Wireless communication method and communication device

Abstract

Provided are a wireless communication method and a communication device. The method comprises: a first device receiving a first data signal and a first reference signal, wherein the first reference signal is non-orthogonally superposed with the first data signal. The first reference signal and the first data signal can be transmitted in a non-orthogonal superposition manner, that is, transmission resources occupied by the first reference signal can also be used for transmitting the first data signal. Thus, the present application can reduce the resource overhead for transmitting a first reference signal.

Description

Wireless communication method and communication device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a wireless communication method and a communication device. Background Art

[0002] Due to the complexity and time-varying nature of wireless channel environments, wireless communication systems require receivers to recover received signals based on channel estimation. In addition to transmitting data signals, the transmitter also transmits a series of reference signals known to the receiver over time-frequency resources. The receiver uses these reference signals to perform channel estimation. To improve signal reliability, the reference signals and data signals transmitted over multiple transmission resources are orthogonally transmitted. In orthogonal transmission, a given transmission resource can only be used to transmit one type of signal, resulting in low resource utilization.

[0003] Summary of the Invention

[0004] The present application provides a wireless communication method and a communication device. The following introduces various aspects involved in the present application.

[0005] In a first aspect, a wireless communication method is provided, the method comprising: a first device receiving a first data signal and a first reference signal; wherein the first reference signal and the first data signal are non-orthogonally superimposed.

[0006] In a second aspect, a wireless communication method is provided, the method comprising: a second device sending a first data signal and a first reference signal to a first device; wherein the first reference signal and the first data signal are non-orthogonally superimposed.

[0007] According to a third aspect, a communication device is provided. The communication device is a first device, and includes: a receiving unit configured to receive a first data signal and a first reference signal; wherein the first reference signal and the first data signal are non-orthogonally superimposed.

[0008] In a fourth aspect, a communication device is provided, which is a second device and includes: a sending unit, configured to send a first data signal and a first reference signal to a first device; wherein the first reference signal and the first data signal are non-orthogonally superimposed.

[0009] In a fifth aspect, a communication device is provided, comprising a processor and a memory, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the communication device executes part or all of the steps in the method of the first aspect and / or the second aspect.

[0010] In a sixth aspect, an embodiment of the present application provides a communication system, which includes the above-mentioned communication device. In another possible design, the system may also include other devices that interact with the communication device in the solution provided in the embodiment of the present application.

[0011] In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program enables a communication device to execute part or all of the steps in the methods of the above aspects.

[0012] In an eighth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a communication device to perform some or all of the steps of the methods described in each of the above aspects. In some implementations, the computer program product may be a software installation package.

[0013] In a ninth aspect, an embodiment of the present application provides a chip comprising a memory and a processor, wherein the processor can call and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.

[0014] In the present application, the first reference signal and the first data signal can be transmitted in a non-orthogonal superposition, that is, the transmission resources occupied by the first reference signal can also be used to transmit the first data signal. Therefore, the present application can reduce the resource overhead of transmitting the first reference signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] FIG1 is a flow chart of signal transmission in a wireless communication system to which an embodiment of the present application is applicable.

[0016] FIG2 is a schematic diagram of channel estimation and signal recovery applicable to an embodiment of the present application.

[0017] FIG3(a) to FIG3(c) show patterns of data symbols and pilot symbols under different configurations.

[0018] FIG4 shows a neural network model applicable to an embodiment of the present application.

[0019] FIG5 shows a neural network model applicable to an embodiment of the present application.

[0020] FIG6 shows a convolutional neural network applicable to an embodiment of the present application.

[0021] FIG7 shows a long short-term memory (LSTM) model applicable to an embodiment of the present application.

[0022] FIG8 shows a process of performing channel estimation based on a channel estimation module.

[0023] FIG9 is a wireless communication system 900 to which an embodiment of the present application is applicable.

[0024] FIG10 is a schematic flowchart of a wireless communication method provided in an embodiment of the present application.

[0025] FIG11 shows a solution for transmitting a first signal and a second signal based on a linear superposition method provided in an embodiment of the present application.

[0026] FIG12 shows an example diagram of non-orthogonal superposition of the second reference signal, the first reference signal, and the first data signal in multi-layer transmission.

[0027] FIG13 shows an example of a pattern in which a first reference signal and a second reference signal are orthogonally configured in the frequency domain, time domain, or time-frequency domain in transmission on the same layer or for the same user.

[0028] FIG14 is an example diagram of a method for achieving code domain orthogonality provided in an embodiment of the present application.

[0029] FIG15 shows an example of a pattern in which the first reference signal is orthogonally configured in the frequency domain, time domain, or time-frequency domain in transmission on different layers.

[0030] FIG16 is an example diagram of a method for achieving code domain orthogonality provided in an embodiment of the present application.

[0031] FIG17 is a schematic structural diagram of a first device 1700 provided in an embodiment of the present application.

[0032] FIG18 is a diagram showing an example structure of an artificial intelligence (AI) / machine learning (ML) receiver provided in Example 1.

[0033] FIG19 is a diagram showing an example structure of an AI / ML receiver provided in Example 2.

[0034] Figure 20 is a schematic structural diagram of a communication device provided in an embodiment of the present application.

[0035] Figure 21 is a schematic structural diagram of another communication device provided in an embodiment of the present application.

[0036] Figure 22 is a schematic structural diagram of a device for communication provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solution in this application will be described below with reference to the accompanying drawings.

[0038] Signal transmission process in wireless communication systems

[0039] Figure 1 is a flow chart of signal transmission in a wireless communication system to which an embodiment of the present application applies. As shown in Figure 1 , the signal transmission process in the wireless communication system can be roughly divided into the various signal processing processes S111 to S118 shown in Figure 1 . Some or all of the signal processing processes shown in Figure 1 can be implemented by a separate AI model. For specific implementation, please refer to the descriptions of Figures 5 to 8 .

[0040] In the channel coding process S111, the transmitter performs channel coding on the information to be transmitted to obtain a coded code stream. The information to be transmitted may be in the form of a bit stream.

[0041] In the modulation process S112 , the code stream is modulated into modulation symbols.

[0042] In the pilot insertion process S113, pilot symbols are inserted into the modulation symbols to form a pilot signal (or reference signal) to be transmitted, wherein the pilot symbols can be used by the receiver for channel estimation and symbol detection.

[0043] In the transmission signal S114, the above signal is carried on the channel and transmitted to the receiver. In the process of transmitting the signal through the channel, noise is usually superimposed.

[0044] In the channel estimation process S115, the receiver can perform channel estimation based on the pilot signal to obtain channel state information (CSI), and feed the CSI back to the transmitter through a feedback link for the transmitter to adjust channel coding, modulation, precoding, etc.

[0045] In the symbol detection process S116, symbol detection is performed on the received modulation symbols to obtain a detection result.

[0046] In the demodulation process S117, the received modulation symbols are demodulated based on the detection result to obtain a code stream.

[0047] In some embodiments, the demodulation process S117 may belong to the symbol detection process S116 .

[0048] In the channel decoding process S118, the code stream is decoded to obtain restored information, wherein the restored information may be in the form of a bit stream.

[0049] It should be understood that the signal processing processes S111 to S118 shown in Figure 1 are merely examples of common signal processing processes in wireless communication systems. Wireless communication systems may also include signal processing processes such as resource mapping, precoding, interference cancellation, and CSI measurement. These signal processing processes can also be implemented through separate AI models. For the sake of brevity, this application will not go into detail.

[0050] Channel Estimation

[0051] Due to the complexity and time-varying nature of wireless channel environments, in wireless communication systems (e.g., the wireless communication systems described above), a receiver needs to recover received signals based on channel estimation results. Figure 2 is a schematic diagram of channel estimation and signal recovery applicable to embodiments of the present application.

[0052] As shown in FIG2 , in step S210 , the transmitter transmits, in addition to the data signal, a series of pilot signals known to the receiver on the time-frequency resources, such as the channel state information-reference signal (CSI-RS) and the demodulation reference signal (DMRS).

[0053] In step S211, the transmitter transmits the above data signal and pilot signal to the transmitter through the channel.

[0054] The time-frequency resources occupied by the pilot signal are different from those occupied by the data signal.

[0055] In step S212, after receiving the pilot signal, the receiver may perform channel estimation. In one possible implementation, the receiver may estimate channel information of the channel transmitting the pilot signal based on the pre-stored pilot signal and the received pilot signal using a channel estimation algorithm (e.g., a least squares (LS) channel estimation method).

[0056] In step S213, the receiver may recover the channel information on all time-frequency resources using an interpolation algorithm based on the channel information of the channel transmitting the pilot sequence, for use in subsequent CSI feedback or data recovery.

[0057] Based on the above description combined with Figure 2, it can be seen that the time-frequency resources used to transmit pilot signals are different from the time-frequency resources used to transmit data signals. In other words, the symbols used to transmit data signals (referred to as "data symbols") and the symbols used to transmit pilot signals (referred to as "pilot symbols") are placed on different resource elements (REs). It can be seen that data symbols and pilot symbols are mutually orthogonal on time, frequency, or code-divided resources. That is, the same RE can only accommodate data symbols or pilot symbols; an RE that transmits pilot symbols cannot transmit data.

[0058] FIG3(a) to FIG3(b) show patterns of data symbols and pilot symbols under different configurations.

[0059] As shown in Figure 3(a), in a resource block (RB), pilot symbols are distributed every other symbol across multiple REs corresponding to symbol 2 within the RB. As shown in Figure 3(b), in an RB, pilot symbols occupy some of the multiple symbols corresponding to symbols 2 and 10 within the RB. As shown in Figure 3(c), in an RB, pilot symbols occupy multiple groups of REs within symbol 2 within the RB, where each group of REs includes two consecutive REs in the frequency domain.

[0060] Generally, different patterns in the patterns shown in Figures 3(a) to 3(c) can be adapted to different communication environments. In some implementations, when the terminal device is moving at a high speed and the channel characteristics vary rapidly, a pattern with a denser distribution of pilot symbols can be selected to help improve the accuracy of channel quality estimation for the entire RB. For example, the pattern shown in Figure 3(b) can be selected.

[0061] In other implementations, when the terminal device moves slowly and the channel characteristics vary slowly over time, a pattern with a sparser distribution of pilot symbols can be selected, which helps to reduce the overhead generated by transmitting pilot signals while ensuring the accuracy of channel quality estimation for the entire RB.

[0062] Neural Networks

[0063] In recent years, artificial intelligence research, exemplified by neural networks, has achieved remarkable success in many fields, and will continue to play a vital role in people's lives and production for a long time to come. A neural network can be understood as a computational model consisting of multiple interconnected neuron nodes. The connections between these nodes represent the weighted values ​​from input signals to output signals, often referred to as parameters. Each node performs a weighted summation of different input signals and outputs the result through a specific activation function.

[0064] The neuron structure can be shown in Figure 4. As shown in Figure 4, neurons can rely on activation functions to implement nonlinear mapping, where the input of the neuron can be recorded as A, and each dimension of the input is recorded as a j , the corresponding parameter is recorded as w j , together with the summation units (SU), the input is strengthened or weakened. In addition, the output of SU can be input into the activation function f to obtain the output t, where the value of j is 1, 2, ..., n.

[0065] Common neural networks include convolutional neural network (CNN), recurrent neural network (RNN), deep neural network (DNN), etc.

[0066] The following describes a neural network applicable to embodiments of the present application in conjunction with FIG5 . The neural network shown in FIG5 can be divided into three categories based on the location of different layers: input layer 510 , hidden layer 520 , and output layer 530 . Generally speaking, the first layer is the input layer 510 , the last layer is the output layer 530 , and the intermediate layers between the first and last layers are all hidden layers 520 .

[0067] The input layer 510 is used to input data, where the input data can be, for example, a received signal received by a receiver. The hidden layer 520 is used to process the input data, for example, decompress the received signal. The output layer 530 is used to output processed output data, for example, a decompressed signal.

[0068] As shown in Figure 5, a neural network consists of multiple layers, each of which contains multiple neurons. The neurons between layers can be fully connected or partially connected. For connected neurons, the output of the neurons in the previous layer can serve as the input of the neurons in the next layer.

[0069] CNN is a deep neural network with a convolutional structure, and its structure is shown in FIG6 , which may include an input layer 610 , a convolutional layer 620 , a pooling layer 630 , a fully connected layer 640 , and an output layer 650 .

[0070] Each convolutional layer 620 may include multiple convolution operators, where each neuron of the convolution operator may be locally connected to its input. A convolution operator, also known as a kernel, can be viewed as a filter that extracts specific information from the input signal. The convolution operator is essentially a parameter matrix, which is typically predefined.

[0071] The parameter values ​​in these parameter matrices need to be obtained through a lot of training in practical applications. The parameter matrices formed by the parameter values ​​obtained through training can extract information from the input signal, thereby helping CNN to make correct predictions.

[0072] When CNN has multiple convolutional layers, the initial convolutional layer tends to extract more general features, which can also be called low-level features. As the depth of CNN increases, the features extracted by the subsequent convolutional layers become more and more complex.

[0073] Pooling layer 630, because it is often necessary to reduce the number of training parameters, it is often necessary to periodically introduce a pooling layer after the convolution layer. For example, it can be a convolution layer followed by a pooling layer as shown in Figure 6, or it can be multiple convolution layers followed by one or more pooling layers. In the signal processing process, the purpose of the pooling layer includes reducing the spatial size of the extracted information. For example, the pooling layer can extract the local maximum or average value features of a certain layer. It can be seen that the pooling layer can effectively reduce the parameters of the network and mine local features, so that the convolutional neural network can converge quickly and achieve excellent performance.

[0074] The fully connected layer 640, after being processed by the convolution layer 620 and the pooling layer 630, is not sufficient for CNN to output the required output information. Because as mentioned above, the convolution layer 620 and the pooling layer 630 only extract features and reduce the parameters brought by the input data. However, in order to generate the final output information (for example, the bit stream of the original information transmitted by the transmitter), CNN also needs to use the fully connected layer 640. Generally, the fully connected layer 640 may include multiple hidden layers, and the parameters contained in the multiple hidden layers may be pre-trained based on relevant training data of a specific task type. For example, the task type may include decoding a data signal received by a receiver. For another example, the task type may also include channel estimation based on a pilot signal received by the receiver.

[0075] Following the multiple hidden layers in the fully connected layer 640, the final layer of the CNN is the output layer 650, which is used to output the results. Typically, the output layer 650 is configured with a loss function (e.g., a loss function similar to categorical cross entropy) to calculate the prediction error, or to evaluate the degree of difference between the result output by the CNN model (also known as the predicted value) and the ideal result (also known as the true value).

[0076] To minimize the loss function, the CNN model needs to be trained. In some implementations, the CNN model can be trained using a backpropagation algorithm (BP). The BP training process consists of a forward propagation process and a backward propagation process. During the forward propagation process (e.g., the propagation from 610 to 650 in Figure 6 is forward propagation), the input data is fed into the aforementioned layers of the CNN model, processed layer by layer, and transmitted to the output layer. If the output result differs significantly from the ideal result, the aforementioned loss function is minimized as the optimization goal, and the backward propagation process is switched to (e.g., the propagation from 650 to 610 in Figure 6 is backward propagation). The partial derivatives of the optimization goal with respect to each neuron weight are calculated layer by layer, forming the gradient of the optimization goal with respect to the weight vector, which serves as the basis for modifying the model parameters. The CNN training process is completed during the parameter modification process. When the aforementioned error reaches the desired value, the CNN training process ends.

[0077] It should be noted that the CNN shown in Figure 6 is only an example of a convolutional neural network. In specific applications, the convolutional neural network can also exist in the form of other network models, which is not limited in this embodiment of the present application.

[0078] The purpose of RNNs is to process sequential data. In traditional neural network models (for example, CNN models), each layer is fully connected, from the input layer to the hidden layer to the output layer, and the nodes within each layer are disconnected. However, these standard neural networks are inadequate for many problems. For example, to predict the next word in a sentence, you generally need to use the previous words, because the previous and next words in a sentence are not independent. RNNs are called recurrent neural networks because the current output of a sequence is also related to the previous output. Specifically, the network remembers previous information and applies it to the calculation of the current output. In other words, the nodes between hidden layers are no longer disconnected but connected, and the input to a hidden layer includes not only the output of the input layer but also the output of the previous hidden layer. In theory, RNNs can process sequence data of any length.

[0079] Training an RNN is similar to training a traditional ANN (artificial neural network). The BP error backpropagation algorithm is also used, but there is a slight difference. If the RNN is expanded, the parameters W, U, and V are shared, while traditional neural networks are not. Furthermore, when using the gradient descent algorithm, the output of each step depends not only on the network state at the current step, but also on the state of the network at the previous steps. For example, at t = 4, three steps need to be propagated backward, and various gradients need to be added to the three subsequent steps. This learning algorithm is called backpropagation through time (BPTT).

[0080] Given the existence of artificial neural networks and convolutional neural networks, why do we still need recurrent neural networks? The reason is simple. Both convolutional and artificial neural networks assume that elements are independent of each other, and that input and output are also independent, such as cats and dogs. However, in the real world, many elements are interconnected, such as the changes in stock prices over time. For example, someone said, "I love traveling, and my favorite place is Yunnan. I must visit __ someday." Everyone knows to fill in the blank with "Yunnan." This is because we infer this based on the context, but it is quite difficult for machines to do this. Therefore, recurrent neural networks were developed. Their essence is: they have the ability to remember, just like humans. Therefore, their output depends on the current input and memory. In a nutshell, RNNs are a unit structure that is reused.

[0081] The long short-term memory (LSTM) model is a commonly used RNN. As shown in Figure 7, LSTM introduces a new memory unit c t (also called "cell state"), which is used for linear cyclic information transmission and outputs information to the external state h of the hidden layer. t At each moment t, c t It records historical information up to the current moment. Unlike RNNs, which only consider the most recent state, memory cells determine which states should be retained and which should be forgotten, addressing the shortcomings of traditional RNNs in long-term memory.

[0082] Continuing to refer to FIG7, in order to achieve the above state selection, the memory unit introduces a gate control mechanism to control the path of information transmission, similar to the gate in the data circuit, "0" means closed, and "1" means open. The memory unit includes a forget gate 710, an input gate 720, and an output gate 730. Among them, the forget gate is used to control the memory unit c at the previous moment. t-1How much information needs to be forgotten? The input gate is used to control the candidate state at the current moment. How much information needs to be stored? The output gate is used to control the memory unit c at the current moment. t How much information needs to be output to the external state h t .

[0083] Channel estimation based on AI decoder

[0084] The channel estimation based on the AI ​​decoder aims to process the pilot signal received by the receiver using the AI-based channel estimation module to achieve channel estimation. The internal implementation of the AI-based channel estimation module can be a neural network such as DNN or CNN. Figure 8 shows the process of channel estimation based on the channel estimation module. Referring to Figure 8, the pilot signal received by the receiver 800 is used as the input of the channel estimation module 810. Accordingly, the channel estimation module 810 processes the input pilot signal to output channel information. In addition, in some implementations, in addition to the pilot signal, other auxiliary information can be added to improve the accuracy of the channel information output by the channel estimation module. For example, the original sequence of the pilot signal pre-stored by the receiver 800, the energy level of the pilot signal received by the receiver 800, the transmission delay when transmitting the pilot signal, or the noise when transmitting the pilot signal, etc. can also be input to the channel estimation module 810.

[0085] The above describes the communication process and terminology involved in the embodiments of the present application in conjunction with Figures 1 to 8, and the following describes the communication system applicable to the embodiments of the present application in conjunction with Figure 9.

[0086] Figure 9 illustrates a wireless communication system 900 to which an embodiment of the present application is applicable. The wireless communication system 900 may include communication devices. For example, the communication devices may include a network device 910 or a terminal device 920. The network device 910 may be a device that communicates with the terminal device 920. The network device 910 may provide communication coverage for a specific geographic area and may communicate with the terminal device 920 within the coverage area.

[0087] Figure 9 exemplarily shows a network device 910 and two terminal devices 920. Optionally, the wireless communication system 900 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area, which is not limited in this embodiment of the present application.

[0088] Optionally, the wireless communication system 900 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0089] Optionally, the terminal devices 920 may also communicate directly with each other. For example, two terminal devices 920 may communicate with each other via a device-to-device (D2D) link.

[0090] It should be noted that the following description uses the first device and the second device as examples. In some implementations, the first device may be the aforementioned network device 910, and accordingly, the second device may be the aforementioned terminal device 920. In other implementations, the first device may be the aforementioned terminal device 920, and accordingly, the second device may be the aforementioned network device 910. In still other implementations, the first device may be the aforementioned terminal device 920, and accordingly, the second device may be the aforementioned terminal device 920. This embodiment of the present application does not specifically limit this.

[0091] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth generation (5G) system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0092] The terminal device in the embodiments of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. The terminal device in the embodiments of the present application may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects, and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity that provides sidelink signals between UEs in V2X or D2D, etc. For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through the base station.

[0093] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmission point (TP), master station MeNB, secondary station SeNB, multi-standard radio (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), positioning node, etc. A base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. A base station can also refer to a communication module, modem or chip used to be set in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs base station functions in device-to-device D2D, vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. The base station can support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by the network equipment.

[0094] 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 based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0095] In some deployments, the network device in the embodiments of the present application may refer to a CU or a DU, or the network device may include a CU and a DU. The gNB may also include an AAU.

[0096] The network equipment and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal devices are located.

[0097] It should be understood that the communication devices referred to in this application may be network devices or terminal devices. For example, both the first device and the second device may be communication devices. For example, the first device may be a network device and the second device may be a terminal device. For another example, the first device may be a terminal device and the second device may be a network device. For another example, both the first device and the second device may be network devices or both may be terminal devices.

[0098] It should also be understood that all or part of the functions of the communication device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).

[0099] Currently, in related technologies, to improve signal reliability, reference signals and data signals transmitted over multiple transmission resources are transmitted in an orthogonal manner. The transmission resources may be REs. Reference signals can be used for channel estimation. In other words, reference signals may include the pilot signals described above. Orthogonal transmission can be understood as processing signals transmitted over multiple transmission resources into mutually orthogonal signals for transmission. The orthogonal signals are transmitted independently and do not interfere with each other. In other words, the orthogonal signals occupy different time and frequency domain resources.

[0100] In the scenario of orthogonal transmission, a certain transmission resource can only be used to transmit one signal, resulting in low utilization of the transmission resources. On the other hand, if the total transmission resources are fixed, if the number of transmission resources occupied by a certain signal increases, it means that the number of transmission resources available for transmitting another signal decreases, which may result in the other signal not being transmitted in a timely manner. For example, if the total transmission resources are fixed, if the number of transmission resources occupied by reference signals increases, it means that the number of transmission resources available for transmitting data signals decreases, which may result in the data signals not being transmitted in a timely manner. For another example, if the number of transmission resources occupied by data signals increases, it means that the number of transmission resources available for transmitting reference signals decreases, which may result in reduced accuracy of channel estimation based on reference signals.

[0101] As shown in Figure 2, orthogonal transmission of data and reference signals means that they occupy different REs. That is, they cannot occupy the same REs. If the reference signal occupies a large number of REs, the REs available for data signal transmission will be reduced, resulting in delayed data signal transmission. If the reference signal occupies a small number of REs, the accuracy of channel estimation based on the reference signal may be reduced.

[0102] To address the above issues, an embodiment of the present application provides a wireless communication method as shown in Figure 10. The method shown in Figure 10 can be performed by a first device and a second device. The first device and / or the second device can be a communication device.

[0103] The method shown in FIG. 10 may include step S1010 .

[0104] Step S1010: A first device receives a first data signal and a first reference signal sent by a second device.

[0105] The first reference signal and the first data signal can be superimposed non-orthogonally. That is, the first data signal and the first reference signal can be superimposed and transmitted on the same transmission resource (also called the "target transmission resource"). This transmission is also called non-orthogonal transmission. For example, the target transmission resource can be the first RE. That is, the first data signal and the first reference signal can both occupy the first RE.

[0106] In some embodiments, the first reference signal may include: CSI-RS, DMRS, phase-tracking reference signal (PT-RS), sounding reference signal (SRS), synchronization signal block (SS / PBCH block, SSB) or positioning reference signal (PRS), etc.

[0107] For ease of understanding, the following text introduces the non-orthogonal transmission method applicable to the embodiment of the present application in conjunction with Figure 11. It should be noted that the non-orthogonal transmission method applicable to the embodiment of the present application is not limited to this.

[0108] As shown in FIG11 , assuming that the target transmission resources for non-orthogonal transmission belong to a transmission resource set, the non-orthogonal superposition signals transmitted on one or more target transmission resources in the transmission resource set are represented by a matrix S. Accordingly, the matrix S is determined by the formula S = V⊙D + X⊙P, or in other words, the matrix S satisfies V⊙D + X⊙P. Here, the matrix V represents the data weights in the transmission resource set; the matrix X represents the pilot weights in the transmission resource set; the matrix D represents the first data signal transmitted on the target transmission resource in the transmission resource set; the matrix P represents the first reference signal transmitted on the target transmission resource in the transmission resource set; and ⊙ represents the Hadamard product.

[0109] A transmission resource set may include N×M transmission resources. For example, N may represent the number of subcarriers, and M may represent the number of time-domain OFDM symbols. M and N are positive integers. A transmission resource may be a RE. For example, a transmission resource set may include one RB, one subband, multiple consecutive RBs, or multiple consecutive subbands.

[0110] The matrix D can satisfy: matrix D∈Q N×M Where Q represents the data symbol set corresponding to the first data signal. The matrix P can satisfy: P∈P N×M Where P represents the pilot symbol set corresponding to the first reference signal. The matrix S can satisfy: S∈C N×M . Where C represents the set of complex numbers.

[0111] In some implementations, assuming that the energy threshold corresponding to the target transmission resource is 1, the matrix V can be determined based on the formula V = sqrt(A), and the matrix X can be determined based on the formula X = sqrt(1-A). Wherein, the matrix A∈[0,1], sqrt() represents the square root calculation. For example, the matrix V can satisfy: V∈[0,1] N×M . The matrix X can satisfy: X=sqrt(1-A)∈[0,1] N×M . Where A∈[0,1] N×M .

[0112] It should be noted that in the embodiments of the present application, there is no limit on the number of target transmission resources included in the transmission resource set. Accordingly, the dimensions of the matrices mentioned above (for example, matrix S, matrix V, matrix D, matrix P, matrix A, matrix V, and matrix X, etc.) are associated with the dimensions (or number) of the target transmission resources in the transmission resource set. For example, each element in the matrix may correspond to a transmission resource in the transmission resource set. In some implementations, the dimension of the matrix is ​​the same as the dimension of the target transmission resource in the transmission resource set. Taking the transmission resource set as RB as an example, the RB can be represented as including N rows and M columns of REs, and all REs in the RB are superimposed transmission resources. Accordingly, the matrix mentioned above can be a matrix with N rows and M columns.

[0113] Typically, the dimensions of the matrix above change when the target transmission resources allocated by the system change. For example, if the target transmission resources allocated by the system are two RBs, the dimensions of the matrix are the same as the dimensions of the REs in the two RBs. Assuming that an RB can be represented as consisting of N rows and M columns of REs, then two RBs contain 2N rows and 2M columns of REs, and the corresponding dimensions of the two RBs are 2N rows and 2M columns. In this case, if all REs in the two RBs are superimposed transmission resources, the dimensions of the matrix mentioned above can be a matrix with 2N rows and 2M columns.

[0114] Typically, for a non-orthogonally transmitted first reference signal, the first device may receive the first reference signal based on a first model. The first model helps improve signal reception performance. The first model may be an AI model and / or an ML model. In this case, the first device may also be referred to as an AI / ML receiver.

[0115] As described above, the implementation of functions such as channel estimation and symbol detection requires the reception and processing of reference signals. In the related technologies described above, reference signals occupy a large amount of system bandwidth resources. In the present application, the first reference signal and the first data signal can be transmitted in a non-orthogonal superposition, and the resources occupied by the first reference signal can also be used to transmit the first data signal. Therefore, the present application can reduce the resource overhead of the first reference signal and even achieve zero reference signal overhead.

[0116] In some embodiments, the first device may also receive a second reference signal.

[0117] The second reference signal may include one or more reference signals. The number of reference signals included in the second reference signal may be represented by N2. N2 may be a positive integer. In conjunction with the first reference signal and the second reference signal received by the first device, it can be understood that the first device may receive multiple reference signals.

[0118] The second reference signal may include one or more of the following: CSI-RS, DMRS, PT-RS, SRS, SSB, PRS, etc.

[0119] The second reference signal may be a different signal from the first reference signal. For example, the type of the second reference signal may be different from the type of the first reference signal. In another example, the function of the second reference signal may be different from the function of the first reference signal.

[0120] The second reference signal may be transmitted through a single layer or multiple layers. The second reference signal may be a reference signal for a single user or a reference signal for multiple users.

[0121] The second reference signal may be non-orthogonally superimposed on the first data signal.

[0122] FIG12 shows an example diagram of non-orthogonal superposition of the second reference signal, the first reference signal, and the first data signal in multi-layer transmission.

[0123] FIG12 illustrates an example in which a transmission resource set includes one RB, two layers of transmission, and the second reference signal includes one reference signal.

[0124] As shown in FIG12 , the symbol S after non-orthogonal superposition can satisfy: S = A1⊙D+A2⊙P1+A3⊙P2. Where D is the data matrix of the first data signal. D can satisfy: D∈Q N×M P1 is the pilot matrix of the first reference signal. P1 can satisfy: P1∈P N×M P2 is the pilot matrix of the second reference channel, and P2 can satisfy: P2∈P N×M P may represent a pilot symbol set. A1, A2, and A3 are power ratio allocation matrices of the first data signal, the first reference signal, and the second reference signal, respectively.

[0125] It should be noted that Figure 12 is only an example. That is, the technical solutions provided in the embodiments of the present application can also be applied to other situations. These other situations include one or more of the following: the number of reference signals in the second reference signal is greater than 1, the number of transmission layers is greater than 2 or equal to 1, and there are multiple users.

[0126] As can be seen from Figure 12, by allocating corresponding power to the first data signal, the first reference signal and the second reference signal, not only non-orthogonal superposition between the first data signal and the first reference signal can be achieved, but also non-orthogonal superposition between the first data signal and the second reference signal can be achieved.

[0127] The inventors of this application have discovered that the second reference signal may occupy the same transmission resources as the first reference signal, resulting in interference between the first and second reference signals. Continuing with Figure 12 , in layer 1, the first reference signal can occupy any RE within a RB, and the second reference signal can also occupy any RE within the RB. If the first and second reference signals occupy the same RE in layer 1, interference may occur between the first and second reference signals.

[0128] To address the above issues, the present application proposes that the first reference signal and the second reference signal may satisfy the following requirements: for transmission on the same layer and / or the same user, the orthogonality of the first reference signal and the second reference signal or the code domain correlation is less than or equal to a first threshold.

[0129] In some embodiments, orthogonality may refer to one or more of the following: frequency domain orthogonality, time domain orthogonality, time-frequency domain orthogonality, and code domain orthogonality.

[0130] In some embodiments, frequency domain orthogonality may refer to placing different reference signals (including a first reference signal and a second reference signal) at different frequency domain intervals. In some embodiments, time domain orthogonality may refer to placing different reference signals at different time domain intervals of OFDM symbols. In some embodiments, time-frequency domain orthogonality may refer to placing different reference signals at different time-frequency domain intervals of REs.

[0131] Figure 13 shows an example of a pattern in which the first reference signal and the second reference signal are orthogonally configured in the frequency domain, time domain, or time-frequency domain in transmissions on the same layer or for the same user. As shown in Figure 13, when the first reference signal and the second reference signal are orthogonal in the frequency domain, the first reference signal and the second reference signal are spaced apart at a subcarrier granularity. When the first reference signal and the second reference signal are orthogonal in the time domain, the first reference signal and the second reference signal are spaced apart at an OFDM symbol granularity. When the first reference signal and the second reference signal are orthogonal in the time-frequency domain, the first reference signal and the second reference signal are spaced apart at an RE granularity.

[0132] It should be noted that Figure 13 is merely an example, and this application does not limit the patterns of the first and second reference signals. For example, the patterns of the first and second reference signals may satisfy the following condition: only one reference signal is non-orthogonally superimposed on the first data signal on the same RE. In other words, this condition may include not placing multiple reference signals on the same RE.

[0133] In some embodiments, code domain orthogonality may refer to that the sequences of the first reference signal and the second reference signal are orthogonal. Code domain orthogonality may be achieved through code division multiplexing (CDM).

[0134] It can be understood that in the case of code domain orthogonality, the first reference signal and the second reference signal can be placed on the same RE, that is, the first RE can carry the first data signal, the first reference signal and the second reference signal at the same time.

[0135] As a possible embodiment, code domain orthogonality may satisfy: ||P1⊙P2|| F =0, where P1 represents the pilot matrix of the first reference signal, P2 represents the pilot matrix of the second reference signal, |||| F represents the Frobenius norm. P1 can satisfy P1∈C N×M . P2 can satisfy P2∈C N×M .

[0136] Figure 14 is an example diagram of a method for achieving code domain orthogonality provided by an embodiment of the present application. All N×M REs allocated by the system can be divided into G=NM / (N2+1) code groups. Wherein, N2 represents the number of reference signals contained in the second reference signal. The pilots of different layers in the group are distinguished by discrete Fourier transform orthogonal mask code (DFT-OMC), that is, the first reference signal sequence and the second reference signal sequence can be generated by the following method: p 1,g =s g ⊙c1;P 2,g =s g ⊙c2. Among them, p 1,g ∈C (N2+1)×1 and p 1,g ∈C (N2+1)×1 They represent the first reference signal symbol and the second reference signal symbol vectorized in the g∈[1,G]th group respectively. g ∈S (N2+1)×1 represents the reference signal seed sequence of group g, and S represents the set of available symbols with zero mean and average normalized power that constitute the seed sequence. For example, S can represent a binary phase shift keying (BPSK) or quadrature phase shift keying (QPSK) symbol set. c1∈C (N2+1)×1 and c2∈C (N2+1)×1 represents the DFT-OMC of the first reference signal and the second reference signal. Further, DFT vectors c1 and c2 can be used to generate. For example, c z =[1,...,e - j2πk(z- 1) / (N2+1) ,...,e - j2π(N2)(z - 1) / (N2+1) ] T . Where, k∈[0,N2], z∈{1,2}.

[0137] It should be noted that the present application does not limit the method for achieving code domain orthogonality. The above method is only an example of a method for achieving code domain orthogonality, and other methods can be used to achieve code domain orthogonality.

[0138] It can be understood that compared with related technologies (such as frequency division multiplexing (FDM)) that require some REs to be vacated for reference signals, CDM can ensure that the REs carrying data in the layer can be equipped with pilots while achieving orthogonality of the pilot signals within the layer, so as to maintain the accurate channel estimation gain of the superimposed pilot while avoiding interference from the pilot signals within the layer.

[0139] In some embodiments, the code domain correlation being less than or equal to the first threshold may refer to: ||P1⊙P2|| F ≤T1. Wherein, P1 represents the pilot matrix of the first reference signal, P2 represents the pilot matrix of the second reference signal, and T1 represents the first threshold. The first threshold can be a small positive number.

[0140] That is, this technical solution can reduce the code domain correlation between the first reference signal and the second reference signal, thereby avoiding interference between the first reference signal and the second reference signal as much as possible.

[0141] This application can also be used for multi-user and / or multi-layer transmission. Reference signals transmitted for different users and / or different layers may interfere with each other. Continuing with Figure 12 , the first reference signal of layer 1 and the first reference signal of layer 2 may occupy the same RE, resulting in interference between the first reference signal of layer 1 and the first reference signal of layer 2.

[0142] The present application proposes that the first reference signal may satisfy the following requirements: the first reference signal of the first layer and the first reference signal of the second layer are orthogonal, or the code-domain correlation is less than or equal to a second threshold; and / or the first reference signal for the first user and the first reference signal for the second user are orthogonal, or the code-domain correlation is less than or equal to a third threshold. Both the second and third thresholds are positive numbers.

[0143] When transmitting the second reference signal, the second reference signal may satisfy: the second reference signal of the first layer and the second reference signal of the second layer are orthogonal or the code domain correlation is less than or equal to the second threshold; and / or the second reference signal for the first user and the second reference signal for the second user are orthogonal or the code domain correlation is less than or equal to a third threshold.

[0144] The first layer may be the lth layer in the multi-layer system, and the second layer may be the jth layer in the multi-layer system. j and l are used to indicate the order or index of the first layer and the second layer in the multi-layer system, respectively. Both j and l can be non-negative integers. j and l can satisfy j ≠ l.

[0145] The first user may be the lth user in a multi-user group, and the second user may be the jth user in the multi-user group. j and l are used to indicate the order or index of the first user and the second user in the multi-user group, respectively. Both j and l can be non-negative integers. j and l can satisfy j≠l.

[0146] It should be noted that the solution for multi-user transmission in this application is similar to the solution for multi-layer transmission. The following discussion uses the technical solution for multi-layer transmission as an example. Replacing "first layer" with "first user" and "second layer" with "second user" yields the technical solution for multi-user transmission.

[0147] In some embodiments, orthogonality may refer to one or more of the following: frequency domain orthogonality, time domain orthogonality, time-frequency domain orthogonality, and code domain orthogonality.

[0148] In some embodiments, frequency domain orthogonality may refer to placing the same reference signal of different layers on subcarriers with different frequency domain intervals, and / or placing the same reference signal of different users on subcarriers with different frequency domain intervals. In some embodiments, time domain orthogonality may refer to placing the same reference signal of different layers on OFDM symbols with different time domain intervals, and / or placing the same reference signal of different users on OFDM symbols with different time domain intervals. In some embodiments, time-frequency domain orthogonality may refer to placing the same reference signal of different layers on time-frequency domain intervals RE, and / or placing the same reference signal of different users on time-frequency domain intervals RE.

[0149] Figure 15 shows examples of patterns in which the first reference signal is orthogonally configured in the frequency domain, time domain, or time-frequency domain in transmission at different layers. The first layer may be layer 1 in Figure 15; the second layer may be layer 2 in Figure 15. As shown in Figure 15, in the case of frequency domain orthogonality, the first reference signal of layer 1 and the first reference signal of layer 2 are spaced at intervals of subcarriers. In the case of time domain orthogonality, the first reference signal of layer 1 and the first reference signal of layer 2 are spaced at intervals of OFDM symbols. In the case of time-frequency domain orthogonality, the first reference signal of layer 1 and the first reference signal of layer 2 are spaced at intervals of REs.

[0150] The patterns of reference signals for different users may be similar to Figure 15. For example, the "layer 1 first reference signal" in Figure 15 may represent the reference signal for the first user; and the "layer 2 first reference signal" in Figure 15 may represent the reference signal for the second user.

[0151] It should be noted that Figure 15 is only an example, and this application does not limit the patterns of the first reference signal of the first layer and the first reference signal of the second layer. For example, the pattern of the first reference signal may meet the following conditions: only one layer or the first reference signal for one user is non-orthogonally superimposed on the first data signal on the same RE.

[0152] In some embodiments, the first reference signals of different layers or for different users may be orthogonal in the code domain. For example, the code domain orthogonality may satisfy: || P' l ⊙P' j || F = 0. Where, P' l represents the pilot matrix of the first reference signal of the first layer or the first reference signal for the first user, P' j The pilot matrix representing the first reference signal of the second layer or the first reference signal for the second user. l Can satisfy P' l ∈C N×M P' j Can satisfy P' j ∈C N×M .

[0153] Figure 16 is an example diagram of a method for achieving code domain orthogonality provided by an embodiment of the present application. All N×M REs allocated by the system can be divided into G=NM / (N2+1) code groups. Wherein, N2 represents the number of reference signals contained in the second reference signal. The pilots of different layers in the group are distinguished by DFT-OMC. In other words, the pilot sequence can be generated by the following method p' l,g =s' g ⊙c' l Where p' l,g ∈C L×1 represents the first vectorized reference signal symbol in the g∈[1,G]th group of the l∈[1,L]th layer, s' g ∈S l×1 represents the first reference signal seed sequence of the gth group, and S represents an available set of symbols with zero mean and average normalized power constituting the seed sequence, such as a BPSK or QPSK symbol set. l ∈C (N2+1)×1 Denotes the DFT-OMC of the first reference signal of layer l∈[1,L]. Similarly, the DFT vector pair c' can be usedl Generate, i.e. c' l =[1,...,e-j2πk(l-1) / L,...,e-j2π(L-1)(l-1) / L] T . Where k∈[0,L-1].

[0154] It should be noted that the present application does not limit the method for achieving code domain orthogonality. The above method is only an example of a method for achieving code domain orthogonality, and other methods can be used to achieve code domain orthogonality.

[0155] It can be understood that compared with related technologies (such as FDM) that require some REs to be left empty for reference signals, CDM can achieve inter-layer orthogonality while ensuring that REs carrying data within a layer can be equipped with pilots, so as to maintain the accurate channel estimation gain of the superimposed pilots while avoiding inter-layer interference.

[0156] In some embodiments, the code domain correlation being less than or equal to the second threshold may refer to: || P' l ⊙P' j || F ≤T2. Among them, P' l represents the pilot matrix of the first layer or the first reference signal, P' j represents the pilot matrix of the first reference signal of the second layer, and T2 represents the second threshold.

[0157] The second threshold can be a small positive number. That is, this technical solution can reduce the code domain correlation between the first reference signal of the first layer and the first reference signal of the second layer, thereby avoiding interference between the first reference signals of different layers as much as possible.

[0158] In some embodiments, the code domain correlation being less than or equal to the third threshold may refer to: || P' l ⊙P' j || F ≤T3. Among them, P' l represents the pilot matrix of the first reference signal for the first user, P' j represents the pilot matrix of the first reference signal for the second user, and T3 represents the third threshold.

[0159] The third threshold may be a small positive number. That is, this technical solution can reduce the code domain correlation between the first reference signal for the first user and the first reference signal for the second user, thereby minimizing interference between the first reference signals of different users.

[0160] It is understandable that frequency domain orthogonality, time domain orthogonality, or time-frequency domain orthogonality require some REs to be vacated to achieve low interference between reference signals. However, for code domain orthogonality or code domain low correlation, low interference between reference signals can be achieved even if different reference signals or reference signals for different layers / users are superimposed on any RE. In other words, the present application can use a reference signal that is non-orthogonal to the first data signal to perform more accurate channel estimation, perception, or synchronization while reducing interference. In addition, code domain orthogonality can abandon the concept of reference signal patterns in the time domain, frequency domain, and time-frequency domain orthogonality, thereby avoiding more cumbersome design of the system to support different patterns.

[0161] As described above, the reference signal may be received and processed using the first model. For example, the first device may process the first reference signal using the first model.

[0162] In order to make the first device adapt to different system configurations, the related art proposes the following solution 1 and solution 2.

[0163] Solution 1 proposes mixing multiple data types together to train a generalized model. However, Solution 1 has a narrow scope of applicability. For example, Solution 1 can address different system configurations, such as transmission speed and / or channel conditions within a cell. However, Solution 1 struggles to train a suitable generalized model for scenarios with varying bandwidths, different numbers of transmission layers, and different MCS configurations, which directly affect the output dimensions of the first model.

[0164] Solution 2 addresses situations where the output dimensions or structure of the first model may differ. For example, different bandwidths, different numbers of transmission layers, and different MCS configurations can directly affect the output dimensions of the first model. In this case, the structure of the first model will change. Solution 2's solution involves training multiple models and relying on a model switching mechanism to change the model structure. Understandably, this model switching mechanism introduces signaling redundancy in the system.

[0165] In summary, in related technologies, a model can mostly only be applied to scenarios where the system configuration remains unchanged or changes slightly, and has low generalization and scalability.

[0166] To address the above issues, this application proposes that the output of the first model is determined based on the values ​​that can be configured in the communication system. The output of the first model can be understood as the output dimension of the first model, that is, the structure of the first model. It is understood that the output of the first model can be determined not by the actual configuration of the communication system, but rather based on the values ​​that can be configured in the communication system. Therefore, the first model can adapt to different communication system configurations, thereby making the first model highly generalizable and scalable.

[0167] It should be noted that the values ​​that can be configured in the communication system may include one or more of the following values: number of transmission layers, bandwidth, MCS, and number of transmission users. In other words, for the scenario involved in the above-mentioned solution 2, this application can train a first model to meet the requirements, thereby avoiding the processing complexity and signaling redundancy caused by training multiple models.

[0168] In addition, the values ​​that can be configured in the communication system may also include other configuration information, which is not limited in this application.

[0169] In some embodiments, the output of the first model can be determined based on a maximum value that can be configured for the communication system. If the actual configuration of the communication system is within the maximum value, determining the output of the first model based on the maximum value can ensure that the output of the first model includes the output corresponding to the actual configuration. In other words, even if the configuration of the communication system changes, the output of the first model can still cover different system configurations.

[0170] Optionally, the first device may crop the output of the first model so that the cropped output of the first model matches the actual configuration of the communication system. For example, the dimensions of the tensor output by the first model may be output with values ​​that are configurable by the communication system. The first device may crop the output along the corresponding dimensions so that the cropped output matches the actual configuration.

[0171] In some embodiments, the input of the first model may include first configuration information. The first configuration information may be used to indicate configuration, transmission, etc. of the communication system and / or the first device.

[0172] For example, the first configuration information can be used to indicate one or more of the following information: the actual configuration of the communication system, the configuration of the first reference signal, the moving speed of the first device, the scenario in which the first device is located, and the cell in which the first device is located.

[0173] The configuration of the first reference signal may include one or more of the following information: information on power allocation of the first data signal and the first reference signal, a sequence of the first reference signal, and a matrix of the first reference signal.

[0174] When the second reference signal is also non-orthogonally superposed with the first data signal, the first configuration information may further include a configuration of the second reference signal. The configuration of the second reference signal may include one or more of the following information: information on power allocation between the second data signal and the second reference signal, a sequence of the second reference signal, and a matrix of the second reference signal.

[0175] This application does not limit the method for indicating the first configuration information. For example, the first configuration information can directly indicate the information described above. For another example, the first configuration information can indicate the index of the information described above.

[0176] In some embodiments, the first configuration information may directly indicate one or more of the following information: the number of transmission layers, the number of transmission users, bandwidth, MCS, cell, first reference signal configuration, second reference signal configuration, terminal speed, and scenario. In some embodiments, the first configuration information may indicate an index to one or more of the following information: the number of transmission layers, the number of transmission users, bandwidth, MCS, cell, first reference signal configuration, second reference signal configuration, terminal speed, and scenario.

[0177] In some embodiments, the configuration of the first reference signal may include one or more of the following: pattern information for allocating power between the first data and the first reference signal, and a sequence of the first reference signal. In some embodiments, the configuration of the first reference signal may also indicate an index of the pattern and / or an index of the sequence information. The configuration of the second reference signal is similar to that of the first reference signal and will not be further described in this application.

[0178] As described above, the first device may tailor the output of the first model. Exemplarily, the tailoring may be performed based on the first configuration information. For example, the output of the first model may be output based on one or more of the maximum number of transmission layers, the maximum bandwidth, and the maximum modulation order corresponding to the MCS configured in the system, and the first model output may be tailored based on the first configuration information to obtain demodulation information that complies with the first configuration information.

[0179] In some embodiments, the first model can be used to perform one or more of the following operations: channel estimation, symbol detection, and channel decoding. When the first model performs channel estimation, the first model can also be referred to as a channel estimation model. When the first model performs channel estimation and symbol detection, the first model can be referred to as an integrated receiver model for joint channel estimation and symbol detection. When the first model performs channel estimation, symbol detection, and channel decoding, the first model can be referred to as an integrated receiver model for joint channel estimation, symbol detection, and channel decoding.

[0180] Exemplarily, depending on the function of the first model, the output of the first model can be: an estimated channel (the first model is a channel estimation model), a log-likelihood ratio (the first model is an integrated receiver model for joint channel estimation and symbol detection), or a received bit stream (the first model is an integrated receiver model for joint channel estimation, symbol detection, and channel decoding).

[0181] Figure 17 is a schematic structural diagram of a first device 1700 provided in an embodiment of the present application. The first device 1700 can implement the technical solution provided in the present application based on AI / ML. The first device 1700 can also be called an AI / ML receiver.

[0182] The first device 1700 may include a first model 1710 and a cropping module 1720 .

[0183] The first model 1710 may be implemented based on a neural network, which may process according to one or more dimensions corresponding to the maximum possible number of transmission layers, bandwidth, MCS, and other factors that may affect the output dimension.

[0184] For the first model 1710, the input of the first model 1710 may include, for example, one or more of the currently configured number of transmission layers, bandwidth, MCS, etc. For another example, the input of the first model 1710 may include a first reference signal and / or a second reference signal. For another example, the input of the first model 1710 may include a signal received by the first device 1700.

[0185] For the output of the first model 1710, the cropping module 1720 can perform cropping according to one or more of the currently configured number of transmission layers, bandwidth, MCS and other factors that may affect the output dimension, thereby obtaining one or more of the estimated channel, log-likelihood ratio, and received bit stream.

[0186] For ease of understanding, the AI / ML receiver provided in this application is described below through Example 1 and Example 2.

[0187] Example 1

[0188] Figure 18 is a diagram illustrating an example structure of an AI / ML receiver provided in Example 1. Figure 18 illustrates a technical solution for MCS generalization of an integrated receiver.

[0189] For the communication system applicable to Figure 18, the resource unit allocated by the communication system is N subcarriers × M time domain OFDM symbols, the system configuration is MCS = m, L-layer transmission, and no second reference signal. In the model structure shown in Figure 18, the overall structure has a convolution kernel number of D and a residual block number of N. block The residual convolutional network is used as the main skeleton.

[0190] It should be noted that Example 1 may also use other network structures as the network design and basic framework, and this application does not impose any restrictions on this.

[0191] First, the input of the model includes the MCS index m indicating the coding and modulation scheme as auxiliary information to guide the model to process the signal of the target MCS configuration. The scalar m is copied and tiled into the MCS information tensor M∈C N×M×1 To facilitate the signal processing of the model, the complex received signal and the first reference signal tensor are converted into real tensors Y∈C N×M×2Nr and P∈C N×M×L .

[0192] Furthermore, the MCS information tensor, the received signal tensor and the first reference signal tensor are concatenated to obtain a feature map T∈C N×M×2(Nr+L)+1 And sent to the subsequent residual convolutional network for processing.

[0193] For example, the specific structure of the residual block can be shown on the right side of Figure 18. The residual block may include: batch normalization, convolution (conv), ReLU activation function, summation (add), etc.

[0194] The AI / ML integrated receiver outputs the log-likelihood ratio tensor V∈C after processing N×M×L×Qmax . Where Q max Indicates the maximum number of bits per symbol corresponding to the maximum modulation order among all possible MCS types supported by the system. The processing of the AI / ML integrated receiver may include convolution and / or reshaping. The convolution filter may satisfy filters = LQ max .

[0195] Furthermore, in V∈C N×M×L×Qmax The last dimension of the tensor is cropped according to the currently set MCS to obtain the final output log-likelihood ratio tensor V out ∈C N×M×L×Q The data is then sent to the subsequent channel decoding module. Q represents the number of bits per symbol corresponding to the modulation order of the configured MCS.

[0196] Example 2

[0197] Figure 19 is a diagram illustrating an example of an AI / ML receiver structure provided in Example 2. Figure 19 illustrates a technical solution for generalization of an integrated receiver layer.

[0198] For the communication system applicable to Figure 19, the resource unit allocated by the communication system is N subcarriers × M time domain OFDM symbols, the system configuration is MCS = m, L layer transmission, and no second reference signal. In the model structure shown in Figure 19, the overall structure has a convolution kernel number D and a residual block number N. block The residual convolutional network is used as the main skeleton.

[0199] It should be noted that Example 2 may also use other network structures as the network design and basic framework, and this application does not impose any restrictions on this.

[0200] First, the input of the model includes the number of transmission layers L configured by the system as auxiliary information to guide the model to process the signal of the target transmission layer number. The scalar L is copied and rolled out as the layer number information tensor L∈C N×M×1 To facilitate the signal processing of the model, the complex received signal and the first reference signal tensor are converted into real tensors Y∈C N×M×2Nr and P∈C N×M×L .

[0201] Furthermore, the layer number information tensor, the received signal tensor and the first reference signal tensor are concatenated to obtain the feature map T∈C N×M×2 (Nr+L)+1 And sent to the subsequent residual convolutional network for processing.

[0202] For example, the specific structure of the residual module can be shown on the right side of Figure 19. The residual module may include: batch normalization, convolution (conv), ReLU activation function, summation (add), etc.

[0203] The AI / ML integrated receiver outputs the log-likelihood ratio tensor after processing using V∈C N×M×Lmax×Q , where Q represents the number of bits per symbol corresponding to the MCS configured in the system, and L max Indicates the maximum number of transmission layers that the system can support. N×M×Lmax×Q The third dimension of the tensor is cut according to the current number of transmission layers L, and the final output log-likelihood ratio tensor V is obtained. out ∈C N×M×L×Q And sent to the subsequent channel decoding module.

[0204] It is understandable that Example 1 and Example 2 can be implemented separately or in combination, and this application does not limit this.

[0205] For example, if embodiment 1 and embodiment 2 are implemented together, the AI / ML integrated receiver can output the log-likelihood ratio tensor after processing using V∈C N×M×Lmax×Qmax Among them, Q max Indicates the maximum number of bits per symbol corresponding to the maximum modulation order among all possible MCS types supported by the system. max Indicates the maximum number of transmission layers that the system can support. N×M×Lmax×Qmax The third dimension of the tensor is cut according to the current number of transmission layers L, in V∈C N×M×Lmax×Qmax The last dimension of the tensor is clipped according to the currently set MCS to obtain the final output log-likelihood ratio tensor V out ∈C N×M×L×QThe data is then sent to the subsequent channel decoding module. Q represents the number of bits per symbol corresponding to the modulation order of the configured MCS.

[0206] It should be noted that when the first model is a separate channel estimation model, the log-likelihood ratio output in Examples 1 and 2 can be replaced with an estimated channel tensor. The difference in implementation can be that the label of the log-likelihood ratio tensor is replaced with the channel tensor as the label during the training phase.

[0207] It should be noted that, in some embodiments, the RB mentioned above may also be referred to as a physical resource block (PRB), that is, PRB and RB may be interchangeable.

[0208] The method embodiments of the present application are described in detail above, and the device embodiments of the present application are described in detail below. It should be understood that the description of the method embodiments corresponds to the description of the device embodiments, so for parts not described in detail, reference can be made to the above method embodiments.

[0209] FIG20 is a schematic structural diagram of a communication device 2000 provided in an embodiment of the present application. The communication device 2000 is a first device and includes a receiving unit 2010.

[0210] The receiving unit 2010 is configured to receive a first data signal and a first reference signal, wherein the first reference signal and the first data signal are non-orthogonally superimposed.

[0211] In an optional embodiment, the receiving unit 2010 may be a transceiver 2230. The communication device 2000 may further include a processor 2210 and a memory 2220, as specifically shown in FIG22 .

[0212] FIG21 is a schematic structural diagram of a communication device 2100 provided in an embodiment of the present application. The communication device 2100 is a second communication device and includes a sending unit 2110.

[0213] The sending unit 2110 is configured to send a first data signal and a first reference signal to a first device; wherein the first reference signal and the first data signal are non-orthogonally superimposed.

[0214] In an optional embodiment, the sending unit 2110 may be a transceiver 2230. The communication device 2100 may further include a processor 2210 and a memory 2220, as specifically shown in FIG22 .

[0215] Figure 22 is a schematic block diagram of a communication device according to an embodiment of the present application. The dashed lines in Figure 22 indicate that the unit or module is optional. Device 2200 may be used to implement the method described in the above method embodiment. Device 2200 may be a chip, a terminal device, or a network device.

[0216] The device 2200 may include one or more processors 2210. The processor 2210 may support the device 2200 to implement the method described in the method embodiment above. The processor 2210 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0217] The apparatus 2200 may further include one or more memories 2220. The memories 2220 store programs that can be executed by the processor 2210, causing the processor 2210 to perform the methods described in the above method embodiments. The memories 2220 may be independent of the processor 2210 or integrated into the processor 2210.

[0218] The apparatus 2200 may further include a transceiver 2230. The processor 2210 may communicate with other devices or chips via the transceiver 2230. For example, the processor 2210 may transmit and receive data with other devices or chips via the transceiver 2230.

[0219] The present invention also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to the communication device provided in the present invention, and the program enables a computer to execute the method performed by the communication device in each embodiment of the present invention.

[0220] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to the communication device provided in the present application, and the program causes a computer to execute the method performed by the communication device in each embodiment of the present application.

[0221] The embodiments of the present application also provide a computer program. The computer program can be applied to the communication device provided in the embodiments of the present application, and the computer program enables a computer to execute the method executed by the communication device in each embodiment of the present application.

[0222] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application.

[0223] It should be understood that the terms "first," "second," "third," and "fourth," etc. in the specification, claims, and drawings of this application are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0224] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0225] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0226] In the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and indication, configuration and configuration, etc.

[0227] In the embodiments of the present application, "pre-definition" or "pre-configuration" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device and a network device). The present application does not limit the specific implementation method. For example, pre-definition may refer to information defined in a protocol.

[0228] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0229] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0230] In the embodiments of this application, the term "include" can refer to direct inclusion or indirect inclusion. Alternatively, the term "include" in the embodiments of this application can be replaced with "indicates" or "is used to determine." For example, "A includes B" can be replaced with "A indicates B" or "A is used to determine B."

[0231] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean 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 the present application.

[0232] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0233] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0234] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0235] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0236] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: include: The first device receives a first data signal and a first reference signal; The first reference signal and the first data signal are non-orthogonally superimposed.

2. The method according to claim 1, characterized in that Also includes: The first device receives a second reference signal; The second reference signal is non-orthogonally superimposed with the first data signal, and the first reference signal and the second reference signal satisfy: For transmission on the same layer and / or for the same user, the orthogonality or code domain correlation of the first reference signal and the second reference signal is less than or equal to a first threshold.

3. The method according to claim 2, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P1⊙P2|| F =0, where P1 represents the pilot matrix of the first reference signal, P2 represents the pilot matrix of the second reference signal, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

4. The method according to claim 2 or 3, characterized in that: The second reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

5. The method according to any one of claims 1 to 4, characterized in that The first reference signal is transmitted through the first layer and the second layer, and / or the first reference signal is a reference signal for the first user and the second user, and the first reference signal satisfies: The orthogonality or code domain correlation of the first reference signal of the first layer and the first reference signal of the second layer is less than or equal to a second threshold; and / or, The orthogonality or code domain correlation of the first reference signal for the first user and the first reference signal for the second user is less than or equal to a third threshold.

6. The method according to claim 5, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P' l ⊙P' j || F =0, where P' l represents the pilot matrix of the first reference signal of the first layer or the first reference signal for the first user, P' j A pilot matrix representing the first reference signal of the second layer or the first reference signal for the second user, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

7. The method according to any one of claims 2 to 6, characterized in that: The orthogonality includes: frequency domain orthogonality, time domain orthogonality, time-frequency domain orthogonality or code domain orthogonality.

8. The method according to any one of claims 1 to 7, characterized in that The first reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

9. The method according to any one of claims 1 to 8, characterized in that The non-orthogonal superposition includes: the first data signal and the first reference signal both occupy a first resource element RE.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: The first device processes the first reference signal using a first model; The output of the first model is determined based on a value that can be configured by the communication system.

11. The method according to claim 10, characterized in that The output of the first model is determined based on a maximum value that the communication system can configure.

12. The method according to claim 10 or 11, characterized in that: The values ​​that can be configured in the communication system include one or more of the following values: number of transmission layers, bandwidth, MCS, and number of transmission users.

13. The method according to any one of claims 10 to 12, characterized in that: The method further comprises: The first device crops the output of the first model; The output of the first model after trimming matches the actual configuration of the communication system.

14. The method according to any one of claims 10 to 13, characterized in that: The input of the first model includes first configuration information, where the first configuration information is used to indicate one or more of the following information: The actual configuration of the communication system; configuration of the first reference signal; a moving speed of the first device; The scene in which the first device is located; The cell where the first device is located.

15. The method according to claim 14, characterized in that The configuration of the first reference signal includes one or more of the following information: information on power allocation of the first data signal and the first reference signal; A sequence of the first reference signal.

16. The method according to any one of claims 10 to 15, characterized in that The first model is used to perform one or more of the following operations: channel estimation, symbol detection, and channel decoding.

17. The method according to any one of claims 10 to 16, characterized in that The first model is an artificial intelligence AI model.

18. A wireless communication method, characterized in that: include: The second device sends a first data signal and a first reference signal to the first device; The first reference signal and the first data signal are non-orthogonally superimposed.

19. The method according to claim 18, characterized in that Also includes: The second device sends a second reference signal to the first device; The second reference signal is non-orthogonally superimposed with the first data signal, and the first reference signal and the second reference signal satisfy: For transmission on the same layer and / or for the same user, the orthogonality or code domain correlation of the first reference signal and the second reference signal is less than or equal to a first threshold.

20. The method according to claim 18, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P1⊙P2|| F =0, where P1 represents the pilot matrix of the first reference signal, P2 represents the pilot matrix of the second reference signal, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

21. The method according to claim 18 or 19, characterized in that The second reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

22. The method according to any one of claims 18 to 21, characterized in that The first reference signal is transmitted through the first layer and the second layer, and / or the first reference signal is a reference signal for the first user and the second user, and the first reference signal satisfies: The orthogonality or code domain correlation of the first reference signal of the first layer and the first reference signal of the second layer is less than or equal to a second threshold; and / or, The orthogonality or code domain correlation of the first reference signal for the first user and the first reference signal for the second user is less than or equal to a third threshold.

23. The method according to claim 22, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P' l ⊙P' j || F =0, where P' l represents the pilot matrix of the first reference signal of the first layer or the first reference signal for the first user, P' j A pilot matrix representing the first reference signal of the second layer or the first reference signal for the second user, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

24. The method according to any one of claims 19 to 23, characterized in that The orthogonality includes: frequency domain orthogonality, time domain orthogonality, time-frequency domain orthogonality or code domain orthogonality.

25. The method according to any one of claims 18 to 24, characterized in that The first reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

26. The method according to any one of claims 18 to 25, characterized in that The non-orthogonal superposition includes: the first data signal and the first reference signal both occupy a first resource element RE.

27. A communication device, characterized in that: The communication device is a first device, and the communication device includes: A receiving unit, configured to receive a first data signal and a first reference signal; The first reference signal and the first data signal are non-orthogonally superimposed.

28. The communication device according to claim 27, characterized in that The communication device is also used for: receiving a second reference signal; The second reference signal is non-orthogonally superimposed with the first data signal, and the first reference signal and the second reference signal satisfy: For transmission on the same layer and / or for the same user, the orthogonality or code domain correlation of the first reference signal and the second reference signal is less than or equal to a first threshold.

29. The communication device according to claim 28, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P1⊙P2|| F =0, where P1 represents the pilot matrix of the first reference signal, P2 represents the pilot matrix of the second reference signal, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

30. The communication device according to claim 28 or 29, characterized in that: The second reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

31. The communication device according to any one of claims 27 to 30, characterized in that: The first reference signal is transmitted through the first layer and the second layer, and / or the first reference signal is a reference signal for the first user and the second user, and the first reference signal satisfies: The orthogonality or code domain correlation of the first reference signal of the first layer and the first reference signal of the second layer is less than or equal to a second threshold; and / or, The orthogonality or code domain correlation of the first reference signal for the first user and the first reference signal for the second user is less than or equal to a third threshold.

32. The communication device according to claim 31, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P' l ⊙P' j || F =0, where P' l represents the pilot matrix of the first reference signal of the first layer or the first reference signal for the first user, P' j A pilot matrix representing the first reference signal of the second layer or the first reference signal for the second user, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

33. The communication device according to any one of claims 28 to 32, characterized in that: The orthogonality includes: frequency domain orthogonality, time domain orthogonality, time-frequency domain orthogonality or code domain orthogonality.

34. The communication device according to any one of claims 27 to 33, characterized in that: The first reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

35. The communication device according to any one of claims 27 to 34, characterized in that: The non-orthogonal superposition includes: the first data signal and the first reference signal both occupy a first resource element RE.

36. The communication device according to any one of claims 27 to 35, characterized in that: The communication device is also used for: Processing the first reference signal using a first model; The output of the first model is determined based on a value that can be configured by the communication system.

37. The communication device according to claim 36, characterized in that The output of the first model is determined based on a maximum value that the communication system can configure.

38. The communication device according to claim 36 or 37, characterized in that: The values ​​that can be configured in the communication system include one or more of the following values: number of transmission layers, bandwidth, MCS, and number of transmission users.

39. The communication device according to any one of claims 36 to 38, characterized in that: The communication device is also used for: cropping the output of the first model; The output of the first model after trimming matches the actual configuration of the communication system.

40. The communication device according to any one of claims 36 to 39, characterized in that: The input of the first model includes first configuration information, where the first configuration information is used to indicate one or more of the following information: The actual configuration of the communication system; configuration of the first reference signal; a moving speed of the first device; The scene in which the first device is located; The cell where the first device is located.

41. The communication device according to claim 40, characterized in that The configuration of the first reference signal includes one or more of the following information: information on power allocation of the first data signal and the first reference signal; A sequence of the first reference signal.

42. The communication device according to any one of claims 36 to 41, characterized in that: The first model is used to perform one or more of the following operations: channel estimation, symbol detection, and channel decoding.

43. The communication device according to any one of claims 36 to 42, characterized in that: The first model is an artificial intelligence AI model.

44. A communication device, characterized in that: The communication device is a second device, and the communication device includes: A sending unit, configured to send a first data signal and a first reference signal to a first device; The first reference signal and the first data signal are non-orthogonally superimposed.

45. The communication device according to claim 44, characterized in that The communication device is also used for: Sending a second reference signal to the first device; The second reference signal is non-orthogonally superimposed with the first data signal, and the first reference signal and the second reference signal satisfy: For transmission of the same layer and / or for the same user, the first reference signal and the second reference signal are orthogonal or code domain correlated. Less than or equal to the first threshold.

46. ​​The communication device according to claim 45, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P1⊙P2|| F =0, where P1 represents the pilot matrix of the first reference signal, P2 represents the pilot matrix of the second reference signal, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

47. The communication device according to claim 45 or 46, characterized in that: The second reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

48. The communication device according to any one of claims 44 to 47, characterized in that: The first reference signal is transmitted through the first layer and the second layer, and / or the first reference signal is a reference signal for the first user and the second user, and the first reference signal satisfies: The orthogonality or code domain correlation of the first reference signal of the first layer and the first reference signal of the second layer is less than or equal to a second threshold; and / or, The orthogonality or code domain correlation of the first reference signal for the first user and the first reference signal for the second user is less than or equal to a third threshold.

49. The communication device according to claim 48, characterized in that The orthogonality includes code domain orthogonality, and the code domain orthogonality satisfies: ||P' l ⊙P' j || F =0, where P' l represents the pilot matrix of the first reference signal of the first layer or the first reference signal for the first user, P' j A pilot matrix representing the first reference signal of the second layer or the first reference signal for the second user, |||| F represents the Frobenius norm, and ⊙ represents the Hadamard product.

50. The communication device according to any one of claims 45 to 49, characterized in that: The orthogonality includes: frequency domain orthogonality, time domain orthogonality, time-frequency domain orthogonality or code domain orthogonality.

51. The communication device according to any one of claims 44 to 50, characterized in that: The first reference signal includes one or more of the following: a channel state indication reference signal CSI-RS, a demodulation reference signal DMRS, a phase tracking reference signal PT-RS, a sounding reference signal SRS, a synchronization signal block SSB, and a positioning reference signal PRS.

52. The communication device according to any one of claims 44 to 51, characterized in that: The non-orthogonal superposition includes: the first data signal and the first reference signal both occupy a first resource element RE.

53. A communication device, characterized in that: The device comprises a memory and a processor, wherein the memory is used to store a program, and the processor is used to call the program in the memory so that the communication device executes the method according to any one of claims 1 to 26.

54. A device, characterized in that The device comprises a processor, configured to call a program from a memory so as to enable the device to execute the method according to any one of claims 1 to 26.

55. A chip, characterized in that: It comprises a processor, which is used to call a program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 26.

56. A computer-readable storage medium, characterized in that A program is stored thereon, the program causing a computer to execute the method according to any one of claims 1 to 26.

57. A computer program product, characterized in that The method comprises a program which causes a computer to execute the method according to any one of claims 1 to 26.

58. A computer program, characterized in that The computer program enables a computer to execute the method according to any one of claims 1 to 26.

Images