receiving end, and the at least one receiving end includes the first receiving end; a determination module 801, which is specifically used to determine the first mode adopted by the multiple first transmitting ends and the first receiving end when performing air calculations based on the first information of each transmitting end and the second information of each receiving end.

[0159] Optionally, the control node is the first receiving end, the first receiving end and multiple first sending ends are used to perform federated learning, the first receiving end is the central node of the federated learning, and the multiple first sending ends are distributed nodes of the federated learning.

[0160] Optionally, the first information of each transmitting end further includes an encoding scheme and / or a quantization scheme of each transmitting end, and the second information of each receiving end further includes a decoding scheme and / or a dequantization scheme of each receiving end.

[0161] Optionally, the multiple first transmitting ends adopt the same encoding scheme; the decoding scheme used by the first receiving end matches the encoding schemes used by the multiple first transmitting ends.

[0162] Optionally, the multiple first transmitting ends use the same quantization scheme; the dequantization scheme used by the first receiving end matches the quantization schemes used by the multiple first transmitting ends.

[0163] It should be noted that the information interaction, execution process, etc. between the modules / units in the data processing device 800 are based on the same concept as the various method embodiments corresponding to Figures 3 to 7 in this application. For specific contents, please refer to the description in the method embodiments shown above in this application, and will not be repeated here.

[0164] Please refer to Figure 9, which is another structural schematic diagram of the data processing device provided in an embodiment of the present application. The data processing device 900 is applied to the first transmitting end, and the data processing device 900 includes: a receiving module 901, used to receive first indication information; a determination module 902, used to determine, based on the first indication information, whether the first transmitting end and the first receiving end adopt a first mode when performing air calculations, the first mode being one of at least two air calculation modes, and the first mode being determined based on the first information of the first transmitting end and the second information of the first receiving end, the first information of the first transmitting end indicating the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicating the channel information acquisition capability of the first receiving end.

[0165] Optionally, the data processing device 900 further includes: a sending module 903, configured to send the first information of the first sending end.

[0166] It should be noted that the information interaction, execution process, etc. between the modules / units in the data processing device 900 are based on the same concept as the various method embodiments corresponding to Figures 3 to 7 in this application. For specific contents, please refer to the description in the method embodiments shown above in this application, and will not be repeated here.

[0167] Please refer to Figure 10, which is another structural schematic diagram of the data processing device provided in an embodiment of the present application. The data processing device 1000 is applied to the first receiving end, and the data processing device 1000 includes: a receiving module 1001, used to receive second indication information; a determination module 1002, used to determine, based on the second indication information, whether the first transmitting end and the first receiving end adopt a first mode when performing air calculations, the first mode being one of at least two air calculation modes, and the first mode being determined based on the first information of the first transmitting end and the second information of the first receiving end, the first information of the first transmitting end indicating the channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicating the channel information acquisition capability of the first receiving end.

[0168] Optionally, the data processing device 900 further includes: a sending module 1003, configured to send the second information of the first receiving end.

[0169] It should be noted that the information interaction, execution process, etc. between the modules / units in the data processing device 1000 are based on the same concept as the various method embodiments corresponding to Figures 3 to 7 in this application. For specific contents, please refer to the description in the method embodiments shown above in this application, and will not be repeated here.

[0170] Please refer to Figure 11, which is a schematic diagram of a structure of a device provided in an embodiment of the present application. The device 1100 can specifically be the device used as the terminal device in the above-mentioned embodiment. The example shown in Figure 11 is that the terminal device is implemented by the terminal device (or a component in the terminal device). In a possible logical structure diagram of the device 1100, the device 1100 may include, but is not limited to, at least one processor 1101 and a communication port 1102.

[0171] Optionally, the device may further include at least one of a memory 1103 and a bus 1104 . In an embodiment of the present application, the at least one processor 1101 is used to control and process the actions of the communication device 1100 .

[0172] In addition, the processor 1101 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.

[0173] It should be noted that when the first transmitting end or the first receiving end involved in the above embodiments is specifically manifested as a terminal device, the device 1100 shown in Figure 11 can be used to implement the steps implemented by the terminal device in the aforementioned method embodiment. The specific implementation methods of the device 1100 shown in Figure 11 to perform the aforementioned steps can refer to the description in the aforementioned method embodiment, and will not be repeated here one by one.

[0174] Please refer to Figure 12, which is another structural diagram of a device provided in an embodiment of the present application. The device 1200 can specifically be the device as a network device in the above-mentioned embodiment. The example shown in Figure 12 is that the network device is implemented by the network device (or a component in the network device); that is, when the control node, the first transmitting end, or the first receiving end involved in the above-mentioned embodiment is specifically manifested as a network device, it can be implemented using the device 1200 shown in Figure 12; illustratively, when the control node is a base station or a network element in the core network, it can be implemented using the device 1200 shown in Figure 12.

[0175] The structure of the communication device can refer to the structure shown in Figure 12. The device 1200 includes at least one processor 1211 and at least one network interface 1212. Further optionally, the communication device also includes at least one memory 1214, at least one transceiver 1213 and one or more antennas 1215. The processor 1211, the transceiver 1213, the memory 1214 and the network interface 1212 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 1215 is connected to the transceiver 1213. The network interface 1212 is used to enable the communication device to communicate with other communication devices through a communication link. For example, the network interface 1212 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.

[0176] Processor 1211 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. A 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 1211 in Figure 12 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.

[0177] The memory is primarily used to store software programs and data. Memory 1214 can exist independently and be connected to processor 1211. Alternatively, memory 1214 and processor 1211 can be integrated together, for example, within a single chip. Memory 1214 can store program code for executing the technical solutions of the embodiments of the present application, and execution is controlled by processor 1211. The various computer program codes executed can also be considered as drivers for processor 1211.

[0178] Figure 12 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.

[0179] The transceiver 1213 can be used to support the reception or transmission of radio frequency signals between the communication device and the terminal. The transceiver 1213 can be connected to the antenna 1215. The transceiver 1213 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1215 can receive radio frequency signals. The receiver Rx of the transceiver 1213 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 1211 so that the processor 1211 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 1213 is also used to receive a modulated digital baseband signal or digital intermediate frequency signal from the processor 1211, 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 1215. 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.

[0180] The transceiver 1213 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.

[0181] Exemplarily, when the control node, the first transmitting end or the first receiving end involved in the above embodiments are specifically manifested as a network device, the device 1200 shown in Figure 12 can be used to implement the steps implemented by the control node, the first transmitting end or the first receiving end in the aforementioned method embodiment. The specific implementation methods of the device 1200 shown in Figure 12 performing the aforementioned steps can refer to the description in the aforementioned method embodiment and will not be repeated here one by one.

[0182] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a program for signal processing. When the computer-readable storage medium is run on a computer, the computer executes the steps performed by the control node in the method described in the embodiments shown in Figures 3 to 7 above, or the computer executes the steps performed by the first sending end in the method described in the embodiments shown in Figures 3 to 7 above, or the computer executes the steps performed by the first receiving end in the method described in the embodiments shown in Figures 3 to 7 above.

[0183] An embodiment of the present application also provides a computer program product, which, when running on a computer, enables the computer to execute the steps performed by the control node in the method described in the embodiments shown in Figures 3 to 7 above, or enables the computer to execute the steps performed by the first sending end in the method described in the embodiments shown in Figures 3 to 7 above, or enables the computer to execute the steps performed by the first receiving end in the method described in the embodiments shown in Figures 3 to 7 above.

[0184] The control node, first transmitting end, or first receiving end provided in the embodiments of the present application may specifically be a chip, which includes: a processing unit and a communication unit. The processing unit may be, for example, a processor, and the communication unit may be, for example, an input / output interface, a pin, or a circuit. The processing unit may execute computer-executable instructions stored in the storage unit to enable the chip to perform the data processing methods described in the embodiments shown in Figures 3 to 7 above. Optionally, the storage unit is a storage unit within the chip, such as a register, a cache, etc. The storage unit may also be a storage unit located outside the chip within the wireless access device, such as a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM), etc.

[0185] The processor mentioned in any of the above places can be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the above-mentioned first aspect method.

[0186] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed 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 the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0187] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0188] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0189] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A data processing method, characterized in that: The method comprises: The control node determines a first mode adopted when multiple first transmitting ends and a first receiving end perform air computing, wherein the first mode is one of at least two air computing modes, and the first mode is determined based on first information of each first transmitting end among the multiple first transmitting ends and second information of the first receiving end, the first information of the first transmitting end indicates a channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates a channel information acquisition capability of the first receiving end; The control node determines indication information, where the indication information instructs the first transmitting end and the first receiving end to perform air computing using the first mode.

2. The method according to claim 1, characterized in that The first information of the first transmitting end further includes a first number of transmitting antennas of the first transmitting end, and the second information of the first receiving end further includes a second number of receiving antennas of the first receiving end.

3. The method according to claim 2, characterized in that In the case where the plurality of first transmitting ends and the first receiving end are both able to obtain channel information, the first mode represents that the first transmitting end performs a pre-equalization operation on a transmitted signal, and the first receiving end performs a denoising process on a received signal according to the channel information; or, In a case where the multiple first transmitting ends are capable of acquiring channel information, the first receiving end is unable to acquire channel information, and the first number is greater than or equal to the second number, the first mode represents that the first transmitting end performs a pre-equalization operation on the transmit signal; or, When the multiple first transmitting ends cannot obtain channel information, the first receiving end can obtain channel information, and the first number is less than the second number, the first mode represents that the first receiving end estimates a sum channel according to the pilot signal sent by the first transmitting end, and processes the received signal according to the sum channel; or, The first mode represents that the first transmitting end performs binarization processing on the transmitting signal.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: The control node receives the first information of each transmitting end of a plurality of transmitting ends, where the plurality of transmitting ends include the plurality of first transmitting ends; The control node receives the second information of each receiving end of at least one receiving end, wherein the at least one receiving end includes the first receiving end; The control node determines a first mode adopted when a plurality of first transmitting ends and a first receiving end perform air computing, including: The control node determines a first mode adopted by the multiple first transmitting ends and the first receiving end when performing over-the-air calculations according to the first information of each transmitting end and the second information of each receiving end.

5. The method according to any one of claims 1 to 4, characterized in that: The control node is the first receiving end. The first receiving end and the multiple first sending ends are used for performing federated learning. The first receiving end is the central node of federated learning, and the multiple first sending ends are distributed nodes of federated learning.

6. The method according to claim 4, characterized in that The first information of each transmitting end further includes the encoding scheme and / or quantization scheme of each transmitting end, and the second information of each receiving end further includes the decoding scheme and / or dequantization scheme of each receiving end.

7. The method according to claim 6, characterized in that The multiple first transmitting ends adopt the same encoding scheme; the decoding scheme used by the first receiving end matches the encoding scheme used by the multiple first transmitting ends.

8. The method according to claim 6, characterized in that The multiple first transmitting ends use the same quantization scheme; the dequantization scheme used by the first receiving end matches the quantization scheme used by the multiple first transmitting ends.

9. A data processing method, characterized in that: The method comprises: The first sending end receives the first indication information; The first transmitting end determines, according to the first indication information, that a first mode is adopted when the first transmitting end and the first receiving end perform air computing, the first mode being one of at least two air computing modes, the first mode being determined based on first information of the first transmitting end and second information of the first receiving end, the first information of the first transmitting end indicating that the channel information acquisition capability of the first transmitting end The second information of the first receiving end indicates the channel information acquisition capability of the first receiving end.

10. The method according to claim 9, characterized in that The method further comprises: The first sending end sends the first information of the first sending end.

11. A data processing method, characterized in that: The method comprises: The first receiving end receives the second indication information; The first receiving end determines, based on the second indication information, that a first mode is adopted when the first transmitting end performs air computing with the first receiving end, the first mode being one of at least two air computing modes, the first mode being determined based on first information of the first transmitting end and second information of the first receiving end, the first information of the first transmitting end indicating a channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicating a channel information acquisition capability of the first receiving end.

12. The method according to claim 11, characterized in that The method further comprises: The first receiving end sends the second information of the first receiving end.

13. A data processing device, characterized in that: The data processing device is applied in a control node, and the device includes: a determination module, configured to determine a first mode adopted by a plurality of first transmitting ends and a first receiving end when performing air computing, wherein the first mode is one of at least two air computing modes, and the first mode is determined based on first information of each first transmitting end among the plurality of first transmitting ends and second information of the first receiving end, the first information of the first transmitting end indicating a channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicating a channel information acquisition capability of the first receiving end; The determination module is further used to determine indication information, where the indication information instructs the first transmitting end and the first receiving end to perform air calculation using the first mode.

14. A data processing device, characterized in that: The data processing device is applied to a first transmitting end, and the device includes: A receiving module, used for receiving first indication information; A determination module is used to determine, based on the first indication information, that the first transmitting end and the first receiving end use a first mode when performing air computing. The first mode is one of at least two air computing modes. The first mode is determined based on first information of the first transmitting end and second information of the first receiving end. The first information of the first transmitting end indicates a channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates a channel information acquisition capability of the first receiving end.

15. A data processing device, characterized in that: The data processing device is applied to a first receiving end, and the device includes: A receiving module, used for receiving second indication information; A determination module is used to determine, based on the second indication information, that a first mode is adopted when the first transmitting end and the first receiving end perform air computing, wherein the first mode is one of at least two air computing modes, and the first mode is determined based on first information of the first transmitting end and second information of the first receiving end, wherein the first information of the first transmitting end indicates a channel information acquisition capability of the first transmitting end, and the second information of the first receiving end indicates a channel information acquisition capability of the first receiving end.

16. A device, characterized in that comprising a processor and a memory, the processor being coupled to the memory, The memory is used to store programs; The processor is configured to execute the program in the memory so that the device performs the method according to any one of claims 1 to 12.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, and when the program is executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 12.

18. A computer program product, characterized in that The computer program product comprises a program, and when the program is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 12 .

Images