Channel estimation method and apparatus

Abstract

The embodiment of the application discloses a channel estimation method and device, a first demodulation reference signal (DMRS) is received, a first DMRS is sent based on a first DMRS pattern by a network device, channel estimation is performed based on a channel estimation model according to the first DMRS, so that terminal devices with different capabilities can all support channel estimation based on artificial intelligence technology, the accuracy of channel estimation is effectively improved, the success rate of decoding is greatly improved, the frequency spectrum efficiency of a communication system is effectively improved, and the pilot overhead of the system is saved.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a channel estimation method and apparatus. Background Technology

[0002] With the continuous development and maturation of 5G and Artificial Intelligence (AI) technologies, AI-assisted wireless communication is gradually emerging. For example, AI-assisted modulation and demodulation, as well as radio frequency (RF) technologies, including AI-assisted Channel State Information (CSI) feedback and AI-assisted beam management, can improve the speed and coverage of 5G networks, and enhance system mobility and robustness. Integrating AI technology into the design of wireless communication systems is also an important development direction for future 6G. Summary of the Invention

[0003] The first aspect of this application provides a channel estimation method, which is executed by a terminal device. The method includes: receiving a first DMRS transmitted by a network device based on a first demodulation reference signal DMRS pattern; and performing channel estimation based on a channel estimation model according to the first DMRS.

[0004] A second aspect of this application provides a channel estimation method, which is executed by a network device. The method includes: sending a first DMRS to a terminal device based on a first demodulation reference signal DMRS pattern; the first DMRS is used to perform channel estimation based on a channel estimation model.

[0005] A third aspect of this application provides a channel estimation method, which is executed by a network device. The method includes: receiving a first DMRS transmitted by a terminal device based on a first demodulation reference signal DMRS pattern; and performing channel estimation based on a channel estimation model according to the first DMRS.

[0006] A fourth aspect of this application provides a channel estimation method, which is executed by a terminal device. The method includes: sending a first DMRS to a network device based on a first demodulation reference signal DMRS pattern; the first DMRS is used to perform channel estimation based on a channel estimation model.

[0007] A fifth aspect of this application provides a channel estimation apparatus, the apparatus comprising:

[0008] The transceiver unit is used to receive the first DMRS transmitted by the network device based on the first demodulation reference signal DMRS pattern;

[0009] The processing unit is configured to perform channel estimation based on the channel estimation model according to the first DMRS.

[0010] A sixth aspect of this application provides a channel estimation apparatus, the apparatus comprising:

[0011] The transceiver unit is used to send the first DMRS to the terminal device based on the first demodulated reference signal DMRS pattern;

[0012] The first DMRS is used for channel estimation based on the channel estimation model.

[0013] A seventh aspect of this application provides a channel estimation apparatus, the apparatus comprising:

[0014] The transceiver unit is used to receive the first DMRS transmitted by the terminal device based on the first demodulation reference signal DMRS pattern;

[0015] The processing unit is configured to perform channel estimation based on the channel estimation model according to the first DMRS.

[0016] An eighth aspect of this application provides a channel estimation apparatus, the apparatus comprising:

[0017] The transceiver unit is used to send a first DMRS to the network device based on a first demodulation reference signal DMRS pattern;

[0018] The first DMRS is used for channel estimation based on the channel estimation model.

[0019] A ninth aspect of this application provides a communication device, the device including a processor and a memory, the memory storing a computer program, the processor executing the computer program stored in the memory to cause the device to perform the channel estimation method described in the first aspect embodiment above, or to perform the channel estimation method described in the second aspect embodiment above.

[0020] A tenth aspect of this application provides a communication device, the device including a processor and a memory, the memory storing a computer program, the processor executing the computer program stored in the memory to cause the device to perform the channel estimation method described in the third aspect embodiment above, or to perform the channel estimation method described in the fourth aspect embodiment above.

[0021] The eleventh aspect of this application provides a communication device, which includes a processor and an interface circuit. The interface circuit is used to receive code instructions and transmit them to the processor. The processor is used to execute the code instructions to cause the device to perform the channel estimation method described in the first aspect embodiment or the channel estimation method described in the second aspect embodiment.

[0022] The twelfth aspect of this application provides a communication device including a processor and an interface circuit. The interface circuit is used to receive code instructions and transmit them to the processor. The processor is used to execute the code instructions to cause the device to perform the channel estimation method described in the third aspect embodiment above, or to perform the channel estimation method described in the fourth aspect embodiment above.

[0023] The thirteenth aspect of this application provides a computer-readable storage medium for storing instructions that, when executed, cause the channel estimation method described in the first aspect embodiment to be implemented, or cause the channel estimation method described in the second aspect embodiment to be implemented.

[0024] The fourteenth aspect of this application provides a computer-readable storage medium for storing instructions that, when executed, enable the channel estimation method described in the third aspect embodiment or the channel estimation method described in the fourth aspect embodiment.

[0025] The fifteenth aspect of this application provides a computer program that, when run on a computer, causes the computer to perform the channel estimation method described in the first aspect embodiment or the channel estimation method described in the second aspect embodiment.

[0026] The sixteenth aspect of this application provides a computer program that, when run on a computer, causes the computer to perform the channel estimation method described in the third aspect embodiment or the channel estimation method described in the fourth aspect embodiment.

[0027] The channel estimation method and apparatus provided in this application embodiment receive a first DMRS transmitted by a network device based on a first demodulation reference signal DMRS pattern, and perform channel estimation based on a channel estimation model according to the first DMRS. This enables terminal devices with different capabilities to support channel estimation based on artificial intelligence technology, effectively improving the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0028] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the background art, the accompanying drawings used in the embodiments of this application or the background art will be described below.

[0030] Figure 1 This application provides a schematic diagram of the architecture of a communication system.

[0031] Figure 2 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0032] Figure 3 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0033] Figure 4 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0034] Figure 5 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0035] Figure 6 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0036] Figure 7 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0037] Figure 8 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0038] Figure 9 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0039] Figure 10 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0040] Figure 11 A flowchart illustrating a channel estimation method provided in an embodiment of this application;

[0041] Figure 12 This is a schematic diagram of the structure of a channel estimation device provided in an embodiment of this application;

[0042] Figure 13 This is a schematic diagram of the structure of a channel estimation device provided in an embodiment of this application;

[0043] Figure 14 This is a schematic diagram of the structure of a channel estimation device provided in an embodiment of this application;

[0044] Figure 15 This is a schematic diagram of the structure of a channel estimation device provided in an embodiment of this application;

[0045] Figure 16 This is a schematic diagram of another channel estimation device provided in an embodiment of this application;

[0046] Figure 17This is a schematic diagram of the structure of a chip provided in an embodiment of the present disclosure. Detailed Implementation

[0047] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0048] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the embodiments of this application. The singular forms “a” and “the” as used in the embodiments of this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0049] It should be understood that although the terms first, second, third, etc., may be used to describe various information in the embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words "if" and "suppose" as used herein can be interpreted as "when," "when," or "in response to a determination."

[0050] Embodiments of this application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0051] To better understand the channel estimation method disclosed in the embodiments of this application, the communication system to which the embodiments of this application are applicable is first described below.

[0052] Please see Figure 1 , Figure 1 This application provides a schematic diagram of the architecture of a communication system according to an embodiment. The communication system may include, but is not limited to, a network device and a terminal device. Figure 1 The number and form of devices shown are for illustrative purposes only and do not constitute a limitation on the embodiments of this application. In actual applications, it may include two or more network devices and two or more terminal devices. Figure 1The communication system shown is exemplified by a network device 101 and a terminal device 102.

[0053] It should be noted that the technical solutions of this application embodiment can be applied to various communication systems. For example, Long Term Evolution (LTE) systems, fifth-generation mobile communication systems, 5G New Radio systems, or other future new mobile communication systems.

[0054] The network device 101 in this embodiment is a network-side entity used for transmitting or receiving signals. For example, network device 101 can be an evolved NodeB (eNB), a Transmission Reception Point (TRP), a Next Generation NodeB (gNB) in an NR system, a base station in other future mobile communication systems, or an access node in a Wireless Fidelity (WiFi) system. The network device 101 in this embodiment can be the network device itself, an Over-The-Top (OTT) server maintained by an operator, base station manufacturer, or a third party, or an Operation Administration and Maintenance (OAM) or Location Management Function (LMF) function. This application does not limit the specific technology or device form used in the network device. The network device provided in this application embodiment can be composed of a central unit (CU) and a distributed unit (DU). The CU can also be called a control unit. By adopting the CU-DU structure, the protocol layer of the network device, such as a base station, can be separated. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU, which is centrally controlled by the CU.

[0055] The terminal device 102 in this embodiment is a user-side entity used to receive or transmit signals, such as a mobile phone. The terminal device can also be called a terminal, user equipment (UE), mobile station (MS), mobile terminal (MT), etc., or a RedCap UE, an evolved RedCap UE, etc. The terminal device can be a car with communication capabilities, a smart car, a mobile phone, a wearable device, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, a wireless terminal device in a smart home, and so on. The terminal device 102 in this application embodiment can be the terminal device itself, or it can be a user equipment vendor (UEvendor), a chip manufacturer, or an OTT server maintained by a third party. This application embodiment does not limit the specific technology or device form used in the terminal device.

[0056] With the continuous development and maturation of 5G and Artificial Intelligence (AI) technologies, AI-assisted wireless communication is gradually emerging. For example, AI-assisted modulation and demodulation, as well as radio frequency (RF) technologies, including AI-assisted Channel State Information (CSI) feedback and AI-assisted beam management, can improve the speed and coverage of 5G networks, and enhance system mobility and robustness. Integrating AI technology into the design of wireless communication systems is also an important development direction for future 6G.

[0057] In typical AI applications, such as image processing and autonomous driving, the power consumption of AI algorithms is usually evaluated using FLOPs / mW, FLOPs / W, or GFLOPs / mW. FLOPs stands for floating point operations, which can be understood as computational complexity and is used to measure the complexity of an algorithm or model. GFLOPs represents one billion floating-point operations.

[0058] It can be understood that the power consumption of a communication device performing one inference using an AI model = the computational complexity of the AI ​​model (FLOPs) / the capability of the communication device (FLOPs / mW).

[0059] For communication equipment, FLOPs / mW, as a hardware capability, is closely related to specific CPU process design and heat dissipation design. In some scenarios, when the terminal's computing power consumption is high, or its supported computing power falls below a certain threshold, it may be unable to quickly complete AI model training, forcing model training to be performed on the network side.

[0060] For AI-based downlink channel estimation methods, model training should ideally be performed on the terminal side. However, some terminal devices may lack the capability to train AI models and require network equipment assistance for training.

[0061] It is understood that the communication system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0062] The channel estimation method and apparatus provided in this application will be described in detail below with reference to the accompanying drawings.

[0063] Please see Figure 2 , Figure 2 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a terminal device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 2 As shown, the method may include the following steps:

[0064] Step 201: Receive the first DMRS transmitted by the network device based on the first demodulation reference signal DMRS pattern.

[0065] In this embodiment, the terminal device can receive a first demodulation reference signal (DMRS) sent by the network device, which is sent by the network device based on a first DMRS pattern. After receiving the first DMRS, the terminal device can perform channel estimation based on a trained channel estimation model and the first DMRS.

[0066] In some implementations, the terminal device can send a first indication message to the network device, the first indication message being used to indicate whether the terminal device has model training capability.

[0067] Optionally, the first indication information may include at least one of the following: model training capability indication information of the terminal device; hardware processing capability information of the terminal device; computing capability information of the terminal device; and power consumption capability information of the terminal device.

[0068] The model training capability indication information of the terminal device indicates whether the terminal device has model training capability. This model training capability indication information can be at least 1 bit.

[0069] In some possible implementations, the terminal device can also send model inference capability indication information to the network device. This indication information indicates whether the terminal device has the capability to perform model inference using a channel estimation model. This model inference capability indication information can also be at least 1 bit.

[0070] It is understood that in the various embodiments of this application, the terminal device has model reasoning capability and can perform channel estimation based on the trained channel estimation model.

[0071] Optionally, the terminal device can determine whether it has model training capability based on network device configuration or protocol-specified thresholds related to model training and inference, such as training latency threshold, training power consumption threshold, and training computational complexity threshold. It can also determine whether it has model inference capability based on inference latency threshold, inference power consumption threshold, and inference computational complexity threshold, and then report the terminal device's model training capability indication information and / or model inference capability indication information. Alternatively, it can directly determine whether it has model training capability and model inference capability based on its own capabilities, such as whether it has a Graphics Processing Unit (GPU), a Neural Network Processing Unit (NPU), and power and storage capacity, and then report the terminal device's model training capability indication information and / or model inference capability indication information.

[0072] Optionally, the terminal device can directly send model training capability indication information and model inference capability indication information to the network device to indicate whether the terminal device has model training capability and model inference capability. Alternatively, if the terminal device has model training capability, it can send indication information to the network device indicating that it has model training capability, reporting that it has model training capability; if the terminal device does not have model training capability, it can directly send indication information to the network device indicating whether it has model inference capability. As an example, the terminal device can send indication information to the network device indicating that it has model training capability, reporting that it has model training capability, implicitly indicating that it also has model inference capability. As another example, the terminal device can send indication information to the network device indicating that it has model inference capability, reporting that it has model inference capability, implicitly indicating that it does not have model training capability.

[0073] In some implementations, the terminal device can send hardware processing capability information, computing capability information, and power consumption capability information to the network device. The network device can determine whether the terminal device has model training capability and model inference capability based on the latency requirements of the service or certain thresholds specified by the protocol, such as latency threshold, power consumption threshold, and computational complexity threshold.

[0074] Optionally, the first indication information may include at least one of the following signaling: UE capability reporting signaling; UE Assistance Information (UAI); Radio Resource Control (RRC) signaling; Medium Access Control (MAC) control element (CE, or control unit); and Uplink Control Information (UCI). The first indication information may also be transmitted via the Physical Uplink Shared Channel (PUSCH).

[0075] Step 202: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0076] In this embodiment of the application, the terminal device can perform channel estimation based on the received first DMRS according to the trained channel estimation model.

[0077] It is understood that, in the embodiments of this application, the terminal device can directly use the received DMRS signal as the input to the channel estimation model, or it can obtain the channel estimate value estimated based on the DMRS and use the channel estimate value as the input to the channel estimation model. This application does not limit this. The channel estimate value at the DMRS obtained based on the DMRS can be estimated using the least squares (LS) method, the minimum mean square error (MMSE) method, or other estimation algorithms, etc. This application does not limit this either.

[0078] In the embodiments of this application, the channel estimation model can be trained by a terminal device or a network device; it can be trained using actual data or simulated data; and it can be trained offline or online.

[0079] In some implementations, the terminal device can receive a second DMRS sent by the network device based on a second DMRS pattern, and determine the training data for the channel estimation model based on the second DMRS.

[0080] Optionally, the terminal device can train the channel estimation model using the determined training data.

[0081] Optionally, the terminal device can send the training data to a network device, which can then use the training data to train the channel estimation model.

[0082] Optionally, before determining the training data to be sent to the network device, the terminal device can also receive a fourth indication information sent by the network device. This fourth indication information indicates the type of training data. For example, it can indicate that the training data is the received signal corresponding to the second DMRS, or it can indicate that the training data is a channel estimate based on the second DMRS, etc. The terminal device can determine what kind of training data the network device needs for model training based on the indication of the fourth indication information, and determine the training data based on the received second DMRS and send it to the network device.

[0083] In some implementations, the terminal device can acquire the simulated signal received by the terminal device in the simulated channel, wherein the simulated signal is the second DMRS sent by the network device in the simulated channel based on the second DMRS pattern. The terminal device can determine the simulation training data of the channel estimation model based on the simulated signal and use the simulation training data to train the channel estimation model.

[0084] In some implementations, the channel estimation model is trained by the network device using simulated training data. The network device can also acquire simulated signals received by terminal devices in a simulated channel, wherein the simulated signals are second DMRS transmitted by the network device based on a second DMRS pattern in the simulated channel. The network device can also determine the simulated training data for the channel estimation model based on the simulated signals and use the simulated training data to train the channel estimation model.

[0085] In this embodiment of the application, when the channel estimation model is trained by the network device, the terminal device can receive the trained channel estimation model sent by the network device.

[0086] In some embodiments of this application, when the channel estimation model is trained by a terminal device, the terminal device can also send a second indication message to the network device, which is used to indicate that the channel estimation model training is complete.

[0087] Optionally, the second indication information may further include at least one of the following: the capability information of the channel estimation model, and the processing delay information of the channel estimation model.

[0088] The capability information of the channel estimation model refers to its capabilities compared to traditional channel estimation methods. For example, the model can use a lower-density DMRS for channel estimation compared to traditional patterns, or it can obtain higher-accuracy channel estimation results compared to traditional methods. The processing latency information of the channel estimation model refers to the processing latency of the terminal device when using the model, which may include the model loading time and the inference time.

[0089] The network device can determine that the channel estimation model has been trained based on the second indication information. At the same time, it can also obtain the capability information and / or processing latency information of the model, and can make reasonable scheduling of the terminal device based on the capability information and processing latency information.

[0090] Optionally, the second indication information may include at least one of the following signaling: UE capability reporting signaling; User Assistance Information (UAI); Unlimited Resource Control (RRC) signaling; Media Access Control Layer (MAC) control element (CE); and Uplink Control Information (UCI). The second indication information may also be sent via PUSCH.

[0091] In some implementations, where the channel estimation model is trained by a terminal device, the terminal device can also receive third indication information sent by the network device. This third indication information is used to instruct the terminal device to begin training the channel estimation model. This third indication information can be at least 1 bit.

[0092] In some implementations, when the channel estimation model is trained by the terminal device, the terminal device can either start training the channel estimation model directly, or it can start training the model after a preset time has elapsed since the first indication information was sent. This preset time can be configured by the network device, or it can be agreed upon or specified by a protocol.

[0093] In some implementations, network devices may also send de-enable signaling to terminal devices according to business needs and circumstances, instructing terminal devices not to start model training.

[0094] In some implementations, if the channel estimation model is trained using a supervised machine learning method, the terminal device can also receive an impulse signal sent by the network device and obtain an ideal channel estimation label based on the impulse signal. This ideal channel estimation label is used for training the channel estimation model.

[0095] In some implementations, where the channel estimation model is trained by the terminal device, if the channel estimation model is trained using a supervised machine learning method, the terminal device also needs to send auxiliary information to the network device to request the network device to send an impulse signal. The terminal device can obtain the ideal channel estimation label of the channel based on the impulse signal and use the ideal channel estimation label to train the channel estimation model.

[0096] In some implementations, the channel estimation model has the capability to perform channel estimation using a low-density DMRS pattern, where the density of the first DMRS pattern is lower than that of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern. The terminal device can obtain channel estimation results based on this channel estimation model using a lower-density DMRS pattern compared to the legacy DMRS pattern.

[0097] In some implementations, the channel estimation model is capable of providing high-precision channel estimation results, where the density of the first DMRS pattern is the same as the density of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern, and the terminal device can use DMRS patterns with the same density as the legacy DMRS pattern to obtain higher-precision channel estimation results compared to traditional channel estimation methods based on this channel estimation model.

[0098] In some implementations, the terminal device can also receive a fifth indication message sent by the network device, which instructs the terminal device to perform channel estimation based on the channel estimation model. The trained channel estimation model will only be activated for channel estimation when the terminal device receives the fifth indication message.

[0099] Optionally, the fifth indication information can be at least 1 bit of information, directly instructing the terminal device to enable the trained channel estimation model for channel estimation. The fifth indication information can also be the first DMRS pattern configuration sent by the network device to the terminal device to reduce pilot overhead.

[0100] In summary, by receiving the first DMRS transmitted by the network device based on the first demodulation reference signal DMRS pattern, and performing channel estimation based on the channel estimation model according to the first DMRS, terminal devices with different capabilities can support channel estimation based on artificial intelligence technology, which effectively improves the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0101] Please see Figure 3 , Figure 3 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a terminal device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 3 As shown, the method may include the following steps:

[0102] Step 301: Send a first indication message to the network device, the first indication message being used to indicate whether the terminal device has model training capability.

[0103] In this embodiment of the application, the terminal device sends a first indication message to the network device to report whether it has the ability to train models.

[0104] Optionally, the first indication information may include at least one of the following: model training capability indication information of the terminal device; hardware processing capability information of the terminal device; computing capability information of the terminal device; and power consumption capability information of the terminal device.

[0105] The model training capability indication information of the terminal device indicates whether the terminal device has model training capability. This model training capability indication information can be at least 1 bit. As an example, "0" can represent that the terminal device does not have model training capability, and "1" can represent that the terminal device has model training capability.

[0106] In some possible implementations, the terminal device can also send model inference capability indication information to the network device. This indication information indicates whether the terminal device has the capability to perform model inference using a channel estimation model. This model inference capability indication information can also be at least 1 bit. As an example, "0" can represent that the terminal device does not have model inference capability, and "1" can represent that the terminal device has model inference capability.

[0107] It is understood that in the various embodiments of this application, the terminal device has model reasoning capability and can perform channel estimation based on the trained channel estimation model.

[0108] Optionally, the terminal device can determine its model training capability based on thresholds configured in the network device or specified in the protocol, such as training latency threshold, training power consumption threshold, and training computational complexity threshold. It can also determine its model inference capability based on inference latency threshold, inference power consumption threshold, and inference computational complexity threshold, and then report the terminal device's model training capability indication information and / or model inference capability indication information. Alternatively, it can directly determine its model training and inference capabilities based on its own capabilities, such as the presence of a GPU, NPU, and power / storage capacity, and then report the terminal device's model training and / or model inference capability indication information.

[0109] Optionally, the terminal device can directly send model training capability indication information and model inference capability indication information to the network device to indicate whether the terminal device has model training capability and model inference capability. Alternatively, if the terminal device has model training capability, it can send indication information to the network device indicating that it has model training capability, reporting that it has model training capability; if the terminal device does not have model training capability, it can directly send indication information to the network device indicating whether it has model inference capability. As an example, the terminal device can send indication information to the network device indicating that it has model training capability, reporting that it has model training capability, implicitly indicating that it also has model inference capability. As another example, the terminal device can send indication information to the network device indicating that it has model inference capability, reporting that it has model inference capability, implicitly indicating that it does not have model training capability.

[0110] In some implementations, the terminal device can send hardware processing capability information, computing capability information, and power consumption capability information to the network device. The network device can determine whether the terminal device has model training capability and model inference capability based on the latency requirements of the service or certain thresholds specified by the protocol, such as latency threshold, power consumption threshold, and computational complexity threshold.

[0111] In some embodiments, the terminal device may have at least one model training capability and / or at least one model inference capability, and the first indication information can be used to determine the model training capability and / or model inference capability of the terminal device. As an example, the first indication information is model training capability indication information. A model training capability indication of "00" indicates that the terminal device does not have model training capability, while "01", "02", and "03" all indicate that the terminal device has model training capability. Different values ​​represent different levels of model training capability, with larger values ​​indicating stronger training capability. Similarly, the model inference capability indication information can also be reported in a similar manner. It is understood that other methods can also be used to determine the model training capability of the terminal device, and this application does not limit this.

[0112] Optionally, the first indication information may include at least one of the following signaling: UE capability reporting signaling; User Assistance Information (UAI); Unlimited Resource Control (RRC) signaling; Media Access Control Layer Control Element (MACCE); Uplink Control Information (UCI). The first indication information may also be sent via PUSCH.

[0113] It is understood that, in the embodiments of this application, the terminal device has model training capability and model inference capability.

[0114] Step 302: Receive the second DMRS sent by the network device based on the second DMRS pattern.

[0115] In this embodiment of the application, the terminal device can receive the second DMRS sent by the network device based on the second DMRS pattern, and can determine the training data of the channel estimation model according to the second DMRS, and use the training data to train the channel estimation model.

[0116] The second DMRS pattern can be a legacy DMRS pattern.

[0117] In this embodiment of the application, the network device sends a reference signal to the terminal device based on the second DMRS pattern, and the terminal device collects actual data as training data based on the received actual reference signal to train the model.

[0118] Step 303: Determine the training data for the channel estimation model based on the second DMRS.

[0119] In this embodiment of the application, the terminal device can determine the training data of the channel estimation model based on the received second DMRS. The training data is the actual data obtained through actual channel transmission.

[0120] Optionally, in this embodiment, the terminal device can directly use the received signal of the second DMRS as training data for the channel estimation model, or it can obtain the channel estimate value estimated based on the second DMRS and use that channel estimate value as training data for the channel estimation model. Alternatively, it can obtain other training data based on the configuration of the channel estimation model; this application does not limit this. The channel estimate value at the DMRS obtained based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms, etc.; this application also does not limit this.

[0121] In some implementations, the terminal device uses a supervised machine learning method to train the channel estimation model. The terminal device can also receive impulse signals sent by network devices and obtain the ideal channel label of the channel based on the impulse signal for training the channel estimation model.

[0122] Optionally, the impulse signal can use a semi-static scheduling transmission method. The terminal device can also receive configuration information of the impulse signal sent by the network device, which may include the transmission period of the impulse signal and the time-frequency resources occupied, etc. The impulse signal can also use a dynamic scheduling transmission method. The terminal device can also receive scheduling information of the impulse signal sent by the network device, which may include the time-frequency domain resources occupied by the transmission of the impulse signal and the DCI's function indication field, etc. (such as one specifically used for scheduling the impulse signal).

[0123] Step 304: Train the channel estimation model using training data.

[0124] In this embodiment of the application, the terminal device can use the training data determined in the aforementioned steps to train the channel estimation model.

[0125] In the embodiments of this application, the channel estimation model can be trained using a supervised machine learning method or an unsupervised machine learning method.

[0126] It should be noted that the channel estimation model in the embodiments of this application can be constructed and trained based on any machine learning method, such as Convolutional Neural Networks (CNN), etc., and this application does not limit it.

[0127] In some implementations, the terminal device trains the channel estimation model using a supervised machine learning method. The terminal device can also train the channel estimation model using the ideal channel label obtained from the received impulse signal.

[0128] It should be noted that the impulse signal sent by the network device can be sent separately from the second DMRS or sent together with the second DMRS; this application does not limit this.

[0129] In some implementations, the terminal device trains the channel estimation model using a supervised machine learning method. The terminal device can also send auxiliary information to the network device to request the impulse signal. Upon receiving the auxiliary information, the network device sends the impulse signal to the terminal device.

[0130] Optionally, the auxiliary information may be a request message or an instruction message indicating the training method of the channel estimation model (e.g., indicating that the model is trained using a supervised / unsupervised machine learning method).

[0131] In some implementations, the terminal device may also receive a third instruction message sent by the network device, which instructs the terminal device to begin training the model.

[0132] Optionally, the third indication information can be a bit information with a value of "0" or "1", used to indicate whether the terminal device should start model training (for example, the third indication information being "0" indicates that the terminal device is disabled and does not start model training, while the third indication information being "1" indicates that the terminal device is enabled and starts model training). The third indication information can also be an impulse signal sent by the network device, or a corresponding configuration of the impulse signal. Receiving the signal or the corresponding configuration indicates that the terminal device is enabled to start model training, and the terminal device can start training the channel estimation model after receiving the impulse signal or the corresponding configuration.

[0133] In some implementations, the terminal device can directly begin training the channel estimation model, or begin training the channel estimation model after a preset time has elapsed since the aforementioned first indication information was sent. This preset time can be configured by the network device, or it can be pre-agreed upon or specified by a protocol.

[0134] It should be noted that, in the embodiments of this application, the training of the model can be carried out online or offline, and this application does not limit it in this regard.

[0135] Step 305: Send a second indication message to the network device, which indicates that the channel estimation model training is complete.

[0136] In this embodiment of the application, after the terminal device completes the training of the channel estimation model, it can also send a second indication information to the network device, and the network device can determine that the channel estimation model training is complete based on the second indication information.

[0137] Optionally, the second indication information may include, in addition to the model training completion indication information, at least one of the following: the capability information of the channel estimation model, and the processing latency information of the channel estimation model. Alternatively, the model training completion indication information may implicitly indicate the completion of training through at least one of the above two types of information.

[0138] The capability information of the channel estimation model refers to its capabilities compared to traditional channel estimation methods. For example, the model can use a lower-density DMRS for channel estimation compared to traditional patterns, or it can obtain higher-accuracy channel estimation results compared to traditional methods. The processing latency information of the channel estimation model refers to the processing latency of the terminal device when using the model, which may include the model loading time and the inference time.

[0139] The network device can determine that the channel estimation model has been trained based on the second instruction information. At the same time, it can also obtain the model's capability information and / or the model's processing latency, model complexity, model inference power consumption, etc. It can make reasonable scheduling of the terminal device based on the capability information and processing latency information. Furthermore, it can decide whether to enable the AI ​​model based on the model's processing latency, model complexity, model inference power consumption, etc.

[0140] Optionally, the second indication information may include at least one of the following signaling: UE capability reporting signaling; User Assistance Information (UAI); Unlimited Resource Control (RRC) signaling; Media Access Control Layer (MAC) control element (CE); and Uplink Control Information (UCI). The second indication information may also be sent via PUSCH.

[0141] Step 306: Receive the first DMRS sent by the network device based on the first DMRS pattern.

[0142] In this embodiment, the terminal device can receive a first DMRS sent by the network device, which is sent by the network device based on a first DMRS pattern. The network device can determine the first DMRS pattern based on the capabilities of the channel estimation model. After receiving the first DMRS, the terminal device can perform channel estimation based on the trained channel estimation model and the first DMRS.

[0143] In some implementations, the channel estimation model has the capability to perform channel estimation using a low-density DMRS pattern, where the density of the first DMRS pattern is lower than that of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern. The terminal device can obtain channel estimation results based on this channel estimation model using a lower-density DMRS pattern compared to the legacy DMRS pattern.

[0144] In some implementations, the channel estimation model is capable of providing high-precision channel estimation results, where the density of the first DMRS pattern is the same as the density of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern, and the terminal device can use DMRS patterns with the same density as the legacy DMRS pattern to obtain higher-precision channel estimation results compared to traditional channel estimation methods based on this channel estimation model.

[0145] It is understood that, in the embodiments of this application, the terminal device can directly use the received signal of the first DMRS as the input to the channel estimation model, or it can obtain the channel estimate value estimated based on the first DMRS and use the channel estimate value as the input to the channel estimation model, or it can obtain other data as input through the configuration of the channel estimation model. This application does not limit this. The channel estimate value obtained based on the first DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms, etc. This application does not limit this either.

[0146] Step 307: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0147] In this embodiment of the application, the terminal device can perform channel estimation based on the received first DMRS and the trained channel estimation model.

[0148] It is understood that, in the embodiments of this application, the terminal device can directly use the received signal of the first DMRS as the input to the channel estimation model, or it can obtain the channel estimate value estimated based on the first DMRS and use the channel estimate value as the input to the channel estimation model, or it can obtain other data as input based on the configuration of the channel estimation model. This application does not limit this. The channel estimate value obtained based on the first DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms, etc. This application does not limit this either.

[0149] In some implementations, the terminal device can also receive a fifth indication message sent by the network device, which instructs the terminal device to perform channel estimation based on the channel estimation model. The trained channel estimation model will only be activated for channel estimation when the terminal device receives the fifth indication message.

[0150] Optionally, the fifth indication information can be at least 1 bit of information, directly instructing the terminal device to enable the trained channel estimation model for channel estimation (for example, a "0" in the fifth indication information indicates that the channel estimation model is disabled, and the terminal device does not enable the channel estimation model for channel estimation; a "1" in the fifth indication information indicates that the channel estimation model is enabled, and the terminal device enables the channel estimation model for channel estimation). The fifth indication information can also be the first DMRS pattern configuration sent by the network device to the terminal device to reduce pilot overhead.

[0151] It is understandable that if the terminal device does not enable the channel estimation model for channel estimation, the density of the first DMRS pattern and the second DMRS pattern will be the same, and the terminal device can use the traditional channel estimation algorithm to perform channel estimation based on the received DMRS.

[0152] In summary, by sending a first indication message to the network device, which indicates whether the terminal device has model training capability, receiving a second DMRS sent by the network device based on a second DMRS pattern, determining the training data for the channel estimation model based on the second DMRS, training the channel estimation model using the training data, sending a second indication message to the network device, which indicates that the channel estimation model training is complete, and receiving a first DMRS sent by the network device based on the first DMRS pattern, and performing channel estimation based on the channel estimation model based on the first DMRS, terminal devices with different capabilities can support channel estimation based on artificial intelligence technology, effectively improving the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving system pilot overhead.

[0153] Please see Figure 4 , Figure 4 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a terminal device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 4 As shown, the method may include the following steps:

[0154] Step 401: Send a first indication message to the network device, the first indication message being used to indicate whether the terminal device has model training capability.

[0155] In the embodiments of this application, step 401 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not elaborate further.

[0156] Step 402: Obtain the simulated signal received by the terminal device in the simulated channel. The simulated signal is the second DMRS sent by the network device in the simulated channel based on the second DMRS pattern.

[0157] In this embodiment, the terminal device can acquire the simulated signal received by the terminal device in the simulated channel. The simulated signal is the second DMRS transmitted by the network device in the simulated channel based on the second DMRS pattern. Furthermore, it can determine the training data for the channel estimation model based on the simulated signal and use the training data to train the channel estimation model.

[0158] The second DMRS pattern can be a legacy DMRS pattern.

[0159] In this embodiment of the application, in the simulated channel model, the network device sends DMRS to the terminal device based on the second DMRS pattern. The terminal device can obtain the simulated signal received in the simulated channel and determine the simulated data as training data to train the model.

[0160] Step 403: Based on the simulation signal, determine the simulation training data for the channel estimation model.

[0161] In this embodiment of the application, the terminal device can determine the training data of the channel estimation model based on the acquired simulation signal. The training data is the simulation data transmitted in the simulation channel.

[0162] Optionally, in this embodiment, the terminal device can directly use the received simulated signal of the second DMRS as training data for the channel estimation model, or it can obtain the channel estimate value estimated based on the simulated signal of the second DMRS and use the channel estimate value as training data for the channel estimation model. Alternatively, it can obtain other training data based on the configuration of the channel estimation model; this application does not limit this. The channel estimate value at the DMRS obtained based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms; this application also does not limit this.

[0163] In some implementations, the terminal device uses a supervised machine learning method to train the channel estimation model, and the terminal device can also obtain the ideal channel label of the simulated channel for training the channel estimation model.

[0164] Step 404: Use the simulation training data to train the channel estimation model.

[0165] In this embodiment of the application, the terminal device can use the simulation training data determined in the aforementioned steps to train the channel estimation model.

[0166] In the embodiments of this application, the channel estimation model can be trained using a supervised machine learning method or an unsupervised machine learning method.

[0167] It should be noted that the channel estimation model in the embodiments of this application can be constructed and trained based on any machine learning method, such as convolutional neural network (CNN), etc., and this application does not limit it.

[0168] In some implementations, the terminal device uses supervised machine learning methods to train the channel estimation model. The terminal device can also obtain the ideal channel label of the simulated channel for training the channel estimation model. It is understood that in the simulated channel model, the ideal channel label of the simulated channel can be obtained by establishing the channel parameters of the simulated channel model.

[0169] In some implementations, the terminal device may also receive a third instruction message sent by the network device, which instructs the terminal device to begin training the model.

[0170] Optionally, the third indication information can be a bit information with a value of "0" or "1", used to indicate whether the terminal device starts model training (for example, the third indication information is "0" to indicate that the terminal device does not start model training, and the third indication information is "1" to indicate that the terminal device starts model training). The third indication information can also be other information, which indicates the terminal device to start model training through implicit indication.

[0171] In some implementations, the terminal device can directly begin training the channel estimation model, or begin training the channel estimation model after a preset time has elapsed since the aforementioned first indication information was sent. This preset time can be configured by the network device, or it can be pre-agreed upon or specified by a protocol.

[0172] It should be noted that, in the embodiments of this application, the training of the model can be carried out online or offline, and this application does not limit it in this regard.

[0173] In some implementations, the terminal device can also send training data indication information to the network device, which instructs the terminal device whether to train the model based on simulated data or actual data. Alternatively, the network device can explicitly or implicitly configure or instruct the terminal device to use simulated data or actual data for model training (e.g., implicitly instructing to use actual data for model training by sending an impulse signal, etc.).

[0174] Step 405: Send a second indication message to the network device, which indicates that the channel estimation model training is complete.

[0175] Step 406: Receive the first DMRS sent by the network device based on the first DMRS pattern.

[0176] Step 407: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0177] In the embodiments of this application, steps 405 to 407 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not elaborate further.

[0178] In summary, by sending a first indication message to the network device, which indicates whether the terminal device has model training capabilities, acquiring the simulated signal received by the terminal device in the simulated channel (the simulated signal being the second DMRS sent by the network device based on the second DMRS pattern in the simulated channel), determining the simulation training data for the channel estimation model based on the simulated signal, training the channel estimation model using the simulation training data, sending a second indication message to the network device, which indicates that the channel estimation model training is complete, receiving the first DMRS sent by the network device based on the first DMRS pattern, and performing channel estimation based on the channel estimation model according to the first DMRS, terminal devices with different capabilities can all support channel estimation based on artificial intelligence technology, effectively improving the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectral efficiency of the communication system, and saving the system's pilot overhead.

[0179] Please see Figure 5 , Figure 5 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a terminal device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 5 As shown, the method may include the following steps:

[0180] Step 501: Send a first indication message to the network device, the first indication message being used to indicate whether the terminal device has model training capability.

[0181] In the embodiments of this application, step 501 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not elaborate further.

[0182] It is understood that in the embodiments of this application, the channel estimation model is trained by the network device. This may be because the terminal device does not have the ability to train the model, or the terminal device has the ability to train the model, but the network device chooses not to train the model on the terminal device side based on service conditions, etc.

[0183] In this embodiment, if the first indication information is a model training capability indication information of the terminal device, the terminal device may also need to send storage capability information, hardware processing capability information, computing capability information, and power consumption capability information to the network device, so that the network device can determine a channel estimation model that matches the terminal device. Alternatively, the terminal device may also send model recommendation information to the network device based on its own hardware capabilities, so that the network device can determine a channel estimation model that matches the terminal device.

[0184] Step 502: Receive fourth indication information sent by the network device, which is used to indicate the type of training data for the channel estimation model.

[0185] In this embodiment, the terminal device can receive a fourth indication information sent by the network device, which is used to indicate the type of training data. For example, the training data can be indicated as the received signal corresponding to the second DMRS, or as the channel estimate value at the DMRS estimated based on the second DMRS, or as other types of training data based on the configuration of the channel estimation model, etc. This application does not limit the scope of the indication information.

[0186] The terminal device can determine what kind of training data the network device needs for model training based on the instructions of the fourth instruction information, and determine the training data based on the received second DMRS and send it to the network device.

[0187] Step 503: Receive the second DMRS sent by the network device based on the second DMRS pattern.

[0188] In this embodiment of the application, the terminal device can receive the second DMRS sent by the network device based on the second DMRS pattern, and can determine the training data of the channel estimation model according to the second DMRS. The training data is the data required by the network device to train the model.

[0189] The second DMRS pattern can be a legacy DMRS pattern.

[0190] Step 504: Determine the training data for the channel estimation model based on the second DMRS.

[0191] In this embodiment of the application, the terminal device can determine the training data of the channel estimation model based on the received second DMRS. The training data is the actual data obtained through actual channel transmission.

[0192] In this embodiment, the terminal device can determine the training data based on the type of training data indicated by the received fourth indication information. For example, the training data can be determined to be the received signal corresponding to the second DMRS based on the fourth indication information, or it can be determined to be the channel estimate value estimated based on the second DMRS, etc. The channel estimate value at the DMRS obtained by estimating the channel based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms, etc., and this application does not limit the specific algorithms used.

[0193] In some implementations, the network device uses a supervised machine learning method to train the channel estimation model. The terminal device can also receive an impulse signal sent by the network device and obtain the ideal channel label of the channel based on the impulse signal. The ideal channel label and training data are then sent to the network device. The ideal channel label is used for training the channel estimation model.

[0194] Optionally, the impulse signal can use a semi-static scheduling transmission method. The terminal device can also receive configuration information of the impulse signal sent by the network device, which may include the transmission period of the impulse signal and the time-frequency resources occupied, etc. The impulse signal can also use a dynamic scheduling transmission method. The terminal device can also receive scheduling information of the impulse signal sent by the network device, which may include the time-frequency domain resources occupied by the transmission of the impulse signal and the function indication field of the DCI (such as a field specifically used for scheduling impulse signals).

[0195] In some implementations, the terminal device can also receive configuration information or indication information for training data reporting sent by the network device, which is used to configure or indicate the period for the terminal device to report training data, the dimension of the reported training data, the quantity of reported training data, and the time-frequency resources used for reporting training data, etc.

[0196] It is understandable that if the network device uses a supervised machine learning method to train the channel estimation model, the terminal device also needs to send the ideal channel label obtained by receiving the impulse signal and the training data to the network device. For example, a sample may contain {training input value, label} which is {received signal of DMRS, data and ideal channel estimate at DMRS} or {channel estimate at DMRS, data and ideal channel estimate at DMRS}.

[0197] Step 505: Send the training data to the network device. The training data is used to train the channel estimation model.

[0198] In this embodiment of the application, the terminal device can send the determined training data to the network device, and the network device can use the training data to train the channel estimation model.

[0199] In the embodiments of this application, the channel estimation model can be trained using a supervised machine learning method or an unsupervised machine learning method.

[0200] It should be noted that the channel estimation model in the embodiments of this application can be constructed and trained based on any machine learning method, such as convolutional neural network (CNN), etc., and this application does not limit it.

[0201] In some implementations, the network device trains the channel estimation model using a supervised machine learning method, and the terminal device can also send an ideal channel label to the network device, wherein the ideal channel label is obtained based on the impulse signal received from the network device.

[0202] It should be noted that the impulse signal sent by the network device can be sent separately from the second DMRS or sent together with the second DMRS; this application does not limit this.

[0203] In some implementations, the terminal device can also send the training data and / or ideal channel label according to the configuration information or indication information of the training data reported by the network device, and according to the period of reporting training data, the dimension of the reported training data, the quantity of reported training data, and the time and frequency resources used for reporting training data, etc. configured or indicated therein.

[0204] Step 506: Receive the completed channel estimation model sent by the network device.

[0205] In this embodiment of the application, the terminal device is able to receive the channel estimation model that has been trained and sent by the network device.

[0206] Optionally, the network device may send the trained channel estimation model to the terminal device in the form of RRC signaling, a new radio signaling bearer (SRB), or a channel identified by a unique logical channel identifier (LCID).

[0207] In this embodiment, the network device can use actual channel data sent by the terminal device as training data to train the channel estimation model. The network device can train the model itself, or it can train the model through an OTT server, OAM, or LMF, etc.

[0208] In the embodiments of this application, the model trained by the network device may be determined based on the model recommendation information reported by the terminal device; it may also be a model determined by the network device itself that matches the capabilities of the terminal device (for example, a model determined by the network device based on the storage capacity, hardware processing capacity information, computing capacity information, and power consumption capacity information reported by the terminal device, etc., that matches the terminal device); or it may be a model determined directly by the network device without being based on the capabilities of the terminal device.

[0209] It should be noted that, in the embodiments of this application, the training of the model can be carried out online or offline, and this application does not limit it in this regard.

[0210] Step 507: Receive the first DMRS sent by the network device based on the first DMRS pattern.

[0211] Step 508: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0212] In the embodiments of this application, steps 507 to 508 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not elaborate further.

[0213] In summary, by sending a first indication message to the network device, which indicates whether the terminal device has model training capabilities, receiving a fourth indication message from the network device, which indicates the type of training data for the channel estimation model, receiving a second DMRS sent by the network device based on a second DMRS pattern, determining the training data for the channel estimation model based on the second DMRS, sending the training data to the network device for training the channel estimation model, receiving the trained channel estimation model from the network device, and receiving the first DMRS sent by the network device based on the first DMRS pattern, and performing channel estimation based on the channel estimation model based on the first DMRS, terminal devices with different capabilities can support channel estimation based on artificial intelligence technology, effectively improving the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectral efficiency of the communication system, and saving system pilot overhead.

[0214] Please see Figure 6 , Figure 6 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a terminal device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 6 As shown, the method may include the following steps:

[0215] Step 601: Send a first indication message to the network device, the first indication message being used to indicate whether the terminal device has model training capability.

[0216] In the embodiments of this application, step 601 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not elaborate further.

[0217] It is understood that in the embodiments of this application, the channel estimation model is trained by the network device. This may be because the terminal device does not have the ability to train the model, or the terminal device has the ability to train the model, but the network device chooses not to train the model on the terminal device side based on service conditions, etc.

[0218] In this embodiment, if the first indication information is a model training capability indication information of the terminal device, the terminal device may also need to send storage capability information, hardware processing capability information, computing capability information, and power consumption capability information to the network device, so that the network device can determine a channel estimation model that matches the terminal device. Alternatively, the terminal device may also send model recommendation information to the network device based on its own hardware capabilities, so that the network device can determine a channel estimation model that matches the terminal device.

[0219] Step 602: Receive the trained channel estimation model sent by the network device.

[0220] In this embodiment of the application, the terminal device is able to receive the channel estimation model that has been trained and sent by the network device.

[0221] Optionally, the network device may send the trained channel estimation model to the terminal device via RRC signaling, a new radio signaling bearer SRB, or a channel identified by a unique LCID.

[0222] In this embodiment, the network device can acquire the simulated signal received by the terminal device in the simulated channel. The simulated signal is the second DMRS transmitted by the network device based on the second DMRS pattern in the simulated channel. Furthermore, it can determine the training data for the channel estimation model based on the simulated signal and use the training data to train the channel estimation model.

[0223] The second DMRS pattern can be a legacy DMRS pattern.

[0224] In this embodiment of the application, in the simulated channel model, the network device sends DMRS to the terminal device based on the second DMRS pattern. The terminal device can obtain the simulated signal received in the simulated channel and determine the simulated data as training data to train the model.

[0225] Optionally, in this embodiment, the network device can directly use the received simulated signal of the second DMRS as training data for the channel estimation model, or it can obtain the channel estimate value estimated based on the simulated signal of the second DMRS and use the channel estimate value as training data for the channel estimation model. Alternatively, it can obtain other training data based on the configuration of the channel estimation model; this application does not limit this. The channel estimate value at the DMRS obtained based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms; this application also does not limit this.

[0226] In some implementations, the network device uses supervised machine learning methods to train the channel estimation model. The network device can also obtain the ideal channel label for the simulated channel to train the channel estimation model. It is understood that in the simulated channel model, the ideal channel label can be obtained by establishing the channel parameters of the simulated channel model.

[0227] In this embodiment of the application, the network device may perform model training on its own, or it may perform model training through an OTT server, OAM, or LMF, etc.

[0228] In the embodiments of this application, the model trained by the network device may be determined based on the model recommendation information reported by the terminal device; it may also be a model determined by the network device itself that matches the capabilities of the terminal device (for example, a model determined by the network device based on the storage capacity, hardware processing capacity information, computing capacity information, and power consumption capacity information reported by the terminal device, etc., that matches the terminal device); or it may be a model determined directly by the network device without being based on the capabilities of the terminal device.

[0229] It should be noted that, in the embodiments of this application, the training of the model can be carried out online or offline, and this application does not limit it in this regard.

[0230] Step 603: Receive the first DMRS sent by the network device based on the first DMRS pattern.

[0231] Step 604: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0232] In the embodiments of this application, steps 603 to 604 can be implemented in any of the ways described in the embodiments of this application. The embodiments of this application do not limit this, nor will they be described in detail.

[0233] In summary, by sending a first indication message to the network device, which indicates whether the terminal device has model training capability, receiving the channel estimation model that has been trained by the network device, receiving the first DMRS sent by the network device based on the first DMRS pattern, and performing channel estimation based on the channel estimation model according to the first DMRS, terminal devices with different capabilities can all support channel estimation based on artificial intelligence technology, effectively improving the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0234] Please see Figure 7 , Figure 7This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a network device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 7 As shown, the method may include the following steps:

[0235] Step 701: Send the first DMRS to the terminal device based on the first DMRS pattern. The first DMRS is used for channel estimation based on the channel estimation model.

[0236] In this embodiment, the network device can send a first DMRS to the terminal device based on a first DMRS pattern. After receiving the first DMRS, the terminal device can perform channel estimation based on the trained channel estimation model and the first DMRS.

[0237] In some implementations, the network device can receive first instruction information sent by the terminal device, and the network device can determine whether the terminal device has model training capability based on the first instruction information.

[0238] Optionally, the first indication information may include at least one of the following: model training capability indication information of the terminal device; hardware processing capability information of the terminal device; computing capability information of the terminal device; and power consumption capability information of the terminal device.

[0239] The model training capability indication information of the terminal device indicates whether the terminal device has model training capability. This model training capability indication information can be at least 1 bit.

[0240] In some possible implementations, the terminal device can also send model inference capability indication information to the network device. This indication information indicates whether the terminal device has the capability to perform model inference using a channel estimation model. This model inference capability indication information can also be at least 1 bit.

[0241] It is understood that in the various embodiments of this application, the terminal device has model reasoning capability and can perform channel estimation based on the trained channel estimation model.

[0242] Optionally, the first indication information may include at least one of the following signaling: UE capability reporting signaling; User Assistance Information (UAI); Unlimited Resource Control (RRC) signaling; Media Access Control (MACCE) layer control element; and Uplink Control Information (UCI). The first indication information may also be transmitted via the Physical Uplink Shared Channel (PUSCH).

[0243] In this embodiment of the application, the terminal device can perform channel estimation based on the received first DMRS according to the trained channel estimation model.

[0244] It is understood that, in the embodiments of this application, the terminal device can directly use the received DMRS signal as input to the channel estimation model, or it can obtain the channel estimate value estimated based on the DMRS and use the channel estimate value as input to the channel estimation model. This application does not limit this. The channel estimate value at the DMRS location is obtained by estimating the channel based on the DMRS. The estimation can be performed using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms. This application does not limit this either.

[0245] In the embodiments of this application, the channel estimation model can be trained by a terminal device or a network device; it can be trained using actual data or simulated data; and it can be trained offline or online.

[0246] In some implementations, the network device can send a second DMRS to the terminal device based on a second DMRS pattern, which is used to determine the training data for the channel estimation model.

[0247] Optionally, the terminal device can train the channel estimation model using the determined training data.

[0248] Optionally, the terminal device can send the training data to a network device, which can then use the training data to train the channel estimation model.

[0249] Optionally, before the terminal device determines the training data to be sent to the network device, the network device can also send a fourth indication message to the terminal device. This fourth indication message indicates the type of training data. For example, it can indicate that the training data is the received signal corresponding to the second DMRS, or it can indicate that the training data is a channel estimate based on the second DMRS, etc. The terminal device can determine what kind of training data the network device needs for model training based on the indication of the fourth indication message, and determine the training data based on the received second DMRS and send it to the network device.

[0250] In some implementations, the channel estimation model is trained by the terminal device using simulation training data. The terminal device can acquire the simulation signal received by the terminal device in the simulation channel, wherein the simulation signal is the second DMRS transmitted by the network device based on the second DMRS pattern in the simulation channel. The terminal device can determine the simulation training data of the channel estimation model based on the simulation signal and use the simulation training data to train the channel estimation model.

[0251] In some implementations, the channel estimation model is trained by the network device using simulated training data. The network device can also acquire simulated signals received by terminal devices in a simulated channel, wherein the simulated signals are second DMRS transmitted by the network device based on a second DMRS pattern in the simulated channel. The network device can also determine the simulated training data for the channel estimation model based on the simulated signals and use the simulated training data to train the channel estimation model.

[0252] In this embodiment of the application, when the channel estimation model is trained by a network device, the network device can send the trained channel estimation model to the terminal device.

[0253] In some embodiments of this application, when the channel estimation model is trained by a terminal device, the network device can also receive a second indication information sent by the terminal device, which is used to indicate that the channel estimation model training is complete.

[0254] Optionally, the second indication information may include, in addition to the model training completion indication information, at least one of the following: the capability information of the channel estimation model, and the processing latency information of the channel estimation model. Alternatively, the model training completion indication information may implicitly indicate the completion of training through at least one of the above two types of information.

[0255] The capability information of the channel estimation model refers to its capabilities compared to traditional channel estimation methods. For example, the model can use a lower-density DMRS for channel estimation compared to traditional patterns, or it can obtain higher-accuracy channel estimation results compared to traditional methods. The processing latency information of the channel estimation model refers to the processing latency of the terminal device when using the model, which may include the model loading time and the inference time.

[0256] The network device can determine that the channel estimation model has been trained based on the second instruction information. At the same time, it can also obtain the model's capability information and / or the model's processing latency information, model complexity, model inference power consumption, etc. It can make reasonable scheduling of the terminal device based on the capability information and processing latency information; and decide whether to enable the AI ​​model based on the model's processing latency, model complexity, model inference power consumption, etc.

[0257] Optionally, the second indication information may include at least one of the following signaling: UE capability reporting signaling; User Assistance Information (UAI); Unlimited Resource Control (RRC) signaling; Media Access Control Layer (MAC) control element (CE); and Uplink Control Information (UCI). The second indication information may also be sent via PUSCH.

[0258] In some implementations, where the channel estimation model is trained by a terminal device, the network device can also send a third indication message to the terminal device, which instructs the terminal device to begin training the channel estimation model. This third indication message can be at least 1 bit.

[0259] In some implementations, when the channel estimation model is trained by the terminal device, the terminal device can either start training the channel estimation model directly, or it can start training the model after a preset time has elapsed since the first indication information was sent. This preset time can be configured by the network device, or it can be agreed upon or specified by a protocol.

[0260] In some implementations, network devices may also send de-enable signaling to terminal devices according to business needs and circumstances, instructing terminal devices not to start model training.

[0261] In some implementations, if the channel estimation model is trained using a supervised machine learning method, the network device can also send an impulse signal to the terminal device, which can obtain an ideal channel estimation label based on the impulse signal. This ideal channel estimation label is used for training the channel estimation model.

[0262] In some implementations, where the channel estimation model is trained by the terminal device, if the channel estimation model is trained using a supervised machine learning method, the network device can also receive auxiliary information sent by the terminal device to request the network device to send an impulse signal. The terminal device can then obtain the ideal channel estimation label based on the impulse signal and use the ideal channel estimation label to train the channel estimation model.

[0263] In some implementations, the channel estimation model has the capability to perform channel estimation using a low-density DMRS pattern, where the density of the first DMRS pattern is lower than that of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern. The terminal device can obtain channel estimation results based on this channel estimation model using a lower-density DMRS pattern compared to the legacy DMRS pattern.

[0264] In some implementations, the channel estimation model is capable of providing high-precision channel estimation results, where the density of the first DMRS pattern is the same as the density of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern, and the terminal device can use DMRS patterns with the same density as the legacy DMRS pattern to obtain higher-precision channel estimation results compared to traditional channel estimation methods based on this channel estimation model.

[0265] In some implementations, the network device can also send a fifth indication message to the terminal device, which instructs the terminal device to perform channel estimation based on the channel estimation model. The trained channel estimation model will only be activated for channel estimation when the terminal device receives the fifth indication message.

[0266] Optionally, the fifth indication information can be at least 1 bit of information, directly instructing the terminal device to enable the trained channel estimation model for channel estimation. The fifth indication information can also be the first DMRS pattern configuration sent by the network device to the terminal device to reduce pilot overhead.

[0267] In summary, by sending a first DMRS based on a first DMRS pattern to the terminal device, the first DMRS is used for channel estimation based on the channel estimation model, enabling terminal devices with different capabilities to support channel estimation based on artificial intelligence technology. This effectively improves the accuracy of channel estimation, thereby significantly increasing the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0268] Additionally, optionally, in various embodiments of this application, online model training can also include model updates, and a model update cycle can be defined. Before the end of this model update cycle, the terminal device needs to complete a new round of model training and / or model testing, and redeploy the retrained model. In some embodiments, considering that model loading such as redeployment may take some time, during this time, the terminal device can use the original model for inference (e.g., the terminal device can store at least two models simultaneously, and the new model will not overwrite the original model), or it can use traditional methods for channel estimation (e.g., the new model stored by the terminal device will overwrite the original model). This time can be configured or indicated by the network device, or it can be specified by the protocol.

[0269] The model update cycle can be configured by the network device; or the terminal device can report the shortest supported model update cycle, and the network device can configure a reasonable model update cycle based on the terminal device's report; or the network device can enable or disable the online model training function based on the update cycle reported by the terminal device (considering that if the model update (re-development) time is too long, the model trained based on the channel data at the start of the update may no longer meet the current channel environment, so the model training function can be disabled to avoid doing meaningless work); or the protocol specifies the shortest model training / update cycle, and the terminal device can decide whether to perform online model training and updating based on its own actual situation.

[0270] Please see Figure 8 , Figure 8 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a network device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 8 As shown, the method may include the following steps:

[0271] Step 801: Receive the first DMRS sent by the terminal device based on the first DMRS pattern.

[0272] In this embodiment, the network device can receive a first DMRS sent by a terminal device, which is sent by the terminal device based on a first DMRS pattern. After receiving the first DMRS, the network device can perform uplink channel estimation based on the trained channel estimation model and the first DMRS.

[0273] In some implementations, the network device can receive a second DMRS sent by the terminal device based on a second DMRS pattern, and can determine training data for the channel estimation model based on the second DMRS, and use the training data to train the channel estimation model. The second DMRS pattern can be a legacy DMRS pattern.

[0274] Optionally, in this embodiment, the network device can directly use the received signal of the second DMRS as training data for the channel estimation model, or it can obtain the channel estimate value estimated based on the second DMRS and use the channel estimate value as training data for the channel estimation model. Alternatively, it can obtain other training data based on the configuration of the channel estimation model; this application does not limit this. The channel estimate value obtained based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms; this application also does not limit this.

[0275] In some implementations, the network device uses a supervised machine learning method to train the channel estimation model. The network device can also send indication information to the terminal device, which instructs the terminal device to send an impulse signal. The network device receives the impulse signal sent by the terminal device and can obtain the ideal channel label of the channel based on the impulse signal to train the channel estimation model.

[0276] The transmission period and time-frequency resources occupied by the impulse signal can be configured by the network device, or dynamically scheduled and indicated by the network device.

[0277] It should be noted that the impulse signal sent by the terminal device can be sent separately from the second DMRS or sent together with the second DMRS; this application does not limit this.

[0278] In some implementations, the network device can acquire a simulated signal received by the network device in a simulated channel, wherein the simulated signal is a second DMRS transmitted by the terminal device in the simulated channel based on a second DMRS pattern. The network device can determine the simulation training data for the channel estimation model based on the simulated signal, and use the simulation training data to train the channel estimation model.

[0279] In the embodiments of this application, the channel estimation model can be trained using a supervised machine learning method or an unsupervised machine learning method.

[0280] It should be noted that the channel estimation model in the embodiments of this application can be constructed and trained based on any machine learning method, such as convolutional neural network (CNN), etc., and this application does not limit it.

[0281] In the embodiments of this application, the channel estimation model can be trained using real data or simulated data; it can be trained offline or online.

[0282] It is understood that, in the embodiments of this application, both the first DMRS pattern and the second DMRS pattern are determined by the terminal device based on the configuration and / or instructions of the network device.

[0283] Step 802: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0284] In this embodiment of the application, the network device can perform channel estimation based on the received first DMRS according to the trained channel estimation model.

[0285] It is understood that, in the embodiments of this application, the network device can directly use the received DMRS signal as input to the channel estimation model, or it can obtain the channel estimate value estimated based on the DMRS and use the channel estimate value as input to the channel estimation model. This application does not limit this. The channel estimate value obtained based on the DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms, etc. This application does not limit this either.

[0286] In some implementations, the channel estimation model has the capability to perform channel estimation using a low-density DMRS pattern, where the density of the first DMRS pattern is lower than that of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern. The network device can obtain uplink channel estimation results based on this channel estimation model using a lower-density DMRS pattern compared to the legacy DMRS pattern. The network device can configure or instruct terminal devices to reduce the density of the DMRS pattern based on the capabilities of its trained model.

[0287] In some implementations, the channel estimation model has the capability to provide high-precision channel estimation results, where the density of the first DMRS pattern is the same as the density of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern, and the network device can use DMRS patterns with the same density as the legacy DMRS pattern to obtain higher-precision uplink channel estimation results compared to traditional channel estimation methods based on this channel estimation model.

[0288] In some implementations, for online model training and model updates, if the network device uses conventional methods for uplink channel estimation when updating the model, it may be necessary to configure or instruct the terminal device to use a high-density DMRS pattern (e.g., legacy DMRS pattern) even if the network device has already configured or instructed the terminal device to reduce the density of the DMRS pattern.

[0289] Understandably, after training the channel estimation model, network devices can flexibly choose whether to use it for channel estimation based on actual conditions. If the network device uses the channel model for channel estimation, it can, based on the model's capabilities, configure or indicate a DMRS pattern with reduced density compared to traditional patterns, or configure or indicate a legacy DMRS pattern to the terminal device. If the network device does not use the channel model for channel estimation, it can configure or indicate a high-density DMRS pattern (such as a legacy DMRS pattern) to the terminal device.

[0290] In summary, by receiving the first DMRS transmitted by the terminal device based on the first DMRS pattern, and performing channel estimation based on the channel estimation model according to the first DMRS, the network device can perform uplink channel estimation based on artificial intelligence technology, which effectively improves the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0291] Please see Figure 9 , Figure 9 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a network device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 9 As shown, the method may include the following steps:

[0292] Step 901: Receive the second DMRS sent by the terminal device based on the second DMRS pattern.

[0293] In this embodiment, the network device can receive a second DMRS sent by the terminal device based on a second DMRS pattern, and can determine training data for the channel estimation model based on the second DMRS, and use the training data to train the channel estimation model. The second DMRS pattern can be a legacy DMRS pattern.

[0294] In some implementations, the network device uses a supervised machine learning method to train the channel estimation model. The network device can also send indication information to the terminal device, which instructs the terminal device to send an impulse signal. The network device receives the impulse signal sent by the terminal device and can obtain the ideal channel label of the channel based on the impulse signal to train the channel estimation model.

[0295] The transmission period and time-frequency resources occupied by the impulse signal can be configured by the network device, or dynamically scheduled and indicated by the network device.

[0296] It should be noted that the impulse signal sent by the terminal device can be sent separately from the second DMRS or sent together with the second DMRS; this application does not limit this.

[0297] Step 902: Determine the training data for the channel estimation model based on the second DMRS.

[0298] In this embodiment of the application, the network device can determine the training data of the channel estimation model based on the received second DMRS, and the training data is the actual data obtained through actual channel transmission.

[0299] Optionally, in this embodiment, the network device can directly use the received signal of the second DMRS as training data for the channel estimation model, or it can obtain the channel estimate value estimated based on the second DMRS and use the channel estimate value as training data for the channel estimation model. Alternatively, it can obtain other training data based on the configuration of the channel estimation model; this application does not limit this. The channel estimate value obtained based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms; this application also does not limit this.

[0300] In some implementations, the network device trains the channel estimation model using a supervised machine learning method. The network device can also send indication information to the terminal device, which instructs the terminal device to send an impulse signal. The network device receives the impulse signal sent by the terminal device.

[0301] It should be noted that the impulse signal sent by the terminal device can be sent separately from the second DMRS or sent together with the second DMRS; this application does not limit this.

[0302] Step 903: Use the training data to train the channel estimation model.

[0303] In this embodiment of the application, the network device can use the training data determined in the aforementioned steps to train the channel estimation model.

[0304] In the embodiments of this application, the channel estimation model can be trained using a supervised machine learning method or an unsupervised machine learning method.

[0305] It should be noted that the channel estimation model in the embodiments of this application can be constructed and trained based on any machine learning method, such as convolutional neural network (CNN), etc., and this application does not limit it.

[0306] In some implementations, the network device trains the channel estimation model using a supervised machine learning method. The network device can also train the channel estimation model using the ideal channel label obtained from the received impulse signal.

[0307] Step 904: Receive the first DMRS sent by the terminal device based on the first DMRS pattern.

[0308] Step 905: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0309] In the embodiments of this application, steps 904 to 905 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not elaborate further.

[0310] In summary, by receiving the second DMRS transmitted by the terminal device based on the second DMRS pattern, and determining the training data for the channel estimation model based on the second DMRS, the channel estimation model is trained using the training data. By receiving the first DMRS transmitted by the terminal device based on the first DMRS pattern, and performing channel estimation based on the channel estimation model according to the first DMRS, the network device can perform uplink channel estimation based on artificial intelligence technology, which effectively improves the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0311] Please see Figure 10 , Figure 10 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a network device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 10 As shown, the method may include the following steps:

[0312] Step 1001: Obtain the simulated signal received by the network device in the simulated channel. The simulated signal is the second DMRS sent by the terminal device in the simulated channel based on the second DMRS pattern.

[0313] In this embodiment, the network device can acquire the simulated signal received by the network device in the simulated channel. The simulated signal is the second DMRS transmitted by the terminal device in the simulated channel based on the second DMRS pattern. Furthermore, it can determine the training data for the channel estimation model based on the simulated signal and use the training data to train the channel estimation model.

[0314] The second DMRS pattern can be a legacy DMRS pattern.

[0315] In this embodiment of the application, in the simulated channel model, the terminal device sends DMRS to the network device based on the second DMRS pattern. The network device can obtain the simulated signal received in the simulated channel and determine the simulated data as training data to train the model.

[0316] Step 1002: Based on the simulation signal, determine the simulation training data for the channel estimation model.

[0317] In this embodiment of the application, the network device can determine the training data of the channel estimation model based on the acquired simulation signal. The training data is the simulation data transmitted in the simulation channel.

[0318] Optionally, in this embodiment, the network device can directly use the received simulated signal of the second DMRS as training data for the channel estimation model, or it can obtain the channel estimate value estimated based on the simulated signal of the second DMRS and use the channel estimate value as training data for the channel estimation model. Alternatively, it can obtain other training data based on the configuration of the channel estimation model; this application does not limit this. The channel estimate value at the DMRS obtained based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms; this application also does not limit this.

[0319] In some implementations, the network device uses supervised machine learning methods to train the channel estimation model, and the network device can also obtain the ideal channel label of the simulated channel for training the channel estimation model.

[0320] Step 1003: Use the simulation training data to train the channel estimation model.

[0321] In this embodiment of the application, the network device can use the simulation training data determined in the aforementioned steps to train the channel estimation model.

[0322] In the embodiments of this application, the channel estimation model can be trained using a supervised machine learning method or an unsupervised machine learning method.

[0323] It should be noted that the channel estimation model in the embodiments of this application can be constructed and trained based on any machine learning method, such as convolutional neural network (CNN), etc., and this application does not limit it.

[0324] In some implementations, the network device uses supervised machine learning methods to train the channel estimation model. The network device can also obtain the ideal channel label for the simulated channel to train the channel estimation model. It is understood that in the simulated channel model, the ideal channel label can be obtained by establishing the channel parameters of the simulated channel model.

[0325] Step 1004: Receive the first DMRS sent by the terminal device based on the first DMRS pattern.

[0326] Step 1005: Based on the first DMRS, perform channel estimation using the channel estimation model.

[0327] In the embodiments of this application, steps 1004 to 1005 can be implemented in any of the embodiments of this application. The embodiments of this application do not limit this and will not elaborate further.

[0328] In summary, by acquiring the simulated signal received by the network device in the simulated channel—the simulated signal being the second DMRS transmitted by the terminal device based on the second DMRS pattern in the simulated channel—the simulation training data for the channel estimation model is determined based on the simulated signal. This simulation training data is then used to train the channel estimation model. The network device receives the first DMRS transmitted by the terminal device based on the first DMRS pattern and performs channel estimation based on the channel estimation model. This enables the network device to perform uplink channel estimation based on artificial intelligence technology, effectively improving the accuracy of channel estimation, thereby significantly increasing the decoding success rate, effectively improving the spectral efficiency of the communication system, and saving system pilot overhead.

[0329] Please see Figure 11 , Figure 11 This is a flowchart illustrating a channel estimation method provided in an embodiment of this application. It should be noted that the channel estimation method in this embodiment is executed by a terminal device. This method can be executed independently or in conjunction with any other embodiment of this application. Figure 11 As shown, the method may include the following steps:

[0330] Step 1101: Send the first DMRS to the network device based on the first DMRS pattern. The first DMRS is used for channel estimation based on the channel estimation model.

[0331] In this embodiment, the terminal device can send a first DMRS to the network device based on a first DMRS pattern. After receiving the first DMRS, the network device can perform uplink channel estimation based on the trained channel estimation model and the first DMRS. The first DMRS pattern is determined by the terminal device based on the network device's configuration and / or instructions.

[0332] In some implementations, the terminal device can send a second DMRS pattern to the network device, and the network device can determine training data for the channel estimation model based on the second DMRS, and use the training data to train the channel estimation model. The second DMRS pattern can be a legacy DMRS pattern. This second DMRS pattern is also determined by the terminal device based on the network device's configuration and / or instructions.

[0333] Optionally, in this embodiment, the network device can directly use the received signal of the second DMRS as training data for the channel estimation model, or it can obtain the channel estimate value estimated based on the second DMRS and use that channel estimate value as training data for the channel estimation model. Alternatively, it can obtain other training data based on the configuration of the channel estimation model; this application does not limit this. The channel estimate value at the DMRS obtained based on the second DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms, etc.; this application also does not limit this.

[0334] In some implementations, the network device uses a supervised machine learning method to train the channel estimation model. The terminal device can also receive indication information sent by the network device, which instructs the terminal device to send an impulse signal. The network device receives the impulse signal sent by the terminal device and can obtain the ideal channel label of the channel based on the impulse signal to train the channel estimation model.

[0335] The transmission period and time-frequency resources occupied by the impulse signal can be configured by the network device, or dynamically scheduled and indicated by the network device.

[0336] It should be noted that the impulse signal sent by the terminal device can be sent separately from the second DMRS or sent together with the second DMRS; this application does not limit this.

[0337] In some implementations, the network device can acquire a simulated signal received by the network device in a simulated channel, wherein the simulated signal is a second DMRS transmitted by the terminal device in the simulated channel based on a second DMRS pattern. The network device can determine the simulation training data for the channel estimation model based on the simulated signal, and use the simulation training data to train the channel estimation model.

[0338] In the embodiments of this application, the channel estimation model can be trained using a supervised machine learning method or an unsupervised machine learning method.

[0339] It should be noted that the channel estimation model in the embodiments of this application can be constructed and trained based on any machine learning method, such as convolutional neural network (CNN), etc., and this application does not limit it.

[0340] In the embodiments of this application, the channel estimation model can be trained using real data or simulated data; it can be trained offline or online.

[0341] In this embodiment of the application, the network device can perform channel estimation based on the received first DMRS according to the trained channel estimation model.

[0342] It is understood that, in the embodiments of this application, the network device can directly use the received DMRS signal as input to the channel estimation model, or it can obtain the channel estimate value estimated based on the DMRS and use the channel estimate value as input to the channel estimation model. This application does not limit this. The channel estimate value at the DMRS obtained by estimating the channel based on the DMRS can be estimated using the least squares method (LS), the minimum mean square error method (MMSE), or other estimation algorithms, etc. This application does not limit this either.

[0343] In some implementations, the channel estimation model has the capability to perform channel estimation using a low-density DMRS pattern, where the density of the first DMRS pattern is lower than that of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern. The network device can obtain uplink channel estimation results based on this channel estimation model using a lower-density DMRS pattern compared to the legacy DMRS pattern. The network device can configure or instruct terminal devices to reduce the density of the DMRS pattern based on the capabilities of its trained model.

[0344] In some implementations, the channel estimation model has the capability to provide high-precision channel estimation results, where the density of the first DMRS pattern is the same as the density of the second DMRS pattern. The second DMRS pattern can be a legacy DMRS pattern, and the network device can use DMRS patterns with the same density as the legacy DMRS pattern to obtain higher-precision uplink channel estimation results compared to traditional channel estimation methods based on this channel estimation model.

[0345] In some implementations, for online model training and model updates, if the network device uses conventional methods for uplink channel estimation during model updates, and the network device has already configured or instructed the terminal device to reduce the density of the DMRS pattern, it may also be necessary to configure or instruct the terminal device to use a high-density DMRS pattern (e.g., a legacy DMRS pattern). The terminal device then sends the DMRS pattern according to the network device's configuration or instructions.

[0346] In summary, by sending a first DMRS based on a first DMRS pattern to the network device, the first DMRS is used for channel estimation based on the channel estimation model, enabling the network device to perform uplink channel estimation based on artificial intelligence technology. This effectively improves the accuracy of channel estimation, thereby significantly increasing the decoding success rate, effectively improving the spectral efficiency of the communication system, and saving the system's pilot overhead.

[0347] Corresponding to the channel estimation methods provided in the above embodiments, this application also provides a channel estimation apparatus. Since the channel estimation apparatus provided in this application corresponds to the methods provided in the above embodiments, the implementation of the channel estimation method is also applicable to the channel estimation apparatus provided in the following embodiments, which will not be described in detail in the following embodiments.

[0348] Please see Figure 12 , Figure 12 This is a schematic diagram of a channel estimation device provided in an embodiment of this application.

[0349] like Figure 12 As shown, the channel estimation device 1200 includes: a transceiver unit 1210 and a processing unit 1220, wherein:

[0350] Transceiver unit 1210 is used to receive a first DMRS transmitted by the network device based on a first demodulation reference signal DMRS pattern;

[0351] The processing unit 1220 is used to perform channel estimation based on the channel estimation model according to the first DMRS.

[0352] Optionally, the transceiver unit 1210 is also used for:

[0353] Send a first indication message to the network device, the first indication message being used to indicate whether the terminal device has model training capability.

[0354] Optionally, the transceiver unit 1210 is also used for:

[0355] Receive the second DMRS sent by the network device based on the second DMRS pattern;

[0356] Based on the second DMRS, the training data for the channel estimation model is determined.

[0357] Optionally, the processing unit 1220 is further configured to:

[0358] The channel estimation model was trained using this training data.

[0359] Optionally, the transceiver unit 1210 is also used for:

[0360] The training data is sent to the network device and used to train the channel estimation model.

[0361] Optionally, the processing unit 1220 is further configured to:

[0362] The simulated signal received by the terminal device in the simulated channel is obtained. The simulated signal is the second DMRS sent by the network device in the simulated channel based on the second DMRS pattern.

[0363] Based on the simulation signal, determine the simulation training data for the channel estimation model;

[0364] The channel estimation model was trained using the simulation training data.

[0365] Optionally, the transceiver unit 1210 is also used for:

[0366] Receive the channel estimation model that has been trained and sent by the network device.

[0367] Optionally, the transceiver unit 1210 is also used for:

[0368] A second indication message is sent to the network device, which indicates that the channel estimation model training is complete.

[0369] Optionally, the second indication information includes at least one of the following: capability information of the channel estimation model, and processing delay information of the channel estimation model.

[0370] Optionally, the transceiver unit 1210 is also used for:

[0371] The terminal device receives a third instruction message sent by the network device, which instructs the terminal device to begin training the channel estimation model.

[0372] Optionally, the transceiver unit 1210 is also used for:

[0373] Receive a fourth indication message sent by the network device, which indicates the type of training data.

[0374] Optionally, the density of the first DMRS pattern is lower than the density of the second DMRS pattern;

[0375] Among them, the capability information of this channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

[0376] Optionally, the density of the first DMRS pattern is the same as the density of the second DMRS pattern;

[0377] Among them, the capability information of this channel estimation model is that it has the ability to provide high-precision channel estimation results.

[0378] Optionally, the transceiver unit 1210 is also used for:

[0379] Receive impulse signals sent by the network device;

[0380] Based on the impulse signal, the ideal channel estimation label for the channel is determined, and the ideal channel estimation label is used for training the channel estimation model.

[0381] The channel estimation model is trained using a supervised machine learning device.

[0382] Optionally, the transceiver unit 1210 is also used for:

[0383] Send auxiliary information to the network device, which is used to request the impulse signal;

[0384] The terminal device uses the ideal channel estimation label to train the channel estimation model.

[0385] Optionally, the first indication information includes at least one of the following:

[0386] This terminal device's model training capability indication information;

[0387] Information on the hardware processing capabilities of the terminal device;

[0388] The computing power information of this terminal device;

[0389] This information pertains to the power consumption capabilities of the terminal device.

[0390] Optionally, the transceiver unit 1210 is also used for:

[0391] The terminal device receives a fifth indication message sent by the network device, which instructs the terminal device to perform channel estimation based on the channel estimation model.

[0392] The channel estimation device in this embodiment can receive a first DMRS sent by a network device based on a first demodulation reference signal DMRS pattern, and perform channel estimation based on a channel estimation model according to the first DMRS. This enables terminal devices with different capabilities to support channel estimation based on artificial intelligence technology, effectively improving the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0393] Please see Figure 13 , Figure 13 This is a schematic diagram of a channel estimation device provided in an embodiment of this application.

[0394] like Figure 13 As shown, the channel estimation device 1300 includes: a transceiver unit 1310, wherein:

[0395] Transceiver unit 1310 is used to transmit a first DMRS to a terminal device based on a first demodulation reference signal DMRS pattern;

[0396] The first DMRS is used for channel estimation based on the channel estimation model.

[0397] Optionally, the transceiver unit 1310 is also used for:

[0398] The terminal device receives a first indication message, which indicates whether the terminal device has model training capability.

[0399] Optionally, the transceiver unit 1310 is also used for:

[0400] Send the second DMRS to the terminal device based on the second DMRS pattern;

[0401] The second DMRS is used to determine the training data for the channel estimation model.

[0402] Optionally, the transceiver unit 1310 is also used for:

[0403] Receive the training data sent by the terminal device;

[0404] The channel estimation model was trained using this training data.

[0405] Optionally, the transceiver unit 1310 is also used for:

[0406] The simulated signal received by the terminal device in the simulated channel is obtained. The simulated signal is the second DMRS sent by the network device in the simulated channel based on the second DMRS pattern.

[0407] Based on the simulation signal, determine the simulation training data for the channel estimation model;

[0408] The channel estimation model was trained using the simulation training data.

[0409] Optionally, the transceiver unit 1310 is also used for:

[0410] Receive the channel estimation model that has been trained and sent by the network device.

[0411] Optionally, the transceiver unit 1310 is also used for:

[0412] The terminal device receives a second indication message, which indicates that the channel estimation model training is complete.

[0413] Optionally, the second indication information includes at least one of the following: capability information of the channel estimation model, and processing delay information of the channel estimation model.

[0414] Optionally, the transceiver unit 1310 is also used for:

[0415] A third instruction message is sent to the terminal device, which instructs the terminal device to begin training the channel estimation model.

[0416] Optionally, the transceiver unit 1310 is also used for:

[0417] A fourth instruction message is sent to the terminal device, which indicates the type of training data.

[0418] Optionally, the density of the first DMRS pattern is lower than the density of the second DMRS pattern;

[0419] Among them, the capability information of this channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

[0420] Optionally, the density of the first DMRS pattern is the same as the density of the second DMRS pattern;

[0421] Among them, the capability information of this channel estimation model is that it has the ability to provide high-precision channel estimation results.

[0422] Optionally, the transceiver unit 1310 is also used for:

[0423] Send an impulse signal to the terminal device;

[0424] The impulse signal is used to determine the ideal channel estimation label for the channel, and the ideal channel estimation label is used to train the channel estimation model;

[0425] The channel estimation model is trained using a supervised machine learning device.

[0426] Optionally, the transceiver unit 1310 is also used for:

[0427] Receive auxiliary information sent by the terminal device, which is used to request the impulse signal;

[0428] The terminal device uses the ideal channel estimation label to train the channel estimation model.

[0429] Optionally, the first indication information includes at least one of the following:

[0430] This terminal device's model training capability indication information;

[0431] Information on the hardware processing capabilities of the terminal device;

[0432] The computing power information of this terminal device;

[0433] This information pertains to the power consumption capabilities of the terminal device.

[0434] Optionally, the transceiver unit 1310 is also used for:

[0435] A fifth instruction message is sent to the terminal device, which instructs the terminal device to perform channel estimation based on the channel estimation model.

[0436] The channel estimation device in this embodiment can send a first DMRS to the terminal device based on a first DMRS pattern. The first DMRS is used to perform channel estimation based on the channel estimation model, so that terminal devices with different capabilities can support channel estimation based on artificial intelligence technology, which effectively improves the accuracy of channel estimation, thereby greatly improving the success rate of decoding, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0437] Please see Figure 14 , Figure 14 This is a schematic diagram of a channel estimation device provided in an embodiment of this application.

[0438] like Figure 14 As shown, the channel estimation device 1400 includes: a transceiver unit 1410 and a processing unit 1420, wherein:

[0439] Transceiver unit 1410 is used to receive a first DMRS transmitted by a terminal device based on a first demodulation reference signal DMRS pattern;

[0440] The processing unit 1420 is used to perform channel estimation based on the channel estimation model according to the first DMRS.

[0441] Optionally, the transceiver unit 1410 is also used for:

[0442] Receive the second DMRS sent by the terminal device based on the second DMRS pattern;

[0443] Based on the second DMRS, the training data for the channel estimation model is determined;

[0444] The channel estimation model was trained using this training data.

[0445] Optionally, the transceiver unit 1410 is also used for:

[0446] Send an instruction message to the terminal device, the instruction message being used to instruct the terminal device to send an impulse signal;

[0447] Receive the impulse signal sent by the terminal device;

[0448] Based on the impulse signal, the ideal channel estimation label for the channel is determined, and the ideal channel estimation label is used for training the channel estimation model.

[0449] The channel estimation model is trained using a supervised machine learning device.

[0450] Optionally, the processing unit 1420 is further configured to:

[0451] The network device receives the simulated signal in the simulated channel, which is the second DMRS sent by the terminal device in the simulated channel based on the second DMRS pattern;

[0452] Based on the simulation signal, determine the simulation training data for the channel estimation model;

[0453] The channel estimation model was trained using the simulation training data.

[0454] Optionally, the density of the first DMRS pattern is lower than the density of the second DMRS pattern;

[0455] Among them, the capability information of this channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

[0456] Optionally, the density of the first DMRS pattern is the same as the density of the second DMRS pattern;

[0457] Among them, the capability information of this channel estimation model is that it has the ability to provide high-precision channel estimation results.

[0458] The channel estimation device in this embodiment can receive a first DMRS sent by a terminal device based on a first DMRS pattern, and perform channel estimation based on the channel estimation model according to the first DMRS. This enables the network device to perform uplink channel estimation based on artificial intelligence technology, which effectively improves the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0459] Please see Figure 15 , Figure 15 This is a schematic diagram of a channel estimation device provided in an embodiment of this application.

[0460] like Figure 15 As shown, the channel estimation device 1500 includes: a transceiver unit 1510, wherein:

[0461] Transceiver unit 1510 is used to transmit a first DMRS to a network device based on a first demodulation reference signal DMRS pattern;

[0462] The first DMRS is used for channel estimation based on the channel estimation model.

[0463] Optionally, the transceiver unit 1510 is also used for:

[0464] Send the second DMRS to the network device based on the second DMRS pattern;

[0465] The second DMRS is used to determine the training data for the channel estimation model.

[0466] Optionally, the transceiver unit 1510 is also used for:

[0467] Receive the indication information sent by the network device, which is used to instruct the terminal device to send an impulse signal;

[0468] Send the impulse signal to the network device;

[0469] Based on the impulse signal, the ideal channel estimation label for the channel is determined, and the ideal channel estimation label is used for training the channel estimation model.

[0470] The channel estimation model is trained using a supervised machine learning device.

[0471] Optionally, the density of the first DMRS pattern is lower than the density of the second DMRS pattern;

[0472] Among them, the capability information of this channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

[0473] Optionally, the density of the first DMRS pattern is the same as the density of the second DMRS pattern;

[0474] Among them, the capability information of this channel estimation model is that it has the ability to provide high-precision channel estimation results.

[0475] The channel estimation device in this embodiment can send a first DMRS to the network device based on a first DMRS pattern. The first DMRS is used to perform channel estimation based on the channel estimation model, enabling the network device to perform uplink channel estimation based on artificial intelligence technology. This effectively improves the accuracy of channel estimation, thereby significantly improving the decoding success rate, effectively improving the spectrum efficiency of the communication system, and saving the system's pilot overhead.

[0476] To implement the above embodiments, this application also proposes a communication device, including: a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory to cause the device to perform... Figures 2 to 6 The method shown in the embodiment.

[0477] To implement the above embodiments, this application also proposes a communication device, including: a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory to cause the device to perform... Figure 7 The method shown in the embodiment.

[0478] To implement the above embodiments, this application also proposes a communication device, including: a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory to cause the device to perform... Figures 8 to 10 The method shown in the embodiment.

[0479] To implement the above embodiments, this application also proposes a communication device, including: a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory to cause the device to perform... Figure 11 The method shown in the embodiment.

[0480] To implement the above embodiments, this application also proposes a communication device, including: a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to execute the code instructions to perform... Figures 2 to 6 The method shown in the embodiment.

[0481] To implement the above embodiments, this application also proposes a communication device, including: a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to execute the code instructions to perform... Figure 7The method shown in the embodiment.

[0482] To implement the above embodiments, this application also proposes a communication device, including: a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to execute the code instructions to perform... Figures 8 to 10 The method shown in the embodiment.

[0483] To implement the above embodiments, this application also proposes a communication device, including: a processor and an interface circuit, wherein the interface circuit is used to receive code instructions and transmit them to the processor, and the processor is used to execute the code instructions to perform... Figure 11 The method shown in the embodiment.

[0484] Please see Figure 16 , Figure 16 This is a schematic diagram of another channel estimation device provided in this embodiment. The channel estimation device 1600 can be a network device, a terminal device, a chip, chip system, or processor that supports the network device in implementing the above method, or a chip, chip system, or processor that supports the terminal device in implementing the above method. This device can be used to implement the methods described in the above method embodiments, and for details, please refer to the description in the above method embodiments.

[0485] The channel estimation device 1600 may include one or more processors 1601. The processor 1601 may be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control the channel estimation device (e.g., base station, baseband chip, terminal equipment, terminal equipment chip, DU or CU, etc.), execute computer programs, and process data from the computer programs.

[0486] Optionally, the channel estimation device 1600 may further include one or more memories 1602, on which a computer program 1603 may be stored. The processor 1601 executes the computer program 1603 to cause the channel estimation device 1600 to perform the method described in the above method embodiments. The computer program 1603 may be embedded in the processor 1601, in which case the processor 1601 may be implemented in hardware.

[0487] Optionally, the memory 1602 may also store data. The channel estimation device 1600 and the memory 1602 can be configured separately or integrated together.

[0488] Optionally, the channel estimation device 1600 may further include a transceiver 1605 and an antenna 1606. The transceiver 1605 may be referred to as a transceiver unit, transceiver, or transceiver circuit, etc., and is used to implement the transceiver function. The transceiver 1605 may include a receiver and a transmitter. The receiver may be referred to as a receiver or receiving circuit, etc., and is used to implement the receiving function; the transmitter may be referred to as a transmitter or transmitting circuit, etc., and is used to implement the transmitting function.

[0489] Optionally, the channel estimation device 1600 may further include one or more interface circuits 1607. The interface circuits 1607 are used to receive code instructions and transmit them to the processor 1601. The processor 1601 executes the code instructions to cause the channel estimation device 1600 to perform the method described in the above method embodiments.

[0490] In one implementation, the processor 1601 may include a transceiver for implementing receive and transmit functions. For example, the transceiver may be a transceiver circuit, an interface, or an interface circuit. The transceiver circuit, interface, or interface circuit for implementing receive and transmit functions may be separate or integrated. The aforementioned transceiver circuit, interface, or interface circuit may be used for reading and writing code / data, or it may be used for transmitting or relaying signals.

[0491] In one implementation, the channel estimation device 1600 may include circuitry capable of performing the transmitting, receiving, or communication functions described in the foregoing method embodiments. The processor and transceiver described in this disclosure can be implemented on integrated circuits (ICs), analog ICs, radio frequency integrated circuits (RFICs), mixed-signal ICs, application-specific integrated circuits (ASICs), printed circuit boards (PCBs), electronic devices, etc. The processor and transceiver can also be manufactured using various IC process technologies, such as complementary metal oxide semiconductors (CMOS), n-metal-oxide-semiconductor (NMOS), positive channel metal oxide semiconductors (PMOS), bipolar junction transistors (BJTs), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

[0492] The channel estimation device described in the above embodiments can be a network device or a terminal device, but the scope of the channel estimation device described in this disclosure is not limited to this, and the structure of the channel estimation device is not limited to this. Figures 12-15 The channel estimation device can be a standalone device or part of a larger device. For example, the channel estimation device could be:

[0493] (1) Independent integrated circuit IC, or chip, or chip system or subsystem;

[0494] (2) A collection of one or more ICs, optionally including storage components for storing data and computer programs;

[0495] (3) ASIC, such as modem;

[0496] (4) Modules that can be embedded in other devices;

[0497] (5) Receivers, terminal equipment, smart terminal equipment, cellular phones, wireless equipment, handheld devices, mobile units, vehicle-mounted equipment, network equipment, cloud equipment, artificial intelligence equipment, etc.

[0498] (6) Others, etc.

[0499] For cases where the channel estimation device can be a chip or a chip system, please refer to [link / reference]. Figure 17 The diagram shows the structure of the chip. Figure 17 The chip shown includes a processor 1701 and an interface 1702. There can be one or more processors 1701, and multiple interfaces 1702.

[0500] For cases where the chip is used to implement the functions of the network device in the embodiments of this disclosure:

[0501] Interface 1702 is used for code instructions and their transmission to the processor;

[0502] Processor 1701 is used to run code instructions to perform tasks such as Figures 2 to 6 The method, or the execution of such Figure 11 The method.

[0503] Regarding the case where the chip is used to implement the functions of the terminal device in the embodiments of this disclosure:

[0504] Interface 1702 is used for code instructions and their transmission to the processor;

[0505] Processor 1701 is used to run code instructions to perform tasks such as Figure 7 The method, or the execution of such Figures 8 to 10 The method.

[0506] Optionally, the chip also includes a memory 1703, which is used to store necessary computer programs and data.

[0507] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this disclosure can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented in hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this disclosure.

[0508] This disclosure also provides a communication system, which includes the aforementioned... Figures 8-9 The embodiments include a channel estimation device as a terminal device and a channel estimation device as a network device; alternatively, the system includes the aforementioned. Figure 10 The embodiments include a channel estimation device as a terminal device and a channel estimation device as a network device.

[0509] This disclosure also provides a readable storage medium having instructions stored thereon that, when executed by a computer, implement the functions of any of the above method embodiments.

[0510] This disclosure also provides a computer program product that, when executed by a computer, implements the functions of any of the above method embodiments.

[0511] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer programs. When a computer program is loaded and executed on a computer, it generates, in whole or in part, the flow or function according to the embodiments of this disclosure. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, a computer program can be transferred from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0512] Those skilled in the art will understand that the various numerical designations such as "first," "second," etc., used in this disclosure are merely for the convenience of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate the order of events.

[0513] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0514] The correspondences shown in the tables of this disclosure can be configured or predefined. The values ​​of the information in each table are merely examples and can be configured to other values; this disclosure is not limiting. When configuring the correspondences between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, the correspondences shown in some rows of the tables in this disclosure may not be configured. Furthermore, appropriate modifications and adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the headers of the above tables can also use other names that the communication device can understand, and the values ​​or representations of the parameters can also be other values ​​or representations that the communication device can understand. In the implementation of the above tables, other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables, or hash tables, etc.

[0515] The predefined terms in this disclosure can be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0516] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0517] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0518] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the embodiments of this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0519] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A channel estimation method, characterized in that, The method is executed by a terminal device, and the method includes: The receiving network device transmits a first DMRS based on a first demodulated reference signal DMRS pattern; Receive the second DMRS sent by the network device based on the second DMRS pattern; Based on the second DMRS, training data for the channel estimation model is determined, and the training data is used to train the channel estimation model. Channel estimation is performed based on the first DMRS and the channel estimation model.

2. The method according to claim 1, characterized in that, The method further includes: Send a first indication message to the network device, the first indication message being used to indicate whether the terminal device has model training capability.

3. The method according to claim 1, characterized in that, The method further includes: The channel estimation model is trained using the training data.

4. The method according to claim 1, characterized in that, The method further includes: The training data is sent to the network device.

5. The method according to claim 2, characterized in that, The method further includes: The simulation signal received by the terminal device in the simulation channel is obtained, wherein the simulation signal is the second DMRS sent by the network device in the simulation channel based on the second DMRS pattern; Based on the simulation signal, determine the simulation training data for the channel estimation model; The channel estimation model is trained using the simulation training data.

6. The method according to claim 2 or 4, characterized in that, The method further includes: Receive the channel estimation model that has been trained and sent by the network device.

7. The method according to claim 3 or 5, characterized in that, The method further includes: Send a second indication message to the network device, the second indication message being used to indicate that the channel estimation model training is complete.

8. The method according to claim 7, characterized in that, The second indication information includes at least one of the following: capability information of the channel estimation model, and processing delay information of the channel estimation model.

9. The method according to claim 3 or 5, characterized in that, The method further includes: The terminal device receives a third indication message sent by the network device, the third indication message being used to instruct the terminal device to start training the channel estimation model.

10. The method according to claim 4, characterized in that, The method further includes: The network device receives a fourth indication message, which indicates the type of the training data.

11. The method according to any one of claims 2-5, characterized in that, The density of the first DMRS pattern is lower than the density of the second DMRS pattern; The capability information of the channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

12. The method according to any one of claims 2-5, characterized in that, The density of the first DMRS pattern is the same as the density of the second DMRS pattern; The capability information of the channel estimation model is its ability to provide high-precision channel estimation results.

13. The method according to claim 3 or 4, characterized in that, The method further includes: Receive impulse signals sent by the network device; Based on the impulse signal, an ideal channel estimation label for the channel is determined, and the ideal channel estimation label is used for training the channel estimation model; The channel estimation model is trained using a supervised machine learning method.

14. The method according to claim 13, characterized in that, The method further includes: Send auxiliary information to the network device, the auxiliary information being used to request the impulse signal; The terminal device uses the ideal channel estimation label to train the channel estimation model.

15. The method according to claim 2, characterized in that, The first indication information includes at least one of the following: The model training capability indication information of the terminal device; The hardware processing capability information of the terminal device; The computing power information of the terminal device; The power consumption capability information of the terminal device.

16. The method according to any one of claims 1-6, characterized in that, The method further includes: The terminal device receives a fifth indication message sent by the network device, the fifth indication message being used to instruct the terminal device to perform channel estimation based on the channel estimation model.

17. A channel estimation method, characterized in that, The method is performed by a network device, and the method includes: The first DMRS is sent to the terminal device based on the first demodulated reference signal DMRS pattern; The second DMRS is sent to the terminal device based on the second DMRS pattern; The second DMRS is used to determine the training data for the channel estimation model, and the training data is used to train the channel estimation model; the first DMRS is used to perform channel estimation based on the channel estimation model.

18. The method according to claim 17, characterized in that, The method further includes: The terminal device receives a first indication message, which indicates whether the terminal device has model training capability.

19. The method according to claim 17, characterized in that, The method further includes: Receive the training data sent by the terminal device; The channel estimation model is trained using the training data.

20. The method according to claim 18, characterized in that, The method further includes: The simulation signal received by the terminal device in the simulation channel is obtained, wherein the simulation signal is the second DMRS sent by the network device in the simulation channel based on the second DMRS pattern; Based on the simulation signal, determine the simulation training data for the channel estimation model; The channel estimation model is trained using the simulation training data.

21. The method according to claim 19 or 20, characterized in that, The method further includes: The trained channel estimation model is sent to the terminal.

22. The method according to claim 18 or 17, characterized in that, The method further includes: The terminal device receives a second indication message, which indicates that the channel estimation model training is complete.

23. The method according to claim 22, characterized in that, The second indication information includes at least one of the following: capability information of the channel estimation model, and processing delay information of the channel estimation model.

24. The method according to claim 17 or 18, characterized in that, The method further includes: A third instruction message is sent to the terminal device, the third instruction message being used to instruct the terminal device to begin training the channel estimation model.

25. The method according to claim 19, characterized in that, The method further includes: A fourth indication message is sent to the terminal device, the fourth indication message being used to indicate the type of the training data.

26. The method according to any one of claims 18-20, characterized in that, The density of the first DMRS pattern is lower than the density of the second DMRS pattern; The capability information of the channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

27. The method according to any one of claims 18-20, characterized in that, The density of the first DMRS pattern is the same as the density of the second DMRS pattern; The capability information of the channel estimation model is its ability to provide high-precision channel estimation results.

28. The method according to claim 17 or 19, characterized in that, The method further includes: Send an impulse signal to the terminal device; The impulse signal is used to determine the ideal channel estimation label of the channel, and the ideal channel estimation label is used for training the channel estimation model; The channel estimation model is trained using a supervised machine learning method.

29. The method according to claim 28, characterized in that, The method further includes: Receive auxiliary information sent by the terminal device, the auxiliary information being used to request the impulse signal; The terminal device uses the ideal channel estimation label to train the channel estimation model.

30. The method according to claim 18, characterized in that, The first indication information includes at least one of the following: The model training capability indication information of the terminal device; The hardware processing capability information of the terminal device; The computing power information of the terminal device; The power consumption capability information of the terminal device.

31. The method according to any one of claims 17-20, characterized in that, The method further includes: A fifth instruction message is sent to the terminal device, the fifth instruction message being used to instruct the terminal device to perform channel estimation based on the channel estimation model.

32. A channel estimation method, characterized in that, The method is performed by a network device, and the method includes: The receiving terminal device transmits a first DMRS based on a first demodulated reference signal DMRS pattern; Receive the second DMRS sent by the terminal device based on the second DMRS pattern; Based on the second DMRS, determine the training data for the channel estimation model; The channel estimation model is trained using the training data; Channel estimation is performed based on the first DMRS and the channel estimation model.

33. The method according to claim 32, characterized in that, The method further includes: Send instruction information to the terminal device, the instruction information being used to instruct the terminal device to send an impulse signal; Receive the impulse signal sent by the terminal device; Based on the impulse signal, an ideal channel estimation label for the channel is determined, and the ideal channel estimation label is used for training the channel estimation model; The channel estimation model is trained using a supervised machine learning method.

34. The method according to claim 32, characterized in that, The method further includes: The network device receives the simulated signal in the simulated channel, wherein the simulated signal is the second DMRS sent by the terminal device in the simulated channel based on the second DMRS pattern; Based on the simulation signal, determine the simulation training data for the channel estimation model; The channel estimation model is trained using the simulation training data.

35. The method according to any one of claims 32-34, characterized in that, The density of the first DMRS pattern is lower than the density of the second DMRS pattern; The capability information of the channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

36. The method according to any one of claims 32-34, characterized in that, The density of the first DMRS pattern is the same as the density of the second DMRS pattern; The capability information of the channel estimation model is its ability to provide high-precision channel estimation results.

37. A channel estimation method, characterized in that, The method is executed by a terminal device, and the method includes: The first DMRS is sent to the network device based on the first demodulation reference signal DMRS pattern; Send the second DMRS to the network device based on the second DMRS pattern; The second DMRS is used to determine the training data for the channel estimation model, and the training data is used to train the channel estimation model; the first DMRS is used to perform channel estimation based on the channel estimation model.

38. The method according to claim 37, characterized in that, The method further includes: The terminal device receives an indication message sent by the network device, the indication message being used to instruct the terminal device to send an impulse signal; Send the impulse signal to the network device; Based on the impulse signal, an ideal channel estimation label for the channel is determined, and the ideal channel estimation label is used for training the channel estimation model; The channel estimation model is trained using a supervised machine learning method.

39. The method according to claim 37 or 38, characterized in that, The density of the first DMRS pattern is lower than the density of the second DMRS pattern; The capability information of the channel estimation model is that it has the ability to perform channel estimation using low-density DMRS.

40. The method according to claim 37 or 38, characterized in that, The density of the first DMRS pattern is the same as the density of the second DMRS pattern; The capability information of the channel estimation model is its ability to provide high-precision channel estimation results.

41. A channel estimation device, characterized in that, The device includes: The transceiver unit is used to receive the first DMRS transmitted by the network device based on the first demodulation reference signal DMRS pattern; The transceiver unit is also configured to receive the second DMRS sent by the network device based on the second DMRS pattern; The processing unit is configured to determine training data for the channel estimation model based on the second DMRS, wherein the training data is used to train the channel estimation model. The processing unit is further configured to perform channel estimation based on the channel estimation model according to the first DMRS.

42. A channel estimation device, characterized in that, The device includes: The transceiver unit is used to send the first DMRS to the terminal device based on the first demodulated reference signal DMRS pattern; The transceiver unit is also configured to send a second DMRS to the terminal device based on the second DMRS pattern; The second DMRS is used to determine the training data for the channel estimation model, and the training data is used to train the channel estimation model; the first DMRS is used to perform channel estimation based on the channel estimation model.

43. A channel estimation device, characterized in that, The device includes: The transceiver unit is used to receive the first DMRS transmitted by the terminal device based on the first demodulation reference signal DMRS pattern; The transceiver unit is also configured to receive the second DMRS transmitted by the terminal device based on the second DMRS pattern; The processing unit is used to determine the training data for the channel estimation model based on the second DMRS. The processing unit is further configured to train the channel estimation model using the training data; The processing unit is further configured to perform channel estimation based on the channel estimation model according to the first DMRS.

44. A channel estimation device, characterized in that, The device includes: The transceiver unit is used to send a first DMRS to the network device based on a first demodulation reference signal DMRS pattern; The transceiver unit is also configured to send a second DMRS to the network device based on the second DMRS pattern; The second DMRS is used to determine the training data for the channel estimation model, and the training data is used to train the channel estimation model; the first DMRS is used to perform channel estimation based on the channel estimation model.

45. A communication device, characterized in that, The device includes a processor and a memory, the memory storing a computer program, the processor executing the computer program stored in the memory to cause the device to perform the method as described in any one of claims 1 to 40.

46. ​​A computer-readable storage medium for storing instructions that, when executed, cause the method of any one of claims 1 to 40 to be implemented.

Images