Communication method and communication apparatus

Abstract

Provided in the present application are a model monitoring method and a communication apparatus. The method comprises: respectively receiving on a first time domain resource and a second time domain resource first information and second information, each of the first information and the second information comprising first data and preset information, and the first data and the preset information being respectively mapped onto each resource element of the first and second time domain resources according to first and second power allocation coefficients; respectively inputting the first information and the second information into a preset AI model, so as to obtain first and second AI channel estimation results; and on the basis of the first AI channel estimation result and the second AI channel estimation result, determining a power allocation coefficient to be used. In the method, the first information and the second information correspond to different power allocation coefficients, so that the power allocation coefficient to be used can be determined on the basis of the first AI channel estimation result and the second AI channel estimation result, for example, a more reasonable power allocation coefficient is determined, thereby improving the throughput of communication systems.

Description

A communication method and a communication apparatus

[0001] The present application claims priority to the Chinese Patent Application No. 202410816786.8, filed on June 21, 2024, and entitled "A communication method and a communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] Embodiments of the present application relate to the field of communication, and more particularly, to a communication method and a communication apparatus. BACKGROUND

[0003] In order to improve the throughput of the communication system, a frame structure of data and pilot superposition is proposed. Specifically, when transmitting a signal, data and pilot can be mapped to the same resource element (RE). In this way, the length and time-frequency position of the pilot can be reduced, giving the pilot more freedom, and the resource rate occupied by the data can also be improved.

[0004] However, how to implement the above-mentioned scheme specifically remains to be studied. SUMMARY

[0005] The present application provides a communication method, which can determine a more appropriate power allocation coefficient, so that data and pilot are mapped to the same resource element (RE), thereby improving the throughput of the communication system.

[0006] In a first aspect, a communication method is provided. The method can be performed by a terminal device or a network device, or by a component (such as a chip, circuit, or module) for a terminal device or a network device.

[0007] The method includes: receiving first information from a first communication apparatus on a first time domain resource, the first information including first data and preset information, the first data and the preset information being mapped on each resource element of the first time domain resource with a first power allocation coefficient; inputting the first information into a preset artificial intelligence (AI) model to obtain a first AI channel estimation result; receiving second information from the first communication apparatus on a second time domain resource, the second information including the first data and the preset information, the first data and the preset information being mapped on each resource element of the second time domain resource with a second power allocation coefficient; inputting the second information into the preset AI model to obtain a second AI channel estimation result; and sending first result information to the first communication apparatus, the first result information being used to determine a power allocation coefficient to be used, the first result information being determined according to the first AI channel estimation result and the second AI channel estimation result.

[0008] Based on the above scheme, the first communication device sends first information and second information to the second communication device. The second communication device can obtain the first AI channel estimation result and the second AI channel estimation result. Since the first information and the second information correspond to different power allocation coefficients, the power allocation coefficient to be used can be determined based on the first AI channel estimation result and the second AI channel estimation result. For example, a more reasonable power allocation coefficient can be determined to improve the throughput of the communication system.

[0009] On the other hand, the first and second information are information transmitted through the actual channel. Therefore, the power allocation coefficient to be used determined based on the first and second information is more in line with the actual channel conditions, thus having higher accuracy.

[0010] For example, the first communication device may be a terminal device or a network device, or it may be a component (such as a chip, circuit or module) used in a terminal device or a network device.

[0011] For example, the power allocation factor to be used is either a first power allocation factor or a second power allocation factor.

[0012] In some implementations, a preset AI model corresponds to a preset power allocation coefficient, the difference between the first power allocation coefficient and the preset power allocation coefficient is less than a first threshold, and the difference between the second power allocation coefficient and the preset power allocation coefficient is less than the first threshold.

[0013] Based on the above scheme, the first communication device and the second communication device can determine a more suitable power allocation coefficient near the value of the preset power allocation coefficient, so that the power allocation coefficient is not only more in line with the actual channel environment, but also more in line with the performance of the preset AI model.

[0014] For example, the preset power allocation factor is either a first power allocation factor or a second power allocation factor.

[0015] In conjunction with the first aspect, in some implementations, the method further includes: receiving or sending configuration information, the configuration information including the correspondence between a first power allocation coefficient and a first time-domain resource, and the correspondence between a second power allocation coefficient and a second time-domain resource.

[0016] Based on the above scheme, by configuring the correspondence between power allocation coefficients and time-domain resources, the second communication device can determine which time-domain resources are superimposed signals transmitted through the same power allocation coefficient, which facilitates the second communication device to classify and process the received signals and improve communication efficiency.

[0017] For example, the first time-domain resource includes N1 time-domain resources, the first information includes N1 pieces of information, and the N1 time-domain resources and the N1 pieces of information correspond one-to-one, where N is an integer greater than or equal to 1; the second time-domain resource includes N2 time-domain resources, the second information includes N2 pieces of information, and the N2 time-domain resources and the N2 pieces of information correspond one-to-one, where N2 is an integer greater than or equal to 1.

[0018] In conjunction with the first aspect, in some implementations, the first result information includes the power allocation factor to be used.

[0019] For example, the configuration information includes a first power allocation coefficient and a second power allocation coefficient.

[0020] Optionally, the method further includes: determining the power allocation coefficient to be used based on the first AI channel estimation result and the second AI channel estimation result.

[0021] In conjunction with the first aspect, in some implementations, the first result information includes the first channel estimation result and the second channel estimation result.

[0022] For example, the configuration information does not include a first power allocation factor and a second power allocation factor.

[0023] Optionally, the second result information may also include the correspondence between the first AI channel estimation result and the first time-domain resource, and the correspondence between the second AI channel estimation result and the second time-domain resource.

[0024] Secondly, a communication method is provided, which can be executed by a terminal device or a network device, or by a component (such as a chip, circuit, or module) used in a terminal device or a network device.

[0025] The method includes: sending first information to a second communication device on a first time-domain resource, the first information including first data and preset information, the first data and preset information being mapped onto each resource unit of the first time-domain resource using a first power allocation coefficient; sending second information to the second communication device on a second time-domain resource, the second information including first data and preset information, the first data and preset information being mapped onto each resource unit of the second time-domain resource using a second power allocation coefficient; and receiving first result information from the second communication device, the first result information being used to determine the power allocation coefficient to be used, the first result information being determined based on a preset AI model, the first information, and the second information, the preset AI model being used for channel estimation.

[0026] For example, the second communication device may be a terminal device or a network device, or it may be a component (such as a chip, circuit or module) used in a terminal device or a network device.

[0027] For example, the power allocation factor to be used is either a first power allocation factor or a second power allocation factor.

[0028] In one implementation, a preset AI model corresponds to a preset power allocation coefficient, the difference between the first power allocation coefficient and the preset power allocation coefficient is less than a first threshold, and the difference between the second power allocation coefficient and the preset power allocation coefficient is less than the first threshold.

[0029] For example, the preset power allocation factor is either a first power allocation factor or a second power allocation factor.

[0030] In conjunction with the second aspect, in some implementations, the method further includes: sending or receiving configuration information, the configuration information including the correspondence between the first power allocation coefficient and the first time-domain resource, and the correspondence between the second power allocation coefficient and the second time-domain resource.

[0031] For example, the first time-domain resource includes N1 time-domain resources, the first information includes N1 pieces of information, and the N1 time-domain resources and the N1 pieces of information correspond one-to-one, where N1 is an integer greater than or equal to 1; the second time-domain resource includes N2 time-domain resources, the second information includes N2 pieces of information, and the N2 time-domain resources and the N2 pieces of information correspond one-to-one, where N2 is an integer greater than or equal to 1.

[0032] In conjunction with the second aspect, in some implementations, the first result information includes the power allocation coefficient to be used.

[0033] For example, the configuration information includes a first power allocation coefficient and a second power allocation coefficient.

[0034] In conjunction with the second aspect, in some implementations, the first result information includes the first channel estimation result and the second channel estimation result.

[0035] For example, the configuration information does not include a first power allocation factor and a second power allocation factor.

[0036] For example, the second result information also includes the correspondence between the first AI channel estimation result and the first time domain resource, and the correspondence between the second AI channel estimation result and the second time domain resource.

[0037] Optionally, the method further includes: determining the power allocation coefficient to be used based on the first AI channel estimation result and the second AI channel estimation result.

[0038] It should be understood that the beneficial effects of the second aspect and any of its implementations can be referenced from the first aspect and any of its implementations.

[0039] Thirdly, a communication method is provided, which can be executed by a terminal device or a network device, or by a component (such as a chip, circuit, or module) used in a terminal device or a network device.

[0040] The method includes: receiving first information from a first communication device on a first time-domain resource, the first information including first data and preset information, the first data and preset information being mapped onto each resource unit of the first time-domain resource using a first power allocation coefficient; determining a first AI model based on the first information; receiving second information from the first communication device on a second time-domain resource, the second information including first data and preset information, the first data and preset information being mapped onto each resource unit of the second time-domain resource using a second power allocation coefficient; determining a second AI model based on the second information; and sending second result information to the first communication device, the second result information being used to determine the power allocation coefficient to be used, the second result information being determined based on the performance of the first AI model and the performance of the second AI model.

[0041] Based on the above scheme, the first communication device sends first information and second information to the second communication device. The second communication device can obtain the first AI model and the second AI model. Since the first information and the second information correspond to different power allocation coefficients, the power allocation coefficient to be used can be determined according to the performance of the first AI model and the second AI model. For example, a more reasonable power allocation coefficient can be determined to improve the throughput of the communication system.

[0042] On the other hand, the first and second information are information transmitted through the actual channel. Therefore, the power allocation coefficient to be used determined based on the first and second information is more in line with the actual channel conditions, thus having higher accuracy.

[0043] For example, the power allocation factor to be used is either a first power allocation factor or a second power allocation factor.

[0044] In conjunction with the third aspect, in some implementation methods, determining the first AI model based on the first information includes: determining the first AI model based on the first non-AI channel estimation result and the first information, wherein the first non-AI channel estimation result is determined based on the non-AI model; determining the second AI model based on the second information includes: determining the second AI model based on the second non-AI channel estimation result and the second information, wherein the second non-AI channel estimation result is determined based on the non-AI model.

[0045] Based on the above scheme, the dataset used to train the AI ​​model also includes non-AI channel estimation results. Since the non-AI channel estimation results are estimation results of the real channel, this makes the training of the AI ​​model more efficient, the performance of the trained AI model is better, and it has greater practicality.

[0046] In conjunction with the third aspect, in some implementations, the method further includes: receiving third information from the first communication device on a third time-domain resource, the third information including first data and preset information, the first data and preset information being mapped onto the third time-domain resource using a third power allocation coefficient, the third time-domain resource corresponding to the first time-domain resource; determining a first non-AI channel estimation result based on a non-AI model and the third information; receiving fourth information from the first communication device on a fourth time-domain resource, the fourth information including first data and preset information, the first data and preset information being mapped onto the fourth time-domain resource using a fourth power allocation coefficient, the fourth time-domain resource corresponding to the second time-domain resource; and determining a second non-AI channel estimation result based on the non-AI model and the fourth information.

[0047] For example, the first time-domain resource includes N1 time-domain resources, the first information includes N1 pieces of information, and the N1 time-domain resources and the N1 pieces of information correspond one-to-one, where N1 is an integer greater than or equal to 1; the second time-domain resource includes N2 time-domain resources, the second information includes N2 pieces of information, and the N2 time-domain resources and the N2 pieces of information correspond one-to-one, where N2 is an integer greater than or equal to 1.

[0048] Based on the above scheme, using the same power allocation coefficient to send superimposed signals on multiple time-domain resources can obtain more data for training the same AI model. This allows for more data to be analyzed when determining the power allocation coefficient to be used, thereby improving accuracy.

[0049] In conjunction with the third aspect, in some implementations, the method further includes: receiving or sending configuration information, the configuration information including the correspondence between the first power allocation coefficient and the first time domain resource, and the correspondence between the second power allocation coefficient and the second time domain resource.

[0050] Based on the above scheme, by configuring the correspondence between power allocation coefficients and time-domain resources, the second communication device can determine which time-domain resources are superimposed signals transmitted through the same power allocation coefficient, which facilitates the second communication device to classify and process the received signals and improve communication efficiency.

[0051] In conjunction with the third aspect, in some implementations, the second result information includes the allocation coefficients to be used.

[0052] For example, the configuration information includes a first power allocation coefficient and a second power allocation coefficient.

[0053] Optionally, the method further includes: determining the power allocation coefficient to be used based on the parameters of the first AI model and the parameters of the second AI model.

[0054] In conjunction with the third aspect, in some implementations, the second result information includes the parameters of the first AI model and the second AI model.

[0055] For example, the configuration information does not include a first power allocation factor and a second power allocation factor.

[0056] Optionally, the second result information may also include the correspondence between the first AI model and the first time-domain resource, and the correspondence between the second AI model and the second time-domain resource.

[0057] Fourthly, a communication method is provided, which can be executed by a terminal device or a network device, or by a component (such as a chip, circuit, or module) used in a terminal device or a network device.

[0058] The method includes: sending first information to a second communication device on a first time-domain resource, the first information including first data and preset information, the first data and preset information being mapped onto each resource unit of the first time-domain resource using a first power allocation coefficient; sending second information to the second communication device on a second time-domain resource, the second information including first data and preset information, the first data and preset information being mapped onto each resource unit of the second time-domain resource using a second power allocation coefficient; and receiving second result information from the second communication device, the second result information being used to determine a power allocation coefficient to be used, the power allocation coefficient to be used being determined based on the first information and the second information.

[0059] For example, the power allocation factor to be used is either a first power allocation factor or a second power allocation factor.

[0060] In conjunction with the fourth aspect, in some implementations, the method further includes: sending third information to the second communication device on a third time-domain resource, the third information including first data and preset information, the first data and preset information being mapped onto the third time-domain resource using a third power allocation coefficient, the third time-domain resource corresponding to the first time-domain resource, and the third information being used to determine second result information; and sending fourth information to the second communication device on a fourth time-domain resource, the fourth information including first data and preset information, the first data and preset information being mapped onto the fourth time-domain resource using a fourth power allocation coefficient, the fourth time-domain resource corresponding to the second time-domain resource, and the fourth information being used to determine the second result information.

[0061] For example, the first time-domain resource includes N1 time-domain resources, the first information includes N1 pieces of information, and the N1 time-domain resources and the N1 pieces of information correspond one-to-one, where N is an integer greater than or equal to 1; the second time-domain resource includes N2 time-domain resources, the second information includes N2 pieces of information, and the N2 time-domain resources and the N2 pieces of information correspond one-to-one, where N2 is an integer greater than or equal to 1.

[0062] In conjunction with the fourth aspect, in some implementations, the method further includes: sending or receiving configuration information, the configuration information including the correspondence between the first power allocation coefficient and the first time-domain resource, and the correspondence between the second power allocation coefficient and the second time-domain resource.

[0063] In conjunction with the fourth aspect, in some implementations, the second result information includes the allocation coefficients to be used.

[0064] For example, the configuration information includes a first power allocation coefficient and a second power allocation coefficient.

[0065] In conjunction with the fourth aspect, in some implementations, the second result information includes the parameters of the first AI model and the second AI model.

[0066] For example, the configuration information does not include a first power allocation factor and a second power allocation factor.

[0067] Optionally, the second result information may also include the correspondence between the first AI model and the first time-domain resource, and the correspondence between the second AI model and the second time-domain resource.

[0068] Optionally, the method further includes: determining the power allocation factor to be used based on the second result information.

[0069] It should be understood that the beneficial effects of the fourth aspect and any of its implementations can be referenced from the third aspect and any of its implementations.

[0070] Fifthly, a communication device is provided, which can be a terminal device or a network device, or a component (such as a chip, circuit or module) for a terminal device or a network device.

[0071] The device includes: a transceiver unit, configured to receive first information from a first communication device on a first time-domain resource, the first information including first data and preset information, the first data and preset information being mapped onto each resource unit of the first time-domain resource using a first power allocation coefficient; a processing unit, configured to input the first information into a preset AI model to obtain a first AI channel estimation result; the transceiver unit is further configured to: receive second information from the first communication device on a second time-domain resource, the second information including first data and preset information, the first data and preset information being mapped onto each resource unit of the second time-domain resource using a second power allocation coefficient; the processing unit is further configured to: input the second information into a preset AI model to obtain a second AI channel estimation result; the transceiver unit is further configured to: send first result information to the first communication device, the first result information being used to determine the power allocation coefficient to be used, the first result information being determined based on the first AI channel estimation result and the second AI channel estimation result.

[0072] Optionally, the transceiver unit is further configured to: receive or send configuration information, the configuration information including the correspondence between a first power allocation coefficient and a first time-domain resource, and the correspondence between a second power allocation coefficient and a second time-domain resource.

[0073] In a sixth aspect, a communication device is provided, which may be a terminal device or a network device, or may be a component (such as a chip, circuit or module) for a terminal device or a network device.

[0074] The device includes: a transceiver unit configured to transmit first information to a second communication device on a first time-domain resource, the first information including first data and preset information, the first data and preset information being mapped onto each resource unit of the first time-domain resource using a first power allocation coefficient; the transceiver unit is further configured to: transmit second information to the second communication device on a second time-domain resource, the second information including first data and preset information, the first data and preset information being mapped onto each resource unit of the second time-domain resource using a second power allocation coefficient; the transceiver unit is further configured to: receive first result information from the second communication device, the first result information being used to determine the power allocation coefficient to be used, the first result information being determined based on a preset AI model, the first information and the second information, the preset AI model being used for channel estimation.

[0075] Optionally, the transceiver unit is further configured to: receive or send configuration information, the configuration information including the correspondence between a first power allocation coefficient and a first time-domain resource, and the correspondence between a second power allocation coefficient and a second time-domain resource.

[0076] In a seventh aspect, a communication device is provided, which may be a terminal device or a network device, or may be a component (such as a chip, circuit or module) for a terminal device or a network device.

[0077] The device includes: a transceiver unit configured to receive first information from a first communication device on a first time-domain resource, the first information including first data and preset information, the first data and preset information being mapped onto each resource unit of the first time-domain resource using a first power allocation coefficient; a processing unit configured to determine a first AI model based on the first information; the transceiver unit is further configured to: receive second information from the first communication device on a second time-domain resource, the second information including first data and preset information, the first data and preset information being mapped onto each resource unit of the second time-domain resource using a second power allocation coefficient; the processing unit is further configured to: determine a second AI model based on the second information; the transceiver unit is further configured to: send second result information to the first communication device, the second result information being used to determine the power allocation coefficient to be used, the second result information being determined based on the performance of the first AI model and the performance of the second AI model.

[0078] Optionally, the transceiver unit is further configured to: receive or send configuration information, the configuration information including the correspondence between a first power allocation coefficient and a first time-domain resource, and the correspondence between a second power allocation coefficient and a second time-domain resource.

[0079] Eighthly, a communication device is provided, which may be a terminal device or a network device, or may be a component (such as a chip, circuit or module) for a terminal device or a network device.

[0080] The device includes: a transceiver unit configured to transmit first information to a second communication device on a first time domain resource, the first information including first data and preset information, the first data and preset information being mapped onto each resource unit of the first time domain resource using a first power allocation coefficient; the transceiver unit is further configured to: transmit second information to the second communication device on a second time domain resource, the second information including first data and preset information, the first data and preset information being mapped onto each resource unit of the second time domain resource using a second power allocation coefficient; the transceiver unit is further configured to: receive second result information from the second communication device, the second result information being used to determine a power allocation coefficient to be used, the power allocation coefficient to be used being determined based on the first information and the second information.

[0081] Optionally, the transceiver unit is further configured to: send or receive configuration information, the configuration information including the correspondence between a first power allocation coefficient and a first time-domain resource, and the correspondence between a second power allocation coefficient and a second time-domain resource.

[0082] It should be understood that for any parts of the fifth to eighth aspects that are not described in detail, please refer to the first to fourth aspects, which will not be repeated here.

[0083] A ninth aspect provides a communication apparatus, comprising: at least one processor for executing a computer program or instructions to perform the methods of the first to fourth aspects and any possible implementation thereof. Optionally, the apparatus further comprises a memory for storing the computer program or instructions. Optionally, the apparatus further comprises a communication interface through which the processor reads the computer program or instructions.

[0084] In one implementation, the device is a first communication device or a second communication device.

[0085] In another implementation, the device is a chip, chip system, or circuit for a first or second communication device.

[0086] In a tenth aspect, a processor is provided for executing the methods of the first to fourth aspects and any possible implementation thereof.

[0087] Unless otherwise specified, or if it does not contradict its actual function or internal logic in the relevant description, the transmission and acquisition / reception operations involved in the processor can be understood as processor output and reception, input and other operations, or as transmission and reception operations performed by radio frequency circuits and antennas. This application does not limit them in this regard.

[0088] Optionally, the device further includes: a memory for storing a program; correspondingly, at least one processor for executing the computer program or instructions in the memory.

[0089] Optionally, the device also includes a communication interface. The communication interface is coupled to the processor and can be used to input information to the processor or output information from the processor.

[0090] Eleventhly, a computer-readable storage medium is provided that stores program code for execution by a device, the program code including methods for performing the first to fourth aspects and any possible implementation thereof.

[0091] In a twelfth aspect, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to perform the methods described in the first to fourth aspects and any possible implementation thereof.

[0092] In a thirteenth aspect, a chip is provided, the chip including a processor and a communication interface, the processor reading instructions from a memory through the communication interface and executing the methods provided in the first to fourth aspects and any of their implementations.

[0093] Optionally, as one implementation, the chip also includes a memory storing computer programs or instructions. The processor executes the computer programs or instructions in the memory. When the computer programs or instructions are executed, the processor performs the methods provided by the first to fourth aspects and any of their implementations.

[0094] In a fourteenth aspect, a communication system is provided, comprising a second communication device and a first communication device, wherein the second communication device is used to implement the method provided by the first aspect and any possible implementation thereof, and the first communication device is used to implement the method provided by the second aspect and any possible implementation thereof; or, the second communication device is used to implement the method provided by the third aspect and any possible implementation thereof, and the first communication device is used to implement the method provided by the fourth aspect and any possible implementation thereof.

[0095] It should be understood that the beneficial effects of aspects five through fourteen and any of their implementations can be referenced from aspects one through four and any of their implementations. Attached Figure Description

[0096] Figure 1 is a schematic diagram of the communication system used in an embodiment of this application.

[0097] Figure 2 is a schematic diagram of another communication system applicable to embodiments of this application.

[0098] Figure 3 is a schematic diagram of a possible application framework in a communication system.

[0099] Figure 4 is a schematic diagram of a possible application framework in a communication system.

[0100] Figure 5 is a schematic diagram of the neural network structure.

[0101] Figure 6 is a schematic diagram of the structure of data and pilot signals within the time-frequency resources.

[0102] Figure 7 is a schematic flowchart of a communication method 400 provided in this application.

[0103] Figure 8 is a schematic diagram of a data processing flow provided in this application.

[0104] Figure 9 is a schematic diagram of the application of the power allocation coefficient provided in this application in the time domain resources.

[0105] Figure 10 is a schematic flowchart of a communication method 500 provided in this application.

[0106] Figure 11 is another schematic diagram of the application of the power allocation coefficient provided in this application in the time domain resources.

[0107] Figures 12 and 13 are schematic block diagrams of a communication device provided in an embodiment of this application. Detailed Implementation

[0108] The scheme of this application will now be described with reference to the accompanying drawings.

[0109] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0110] In a communication system, a device can send signals to or receive signals from another device. These signals can include information, signaling, or data. The device can also be replaced by an entity, network entity, network element, communication equipment, communication module, node, communication node, etc. This application uses a device as an example for description. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the terminal device in this application can be replaced by a second device, and the network device can be replaced by a first device, both performing the corresponding communication methods described in this application.

[0111] Figure 1 is a schematic diagram of a communication system applicable to an embodiment of this application. As shown in Figure 1, the communication system 100 may include at least one network device, such as network device 110 shown in Figure 1; the communication system 100 may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in Figure 1. Network device 110 and terminal devices (such as terminal devices 120 and 130) can communicate via a wireless link. The communication devices in this communication system, for example, network device 110 and terminal device 120, can communicate via multi-antenna technology.

[0112] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus.

[0113] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving vehicles, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0114] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0115] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0116] The network device in this application embodiment may include a device for communicating with a terminal device. This network device may include an access network device or a radio access network device, such as a base station. In this application embodiment, the access network device may refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), 5G base station (gNodeB, gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device performing base station functions in D2D, V2X, and M2M communications, a device performing base station functions in future communication systems, or a network-side device. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0117] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0118] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CUs, DUs, or devices including both CUs and DUs, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0119] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0120] RAN nodes can support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is an enhanced common public radio interface (eCPRI), compared to CPRI, some downlink and / or uplink baseband functions are moved from the DU to the RU. Different splitting methods between DUs and RUs correspond to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0121] Taking eCPRI Cat A as an example, for downlink transmission, the DU is configured to implement one or more functions before and after layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (e.g., RE mapping, digital beamforming (BF), or one or more functions of inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) are moved to the RU. For uplink transmission, the DU is configured to implement one or more functions before and after de-RE mapping (i.e., decoding, de-rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping), while other functions after de-RE mapping (e.g., digital BF or one or more functions of fast Fourier transform (FFT) / removing CP) are moved to the RU. It is understandable that the functional descriptions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol, and will not be elaborated here.

[0122] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0123] 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 meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0124] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0125] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0126] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, leading to increasingly diverse requirements. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or supporting beam management, network energy efficiency has become a hot research topic. These new requirements, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence.

[0127] To support artificial intelligence (AI) technology in wireless networks, AI nodes may also be introduced into the network.

[0128] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network equipment, terminal equipment, or core network equipment, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: network equipment, terminal equipment, or core network elements, etc.

[0129] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0130] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0131] AI nodes can be AI network elements or AI modules. The following explanation is based on Figures 2 to 4.

[0132] Figure 2 is a schematic diagram of another communication system applicable to embodiments of this application. Compared to the communication system 100 shown in Figure 1, the communication system 200 shown in Figure 2 further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models.

[0133] In one possible implementation, network device 110 can send data related to the training of the AI ​​model to AI network element 140, which then constructs a training dataset and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. AI network element 140 can send the results of operations related to the AI ​​model to network device 110, which then forwards them to the terminal device. For example, the results of operations related to the AI ​​model may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on network device 110, and another portion on the terminal device. Alternatively, the trained AI model may be deployed on network device 110. Or, the trained AI model may be deployed on the terminal device.

[0134] It should be understood that Figure 2 is only used as an example of the AI ​​network element 140 being directly connected to the network device 110. In other scenarios, the AI ​​network element 140 can also be connected to a terminal device. Alternatively, the AI ​​network element 140 can be connected to both the network device 110 and a terminal device simultaneously. Alternatively, the AI ​​network element 140 can also be connected to the network device 110 through a third-party network element. This application embodiment does not limit the connection relationship between the AI ​​network element and other network elements.

[0135] AI element 140 can also be set as a module in network devices and / or terminal devices, for example, in network device 110 or terminal device shown in Figure 1.

[0136] Figure 3 illustrates a possible application framework in a communication system. As shown in Figure 3, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the operations, administration, and maintenance (OAM) system, are equipped with one or more AI modules (only one is shown in Figure 3 for clarity). The access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. Optionally, the CU can be further divided into CU-CP and CU-UP. One or more AI models are configured in CU-CP and / or CU-UP.

[0137] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0138] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0139] Figure 4 illustrates a possible application framework in a communication system. As shown in Figure 4, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​modules 117 and 118 shown in Figure 3, used to implement AI-related functions. The RIC includes near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0140] The near real-time RIC is used for model training and inference. For example, it can be used to train an AI model and then use that AI model for inference. The near real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the near real-time RIC delivers the inference result to the DU, and the DU sends it to the RU.

[0141] The non-real-time RIC is also used for model training and inference. For example, it can be used to train an AI model and then use that model for inference. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminals. Optionally, inference results can be exchanged between CU and DU, and / or between DU and RU. For example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0142] The near real-time RIC and non-real-time RIC can also be set up as separate network elements. Optionally, the near real-time RIC and non-real-time RIC can also be part of other devices. For example, the near real-time RIC can be set in the RAN node (e.g., in CU, DU), while the non-real-time RIC can be set in the OAM, cloud server, core network device, or other network device.

[0143] It should be understood that Figures 1 to 4 are simplified schematic diagrams for ease of understanding only. The communication system may also include other network devices, other terminal devices, or other AI nodes, which are not limited in this application.

[0144] To facilitate understanding of the embodiments of this application, some basic concepts involved in this application will be briefly explained.

[0145] 1. Artificial Intelligence (AI): This refers to enabling machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. AI can be understood as the intelligence exhibited by machines created by humans. Generally, AI refers to the technology of using computer programs to represent human intelligence. The goals of AI include understanding intelligence by constructing computer programs that demonstrate symbolic reasoning or logical reasoning.

[0146] 2. Machine Learning (ML): This is an implementation method of artificial intelligence. Machine learning is a method that endows machines with the ability to perform functions that cannot be done directly by programming. In practical terms, machine learning is a method of training a model using data and then using the model to make predictions. There are many methods of machine learning, such as neural networks (NN), decision trees, and support vector machines. Machine learning theory mainly involves designing and analyzing algorithms that enable computers to learn automatically. Machine learning algorithms are a class of algorithms that automatically analyze data to obtain patterns and use these patterns to predict unknown data.

[0147] 3. Neural Networks: A specific manifestation of machine learning methods. A neural network is a mathematical model that mimics the behavioral characteristics of animal neural networks to process information. The idea behind neural networks originates from the neuronal structure of the brain. Each neuron can perform a weighted summation operation on its input values, and the result of the weighted summation operation is passed through an activation function to generate the output.

[0148] Figure 5(a) is a schematic diagram of the neuron structure. As shown in Figure 5(a), assume the neuron's input is x = [x0, x1, ..., x...]. n The weights corresponding to each input are w = [w, w1, ..., w], and w2, w3, w4, w5, w6, w7, w8, w9, w1, w1, w2, w9, w1, w2, w1, w2, w3 ... n The bias of the weighted summation is b. Here, b can be an integer, a decimal, a complex number, or any other possible value. The activation function can take many forms. As an example, suppose the activation function of a neuron is: y = f(z) = max(0,z), then the output of this neuron is: As another example, suppose the activation function of a neuron is: y = f(z) = z, then the output of the neuron is: As shown in Figure 5(a), the activation functions of different neurons in a neural network can be the same or different.

[0149] Neural networks typically consist of multiple layers, each layer containing one or more logical decision units, which are called neurons. Increasing the depth and / or width of a neural network can enhance its expressive power, providing more robust information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can be understood as the number of layers it comprises, and the number of neurons in each layer can be called the width of that layer.

[0150] Figure 5(b) is a schematic diagram of the layer relationship of a neural network.

[0151] One possible implementation involves a neural network comprising an input layer and an output layer. The input layer processes the received input through neurons and then passes the results to the output layer, which obtains the output of the neural network.

[0152] Another possible implementation involves a neural network comprising an input layer, hidden layers, and an output layer, as shown in Figure 5(b). The input layer processes the received input through neurons and passes the result to the intermediate hidden layers. The hidden layers then pass their calculations to the output layer or adjacent hidden layers, and finally, the output layer obtains the output of the neural network. A neural network can include one or more sequentially connected hidden layers, without limitation.

[0153] During the training of a neural network, a loss function can be defined. The loss function measures the difference between the model's predicted value and the true value. In the training process, the loss function describes the gap or difference between the neural network's output value and the desired target value. The training process involves adjusting the neural network parameters so that the loss function value is less than a threshold or meets the target requirement. The neural network parameters can include at least one of the following: the number of layers, the width of the neural network, the weights of the neurons, or the parameters in the activation function of the neurons.

[0154] 4. AI Model: An AI model is an algorithm or computer program that enables AI functionality. It represents the mapping relationship between the model's input and output; in other words, it's a function model that maps a certain dimension of input to a certain dimension of output. The parameters of this function model can be obtained through machine learning training. For example, f(x) = ax 2+b is a quadratic function model, which can be viewed as an AI model, where a and b are the parameters of this AI model, and a and b can be obtained through machine learning training. An AI model can also be called an ML model.

[0155] It is understood that AI models can be implemented as hardware circuits, software, or a combination of both; there are no restrictions. Non-restrictive examples of software include: program code, program, subroutine, instructions, instruction sets, code, code segments, software modules, applications, or software applications, etc. AI models can be neural networks, linear regression models, decision tree models, support vector machines (SVM), Bayesian networks, Q-learning models, or other machine learning models.

[0156] 5. Dataset: Data used for model training, model validation, or model testing in machine learning. The quantity and quality of the data will affect the effectiveness of machine learning.

[0157] 6. Model Training. By selecting an appropriate loss function, the model parameters are trained using optimization algorithms to minimize the loss function value.

[0158] 7. Pilot: Also known as reference signal or preset information, it is mainly used for channel estimation, data demodulation, beam training, and time-frequency parameter tracking. Commonly used pilots include synchronization signal, demodulation reference signal (DMRS), channel state information-reference signal (CSI-RS), sounding reference signal (SRS), phase tracking reference signal (PTRS), positioning reference signal (PRS), and tracking reference signal (TRS). Among them, CSI-RS and PRS are mainly used for downlink, SRS and TRS are mainly used for uplink, and DMRS and PTRS are applicable to both uplink and downlink.

[0159] Currently, there are two main types of frame structures for pilots and data within time-frequency resources. One is a frame structure where data and pilots are orthogonal, i.e., data and pilots are mapped to different REs, as shown in Figure 6(a). The other is a frame structure where data and pilots are superimposed, i.e., data and pilots are mapped to the same RE, as shown in Figure 6(b). In Figure 6, each small square represents a RE, and each RE has a time domain width of one symbol and a frequency domain width of one subcarrier. For example, a time slot in the time domain can include 14 symbols with symbol indices from 0 to 13, and a resource block (RB) in the frequency domain can include 12 subcarriers with subcarrier indices from 0 to 11.

[0160] For frame structures where data and pilots are orthogonal, pilots have a fixed and regular format and structure, and the pilot pattern (including its time-frequency position, length, granularity, and other parameters) is predefined by the protocol. In other words, pilot patterns can only be selected from fixed patterns, resulting in a limited variety. Faced with flexible and changing wireless communication environments, this frame structure has poor environmental adaptability.

[0161] In contrast, in a frame structure that overlays data and pilot signals, mapping both data and pilot signals to the same RE reduces restrictions on pilot length, time-frequency position, and other parameters, giving pilot signals greater freedom. Furthermore, in this frame structure, data can reside on any RE, thus increasing data utilization and throughput.

[0162] However, how to implement the above scheme in detail still needs further research.

[0163] Specifically, the transmitting end needs to map the data and pilot signals to the same RE with a certain transmission power. That is, the transmitting end needs to determine an appropriate power allocation coefficient so that the receiving end can correctly receive and demodulate the data. Therefore, determining the power allocation coefficient is crucial to the implementation of the above scheme.

[0164] In view of this, this application provides a communication method and a communication device that can determine a more suitable power allocation coefficient so that data and pilot signals can be mapped to the same RE, thereby improving throughput.

[0165] Figure 7 is a schematic flowchart of a communication method 400 provided in this application. As shown in Figure 7, the method 400 includes the following steps.

[0166] S410, the first communication device sends first information on the first time domain resource, and correspondingly, the second communication device receives the first information on the first time domain resource.

[0167] In this application, the first communication device can be a terminal-side device, a network-side device, or a functional module within the terminal-side device or network-side device capable of calling and executing a program, such as a processor, circuit, chip, or chip system. Similarly, the second communication device can be a terminal-side device, a network-side device, or a functional module within the terminal-side device or network-side device capable of calling and executing a program, such as a processor, circuit, chip, or chip system. Therefore, the embodiments of this application are applicable to communication between network devices and terminal devices, communication between terminal devices, and communication between network devices.

[0168] The first information includes first data and preset information, which are mapped onto each RE of the first time-domain resource using a first power allocation coefficient. In other words, the first information is the information obtained by superimposing the first data and the preset information using the first power allocation coefficient.

[0169] In this application, the first data can be information carried on a data channel (such as physical downlink shared channel (PDSCH), physical uplink shared channel (PUSCH), physical downlink control channel (PDCCH), physical uplink control channel (PUCCH), physical sidelink shared channel (PSSCH), physical sidelink control channel (PSCCH), etc.), or information carried on a broadcast channel (such as broadcast channel (BCH), broadcast control channel (BCCH), etc.), or information transmitted on the Xn interface between network devices.

[0170] In this application, the preset information can also be referred to as known information, pilot signal, first signal, reference signal, etc., and the preset information can be a synchronization signal, DMRS, CSI-RS, SRS, PTRS, PRS, TRS, etc. The preset information can be the pre-configuration information of the second communication device, or the information indicated by the first communication device to the second communication device.

[0171] Specifically, the first data and preset information can be mapped onto each RE of the first time-domain resource using a first power allocation coefficient. In other words, the first data and preset information are carried on the same resource unit, as shown in Figure 6(b). The power allocation coefficient can be used to determine the power of the first data and / or preset information, and the power allocation coefficient of the first data and preset information on each RE of the first time-domain resource is the first power allocation coefficient. The first power allocation coefficient can be understood as the power allocation coefficient taking the first value.

[0172] In this application, the power allocation coefficient may also be referred to as the power superposition coefficient, pilot superposition coefficient, power division coefficient, pilot power superposition coefficient, or pilot power division coefficient, etc.

[0173] Specifically, when performing resource mapping, the first communication device can map both preset information and first data to the same RE, and schedule the power allocated to the first data and / or preset information. The power allocation coefficient can be the proportion of the preset information's transmission power in the total transmission power on that RE, where the total transmission power is the sum of the preset information's transmission power and the first data's transmission power. For example, a power allocation coefficient of 0.5 indicates that the preset information's transmission power accounts for 0.5% of the total transmission power on that RE. Optionally, the power allocation coefficient can also be the proportion of the first data's transmission power in the total transmission power on that RE, or the ratio of the preset information's transmission power to the first data's transmission power, as long as it represents the magnitude relationship between the preset information's and the first data's transmission power. For ease of description, unless otherwise specified below, the power allocation coefficient is the proportion of the preset information's transmission power in the total transmission power on that RE.

[0174] For example, when mapped to the same RE, if the power allocated to the preset information is 0.5 and the power allocated to the first data is 0.5, then the resulting superimposed signal X is:

[0175] In formula (1), P represents the symbol of the preset information on a RE, S represents the symbol of the first data on that RE, and 0.5 is an example of the power allocation coefficient. In this application, the power allocation coefficient (including the first power allocation coefficient, the second power allocation coefficient, the third power allocation coefficient, and the fourth power allocation coefficient, etc.) is a value greater than or equal to 0 and less than or equal to 1.

[0176] In this application, the first data and preset information can be generated based on a constellation mapping method. For example, the preset information can be generated based on quadrature phase shift keying (QPSK), and the first data can be generated based on QPSK, quadrature amplitude modulation (QAM), 64QAM, 256QAM, 1024QAM, or other QAM (such as higher-order QAM such as 4K QAM). Optionally, the first data can also be generated based on a constellation modulation method trained by AI. It should be understood that the embodiments of this application do not limit the constellation mapping method of the preset information and / or the first data. As long as the constellation mapping meets the requirements (e.g., energy normalization), it can be implemented to map both onto the same RE.

[0177] The first time-domain resource can occupy at least one frame, at least one subframe, at least one time slot, or at least one symbol. Taking the NR system as an example, a frame has a duration of 10 ms, and a frame can be divided into 10 subframes, numbered 0-9, each with a duration of 1 ms. The number of time slots included in each subframe is related to the subcarrier spacing (SCS), as shown in Table 1. Furthermore, under a normal cyclic prefix (CP), each time slot includes 14 symbols.

[0178] Table 1

[0179] S420, the second communication device determines the first AI channel estimation result based on the first information and the preset AI model. Alternatively, the second communication device inputs the first information into the preset AI model to obtain the first AI channel estimation result.

[0180] The information of the preset AI model can be indicated by the first communication device to the second communication device, or it can be received by the second communication device from the cloud, such as an OTT device or a server. For example, the first communication device can train the AI ​​model and send the parameters of the AI ​​model, such as weights and biases, to the second communication device in advance so that the second communication device can use the AI ​​model (i.e. the preset AI model) to obtain the first AI channel estimation result.

[0181] In this application, the AI ​​model (including the preset AI model and the first AI model, second AI model, etc. below) can be understood as the AI ​​algorithm. The AI ​​model can be used to complete channel estimation, that is, the output of the AI ​​model is the channel estimation result, such as the channel order, Doppler frequency shift and multipath delay, the impulse response of the channel, channel state information (CSI), etc.

[0182] It should be understood that channel estimation can also be called channel measurement, without limitation. For example, when the reference signal is DMRS, channel estimation can refer to DMRS estimation; when the reference signal is CSI-RS or SRS, channel estimation can refer to CSI-RS or SRS channel estimation.

[0183] Optionally, the AI ​​model can also be used to implement one or more functions such as channel equalization, data demodulation, and decoding.

[0184] In this application, the AI ​​channel estimation result (including the first AI channel estimation result and the second AI channel estimation result) refers to the channel estimation result obtained through AI algorithms.

[0185] As shown in Figure 8, assuming the first power allocation coefficient is A, that is, the power allocated to the preset information is A, then the power allocated to the first data is 1-A. The preset information mapped to a RE can then be represented as follows: The first data mapped to this RE can be represented as This allows for the formation of superimposed signals. The signal passes through the channel, and the signal received by the second communication device is Y. The second communication device inputs Y into the AI ​​model to obtain the channel estimation result H.

[0186] Optionally, as shown in Figure 8, in addition to the received signal, the input of the AI ​​model may also include other known signals, such as pilot symbols known to the second communication device.

[0187] S430, the first communication device sends second information on the second time domain resource, and correspondingly, the second communication device receives the second information on the second time domain resource.

[0188] Similar to S410, the second information also includes the first data and preset information. The difference is that the first data and preset information are mapped onto each resource unit of the second time domain resource using the second power allocation coefficient.

[0189] The second power allocation coefficient can be understood as the power allocation coefficient taking the second value.

[0190] Optionally, in this application, the first power allocation coefficient and the second power allocation coefficient are different.

[0191] The second time-domain resource occupies at least one frame, or at least one subframe, or at least one time slot, or at least one symbol.

[0192] Optionally, the lengths of the first and second temporal resources may be in the same dimension or not. For example, the first temporal resource may consist of multiple subframes, and the second temporal resource may also consist of multiple subframes. Alternatively, the first temporal resource may consist of multiple frames, and the second temporal resource may consist of multiple time slots or multiple symbols. Another example is that the first temporal resource may include at least one subframe and at least one time slot, and the second temporal resource may include at least one time slot and at least one symbol.

[0193] Optionally, the length of the first time-domain resource is predefined, or is indicated by the first communication device to the second communication device, and the second time-domain resource is similar.

[0194] Optionally, the first time-domain resource can be a continuous segment of time-domain resources, or it can include multiple time-domain resources, which may be discontinuous in the time domain.

[0195] S440, the second communication device determines the second AI channel estimation result based on the second information and the preset AI model. Alternatively, the second communication device inputs the second information into the preset AI model to obtain the second AI channel estimation result.

[0196] Similar to S420, the second communication device inputs the second information into a preset AI model, and the output of the AI ​​model can be the second AI channel estimation result.

[0197] Optionally, the order of S410 to S440 is not restricted. For example, S430 can be executed before S420, or S430 and S440 can be executed simultaneously.

[0198] Optionally, in method 400, the preset AI model can be deployed in the second communication device or outside the second communication device, for example, deployed in the OTT device of the second communication device. Therefore, S420 and S440 can be implemented by the second communication device or by the OTT device.

[0199] It should be understood that when the preset AI model is deployed in the OTT device of the second communication device, the second communication device can send the first information and the second information to the OTT device, and the OTT device can send the first AI channel estimation result and the second AI channel estimation result to the second communication device.

[0200] S450, the second communication device sends the first result information to the first communication device, and correspondingly, the first communication device receives the first result information.

[0201] The first result information is used to determine the power allocation coefficient to be used, and the first result information is determined based on the first AI channel estimation result and the second AI channel estimation result.

[0202] Optionally, the power allocation factor to be used in this application can be understood as a preferred power allocation factor.

[0203] As an example, the first result information includes the power allocation factor to be used.

[0204] Specifically, the second communication device can determine which is better, the first power allocation coefficient or the second power allocation coefficient, based on the better of the first AI channel estimation result and the second AI channel estimation result. The power allocation coefficient corresponding to the better channel estimation result is the better power allocation coefficient. Furthermore, the second communication device can determine the better power allocation coefficient as the power allocation coefficient to be used and send this power allocation coefficient to the first communication device.

[0205] In other words, in this example, the power allocation factor to be used is either the first power allocation factor or the second power allocation factor.

[0206] For example, the second communication device may determine the better of the first AI channel estimation result and the second AI channel estimation result in the following manner.

[0207] Method 1: First, determine the channel estimation-related parameter #1 based on the first AI channel estimation result, and then determine the channel estimation-related parameter #2 based on the second AI channel estimation result. Finally, compare parameter #1 and parameter #2 to determine the better channel estimation result. Parameters #1 and #2 can be posterior information. For example, if parameters #1 and #2 are the posterior signal-to-interference-plus-noise ratio (post-SINR), then a higher post-SINR indicates a better channel estimation result. Alternatively, if parameters #1 and #2 are cyclic redundancy check (CRC) parameters related to correct bit decoding, such as the bit error rate (BER), then a lower BER indicates a better channel estimation result.

[0208] Method 2: Compare the first AI channel estimation result with the non-AI channel estimation result to obtain error #1 or similarity #1. Compare the second AI channel estimation result with the non-AI channel estimation result to obtain error #2 or similarity #2. Determine the better channel estimation result based on the magnitude of error #1 and error #2 or the magnitude of similarity #1 and similarity #2. The result with the smaller error or higher similarity is considered the better channel estimation result.

[0209] For example, the error can be represented by normalized mean squared error (NMSE), variance, standard deviation, etc., and the similarity can be represented by cosine similarity, Pearson correlation coefficient, Jaccard coefficient, etc.

[0210] Optionally, in this second method, the method 400 further includes: the first communication device transmitting fifth information on the fifth time-domain resource, and correspondingly, the second communication device receiving the fifth information; the second communication device determining the above-mentioned non-AI channel estimation result based on the fifth information and the non-AI model.

[0211] The fifth information includes the first data and preset information, which are mapped onto the same RE of the fifth time domain resource using the fifth power allocation coefficient.

[0212] In this application, the fifth power allocation coefficient is a number close to 1, for example, the fifth power allocation coefficient is 1. When the fifth power allocation coefficient is 1, it means that the transmission power is all concentrated on the preset information. For the receiving end, it can be understood that the fifth information only includes the preset information and does not include the first data, or in other words, it does not include the useful first data.

[0213] Specifically, the fifth power allocation coefficient is much larger than the first power allocation coefficient, and also much larger than the second power allocation coefficient. In other words, the difference between the fifth power allocation coefficient and the first power allocation coefficient is greater than the second threshold, and the difference between the fifth power allocation coefficient and the first power allocation coefficient is greater than the second threshold. For example, the second threshold is 0.5.

[0214] As an example, when the power allocation coefficient is the ratio of the transmission power of the preset information to the transmission power of the first data, the first power allocation coefficient and the second power allocation coefficient can be values ​​close to 1, such as 0.8, 0.9, etc., and the fifth power allocation coefficient can be a value much larger than the first power allocation coefficient, such as 10, 50, etc.

[0215] In this application, non-AI channel estimation results refer to channel estimation results obtained through non-AI algorithms. AI channel estimation results and non-AI channel estimation results can be represented by the same parameters; for example, both AI channel estimation results and non-AI channel estimation results can be CSI or both can be the impulse response of the channel.

[0216] In this application, the non-AI model can be understood as a non-AI algorithm or a traditional mathematical algorithm that can be used for channel estimation. Examples include least squares (LS), linear minimum mean square error (LMMESE), and compressed sensing (CS) algorithms.

[0217] As yet another example, the first result information includes a suggested power allocation factor, which is used to determine the power allocation factor to be used.

[0218] Specifically, the second communication device can determine which power allocation coefficient is better, the first or the second, based on the better of the first and second AI channel estimation results. The power allocation coefficient corresponding to the better channel estimation result is the better power allocation coefficient. Furthermore, the second communication device can determine the better power allocation coefficient as a suggested power allocation coefficient and send it to the first communication device. The first communication device can determine the power allocation coefficient to be used based on this coefficient. For example, if multiple second communication devices have provided suggested power allocation coefficients, the first communication device can use the average of these suggested power allocation coefficients as the power allocation coefficient to be used.

[0219] In other words, in this example, the suggested power allocation factor is either the first power allocation factor or the second power allocation factor. The power allocation factor to be used can be the suggested power allocation factor or other values.

[0220] As yet another example, the first result information includes the first channel estimation result and the second channel estimation result.

[0221] Specifically, the second communication device can send the output of the preset AI model (i.e., the first AI channel estimation result and the second AI channel estimation result) to the first communication device, which then determines the better channel estimation result and thus determines the power allocation coefficient to be used. The power allocation coefficient to be used can be either the first power allocation coefficient or the second power allocation coefficient, or other values.

[0222] Optionally, the specific method by which the second communication device determines a better channel estimation result can be referred to that of the first communication device, and will not be elaborated here.

[0223] Optionally, in this example, the first result information further includes the correspondence between the first AI channel estimation result and the first time-domain resource, and the correspondence between the second AI channel estimation result and the second time-domain resource. Alternatively, it may include the correspondence between the first AI channel estimation result and the first power allocation coefficient, and the correspondence between the second AI channel estimation result and the second power allocation coefficient. Based on the above correspondences, the first communication device can select the power allocation coefficient corresponding to the better channel estimation result as the power allocation coefficient to be used.

[0224] Based on the above scheme, the first communication device sends first information and second information to the second communication device. The second communication device can obtain the first AI channel estimation result and the second AI channel estimation result. Since the first information and the second information correspond to different power allocation coefficients, the power allocation coefficient to be used can be determined based on the first AI channel estimation result and the second AI channel estimation result. For example, a more reasonable power allocation coefficient can be determined to improve the throughput of the communication system.

[0225] On the other hand, the first and second information are information transmitted through the actual channel. Therefore, the power allocation coefficient to be used determined based on the first and second information is more in line with the actual channel conditions, thus having higher accuracy.

[0226] Optionally, method 400 can be understood as follows: the first communication device can transmit M pieces of information on M time-domain resources respectively. Each of the M pieces of information includes first data and preset information. The M pieces of information are different, and the M pieces of information correspond to M power allocation coefficients. The first data and the preset information are mapped onto the M time-domain resources respectively using the M power allocation coefficients. Based on the M pieces of information, the second communication device can determine M AI channel estimation results, and then, based on the M channel estimation results, can determine the power allocation coefficient to be used. The power allocation coefficient to be used can be one of the M power allocation coefficients. Here, M is a number greater than or equal to 2. The M time-domain resources can include first time-domain resources and second time-domain resources, the M pieces of information can include first information and second information, the M power allocation coefficients can include first power allocation coefficients and second power allocation coefficients, and the M AI channel estimation results can include first AI channel estimation results and second AI channel estimation results.

[0227] Optionally, in method 400, the preset AI model corresponds to a preset power allocation coefficient.

[0228] Specifically, the preset power allocation coefficient can be determined through AI training. For example, when training a preset AI model, the preset power allocation coefficient can be obtained simultaneously through simulation parameters.

[0229] Specifically, the difference between the preset power allocation coefficient and the first power allocation coefficient is less than the first threshold, and the difference between the preset power allocation coefficient and the second power allocation coefficient is less than the first threshold. In other words, the values ​​of the first power allocation coefficient and the second power allocation coefficient range from (preset power allocation coefficient - first threshold) to (preset power allocation coefficient - +th threshold).

[0230] Specifically, the first power allocation coefficient and the second power allocation coefficient can be values ​​whose difference from the preset power allocation coefficient is less than the first threshold. For example, if the preset power allocation coefficient is 0.3 and the first threshold is 0.1, then the range of the first power allocation coefficient and the second power allocation coefficient can be 0.2 to 0.4, such as any two of 0.25, 0.3, 0.35, and 0.4. As another example, if the preset power allocation coefficient is 0.2 and the first threshold is 0.02, then the range of the first power allocation coefficient and the second power allocation coefficient can be 0.18 to 0.22, such as any two of 0.18, 0.19, 0.2, 0.21, and 0.22.

[0231] Optionally, the preset power allocation coefficient is either a first power allocation coefficient or a second power allocation coefficient.

[0232] It should be understood that in method 400, the preset AI model can be adapted to a certain range of power allocation coefficients. That is, if the power allocation coefficients of the preset information and the first data are within this range, the second communication device can input the superimposed signal (such as the first information or the second information) into the AI ​​model to obtain the AI ​​channel estimation result (such as the first AI channel estimation result or the second AI channel estimation result).

[0233] Based on the above scheme, the first communication device and the second communication device can determine a more suitable power allocation coefficient near the value of the preset power allocation coefficient, so that the power allocation coefficient is not only more in line with the actual channel environment, but also more in line with the performance of the preset AI model.

[0234] It should be understood that since the preset AI model and preset power allocation coefficients are matched and trained together based on data, however, due to the differences between the real channel environment and the training data, and the differences in the performance of each receiver (such as the second communication device), the preset pilot power allocation coefficients corresponding to the preset AI model may not be the most suitable. Through method 400, the preset power allocation coefficients can be adjusted to determine the power allocation coefficients that are more suitable for the second communication device and the channel conditions, thereby improving the communication performance.

[0235] Optionally, the first time-domain resource includes N1 time-domain resources, the first information includes N1 pieces of information, and the N1 time-domain resources and the N1 pieces of information correspond one-to-one, where N1 is an integer greater than or equal to 1; the second time-domain resource includes N2 time-domain resources, the second information includes N2 pieces of information, and the N2 time-domain resources and the N2 pieces of information correspond one-to-one, where N2 is an integer greater than or equal to 1.

[0236] Specifically, the first communication device can superimpose the first data and preset information using a first power allocation coefficient on multiple time-domain resources. The second communication device can obtain an AI channel estimation result for each received superimposed signal (i.e., the first information), i.e., N1 channel estimation results. The first AI channel estimation result can include the N1 channel estimation results, or it can be the average of the N1 channel estimation results. Similarly, the first communication device can superimpose the first data and preset information using a second power allocation coefficient on multiple time-domain resources. The second communication device can obtain an AI channel estimation result for each received superimposed signal (i.e., the second information), i.e., N2 channel estimation results. The second AI channel estimation result can include the N2 channel estimation results, or it can be the average of the N2 channel estimation results.

[0237] N1 and N2 can be the same or different, and there is no restriction.

[0238] The following explanation uses Figure 9 as an example.

[0239] As shown in Figure 9, coefficient #1 (an example of the first power allocation coefficient) is 0.18. This coefficient #1 can be used in subframes 1, 4, and 7 (denoted as resource #1, which is an example of the first time-domain resource, i.e., the first time-domain resource includes 3 subframes), meaning the power allocation coefficient for the superimposed signal transmitted on subframes 1, 4, and 7 is 0.18. Coefficient #2 (an example of the preset power allocation coefficient) is 0.2. This coefficient #2 can be used in subframes 2, 5, and 8 (denoted as resource #2, which is an example of the second time-domain resource, i.e., the second time-domain resource includes 3 subframes), meaning the power allocation coefficient for the superimposed signal transmitted on subframes 2, 5, and 8 is 0.2. The coefficient #3 (an example of the second power allocation coefficient) is 0.22. This coefficient #3 can be used for subframes 3, 6 and 9 (denoted as resource #3, which can be regarded as another example of the first time domain resource, or as another example of the second time domain resource). That is, the power allocation coefficient of the superimposed signal transmitted on subframes 3, 6 and 9 is 0.22.

[0240] Taking downlink communication as an example, the UE can determine three results #1 (an example of the first AI channel estimation result) corresponding to coefficient #1 based on the superimposed signals received on subframes 1, 4, and 7. Based on the superimposed signals received on subframes 2, 5, and 8, the UE can determine three results #2 (an example of the second AI channel estimation result) corresponding to coefficient #2. Based on the superimposed signals received on subframes 3, 6, and 9, the UE can determine three results #3 (which can be regarded as another example of the first AI channel estimation result or another example of the second AI channel estimation result) corresponding to coefficient #3. The UE can first determine the average value of the three results #1 (denoted as average value #1), the average value of the three results #2 (denoted as average value #2), and the average value of the three results #3 (denoted as average value #3). By comparing the average values ​​#1, #2, and #3, the UE can determine the better value among coefficients #1, #2, and #3 and feed it back to the base station. Alternatively, the UE can feed back the average values ​​#1, #2, and #3 to the base station, which will then determine the optimal value among the coefficients #1, #2, and #3.

[0241] Optionally, coefficient #0 (an example of the fifth power allocation coefficient) is 1, which can be used for subframe 0 (an example of the fifth time-domain resource). That is, the power allocation coefficient of the superimposed signal transmitted on subframe 0 is 1. The UE can calculate the superimposed signal received on subframe 0 using a non-AI model to obtain the non-AI channel estimation result. When comparing the average values ​​#1, #2, and #3, the UE can compare the average values ​​#1, #2, and #3 with the non-AI channel estimation result to determine the better value among coefficients #1, #2, and #3.

[0242] Based on the above scheme, using the same power allocation coefficient to transmit superimposed signals on multiple time-domain resources can yield more AI channel estimation results. This allows for more data to be analyzed when determining the power allocation coefficient to be used, thereby improving accuracy.

[0243] Optionally, prior to S410, method 400 further includes: S401, whereby the first communication device sends configuration information to the second communication device, and correspondingly, the second communication device receives the configuration information. Alternatively, the second communication device sends configuration information to the first communication device, and correspondingly, the first communication device receives the configuration information. Alternatively, the third communication device sends configuration information to both the first and second communication devices, and the first and second communication devices respectively receive the configuration information.

[0244] For example, the first communication device is a network device, and the second communication device is a terminal device; the network device sends configuration information to the terminal device. Alternatively, the first communication device is a terminal device, and the second communication device is a network device; the network device sends configuration information to the terminal device. Another example is that the first communication device is network device A, and the second communication device is network device B; network device A sends configuration information to network device B. Yet another example is that the first communication device is terminal device A, and the second communication device is terminal device B; terminal device A and terminal device B each receive configuration information from the network device.

[0245] The configuration information includes the correspondence between the first power allocation coefficient and the first time-domain resource, as well as the correspondence between the second power allocation coefficient and the second time-domain resource.

[0246] Specifically, the configuration information can indicate the correspondence between power allocation coefficients and time-domain resources. Based on this configuration information, the second communication device can determine which time-domain resources correspond to the same power allocation coefficient. The set of time-domain resources corresponding to the same power allocation coefficient can be understood as a time-domain resource group. For example, in Figure 9, resource #1 is one time-domain resource group, resource #2 is another, and resource #3 is yet another.

[0247] As an example, the configuration information includes a first power allocation factor and a second power allocation factor.

[0248] Specifically, the first communication device can indicate the value of the power allocation coefficient and the correspondence between the power allocation coefficient and time-domain resources to the second communication device through configuration information. In other words, the configuration information may include which time-domain resources are overlaid signals transmitted using the first power allocation coefficient, which time-domain resources are overlaid signals transmitted using the second power allocation coefficient, and the values ​​of the first and second power allocation coefficients.

[0249] Taking the temporal resources in Figure 9 as an example, the base station can send the UE the correspondence between coefficient #1 and resource #1 (including subframe 1, subframe 4 and subframe 7), the correspondence between coefficient #2 and resource #2 (including subframe 2, subframe 5 and subframe 8), and the correspondence between coefficient #3 and resource #3 (including subframe 3, subframe 6 and subframe 9). This configuration information can also include coefficient #1 being 0.18, coefficient #2 being 0.2, and coefficient #3 being 0.22.

[0250] As yet another example, the configuration information does not include the first power allocation factor and the second power allocation factor.

[0251] Specifically, the first communication device can indicate the correspondence between power allocation coefficients and time-domain resources to the second communication device through configuration information, without indicating the value of the power allocation coefficients. In other words, the configuration information only includes which first time-domain resources correspond to the first power allocation coefficient and which second time-domain resources correspond to the second power allocation coefficient, without indicating the specific values ​​of the first and second power allocation coefficients.

[0252] Taking the temporal resources in Figure 9 as an example, the base station can send the UE the correspondence between coefficient #1 and resource #1 (including subframe 1, subframe 4 and subframe 7), the correspondence between coefficient #2 and resource #2 (including subframe 2, subframe 5 and subframe 8), and the correspondence between coefficient #3 and resource #3 (including subframe 3, subframe 6 and subframe 9). This configuration information may not include the specific values ​​of coefficient #1, coefficient #2 and coefficient #3.

[0253] Optionally, when the configuration information does not include the first power allocation coefficient and the second power allocation coefficient, the second communication device cannot determine the specific value of the power allocation coefficient. Therefore, the first result information may not include the power allocation coefficient to be used, nor the suggested power allocation coefficient. For example, the first result information may include the first AI channel estimation result and the second AI channel estimation result.

[0254] Optionally, the configuration information may also include the correspondence between the fifth power configuration factor and the fifth time-domain resource.

[0255] Taking the time-domain resources in Figure 9 as an example, the base station can indicate the correspondence between coefficient #0 and subframe 0 to the UE, and the indication coefficient #0 is 1, so that the UE can process the superimposed signal received on subframe 0 based on the non-AI model.

[0256] Based on the above scheme, by configuring the correspondence between power allocation coefficients and time-domain resources, the second communication device can determine which time-domain resources are superimposed signals transmitted through the same power allocation coefficient, which facilitates the second communication device to classify and process the received signals and improve communication efficiency.

[0257] Optionally, after S450, method 400 further includes: the first communication device sending first data and preset information to the second communication device, and correspondingly, the second communication device receiving the first data and preset information, wherein the first data and preset information are mapped onto the same RE with the power allocation coefficient to be used. Further, the second communication device inputs the received superimposed signal into a preset AI model to obtain a channel estimation result.

[0258] Specifically, after determining the power allocation coefficient to be used, the first communication device and the second communication device can perform transmission and channel estimation based on the allocation coefficient.

[0259] For example, the first communication device is a network device, and the second communication device is a terminal device. The network device maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends them to the terminal device. The terminal device inputs the received superimposed signal into a preset AI model to obtain the channel estimation result. In this case, method 400 is applicable to downlink scenarios.

[0260] For example, the first communication device is a terminal device, and the second communication device is a network device. The terminal device maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends them to the network device. The network device inputs the received superimposed signal into a preset AI model to obtain the channel estimation result. In this case, method 400 is applicable to the uplink scenario.

[0261] For example, the first communication device is network device A, and the second communication device is network device B. Network device A maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends them to network device B. Network device B inputs the received superimposed signal into a preset AI model to obtain the channel estimation result. In this case, method 400 is applicable to scenarios where network devices communicate with each other.

[0262] For example, the first communication device is terminal device A, and the second communication device is terminal device B. Terminal device A maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends them to terminal device B. Terminal device B inputs the received superimposed signal into a preset AI model to obtain the channel estimation result. In this case, method 400 is applicable to side-channel scenarios.

[0263] Figure 10 is a schematic flowchart of a communication method 500 provided in this application. As shown in Figure 10, the method 500 includes the following steps.

[0264] S510, the first communication device sends first information on the first time domain resource, and correspondingly, the second communication device receives the first information on the first time domain resource.

[0265] The specific details of S510 can be found in S410, and will not be elaborated here.

[0266] S520, the second communication device determines the first AI model based on the first information. Or, in other words, it trains and obtains the first AI model based on the first information.

[0267] Specifically, the second communication device can use the first information as the first dataset to train a first AI model. The AI ​​training includes steps such as dataset determination, model selection, model construction, model training, model evaluation, and model optimization. The process of the second communication device receiving the first information in S510 can be considered as the step of determining the first dataset.

[0268] The first AI model is used for channel estimation.

[0269] S530, the first communication device sends second information on the second time domain resource, and correspondingly, the second communication device receives the second information on the second time domain resource.

[0270] The specific details of S530 are the same as those of S430, and will not be elaborated here.

[0271] S540, the second communication device determines the second AI model based on the second information. Or, in other words, it trains the second AI model based on the second information.

[0272] Similar to S520, the second communication device can use the second information as a second dataset to train a second AI model.

[0273] Optionally, the order of S510 to S540 is not restricted. For example, S530 can be executed before S520, or S530 and S540 can be executed simultaneously.

[0274] Optionally, in method 500, the AI ​​model can be deployed in the second communication device or outside the second communication device, for example, in an OTT device of the second communication device. Therefore, S520 and S540 can be implemented by the second communication device or by the OTT device.

[0275] It should be understood that when the training of the AI ​​model is implemented by the OTT device of the second communication device, the second communication device can send the first information and the second information to the OTT device, and the OTT device can send the parameters of the first AI model and the second AI model to the second communication device.

[0276] S550, the second communication device sends the second result information to the first communication device, and correspondingly, the first communication device receives the second result information.

[0277] The second result information is used to determine the power allocation coefficient to be used, and the second result information is determined based on the performance of the first AI model and the second AI model.

[0278] Optionally, the power allocation factor to be used in this application can be understood as a preferred power allocation factor.

[0279] In this application, the performance of the AI ​​model includes aspects such as accuracy, robustness, and training efficiency. Accuracy refers to the difference between the AI ​​model's output and the actual result; robustness refers to the reliability of the AI ​​model when facing variations such as different types of noise, different channel types, or attacks; and training efficiency refers to the time cost of training the AI ​​model given the available time and computing resources.

[0280] As an example, the second result information includes the power allocation factor to be used.

[0281] Specifically, similar to S450, the second communication device can determine which power allocation coefficient is better, the first or the second, based on the performance of the first AI model or the second AI model. The power allocation coefficient corresponding to the AI ​​model with better performance is then considered the better power allocation coefficient. Furthermore, the second communication device can determine the better power allocation coefficient as the power allocation coefficient to be used and send it to the first communication device.

[0282] In other words, in this example, the power allocation factor to be used is either the first power allocation factor or the second power allocation factor.

[0283] For example, different proportions can be configured for different performance aspects to comprehensively evaluate the performance of an AI model. For instance, the accuracy of the first AI model is x1, robustness is y1, and training efficiency is z1, while the accuracy of the second AI model is x2, robustness is y2, and training efficiency is z2. Assuming the proportion configured for accuracy is 0.5, for robustness is 0.3, and for training efficiency is 0.3, then the performance of the first AI model can be expressed as R1 = 0.5x1 + 0.3y1 + 0.2z1, and the performance of the second AI model can be expressed as R2 = 0.5x2 + 0.3y2 + 0.2z2. By comparing the values ​​of R1 and R2, the better-performing AI model can be determined.

[0284] Optionally, the accuracy of the AI ​​model can be evaluated by the final convergence value of the loss function. For example, if the first AI model and the second AI model use NMSE as the training loss function and are trained for the same number of epochs, the loss function of the first AI model decreases to 'a', and the loss function of the second AI model decreases to 'b'. By comparing the values ​​of 'a' and 'b', it can be determined which model performs better.

[0285] It should be understood that in evaluating the performance of AI models, the priority of accuracy, robustness, training efficiency, etc., depends on the actual situation and is not restricted.

[0286] As yet another example, the second result information includes a suggested power allocation factor, which is used to determine the power allocation factor to be used.

[0287] Similar to S450, the second communication device can determine which of the first and second power allocation coefficients is better based on the better performance of the first and second AI models. The power allocation coefficient corresponding to the AI ​​model with better performance is then considered the better power allocation coefficient. Furthermore, the second communication device can determine the better power allocation coefficient as a suggested power allocation coefficient and send this coefficient to the first communication device.

[0288] As yet another example, the second result information includes the parameters of the first AI model and the parameters of the second AI model.

[0289] Specifically, the second communication device can send the parameters (such as weights, biases, etc.) of the trained first and second AI models to the first communication device, which then determines the AI ​​model with better performance, thereby determining the power allocation coefficient to be used. The power allocation coefficient to be used can be either the first power allocation coefficient or the second power allocation coefficient, or other values.

[0290] Optionally, the specific method by which the second communication device determines the AI ​​model with better performance can be referenced from that of the first communication device, and will not be elaborated here.

[0291] Optionally, in this example, the second result information may also include the correspondence between the first AI model and the first time-domain resource, and the correspondence between the second AI model and the second time-domain resource. Alternatively, it may include the correspondence between the first AI model and the first power allocation coefficient, and the correspondence between the second AI model and the second power allocation coefficient. Based on the above correspondences, the first communication device can select the power allocation coefficient corresponding to the AI ​​model with better performance as the power allocation coefficient to be used.

[0292] Based on the above scheme, the first communication device sends first information and second information to the second communication device. The second communication device can obtain the first AI model and the second AI model. Since the first information and the second information correspond to different power allocation coefficients, the power allocation coefficient to be used can be determined according to the performance of the first AI model and the second AI model. For example, a more reasonable power allocation coefficient can be determined to improve the throughput of the communication system.

[0293] On the other hand, the first and second information are information transmitted through the actual channel. Therefore, the power allocation coefficient to be used determined based on the first and second information is more in line with the actual channel conditions, thus having higher accuracy.

[0294] Optionally, in S520, the second communication device determines the first AI model based on the first information, including: the second communication device determines the first AI model based on the first information and the first non-AI channel estimation result.

[0295] In other words, when training an AI, the first dataset used to train the first AI model includes not only the first information, but also the first non-AI channel estimation results.

[0296] The first non-AI channel estimation result is determined based on the non-AI model and has a correlation or correspondence with the first information. For example, the time-domain resources used to determine the first non-AI channel estimation result are adjacent to the first time-domain resources.

[0297] Optionally, the method 500 further includes: S560, the first communication device sends third information to the second communication device on the third time domain resources, and correspondingly, the second communication device receives the third information; the second communication device determines the first non-AI channel estimation result based on the third information and the non-AI model.

[0298] The third information includes the first data and preset information, which are mapped onto the same RE of the third time domain resource by the third power allocation coefficient.

[0299] In this application, the third power allocation coefficient is a number close to 1, for example, the third power allocation coefficient is 1. When the third power allocation coefficient is 1, it means that the transmission power is entirely concentrated on the preset information. From the receiver's perspective, this can be understood as the third information only including the preset information and not including the first data, or in other words, not including the useful first data. Therefore, the second communication device can process the third information using a non-AI model to obtain the first non-AI channel estimation result.

[0300] Specifically, the third power allocation coefficient is much larger than the first power allocation coefficient, or in other words, the difference between the third power allocation coefficient and the first power allocation coefficient is greater than the second threshold. For example, the second threshold is 0.5, the first power allocation coefficient is 0.2, and the third power allocation coefficient is 0.98.

[0301] In this application, the third time-domain resource and the first time-domain resource have a corresponding relationship, or in other words, the third time-domain resource and the first time-domain resource are a group. The third information received on the third time-domain resource and the first information received on the first time-domain resource can both be used as data in the first dataset to train the first AI model.

[0302] For example, the correspondence between the third time-domain resource and the first time-domain resource can refer to the temporal correlation between the third time-domain resource and the first time-domain resource. For instance, the third time-domain resource and the first time-domain resource are temporally adjacent.

[0303] Similarly, in S540, the second communication device determines the second AI model based on the second information, including: the second communication device determines the second AI model based on the second information and the second non-AI channel estimation result.

[0304] In other words, when training an AI model, the second dataset used to train the second AI model includes not only the second information, but also the second non-AI channel estimation results.

[0305] The second non-AI channel estimation result is determined based on the non-AI model and has a correlation or correspondence with the second information. For example, the time-domain resources used to determine the second non-AI channel estimation result are adjacent to the second time-domain resources.

[0306] Optionally, the method 500 further includes: S570, the first communication device sends fourth information to the second communication device on the fourth time domain resources, and correspondingly, the second communication device receives the fourth information; the second communication device determines the second non-AI channel estimation result based on the fourth information and the non-AI model.

[0307] The fourth information includes the first data and preset information, which are mapped onto the same RE of the fourth time domain resource using the fourth power allocation coefficient.

[0308] In this application, the fourth power allocation coefficient is a number close to 1, for example, the fourth power allocation coefficient is 1. When the fourth power allocation coefficient is 1, it means that the transmission power is entirely concentrated on the preset information. From the receiver's perspective, this can be understood as the fourth information only including the preset information and not including the first data, or in other words, not including the useful first data. Therefore, the second communication device can process the fourth information using a non-AI model to obtain the second non-AI channel estimation result.

[0309] Specifically, the fourth power allocation coefficient is much larger than the second power allocation coefficient, or in other words, the difference between the fourth power allocation coefficient and the second power allocation coefficient is greater than the second threshold. For example, the second threshold is 0.5, the second power allocation coefficient is 0.3, and the fourth power allocation coefficient is 0.99.

[0310] Optionally, in this application, the third power allocation coefficient and the fourth power allocation coefficient are the same, for example, both are 1.

[0311] In this application, the fourth time-domain resource and the second time-domain resource have a corresponding relationship, or in other words, the fourth time-domain resource and the second time-domain resource are a group, and the fourth information received on the fourth time-domain resource and the second information received on the second time-domain resource can both be used as data in the second dataset to train the second AI model.

[0312] For example, the correspondence between the fourth time-domain resource and the second time-domain resource can refer to the temporal correlation between the fourth time-domain resource and the second time-domain resource, such as the fourth time-domain resource and the second time-domain resource being temporally adjacent.

[0313] Based on the above scheme, the dataset used to train the AI ​​model also includes non-AI channel estimation results. Since the non-AI channel estimation results are estimation results of the real channel, this makes the training of the AI ​​model more efficient, the performance of the trained AI model is better, and it has greater practicality.

[0314] Optionally, method 500 can be understood as follows: the first communication device transmits M pieces of information on M time-domain resources respectively. Each of the M pieces of information includes first data and preset information. The M pieces of information are different, and the M pieces of information correspond to M power allocation coefficients. The first data and the preset information are mapped onto the M time-domain resources respectively using the M power allocation coefficients. Based on the M pieces of information, the second communication device can determine M AI models, and then, based on the performance of the M models, can determine the power allocation coefficient to be used. The power allocation coefficient to be used can be one of the M power allocation coefficients. Here, M is a number greater than or equal to 2. The M time-domain resources can include first time-domain resources and second time-domain resources, the M pieces of information can include first information and second information, the M power allocation coefficients can include first power allocation coefficients and second power allocation coefficients, and the M AI models can include first AI models and second AI models.

[0315] Optionally, the first time-domain resource includes N1 time-domain resources, the first information includes N1 pieces of information, and the N1 time-domain resources and the N1 pieces of information correspond one-to-one, where N1 is an integer greater than or equal to 1; the second time-domain resource includes N2 time-domain resources, the second information includes N2 pieces of information, and the N2 time-domain resources and the N2 pieces of information correspond one-to-one, where N2 is an integer greater than or equal to 1.

[0316] Specifically, the first communication device can superimpose first data and preset information using a first power allocation coefficient on multiple time-domain resources, and the second communication device uses each received superimposed signal (i.e., the first information) as a data point in the first dataset to train a first AI model. Similarly, the first communication device can superimpose first data and preset information using a second power allocation coefficient on multiple time-domain resources, and the second communication device uses each received superimposed signal (i.e., the second information) as a data point in the second dataset to train a second AI model.

[0317] N1 and N2 can be the same or different, and there is no restriction.

[0318] Optionally, the third time-domain resource includes N1 time-domain resources, and the N1 time-domain resources in the third time-domain resource correspond one-to-one with the N1 time-domain resources in the first time-domain resource; the third information includes N1 pieces of information, and the N1 time-domain resources in the third time-domain resource correspond one-to-one with the N1 pieces of information in the third information; the fourth time-domain resource includes N2 time-domain resources, and the N2 time-domain resources in the fourth time-domain resource correspond one-to-one with the N2 time-domain resources in the second time-domain resource; the fourth information includes N2 pieces of information, and the N2 time-domain resources in the fourth time-domain resource correspond one-to-one with the N2 pieces of information in the fourth information.

[0319] Specifically, the first communication device can superimpose the first data and preset information using a third power allocation coefficient on multiple time-domain resources. The second communication device can obtain a non-AI channel estimation result for each received superimposed signal (i.e., the third information) using a non-AI model, i.e., N1 non-channel estimation results. In other words, the first non-AI channel estimation result can include N1 non-channel estimation results. The second communication device can use the N1 non-channel estimation results and each received superimposed signal (i.e., the first information) on the first time-domain resources as data in the first dataset to train the first AI model. Similarly, the first communication device can superimpose the first data and preset information using a fourth power allocation coefficient on multiple time-domain resources. The second communication device can obtain a non-AI channel estimation result for each received superimposed signal (i.e., the fourth information) using a non-AI model, i.e., N2 non-channel estimation results. In other words, the second non-AI channel estimation result can include N2 non-channel estimation results. The second communication device can use the N2 non-channel estimation results and each received superimposed signal (i.e., the second information) on the second time-domain resources as data in the second dataset to train the second AI model.

[0320] For example, as shown in Figure 11, coefficient #4 (another example of the first power allocation coefficient) is 0.2. This coefficient #4 can be used in subframes 1 and 7 (denoted as resource #4, which is an example of the first time-domain resource, i.e., the first time-domain resource includes 2 subframes), meaning the power allocation coefficient for the superimposed signal transmitted on subframes 1 and 7 is 0.2. Coefficient #5 (another example of the second power allocation coefficient) is 0.3. This coefficient #5 can be used in subframes 3 and 9 (denoted as resource #5, which is an example of the second time-domain resource, i.e., the second time-domain resource includes 2 subframes), meaning the power allocation coefficient for the superimposed signal transmitted on subframes 3 and 9 is 0.3. Coefficient #6 (which can be considered another example of the first power allocation coefficient, or another example of the second power allocation coefficient) is 0.4. This coefficient #6 can be used for subframes 5 and 11 (denoted as resource #6, which can be considered another example of the first time-domain resource, or another example of the second time-domain resource). That is, the power allocation coefficient of the superimposed signal transmitted on subframes 5 and 11 is 0.4. In addition, coefficient #0 (an example of the third power allocation coefficient, and also an example of the fourth power allocation coefficient) is 1. This coefficient #0 can be used for subframes 0, 2, 4, 6, 8, and 10. That is, the power allocation coefficient of the superimposed signal transmitted on subframes 0, 2, 4, 6, 8, and 10 is all 1. Subframe 0 corresponds to subframe 1, subframe 2 corresponds to subframe 3, subframe 4 corresponds to subframe 5, subframe 6 corresponds to subframe 7, subframe 8 corresponds to subframe 9, and subframe 10 corresponds to subframe 11. Therefore, subframe 0 and subframe 6 can be regarded as the third time domain resource corresponding to the first time domain resource, subframe 2 and subframe 8 can be regarded as the fourth time domain resource corresponding to the second time domain resource, and subframe 4 and subframe 10 can be regarded as the third time domain resource corresponding to the first time domain resource, or as the fourth time domain resource corresponding to the second time domain resource.

[0321] Taking downlink communication as an example, the UE can use a non-AI model to calculate the superimposed signals received on subframes 0, 2, 4, 6, 8, and 10 respectively, and obtain 6 non-AI channel estimation results, denoted as H0, H2, H4, H6, H8, and H10. Furthermore, the UE can use the superimposed signals received on subframes 1 and 7, as well as the non-AI channel estimation results (i.e., H0 and H6) on subframes 0 and 6, as dataset #1 (an example of the first dataset) to train AI model #1 (an example of the first AI model). It can use the superimposed signals received on subframes 3 and 9, as well as the non-AI channel estimation results (i.e., H2 and H8) on subframes 2 and 8, as dataset #2 (an example of the second dataset) to train AI model #2 (an example of the second AI model). It can use the superimposed signals received on subframes 5 and 11, as well as the non-AI channel estimation results (i.e., H4 and H10) on subframes 4 and 10, as dataset #3 (which can be regarded as another example of the first dataset or another example of the second dataset) to train AI model #3 (which can be regarded as another example of the first AI model or another example of the second AI model). By comparing the performance of AI models #1, #2, and #3, the UE can determine the optimal value among coefficients #4, #5, and #6 and feed it back to the base station. Alternatively, the UE can feed back the parameters of AI models #1, #2, and #3 to the base station, which will then determine the optimal value among coefficients #4, #5, and #6.

[0322] Based on the above scheme, using the same power allocation coefficient to send superimposed signals on multiple time-domain resources can obtain more data for training the same AI model. This allows for more data to be analyzed when determining the power allocation coefficient to be used, thereby improving accuracy.

[0323] Optionally, prior to S510, method 500 further includes: S501, whereby the first communication device sends configuration information to the second communication device, and correspondingly, the second communication device receives the configuration information. Alternatively, the second communication device sends configuration information to the first communication device, and correspondingly, the first communication device receives the configuration information. Alternatively, the third communication device sends configuration information to both the first and second communication devices, and the first and second communication devices respectively receive the configuration information.

[0324] For details on S501, please refer to S401.

[0325] The configuration information includes the correspondence between the first power allocation coefficient and the first time-domain resource, as well as the correspondence between the second power allocation coefficient and the second time-domain resource.

[0326] Specifically, the configuration information can indicate the correspondence between power allocation coefficients and time-domain resources. Based on this configuration information, the second communication device can determine which time-domain resources correspond to the same power allocation coefficient. The set of time-domain resources corresponding to the same power allocation coefficient can be understood as a time-domain resource group. For example, in Figure 11, resource #4 is one time-domain resource group, resource #5 is another, and resource #6 is yet another.

[0327] As an example, the configuration information includes a first power allocation factor and a second power allocation factor.

[0328] Taking the temporal resources in Figure 11 as an example, the base station can send the UE the correspondence between coefficient #4 and resource #4 (including subframe 1 and subframe 7), the correspondence between coefficient #5 and resource #5 (including subframe 3 and subframe 9), and the correspondence between coefficient #6 and resource #6 (including subframe 5 and subframe 11). This configuration information can also include coefficient #4 being 0.2, coefficient #5 being 0.3, and coefficient #6 being 0.4.

[0329] As yet another example, the configuration information does not include the first power allocation factor and the second power allocation factor.

[0330] Taking the temporal resources in Figure 11 as an example, the base station can send the UE the correspondence between coefficient #4 and resource #4 (including subframe 1 and subframe 7), the correspondence between coefficient #5 and resource #5 (including subframe 3 and subframe 9), and the correspondence between coefficient #6 and resource #6 (including subframe 5 and subframe 11). This configuration information may not include the specific values ​​of coefficient #4, coefficient #5, and coefficient #6.

[0331] Optionally, when the configuration information does not include the first power allocation coefficient and the second power allocation coefficient, the second communication device cannot determine the specific value of the power allocation coefficient. Therefore, the first result information may not include the power allocation coefficient to be used, nor the suggested power allocation coefficient. For example, the first result information may include the parameters of the first AI model and the parameters of the second AI model.

[0332] Optionally, the configuration information may also include the correspondence between the third power allocation coefficient and the third time-domain resource, as well as the correspondence between the fourth power allocation coefficient and the fourth time-domain resource.

[0333] Optionally, the configuration information may also include a third power allocation factor and a fourth power allocation factor.

[0334] Taking the time-domain resources in Figure 11 as an example, the base station can indicate to the UE the correspondence between coefficient #0 and subframes 0, 2, 4, 6, 8, and 10, the correspondence between coefficient #5 and resource #5 (including subframes 3 and 9), and the correspondence between coefficient #6 and resource #6 (including subframes 5 and 11). This configuration information may also include coefficient #0 = 1.

[0335] Optionally, the configuration information may also include the correspondence between the third time domain resources and the first time domain resources, and the correspondence between the fourth time domain resources and the second time domain resources.

[0336] Taking the temporal resources in Figure 11 as an example, the base station can indicate to the UE that subframe 0 corresponds to subframe 1, subframe 2 corresponds to subframe 3, subframe 4 corresponds to subframe 5, subframe 6 corresponds to subframe 7, subframe 8 corresponds to subframe 9, and subframe 10 corresponds to subframe 11. Thus, the UE can determine which data are included in dataset #1, dataset #2, and dataset #3.

[0337] Based on the above scheme, by configuring the correspondence between power allocation coefficients and time-domain resources, the second communication device can determine which time-domain resources are superimposed signals transmitted through the same power allocation coefficient, which facilitates the second communication device to classify and process the received signals and improve communication efficiency.

[0338] Optionally, after S450, the method 500 further includes: the second communication device sending the parameters of the AI ​​model (i.e., the AI ​​model to be used) corresponding to the power allocation coefficient to be used to the first communication device.

[0339] Optionally, method 400 further includes: the first communication device sending first data and preset information to the second communication device, and correspondingly, the second communication device receiving the first data and preset information, wherein the first data and preset information are mapped onto the same RE with the power allocation coefficient to be used. Further, the second communication device inputs the received superimposed signal into the AI ​​model to be used to obtain channel estimation results.

[0340] Specifically, after determining the power allocation coefficient to be used, the first communication device and the second communication device can perform transmission and channel estimation based on the allocation coefficient.

[0341] For example, the first communication device is a network device, and the second communication device is a terminal device. The network device maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends them to the terminal device. The terminal device inputs the received superimposed signal into the AI ​​model to be used to obtain the channel estimation result. In this case, method 400 is applicable to the downlink scenario.

[0342] For example, the first communication device is a terminal device, and the second communication device is a network device. The terminal device maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends them to the network device. The network device inputs the received superimposed signal into the AI ​​model to be used to obtain the channel estimation result. In this case, method 400 is applicable to the uplink scenario.

[0343] For example, the first communication device is network device A, and the second communication device is network device B. Network device A maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends them to network device B. Network device B inputs the received superimposed signal into the AI ​​model to be used to obtain the channel estimation result. In this case, method 400 is applicable to scenarios where network devices communicate with each other.

[0344] For example, the first communication device is terminal device A, and the second communication device is terminal device B. Terminal device A maps the first data and preset information to the same RE based on the power allocation coefficient to be used, and then sends it to terminal device B. Terminal device B inputs the received superimposed signal into the AI ​​model to be used to obtain the channel estimation result. In this case, method 400 is applicable to side-channel scenarios.

[0345] It should be understood that for any parts of Method 500 that are not described in detail, please refer to Method 400.

[0346] It should also be understood that the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0347] It should also be understood that, in the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0348] It should also be understood that in some of the above embodiments, the examples are mainly based on devices in existing network architectures (such as network devices, terminal devices, etc.). It should be understood that the specific form of the device is not limited in the embodiments of this application. For example, any device that can achieve the same function in the future is applicable to the embodiments of this application.

[0349] It is understood that, in the above-described method embodiments, the methods and operations implemented by a device (such as a network device or a terminal device) can also be implemented by components of the device (such as a chip or circuit).

[0350] The communication method provided by the embodiments of this application has been described in detail above with reference to Figures 1 to 11. The above communication method is mainly described from the perspective of interaction between terminal devices and network devices. It is understood that, in order to realize the above functions, the terminal devices and network devices include hardware structures and / or software modules corresponding to perform each function.

[0351] It is understood that, in order to implement the functions in the above embodiments, the terminal device and network device include hardware structures and / or software modules corresponding to perform each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0352] Figures 12 and 13 are schematic block diagrams of communication devices provided in embodiments of this application. These communication devices can be used to implement the functions of terminal devices or network devices in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0353] Figure 12 is a schematic block diagram of a communication device 2000 provided in an embodiment of this application. As shown in Figure 12, the communication device 2000 includes a transceiver unit (or communication unit) 2020. Optionally, the communication device 2000 also includes a processing unit 2010. The communication device 2000 is used to implement the functions of the terminal device or network device in the method embodiments shown in Figure 7 or Figure 10 above.

[0354] When the communication device 2000 is used to implement the function of the first communication device in the method embodiment shown in FIG7: the transceiver unit 2020 is used to receive first information from the first communication device on the first time domain resource; the processing unit 2010 is used to input the first information into a preset AI model to obtain a first AI channel estimation result; the transceiver unit 2020 is also used to: receive second information from the first communication device on the second time domain resource; the processing unit 2010 is also used to: input the second information into a preset AI model to obtain a second AI channel estimation result; the transceiver unit 2020 is also used to: send first result information to the first communication device, the first result information being used to determine the power allocation coefficient to be used, the first result information being determined based on the first AI channel estimation result and the second AI channel estimation result.

[0355] When the communication device 2000 is used to implement the function of the second communication device in the method embodiment shown in FIG7: the transceiver unit 2020 is used to send first information to the second communication device on the first time domain resource; the transceiver unit 2020 is also used to send second information to the second communication device on the second time domain resource; the transceiver unit 2020 is also used to receive first result information from the second communication device.

[0356] When the communication device 2000 is used to implement the function of the first communication device in the method embodiment shown in FIG10: the transceiver unit 2020 is used to receive first information from the first communication device on the first time domain resource; the processing unit 2010 is used to determine a first AI model based on the first information; the transceiver unit 2020 is also used to receive second information from the first communication device on the second time domain resource; the processing unit 2010 is also used to determine a second AI model based on the second information; the transceiver unit 2020 is also used to send second result information to the first communication device, the second result information being used to determine the power allocation coefficient to be used, the second result information being determined based on the performance of the first AI model and the performance of the second AI model.

[0357] When the communication device 2000 is used to implement the function of the second communication device in the method embodiment shown in FIG10: the transceiver unit 2020 is used to send first information to the second communication device on the first time domain resources; the transceiver unit 2020 is also used to send second information to the second communication device on the second time domain resources; the transceiver unit 2020 is also used to receive second result information from the second communication device.

[0358] For a more detailed description of the processing unit 2010 and the transceiver unit 2020, please refer to the relevant descriptions in the method embodiments shown in Figure 7 or Figure 10.

[0359] The apparatus 2000 of each of the above-described schemes has the function of implementing the corresponding steps performed by the terminal device in the above-described method, or the apparatus 2000 of each of the above-described schemes has the function of implementing the corresponding steps performed by the network device in the above-described method. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (e.g., the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as processing units, can be replaced by processors, respectively executing the transceiver operations and related processing operations in each method embodiment.

[0360] Furthermore, the aforementioned transceiver unit can also be a transceiver circuit (e.g., it may include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit. The processing circuit can be one or more processors, or all or part of the circuitry within one or more processors used for control or processing functions. In embodiments of this application, the device in FIG12 can be a terminal device or network device as described in the foregoing embodiments, or it can be a chip or a chip system, such as a system-on-a-chip (SoC). The transceiver unit can be an input / output circuit or a communication interface; the processing unit is a processor, microprocessor, or integrated circuit integrated on the chip. No limitations are imposed here.

[0361] Figure 13 is a schematic block diagram of a communication device 3000 provided in an embodiment of this application. The device 3000 includes a processing circuit. The device may also include a communication circuit. The processing circuit and the communication circuit communicate with each other via an internal connection path. The processing circuit executes instructions to control the communication circuit to send and / or receive signals.

[0362] Taking a processing circuit including one or more processors and a communication circuit including a transceiver as an example, as shown in Figure 13, the communication device 3000 includes a processor 3010 and a transceiver 3020. The processor 3010 and the transceiver 3020 are coupled to each other. It is understood that the transceiver 3020 can be a transceiver or an input / output interface. Optionally, the communication device 3000 may also include a memory 3030 for storing instructions executed by the processor 3010, or storing input data required by the processor 3010 to execute instructions, or storing data generated after the processor 3010 executes instructions. Sometimes, the transceiver 3020 can also be understood as part of the processor 3010, in which case the communication device 3000 includes the processor 3010.

[0363] In one possible implementation, the apparatus 3000 is used to implement the various processes and steps corresponding to the terminal device in the above method embodiments. In another possible implementation, the apparatus 3000 is used to implement the various processes and steps corresponding to the network device in the above method embodiments.

[0364] It is understood that the device 3000 can specifically be the terminal device or network device in the above embodiments, or it can be a chip or chip system. Correspondingly, the communication circuit can be the interface circuit of the chip, or an input / output circuit, which is not limited here. Specifically, the device 3000 can be used to execute the various steps and / or processes corresponding to the terminal device or network device in the above method embodiments.

[0365] When the communication device 3000 is used to implement the method shown in FIG7 or FIG10, the processor 3010 is used to implement the function of the processing unit 2010, and the transceiver 3020 is used to implement the function of the transceiver unit 2020.

[0366] When the aforementioned communication device is a chip or OTT device applied to a terminal, the terminal chip or OTT device implements the functions of the terminal in the above method embodiments, such as implementing the terminal's processing functions. The terminal chip or OTT device receiving information from a base station can be understood as the information being first received by other modules in the terminal (such as a radio frequency module or antenna), and then sent to the terminal chip or OTT device by these modules. The terminal chip or OTT device sending information to the base station can be understood as the information being first sent by the terminal chip or OTT device to other modules in the terminal (such as a radio frequency module or antenna), and then sent to the base station by these modules.

[0367] When the aforementioned communication device is a chip or OTT device applied to a base station, the base station chip or OTT device implements the functions of the base station in the above method embodiments, for example, implementing the processing functions of the base station. The base station chip or OTT device receiving information from the terminal can be understood as the information being first received by other modules in the base station (such as a radio frequency module or antenna), and then sent to the base station chip or OTT device by these modules. The base station chip or OTT device sending information to the terminal can be understood as the information being first sent by the base station chip or OTT device to other modules in the base station (such as a radio frequency module or antenna), and then sent to the terminal by these modules.

[0368] In this application, entity A sends information to entity B, either directly or indirectly through other entities. Similarly, entity B receives information from entity A, either directly or indirectly through other entities. Entities A and B can be RAN nodes or terminals, or modules within RAN nodes or terminals. Information transmission and reception can be between RAN nodes and terminals, such as between a base station and a terminal; between two RAN nodes, such as between a CU and a DU; or between different modules within a single device, such as between a terminal chip and other modules of the terminal, or between a base station chip and other modules of the base station.

[0369] It is understood that, in order to implement the functions in the above embodiments, the terminal device and network device include hardware structures and / or software modules corresponding to perform each function. Those skilled in the art should readily recognize that, based on the units and method steps of the various examples described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0370] It should be understood that in the embodiments of this application, the time-domain symbol can be an orthogonal frequency division multiplexing (OFDM) symbol or a discrete fourier transform-spread-of-dm (DFT-s-OFDM) symbol. Unless otherwise specified, the symbols in the embodiments of this application refer to time-domain symbols.

[0371] In this document, PDSCH, PUSCH, PDCCH, PUCCH, PSSCH, PSCCH, and PUSCH are merely examples of downlink data channel, uplink data channel, downlink control channel, uplink control channel, sidelink data channel, sidelink control channel, and uplink data channel, respectively. In different systems and scenarios, data channels and control channels may have different names, and the embodiments of this application do not limit this.

[0372] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), image processors, artificial intelligence processors, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0373] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a base station or terminal. The processor and storage medium can also exist as discrete components in a base station or terminal.

[0374] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0375] In the above embodiments, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0376] In this document, "at least one" means one or more. "More than one" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the related objects before and after are in an "or" relationship; in the formulas of this application, the character " / " indicates that the related objects before and after are in a "division" relationship. "Including at least one of A, B, and C" can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B, and C.

[0377] Furthermore, the numerical range a to b in this application refers to all integers and decimals including a and b, as well as those between a and b. For example, 0 to 1 refers to 0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1, and other decimals between 0 and 1, and the number of decimal places can be arbitrary.

[0378] It should be understood that in the various embodiments of this application, the terms "first," "second," and various numerical designations are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above processes does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0379] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0380] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0381] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0382] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0383] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0384] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0385] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, include: Receive first information from a first communication device on a first time domain resource, the first information including first data and preset information, the first data and the preset information being mapped onto each resource unit of the first time domain resource with a first power allocation coefficient; Input the first information into a preset AI model to obtain the first AI channel estimation result; The second information received from the first communication device is received on the second time domain resource. The second information includes the first data and the preset information. The first data and the preset information are mapped onto each resource unit of the second time domain resource with a second power allocation coefficient. The second information is input into the preset AI model to obtain the second AI channel estimation result; Send first result information to the first communication device. The first result information is used to determine the power allocation coefficient to be used. The first result information is determined based on the first AI channel estimation result and the second AI channel estimation result.

2. The method according to claim 1, characterized in that, The preset AI model corresponds to a preset power allocation coefficient. The difference between the first power allocation coefficient and the preset power allocation coefficient is less than a first threshold, and the difference between the second power allocation coefficient and the preset power allocation coefficient is less than the first threshold.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Receive or send configuration information, the configuration information including the correspondence between the first power allocation coefficient and the first time domain resource, and the correspondence between the second power allocation coefficient and the second time domain resource.

4. The method according to any one of claims 1 to 3, characterized in that, The first time-domain resource includes N1 time-domain resources, and the first information includes N1 pieces of information. The N1 time-domain resources and the N1 pieces of information correspond one-to-one, and N is an integer greater than or equal to 1. The second time-domain resource includes N2 time-domain resources, and the second information includes N2 pieces of information. The N2 time-domain resources and the N2 pieces of information correspond one-to-one, and N2 is an integer greater than or equal to 1.

5. The method according to any one of claims 1 to 4, characterized in that, The first result information includes the power allocation coefficient to be used; or, The first result information includes the first channel estimation result and the second channel estimation result.

6. A communication method, characterized in that, include: Send first information to a second communication device on a first time domain resource. The first information includes first data and preset information. The first data and the preset information are mapped onto each resource unit of the first time domain resource with a first power allocation coefficient. Send second information to the second communication device on the second time domain resource. The second information includes the first data and the preset information. The first data and the preset information are mapped to each resource unit of the second time domain resource with a second power allocation coefficient. The system receives first result information from the second communication device. The first result information is used to determine the power allocation coefficient to be used. The first result information is determined based on a preset AI model, the first information, and the second information. The preset AI model is used for channel estimation.

7. The method according to claim 6, characterized in that, The preset AI model corresponds to a preset power allocation coefficient. The difference between the first power allocation coefficient and the preset power allocation coefficient is less than a first threshold, and the difference between the second power allocation coefficient and the preset power allocation coefficient is less than the first threshold.

8. The method according to claim 6 or 7, characterized in that, The method further includes: Sending or receiving configuration information, the configuration information including the correspondence between the first power allocation coefficient and the first time domain resource, and the correspondence between the second power allocation coefficient and the second time domain resource.

9. The method according to any one of claims 6 to 8, characterized in that, The first time-domain resource includes N1 time-domain resources, and the first information includes N1 pieces of information. The N1 time-domain resources and the N1 pieces of information correspond one-to-one, and N1 is an integer greater than or equal to 1. The second time-domain resource includes N2 time-domain resources, and the second information includes N2 pieces of information. The N2 time-domain resources and the N2 pieces of information correspond one-to-one, and N2 is an integer greater than or equal to 1.

10. The method according to any one of claims 6 to 9, characterized in that, The first result information includes the power allocation coefficient to be used; or, The first result information includes the first channel estimation result and the second channel estimation result.

11. A communication method, characterized in that, include: Receive first information from a first communication device on a first time domain resource, the first information including first data and preset information, the first data and the preset information being mapped onto each resource unit of the first time domain resource with a first power allocation coefficient; The first AI model is determined based on the first information; The second information received from the first communication device is received on the second time domain resource. The second information includes the first data and the preset information. The first data and the preset information are mapped onto each resource unit of the second time domain resource with a second power allocation coefficient. Determine the second AI model based on the second information; The second result information is sent to the first communication device. The second result information is used to determine the power allocation coefficient to be used. The second result information is determined based on the performance of the first AI model and the performance of the second AI model.

12. The method according to claim 11, characterized in that, Determining the first AI model based on the first information includes: The first AI model is determined based on the first non-AI channel estimation result and the first information, and the first non-AI channel estimation result is determined based on the non-AI model. The step of determining the second AI model based on the second information includes: The second AI model is determined based on the second non-AI channel estimation result and the second information, and the second non-AI channel estimation result is determined based on the non-AI model.

13. The method according to claim 12, characterized in that, The method further includes: The third information received from the first communication device is received on a third time domain resource. The third information includes the first data and the preset information. The first data and the preset information are mapped on the third time domain resource with a third power allocation coefficient. The third time domain resource corresponds to the first time domain resource. The first non-AI channel estimation result is determined based on the non-AI model and the third information; Fourth information from the first communication device is received on a fourth time domain resource. The fourth information includes the first data and the preset information. The first data and the preset information are mapped on the fourth time domain resource with a fourth power allocation coefficient. The fourth time domain resource corresponds to the second time domain resource. The second non-AI channel estimation result is determined based on the non-AI model and the fourth information.

14. The method according to any one of claims 11 to 13, characterized in that, The first time-domain resource includes N1 time-domain resources, and the first information includes N1 pieces of information. The N1 time-domain resources and the N1 pieces of information correspond one-to-one, and N1 is an integer greater than or equal to 1. The second time-domain resource includes N2 time-domain resources, and the second information includes N2 pieces of information. The N2 time-domain resources and the N2 pieces of information correspond one-to-one, and N2 is an integer greater than or equal to 1.

15. The method according to any one of claims 11 to 14, characterized in that, The method further includes: Receive or send configuration information, the configuration information including the correspondence between the first power allocation coefficient and the first time domain resource, and the correspondence between the second power allocation coefficient and the second time domain resource.

16. The method according to any one of claims 11 to 15, characterized in that, The second result information includes the allocation coefficient to be used; or, The second result information includes the parameters of the first AI model and the second AI model.

17. A communication method, characterized in that, include: Send first information to a second communication device on a first time domain resource. The first information includes first data and preset information. The first data and the preset information are mapped onto each resource unit of the first time domain resource with a first power allocation coefficient. Send second information to the second communication device on the second time domain resource. The second information includes the first data and the preset information. The first data and the preset information are mapped to each resource unit of the second time domain resource with a second power allocation coefficient. The system receives second result information from the second communication device, the second result information being used to determine a power allocation coefficient to be used, the power allocation coefficient to be used being determined based on the first information and the second information.

18. The method according to claim 17, characterized in that, The method further includes: A third message is sent to the second communication device on a third time domain resource. The third message includes the first data and the preset information. The first data and the preset information are mapped on the third time domain resource with a third power allocation coefficient. The third time domain resource corresponds to the first time domain resource. The third message is used to determine the second result information. A fourth message is sent to the second communication device on a fourth time-domain resource. The fourth message includes the first data and the preset information. The first data and the preset information are mapped on the fourth time-domain resource using a fourth power allocation coefficient. The fourth time-domain resource corresponds to the second time-domain resource. The fourth message is used to determine the second result information.

19. The method according to claim 17 or 18, characterized in that, The first time-domain resource includes N1 time-domain resources, and the first information includes N1 pieces of information. The N1 time-domain resources and the N1 pieces of information correspond one-to-one, and N is an integer greater than or equal to 1. The second time-domain resource includes N2 time-domain resources, and the second information includes N2 pieces of information. The N2 time-domain resources and the N2 pieces of information correspond one-to-one, and N2 is an integer greater than or equal to 1.

20. The method according to any one of claims 17 to 19, characterized in that, The method further includes: Sending or receiving configuration information, the configuration information including the correspondence between the first power allocation coefficient and the first time domain resource, and the correspondence between the second power allocation coefficient and the second time domain resource.

21. The method according to any one of claims 17 to 20, characterized in that, The second result information includes the allocation coefficient to be used; or, The second result information includes the parameters of the first AI model and the second AI model.

22. A communication device, characterized in that, It includes modules or units for performing the method as described in any one of claims 1 to 5, or modules or units for performing the method as described in any one of claims 6 to 10, or modules or units for performing the method as described in any one of claims 11 to 16, or modules or units for performing the method as described in any one of claims 17 to 21.

23. A communication device, characterized in that, The device includes one or more processors, the processors being configured to execute a computer program or instructions stored in a memory, causing the device to perform the method of any one of claims 1 to 5, or to perform the method of any one of claims 6 to 10, or to perform the method of any one of claims 11 to 16, or to perform the method of any one of claims 17 to 21.

24. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions that, when executed by a communication device, implement the method as described in any one of claims 1 to 5, or the method as described in any one of claims 6 to 10, or the method as described in any one of claims 11 to 16, or the method as described in any one of claims 17 to 21.

25. A computer program product, characterized in that, Includes a computer program that, when run, implements the method as described in any one of claims 1 to 5, or the method as described in any one of claims 6 to 10, or the method as described in any one of claims 11 to 16, or the method as described in any one of claims 17 to 21.

Images