Wireless communication method, terminal device and network device

Abstract

A wireless communication method, a terminal device and a network device, the method comprising: a terminal device performing joint training on a first model and a second model according to first input information and tag channel data; wherein the first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, and the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information; the resource density of the reference signal configured by the first configuration information is smaller than the resource density of the reference signal configured by the second configuration information; the first model is used for performing channel estimation based on first input information to obtain first output information, the second model is used for compressing and recovering second input information to obtain target channel state information (CSI), and the second input information is determined according to the first output information.

Description

Wireless communication method, terminal device and network device Technical Field

[0001] The embodiments of the present application relate to the field of communications, and specifically to a wireless communication method, terminal device, and network device. Background Art

[0002] The signal transmission performance under Multiple-Input Multiple-Output (MIMO) technology depends largely on the feedback accuracy of Channel State Information (CSI).

[0003] In related technologies, terminal devices can use received pilot signals to perform channel estimation and further provide CSI feedback based on the estimated channel information. Therefore, the performance of CSI estimation and CSI feedback will affect the final signal transmission performance. How to perform CSI estimation and feedback to improve signal transmission performance is an issue that needs to be addressed urgently.

[0004] Summary of the Invention

[0005] The present application provides a wireless communication method, terminal device and network device, wherein the terminal device or network device can jointly train the CSI estimation model and the CSI feedback model, thereby taking into account both the channel estimation performance and the CSI feedback performance, thereby improving the signal transmission performance.

[0006] In a first aspect, a method for wireless communication is provided, including: a terminal device jointly training a first model and a second model based on first input information and labeled channel data; wherein, the first input information is channel data obtained by the terminal device based on receiving a reference signal based on first configuration information, and the labeled channel data is channel data obtained by the terminal device based on receiving a reference signal based on second configuration information, and the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; the first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined based on the first output information.

[0007] In a second aspect, a method for wireless communication is provided, including: a network device sends first configuration information and second configuration information to a terminal device, wherein the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information.

[0008] According to a third aspect, a method for wireless communication is provided, including: a network device jointly training a first model and a second model based on first input information and labeled channel data; wherein, the first input information is channel data obtained by a terminal device receiving a reference signal based on first configuration information, and the labeled channel data is channel data obtained by the terminal device receiving a reference signal based on second configuration information, and the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; the first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined based on the first output information.

[0009] In a fourth aspect, a method for wireless communication is provided, including: a terminal device sends first input information and labeled channel data to a network device, the first input information and the labeled channel data are used to jointly train a first model and a second model; wherein, the first input information is channel data obtained by the terminal device based on receiving a reference signal based on first configuration information, and the labeled channel data is channel data obtained by the terminal device based on receiving a reference signal based on second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; the first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined based on the first output information.

[0010] In a fifth aspect, a terminal device is provided for executing the method in the above-mentioned first aspect or fourth aspect or its respective implementation manners.

[0011] Specifically, the terminal device includes a functional module for executing the method in the above-mentioned first aspect or fourth aspect or its respective implementation manners.

[0012] In a sixth aspect, a network device is provided for executing the method in the second aspect or the third aspect or their respective implementations.

[0013] Specifically, the network device includes a functional module for executing the method in the above-mentioned second aspect or third aspect or its respective implementation manners.

[0014] In a seventh aspect, a terminal device is provided, comprising a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the method of the first aspect or the fourth aspect or any implementation thereof.

[0015] In an eighth aspect, a network device is provided, comprising a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the method of the second aspect or the third aspect or any implementation thereof.

[0016] In a ninth aspect, a chip is provided for implementing the method described in any one of the first to fourth aspects or their respective implementations. Specifically, the chip includes a processor configured to retrieve and execute a computer program from a memory, causing a device equipped with the chip to perform the method described in any one of the first to fourth aspects or their respective implementations.

[0017] In a tenth aspect, a computer-readable storage medium is provided for storing a computer program, which enables a computer to execute the method of any one of the first to fourth aspects or its various implementations.

[0018] In an eleventh aspect, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method of any one of the first to fourth aspects or any of their implementations.

[0019] In the twelfth aspect, a computer program is provided, which, when executed on a computer, enables the computer to execute the method in any one of the above-mentioned first to fourth aspects or their respective implementations.

[0020] Through the above technical solution, terminal devices or network equipment can jointly train the CSI estimation model and the CSI feedback model, thereby ensuring better adaptation of the channel estimation model and the CSI feedback model, thereby improving the overall performance of the model. Furthermore, CSI feedback based on the trained model can improve CSI feedback performance, thereby improving signal transmission performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] FIG1 is a schematic diagram of an application scenario provided by an embodiment of the present application.

[0022] FIG2 is a schematic diagram of a CSI feedback method in the related art.

[0023] FIG3 is a schematic diagram of CSI feedback based on a traditional CSI acquisition solution.

[0024] FIG4 is a schematic diagram of CSI feedback based on an AI-based CSI acquisition solution.

[0025] FIG5 is a schematic diagram of a wireless communication method provided in an embodiment of the present application.

[0026] FIG6 is a schematic interaction diagram of a wireless communication method provided by an embodiment of the present application.

[0027] FIG7 is a schematic diagram of another wireless communication method provided in an embodiment of the present application.

[0028] FIG8 is a schematic interaction diagram of a wireless communication method provided by an embodiment of the present application.

[0029] FIG9 is a schematic block diagram of a terminal device according to an embodiment of the present application.

[0030] FIG10 is a schematic block diagram of a network device according to an embodiment of the present application.

[0031] FIG11 is a schematic block diagram of another terminal device according to an embodiment of the present application.

[0032] FIG12 is a schematic block diagram of another network device according to an embodiment of the present application.

[0033] FIG13 is a schematic block diagram of a communication device provided in another embodiment of the present application.

[0034] FIG14 is a schematic block diagram of a chip provided in an embodiment of the present application.

[0035] FIG15 is a schematic block diagram of a communication system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. With respect to the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0037] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity) system. Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system or other communication systems, etc.

[0038] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.

[0039] Optionally, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) networking scenario.

[0040] Optionally, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, where the authorized spectrum can also be considered as an unshared spectrum.

[0041] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0042] The terminal device can be a station (ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0043] In an embodiment of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0044] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, 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, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0045] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0046] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.

[0047] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.

[0048] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

[0049] For example, a communication system 100 used in an embodiment of the present application is shown in FIG1 . The communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or a communication terminal or terminal). The network device 110 may provide communication coverage for a specific geographic area and may communicate with terminal devices within the coverage area.

[0050] FIG1 exemplarily shows a network device and two terminal devices. Optionally, the communication system 100 may include multiple network devices and each network device may include another number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0051] Optionally, the communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0052] It should be understood that in the embodiments of the present application, a device having communication functionality in a network / system may be referred to as a communication device. Taking the communication system 100 shown in FIG1 as an example, the communication device may include a network device 110 and a terminal device 120 having communication functionality. Network device 110 and terminal device 120 may be the specific devices described above and will not be described in detail here. The communication device may also include other devices in the communication system 100, such as a network controller, a mobility management entity, or other network entities, which is not limited in the embodiments of the present application.

[0053] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.

[0054] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0055] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0056] In the embodiments of the present application, "pre-defined" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device or a network device). The present application does not limit the specific implementation method. For example, pre-defined may refer to information defined in a protocol.

[0057] In the embodiments of the present application, the "protocol" may refer to a standard protocol in the communication field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and this application does not limit this.

[0058] To facilitate understanding of the technical solutions of the embodiments of the present application, a process for obtaining channel state information (CSI) in a wireless communication system is described.

[0059] Multiple-Input Multiple-Output (MIMO) technology plays an important role in LTE systems and NR systems, and will continue to be one of the key technologies in future next-generation wireless communication systems. The signal transmission performance under MIMO depends largely on the feedback accuracy of CSI. Specifically, as shown in Figure 2, the base station will first configure the relevant parameter information for CSI feedback, such as which specific information the UE needs to feedback (such as Rank Indication (RI), Precoding Matrix Indicator (PMI), Channel Quality Indicator (CQI)) and the corresponding feedback period. At the same time, the base station will configure and send reference signals for the UE to perform CSI measurements, such as Synchronization Signal Block (SSB) or Channel State Information Reference Signal (CSI-RS). By performing measurements on the above reference signals, the UE will first perform channel estimation, and then calculate the current CSI based on the estimated channel and feedback it to the base station, so that the base station can configure a reasonable and efficient data transmission method based on the current channel conditions.

[0060] To facilitate understanding of the technical solutions of the embodiments of the present application, a CSI feedback method based on artificial intelligence (AI) is described.

[0061] In some scenarios, AI technology is considered to achieve high-precision CSI feedback. Figure 3 shows an architecture diagram of AI-based CSI feedback, in which the UE can use a pre-trained encoder neural network to convert the obtained CSI information into indication information (e.g., bit stream) that can be fed back through the uplink channel. After receiving the indication information, the base station can use the corresponding trained decoder neural network to restore the indication information to CSI information. The closer the CSI recovered by the base station is to the CSI obtained by the UE, the better the performance of the neural network model.

[0062] To facilitate understanding of the technical solutions of the embodiments of the present application, an AI-based channel estimation method is described.

[0063] The fundamental goal of channel estimation is to obtain the most complete and accurate channel information possible based on the received pilot signal. Based on the performance of auditing neural network models, the use of neural network models for channel estimation is considered. Specifically, the received reference signal is input into a trained neural network model, which then outputs an estimate of the complete channel information.

[0064] Traditional CSI acquisition solutions are primarily based on theoretical modeling and parameter selection of actual communication environments. However, as demands for wireless communication system flexibility, adaptability, and system capacity continue to increase, the gains offered by traditional wireless communication system design and optimization approaches based on classical mathematical models are gradually diminishing.

[0065] The AI-based CSI acquisition solution has higher feedback accuracy and lower feedback overhead compared to traditional CSI acquisition solutions because it utilizes the powerful nonlinear fitting, compression, and recovery capabilities of neural networks.

[0066] However, both the traditional CSI acquisition solution and the AI-based CSI acquisition solution follow a modular system design approach. Specifically, the complete CSI acquisition process will be split into several relatively independent modules, including a channel estimation module and a CSI feedback module, which will be designed and optimized separately. The modular approach can split a complex problem into several relatively simple sub-problems and solve them separately, thereby reducing the difficulty of system design and optimization. However, modular splitting will also bring limitations to system design, thereby limiting the overall performance of the system. Taking the AI-based CSI acquisition solution as an example, two different neural networks need to be designed and trained separately to complete channel estimation and CSI feedback, as shown in Figure 4. Among them, the task of the neural network for channel estimation is to estimate the channel information as accurately and completely as possible, but it cannot take into account the actual compression capability of the subsequent neural network used for CSI feedback. The neural network for CSI feedback is designed and trained to compress and recover CSI information, but it cannot accurately adapt to the previous neural network used for channel estimation. For example, in actual communication environments, fluctuations in the signal-to-noise ratio (SNR) can cause significant changes in channel estimation errors. The neural network used for CSI feedback cannot adapt to or even compensate for such errors, ultimately leading to decreased and unstable system performance, which in turn affects the ultimate signal transmission performance.

[0067] Therefore, how to perform CSI estimation and feedback to improve signal transmission performance is an urgent problem to be solved.

[0068] In view of this, an embodiment of the present application provides a solution that can jointly train the channel estimation model and the CSI feedback model, so that the trained channel estimation model and the CSI feedback model can adapt to each other, thereby improving system performance. Furthermore, the network device can determine the appropriate signal transmission method based on the CSI information fed back by the trained model, thereby improving signal transmission performance.

[0069] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The following related technologies can be combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the scope of protection of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0070] FIG5 is a schematic diagram of a wireless communication method 200 according to an embodiment of the present application. As shown in FIG5 , the method 200 includes the following contents:

[0071] S210: The terminal device jointly trains the first model and the second model according to the first input information and the label channel data.

[0072] It should be understood that the joint training of the first model and the second model in the embodiment of the present application can be the initial training of the first model and the second model, or it can be the updating of the trained first model and the second model. For example, when the scene changes, the first model and the second model are jointly trained based on the channel data under the changed scene to update the first model and the second model.

[0073] In some embodiments, the first model is used to perform channel estimation based on the first input information to obtain the first output information, and the second model is used to compress and restore the second input information to obtain the target CSI, wherein the second input information is determined according to the first output information.

[0074] In the embodiment of the present application, the first model is also called a channel estimation model, and the second model is also called a CSI feedback model.

[0075] In some embodiments, determining the second input information based on the first input information may include:

[0076] The second input information is the first input information, or the second input information is processed from the first input information.

[0077] In some embodiments, the first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, and the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information.

[0078] In some embodiments, the second configuration information is used to obtain more complete and accurate channel data as label data for joint training.

[0079] In some embodiments, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information.

[0080] In other words, the reference signal configured in the configuration information for joint training has a higher resource density than the reference signal configured in the configuration information for CSI acquisition. Therefore, receiving the reference signal based on the configuration information for joint training can obtain more complete and accurate channel data. Furthermore, using this channel data as label data for joint training helps ensure that the jointly trained model can feedback more complete and accurate CSI.

[0081] In some embodiments, the second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

[0082] In some embodiments, the encoder model in the first model and the second model is deployed on the terminal device side, and the decoder model in the second model is deployed on the network device side.

[0083] In some embodiments, the method 200 further includes:

[0084] The terminal device obtains the first model and the second model.

[0085] It should be noted that this application does not limit the manner in which the terminal device obtains the first model and the second model. Optionally, the first model and the second model may be obtained in the same manner, or in different manners. The encoder model and the decoder model in the second model may be obtained in the same manner, or in different manners.

[0086] In some embodiments, the first model is obtained from a network device, for example, the network device is configured through downlink signaling. The downlink signaling may include, but is not limited to, system messages, Radio Resource Control (RRC) messages, Media Access Control Control Element (MAC CE), and Downlink Control Information (DCI).

[0087] In some embodiments, the first model is predefined, for example, predefined by a device manufacturer.

[0088] In some embodiments, the first model is obtained from a third-party device, for example, through a third-party channel or agreement.

[0089] In some embodiments, the second model is predefined, for example, predefined by a device manufacturer.

[0090] In some embodiments, the second model is obtained from a third-party device, for example, through a third-party channel or agreement.

[0091] In some embodiments, the second model is obtained from a network device, for example, the network device is configured through downlink signaling. The downlink signaling may include, but is not limited to, system messages, RRC messages, MAC CE, and DCI.

[0092] In some embodiments of the present application, the terminal device may decide on its own whether to jointly train the first model and the second model.

[0093] For example, the terminal device can determine whether to trigger joint training of the first model and the second model based on whether one or more monitoring indicators meet preset conditions.

[0094] In some specific embodiments, the method 200 further includes:

[0095] The terminal device determines, based on the first information, whether to perform joint training on the first model and the second model;

[0096] The first information includes at least one of the following:

[0097] Channel quality information of the environment in which the terminal device is located;

[0098] Data transmission status in the recent period;

[0099] CSI feedback performance of the second model;

[0100] Mobility information of the terminal device.

[0101] Changes in the channel environment directly affect the accuracy of channel estimation, and due to the impact of error propagation, the CSI feedback performance may also be affected. Therefore, by monitoring the channel quality indicator, the first model and the second model can be jointly trained when the channel environment changes, which helps to ensure that the model used for CSI feedback is applicable to the current channel environment.

[0102] In some embodiments, the channel quality information of the environment in which the terminal device is located may include but is not limited to at least one of the following channel quality indicators:

[0103] Reference Signal Receiving Power (RSRP), Reference Signal Receiving Quality (RSRQ), Signal to Interference plus Noise Ratio (SINR), Signal to Noise Ratio (SNR), Received Signal Strength Indication (RSSI).

[0104] For example, the terminal device may determine to trigger joint training of the first model and the second model when the change in the channel quality indicator is greater than a first threshold.

[0105] Optionally, the first threshold may be predefined and configured by the network device, for example, configured through at least one of a system message, an RRC message, a MAC CE, and a DCI.

[0106] The data transmission status can reflect whether the data transmission method selected by the network device is appropriate. The data transmission method selected by the network device is determined based on the CSI feedback from the terminal device. Therefore, the data transmission status can reflect the CSI feedback performance of the terminal device. When the data transmission condition deteriorates, it means that the CSI feedback performance of the terminal device also deteriorates. In this case, the terminal device can trigger joint training of the first model and the second model, and further perform CSI feedback based on the trained model, so as to ensure the selection of an appropriate data transmission method and improve data transmission performance.

[0107] In some embodiments, the data transmission status in the recent period includes:

[0108] The success rate of data packet reception in the recent period, such as the block error rate (BLER) and bit error rate (BER).

[0109] In some specific embodiments, the terminal device may trigger joint training of the first model and the second model when the success rate of receiving data packets within a period of time is lower than a second threshold.

[0110] Optionally, the second threshold may be predefined and configured by the network device, for example, configured through at least one of a system message, an RRC message, a MAC CE, and a DCI.

[0111] The CSI feedback performance of the second model will affect the data transmission performance. When the CSI feedback performance of the second model deteriorates, it triggers joint training of the first model and the second model, and further CSI feedback is performed based on the trained model, thereby ensuring the CSI feedback performance. Furthermore, the network device can select a suitable data transmission method based on the feedback CSI to improve the data transmission performance.

[0112] In some embodiments, the CSI feedback performance of the second model includes but is not limited to:

[0113] Similarity, cosine similarity, square of cosine similarity, mean square error, and normalized mean square error between the input information and output information of the second model.

[0114] In some embodiments, the mobility information of the terminal device may include but is not limited to the moving speed of the terminal device, the distance information between the terminal device and the network device, the relative position relationship, etc. When the terminal device moves rapidly relative to the network device, the difficulty and error of channel estimation will increase due to the Doppler effect, thereby affecting the CSI feedback performance. When the distance or relative position relationship between the terminal device and the network device changes, the channel environment between the terminal device and the network device may change, thereby affecting the CSI feedback performance. Therefore, when determining whether to trigger the joint training of the first model and the second model based on the mobility information of the terminal device, it is beneficial to ensure that the terminal device updates the model in a timely manner to ensure the CSI feedback performance of the model.

[0115] Optionally, the moving speed of the terminal device may be determined based on sensor information on the terminal device.

[0116] In some embodiments, when the movement rate of the terminal device is greater than a third threshold, joint training of the first model and the second model is triggered.

[0117] Optionally, the third threshold may be predefined and configured by the network device, for example, configured through at least one of a system message, an RRC message, a MAC CE, and a DCI.

[0118] In other embodiments of the present application, the terminal device may perform joint training on the first model and the second model based on a trigger of a network device. For example, the terminal device receives first indication information sent by the network device, where the first indication information is used to instruct the terminal device to perform joint training on the first model and the second model.

[0119] As an example, the first indication information is sent through at least one of the following signaling methods, but not limited to:

[0120] DCI, RRC message, MAC CE.

[0121] In some embodiments, the network device may determine whether to trigger joint training of the first model and the second model based on whether one or more monitoring indicators meet preset conditions.

[0122] For example, the network device determines whether to jointly train the first model and the second model based on the third information;

[0123] The third information includes at least one of the following:

[0124] Channel quality information of the environment in which the network device is located;

[0125] Data transmission status in the recent period.

[0126] Changes in the channel environment directly affect the accuracy of channel estimation, and due to the impact of error propagation, the CSI feedback performance may also be affected. Therefore, by monitoring the channel quality indicator, the first model and the second model can be jointly trained when the channel environment changes, which helps to ensure that the model used for CSI feedback is applicable to the current channel environment.

[0127] For example, the network device may determine to trigger joint training of the first model and the second model when the change in the channel quality indicator is greater than a fourth threshold.

[0128] Optionally, the fourth threshold may be predefined or determined by the network device.

[0129] The data transmission status can reflect whether the data transmission method selected by the network device is appropriate. The data transmission method selected by the network device is determined based on the CSI feedback from the terminal device. Therefore, the data transmission status can reflect the CSI feedback performance of the terminal device. When the data transmission condition deteriorates, it means that the CSI feedback performance of the terminal device also deteriorates. In this case, the first model and the second model can be triggered to be jointly trained, and the terminal device can further provide CSI feedback based on the trained model, thereby ensuring that the network device selects an appropriate data transmission method and improves data transmission performance.

[0130] In some embodiments, the data transmission status in the recent period includes:

[0131] The Hybrid Automatic Repeat reQuest (HARQ) status of the terminal device, for example, the number and frequency of HARQ retransmissions initiated by the terminal device, reflects to a certain extent the success rate of data reception on the terminal device side.

[0132] For example, the network device may determine to trigger joint training of the first model and the second model when the number of HARQ retransmissions of the terminal device is greater than a fifth threshold.

[0133] Optionally, the fifth threshold may be predefined or determined by the network device.

[0134] In some embodiments, the second configuration information is sent by the network device when determining to trigger joint training of the first model and the second model.

[0135] Optionally, the first indication information and the second configuration information may be sent through the same signaling, or may be sent through different signaling, which is not limited in this application.

[0136] For example, when the network device determines to trigger the terminal device to jointly train the first model and the second model, it indicates the second configuration information to the terminal device so that the terminal device receives the reference signal based on the second configuration information to obtain the label channel data used for joint training.

[0137] In some embodiments, the second configuration information may be sent through at least one of the following signaling methods, but is not limited to:

[0138] DCI, RRC message, MAC CE.

[0139] In some embodiments, the method 200 further includes:

[0140] The terminal device sends second indication information to the network device, where the second indication information is used to indicate that the terminal device will jointly train the first model and the second model, or the second indication information is used to request joint training of the first model and the second model.

[0141] For example, when the terminal device determines to trigger joint training of the first model and the second model, the terminal device may indicate to the network device that the joint training of the first model and the second model is triggered.

[0142] In some embodiments, the second indication information may be sent via uplink signaling, which may include but is not limited to at least one of the following signaling: uplink control information (UCI), RRC message, and physical uplink shared channel (PUSCH).

[0143] In some embodiments, the second configuration information is sent by the network device upon receiving the second indication information. For example, upon determining to trigger joint training of the first model and the second model, the terminal device sends the second indication information to the network device. Furthermore, the network device may configure the second configuration information for the terminal device so that the terminal device receives a reference signal based on the second configuration information to obtain labeled channel data for joint training.

[0144] When determining to jointly train the first model and the second model, the terminal device can obtain a data set and label data for the joint training. For example, the channel data (denoted as H1) obtained by receiving the reference signal based on the first configuration information is used as the input of the model, and the high-precision channel data (denoted as H2) obtained by receiving the reference signal based on the second configuration information is used as the label data of the model. The first model and the second model are further jointly trained, for example, using a loss function to make the output of the second model as close to H2 as possible.

[0145] The greater the correlation or similarity between the output of the second model and H2, or the smaller the deviation, the better the effect of the joint model training. The model training process for achieving joint optimization is shown in Figure 4.

[0146] It should be noted that the specific representation form of the label channel data, i.e., H2, is not limited in the embodiment of the present application. For example, it can be the channel itself, or it can be a feature vector representing the channel angle information constructed based on the channel characteristics obtained by calculation, such as through eigenvector decomposition.

[0147] In some embodiments, the terminal device may determine whether to stop jointly training the first model and the second model based on whether one or more monitoring indicators meet preset conditions.

[0148] In some embodiments, the method 200 further includes:

[0149] The terminal device determines, based on the second information, whether to stop jointly training the first model and the second model;

[0150] The second information includes the similarity between the output information of the second model and the label channel data.

[0151] For example, during joint model training on a terminal device, the terminal device can determine whether to stop joint training of the first model and the second model by evaluating the model's performance indicators. Model performance indicators may include, but are not limited to, similarity between the output information of the second model and the labeled channel data, cosine similarity, squared cosine similarity, mean square error, and normalized mean square error.

[0152] In some embodiments, the method 200 further includes:

[0153] The terminal device sends a third indication message to the network device, where the third indication message is used to instruct to stop the joint training of the first model and the second model, or the third indication message is used to request to stop the joint training of the first model and the second model.

[0154] For example, when the terminal device determines to stop joint training of the first model and the second model, the terminal device sends third indication information to the network device.

[0155] Optionally, the third indication information is sent via at least one of the following signaling: UCI, RRC message, PUSCH.

[0156] In some embodiments, the method 200 further includes:

[0157] The terminal device sends the updated decoder model in the second model to the network device.

[0158] For example, after the terminal device completes the joint training of the first model and the second model, the terminal device can send the decoder model in the trained second model to the network device. Further, the network device can use the updated decoder model to restore the target bit rate feedback by the terminal device.

[0159] In some embodiments, when the wireless communication environment changes, if the current first model and the second model are no longer applicable to the current environment, the terminal device can trigger joint training of the first model and the second model again, or it can fall back to CSI estimation and feedback based on the traditional scheme, or it can fall back to the initial model (or basic model) of the first model and the second model.

[0160] 6 , the following describes an execution process of joint training of a terminal device execution model according to a specific embodiment of the present application. As shown in FIG6 , the following steps may be included:

[0161] S221: The network device sends a model to the terminal device, such as the decoder model in the second model.

[0162] S222: The terminal device determines whether to trigger joint training of the first model and the second model based on the monitoring indicators.

[0163] For the specific determination method, please refer to the relevant description of the above embodiment.

[0164] S223, the terminal device sends second indication information to the network device, requesting to jointly train the first model and the second model, or the terminal device will jointly train the first model and the second model.

[0165] S224, the terminal device receives second configuration information sent by the network device, where the second configuration information is used to configure a reference signal for joint training.

[0166] S225: The network device sends a reference signal for joint training.

[0167] S226: The terminal device receives a reference signal based on the second configuration information to obtain label channel data, and receives a reference signal based on the first configuration information to obtain channel data for model input, corresponding to the first input information mentioned above.

[0168] The first model and the second model are further jointly trained based on the first input information and the label channel data.

[0169] S227: The terminal device determines whether to stop the joint training of the first model and the second model based on the performance indicators of the models. For specific implementation, please refer to the relevant description of the above embodiment.

[0170] S228, the terminal device sends a third indication message to the network device, which is used to request to stop the joint training of the first model and the second model, or to instruct to stop the joint training of the first model and the second model.

[0171] For example, when the terminal device determines to stop joint training of the first model and the second model, the terminal device sends the third indication information.

[0172] S229, the terminal device sends the updated model to the network device.

[0173] For example, the updated decoder model in the second model is sent to the network device.

[0174] S2210, the terminal device performs channel estimation based on the updated first model, and performs CSI feedback according to the encoder model in the second model.

[0175] S2211: The network device recovers the CSI feedback of the terminal device based on the updated decoder model.

[0176] In summary, in an embodiment of the present application, the terminal device can jointly train the CSI estimation model and the CSI feedback model, thereby ensuring better adaptation of the channel estimation model and the CSI feedback model, thereby improving the overall performance of the model. Furthermore, CSI feedback based on the trained model can improve the CSI feedback performance, thereby improving the signal transmission performance.

[0177] It should be understood that the model training method in method 200 can also be applied to the training of the second model. In this case, during model acquisition, the network device only needs to obtain the second model. The input of the second model can be channel data obtained based on a traditional channel estimation scheme, and the labeled channel data can be the labeled channel data in method 200. In this case, the second model can also better adapt to the errors caused by traditional channel estimation methods, reduce the impact of error propagation, and thus improve the final CSI feedback effect. When the model is updated, the terminal device can send the updated decoder model to the network device.

[0178] FIG7 is a schematic diagram of another wireless communication method 300 according to an embodiment of the present application. As shown in FIG7 , the method 300 includes the following contents:

[0179] S310, the network device jointly trains the first model and the second model according to the first input information and the labeled channel data;

[0180] The first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information;

[0181] The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

[0182] In some embodiments, the second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

[0183] In method 300, the specific implementation of the first input information, label channel data, first configuration information, second configuration information, first model and second model refers to the relevant description of the first input information, label channel data, first configuration information, second configuration information, first model and second model in method 200. For the sake of brevity, they are not repeated here.

[0184] In some embodiments, the method 300 further includes:

[0185] The network device obtains the first model and the second model.

[0186] It should be noted that this application does not limit the manner in which the network device obtains the first model and the second model. Optionally, the first model and the second model may be obtained in the same manner, or in different manners, and the encoder model and the decoder model in the second model may be obtained in the same manner, or in different manners.

[0187] In some embodiments, the first model is predefined, for example, predefined by a device manufacturer.

[0188] In some embodiments, the first model is obtained from a third-party device, for example, through a third-party channel or agreement.

[0189] In some embodiments, the first model is obtained from a terminal device, for example, sent by the terminal device via uplink signaling. The downlink signaling may include, but is not limited to, RRC messages, UCI, and PUSCH.

[0190] In some embodiments, the second model is predefined, for example, predefined by a device manufacturer.

[0191] In some embodiments, the second model is obtained from a third-party device, for example, through a third-party channel or agreement.

[0192] In some embodiments, the second model is obtained from the terminal device, for example, sent by the terminal device through uplink signaling. The downlink signaling may include, but is not limited to, RRC messages, UCI, and PUSCH.

[0193] In some embodiments of the present application, the network device may independently determine whether to jointly train the first model and the second model. For example, the network device may determine whether to trigger the joint training of the first model and the second model based on whether one or more monitoring indicators meet preset conditions.

[0194] In some embodiments, the method 300 further includes:

[0195] The network device determines, based on the third information, whether to perform joint training on the first model and the second model;

[0196] The third information includes at least one of the following:

[0197] Channel quality information of the environment in which the network device is located;

[0198] Data transmission status in the recent period.

[0199] The specific implementation of the network device determining whether to trigger joint training of the first model and the second model refers to the relevant description in method 200, which will not be repeated here for the sake of brevity.

[0200] In some embodiments, the method 300 further includes:

[0201] The network device sends fourth indication information to the terminal device, where the fourth indication information is used to instruct the network device to jointly train the first model and the second model.

[0202] In some embodiments, the fourth indication information is sent through at least one of the following signaling methods, but is not limited to:

[0203] DCI, RRC message, MAC CE.

[0204] In some embodiments, the network device may send the second configuration information to the terminal device when determining to trigger joint training of the first model and the second model. Optionally, the fourth indication information and the second configuration information may be sent via the same signaling, or may be sent via different signaling. For example, when the network device determines to trigger joint training of the first model and the second model, it simultaneously configures the second configuration information to the terminal device.

[0205] In other embodiments of the present application, the network device may perform joint training of the first model and the second model based on a trigger from a terminal device. For example, the network device may receive fifth indication information sent by the terminal device, where the fifth indication information is used to instruct the network device to perform joint training of the first model and the second model, or to request the network device to perform joint training of the first model and the second model.

[0206] In some embodiments, the terminal device may determine whether to trigger joint training of the first model and the second model based on whether one or more monitoring indicators meet preset conditions. The specific implementation of the terminal device determining whether to trigger joint training of the first model and the second model is described in method 200, which is not repeated here for the sake of brevity.

[0207] In some embodiments, the second configuration information may be sent by the network device when the network device receives the fifth indication information sent by the terminal device.

[0208] In some embodiments, the method 300 further includes:

[0209] The network device obtains the first input information and the tag channel data from the terminal device.

[0210] For example, when the network device receives the fifth indication information sent by the terminal device, the network device obtains the first input information and the tag channel data from the terminal device.

[0211] For another example, when the network device determines to trigger joint training of the first model and the second model, the first input information and label channel data are obtained from the terminal device.

[0212] In some embodiments, the method 300 further includes:

[0213] The network device determines, based on the fourth information, whether to stop jointly training the first model and the second model;

[0214] The fourth information includes the similarity between the output information of the second model and the label channel data.

[0215] The specific implementation of the network device determining whether to stop the joint training of the first model and the second model refers to the relevant description of the terminal device determining whether to stop the joint training of the first model and the second model in method 200. For the sake of brevity, it is not repeated here.

[0216] In some embodiments, the method 300 further includes:

[0217] The network device sends sixth indication information to the terminal device, where the sixth indication information is used to instruct to stop joint training of the first model and the second model.

[0218] For example, when the network device determines to stop the joint training of the first model and the second model, the sixth indication information is sent to the terminal device.

[0219] In some embodiments, the method 300 further includes:

[0220] The network device sends the updated encoder model in the second model and the updated first model to the terminal device.

[0221] For example, after the network device completes the joint training of the first model and the second model, the network device can send the encoder model in the trained first model and the second model to the terminal device. Furthermore, the terminal device can perform channel estimation based on the trained first model and perform CSI feedback based on the trained encoder model, such as sending a target bit stream. The network device can use the trained decoder model to restore the target bit rate fed back by the terminal device.

[0222] In some embodiments, when the wireless communication environment changes, if the current first model and the second model are no longer applicable to the current environment, the network device can trigger joint training of the first model and the second model again, or it can fall back to CSI estimation and feedback based on the traditional scheme, or it can fall back to the initial model (or basic model) of the first model and the second model.

[0223] 8 , the following describes an execution process of joint training of a network device execution model according to a specific embodiment of the present application. As shown in FIG8 , the following steps may be included:

[0224] S321: The terminal device sends a model to the network device, such as the encoder model in the first model and the second model.

[0225] S322: The network device determines whether to trigger joint training of the first model and the second model based on the monitoring indicators.

[0226] For the specific determination method, please refer to the relevant description of the above embodiment.

[0227] S323, the network device sends fourth indication information to the terminal device, used to instruct to jointly train the first model and the second model.

[0228] S324: The network device sends second configuration information to the terminal device, where the second configuration information is used to configure a reference signal for joint training.

[0229] S325: The network device sends a reference signal for joint training.

[0230] S326: The terminal device receives a reference signal based on the second configuration information to obtain label channel data, and receives a reference signal based on the first configuration information to obtain channel data for model input, corresponding to the first input information mentioned above.

[0231] S327, the terminal device sends the channel data and label channel data for model input to the network device.

[0232] S328: The network device jointly trains the first model and the second model based on the channel data and the label channel data used for model input.

[0233] S329: The network device determines whether to stop the joint training of the first model and the second model based on the performance indicators of the models. For specific implementation, refer to the relevant description of the above embodiment.

[0234] S330: The network device sends sixth indication information to the terminal device, for indicating to stop the joint training of the first model and the second model.

[0235] For example, when the network device determines to stop joint training of the first model and the second model, the network device sends the sixth indication information.

[0236] S331, the network device sends the updated model to the terminal device.

[0237] For example, the updated encoder model and the first model in the second model are sent to the terminal device.

[0238] S332, the terminal device performs channel estimation based on the updated first model, and performs CSI feedback based on the encoder model in the second model.

[0239] S333: The network device recovers the CSI feedback of the terminal device based on the updated decoder model.

[0240] In summary, in an embodiment of the present application, the network device can jointly train the CSI estimation model and the CSI feedback model, thereby ensuring better adaptation of the channel estimation model and the CSI feedback model, thereby improving the overall performance of the model. Furthermore, CSI feedback based on the trained model can improve the CSI feedback performance, thereby improving the signal transmission performance.

[0241] It should be understood that the model training method in method 300 can also be applied to the training of the second model. In this case, during model acquisition, the network device only needs to obtain the second model. The input of the second model can be channel data obtained based on a traditional channel estimation scheme, and the labeled channel data can be the labeled channel data in method 300. In this case, the second model can also better adapt to the errors introduced by traditional channel estimation methods, reduce the impact of error propagation, and thus improve the final CSI feedback effect. When the model is updated, the network device can send the updated encoder model to the terminal device.

[0242] The above text, in combination with Figures 5 to 8, describes in detail the method embodiment of the present application. The following text, in combination with Figures 9 to 15, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.

[0243] FIG9 shows a schematic block diagram of a terminal device 1000 according to an embodiment of the present application. As shown in FIG9 , the terminal device 1000 includes:

[0244] A processing unit 1010 is configured to jointly train the first model and the second model based on the first input information and the label channel data;

[0245] The first input information is channel data obtained by the terminal device receiving a reference signal based on first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information, and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information;

[0246] The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

[0247] In some embodiments, the second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

[0248] In some embodiments, the processing unit 1010 is further configured to: obtain the first model and the second model.

[0249] In some embodiments, the first model is obtained from a network device, or the first model is predefined, or the first model is obtained from a third-party device.

[0250] In some embodiments, the second model is obtained from a network device, or the second model is predefined, or the second model is obtained from a third-party device.

[0251] In some embodiments, the terminal device 1000 further includes:

[0252] A communication unit is used to receive first indication information sent by a network device, where the first indication information is used to instruct the terminal device to jointly train the first model and the second model.

[0253] In some embodiments, the first indication information is sent via at least one of the following signaling: downlink control information DCI, radio resource control RRC message, and media access control element MAC CE.

[0254] In some embodiments, the processing unit 1010 is further configured to:

[0255] Determining, based on the first information, whether to jointly train the first model and the second model;

[0256] The first information includes at least one of the following:

[0257] Channel quality information of the environment in which the terminal device is located;

[0258] Data transmission status in the recent period;

[0259] CSI feedback performance of the second model;

[0260] Mobility information of the terminal device.

[0261] In some embodiments, the data transmission status in the recent period includes:

[0262] The success rate of data packet reception in the recent period.

[0263] In some embodiments, the CSI feedback performance of the second model includes:

[0264] The similarity between the input information and the output information of the second model.

[0265] In some embodiments, the terminal device 1000 further includes:

[0266] A communication unit is used to send second indication information to the network device, where the second indication information is used to instruct the terminal device to jointly train the first model and the second model.

[0267] In some embodiments, the second indication information is sent via at least one of the following signaling: uplink control information UCI, RRC message, physical uplink shared channel PUSCH.

[0268] In some embodiments, the second configuration information is sent by the network device upon receiving the second indication information.

[0269] In some embodiments, the processing unit 1010 is further configured to:

[0270] determining, based on the second information, whether to stop jointly training the first model and the second model;

[0271] The second information includes the similarity between the output information of the second model and the label channel data.

[0272] In some embodiments, the terminal device further includes:

[0273] A communication unit is used to send third indication information to the network device, where the third indication information is used to instruct to stop joint training of the first model and the second model.

[0274] In some embodiments, the third indication information is sent via at least one of the following signaling: UCI, RRC message, PUSCH.

[0275] In some embodiments, the terminal device further includes:

[0276] A communication unit is configured to send the updated decoder model in the second model to a network device.

[0277] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0278] It should be understood that the terminal device 400 according to the embodiment of the present application may correspond to the terminal device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the terminal device 400 are respectively for realizing the corresponding processes of the terminal device in the method 200 shown in Figures 5 to 6. For the sake of brevity, they will not be repeated here.

[0279] FIG10 is a schematic block diagram of a network device according to an embodiment of the present application. The network device 1100 of FIG10 includes:

[0280] Communication unit 1110 is used to send first configuration information and second configuration information to a terminal device, wherein the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information.

[0281] In some embodiments, the first configuration information is used by the terminal device to receive a reference signal to obtain first input information, and the second configuration information is used by the terminal device to receive a reference signal to obtain labeled channel data, and the first input information and the labeled channel data are used to jointly train the first model and the second model;

[0282] The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined based on the first output information.

[0283] In some embodiments, the network device 1100 further includes:

[0284] a processing unit, configured to determine whether to jointly train the first model and the second model based on third information;

[0285] The third information includes at least one of the following:

[0286] Channel quality information of the environment in which the network device is located;

[0287] Data transmission status in the recent period.

[0288] In some embodiments, the communication unit 1110 is further configured to:

[0289] Send first indication information to the terminal device, where the first indication information is used to instruct the terminal device to jointly train the first model and the second model.

[0290] In some embodiments, the first indication information is sent via at least one of the following signaling: downlink control information DCI, radio resource control RRC message, and media access control element MAC CE.

[0291] In some embodiments, the communication unit 1110 is further configured to:

[0292] Receive second indication information sent by the terminal device, where the second indication information is used to indicate that the terminal device will jointly train the first model and the second model.

[0293] In some embodiments, the second indication information is sent via at least one of the following signaling:

[0294] Uplink control information UCI, RRC message, physical uplink shared channel PUSCH.

[0295] In some embodiments, the second configuration information is sent by the network device upon receiving the second indication information.

[0296] In some embodiments, the communication unit 1110 is further configured to:

[0297] Receive third indication information sent by the terminal device, where the third indication information is used to instruct to stop joint training of the first model and the second model.

[0298] In some embodiments, the third indication information is sent via at least one of the following signaling: UCI, RRC message, PUSCH.

[0299] In some embodiments, the communication unit 1110 is further configured to:

[0300] The updated decoder model in the second model is received by the terminal device.

[0301] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0302] It should be understood that the network device 1100 according to the embodiment of the present application may correspond to the network device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the network device 1100 are respectively for implementing the corresponding processes of the network device in the method 300 shown in Figures 5 to 6. For the sake of brevity, they will not be repeated here.

[0303] FIG11 is a schematic block diagram of a network device according to an embodiment of the present application. The network device 1200 of FIG11 includes:

[0304] The processing unit 1210 is configured to jointly train the first model and the second model based on the first input information and the label channel data;

[0305] The first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information;

[0306] The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

[0307] In some embodiments, the second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

[0308] In some embodiments, the processing unit 1210 is further configured to obtain the first model and the second model.

[0309] In some embodiments, the first model is obtained from a terminal device, or the first model is predefined, or the first model is obtained from a third-party device.

[0310] In some embodiments, the second model is obtained from a terminal device, or the second model is predefined, or the second model is obtained from a third-party device.

[0311] In some embodiments, the processing unit 1210 is further configured to:

[0312] Determining whether to jointly train the first model and the second model according to the third information;

[0313] The third information includes at least one of the following:

[0314] Channel quality information of the environment in which the network device is located;

[0315] Data transmission status in the recent period.

[0316] In some embodiments, the data transmission status in the recent period includes: a hybrid automatic repeat request HARQ state of the terminal device.

[0317] In some embodiments, the network device 1200 further includes:

[0318] A communication unit is used to send fourth indication information to the terminal device, where the fourth indication information is used to instruct the network device to jointly train the first model and the second model.

[0319] In some embodiments, the fourth indication information is sent via at least one of the following signaling: downlink control information DCI, radio resource control RRC message, media access control element MAC CE.

[0320] In some embodiments, the network device 1200 further includes:

[0321] A communication unit is used to receive fifth indication information sent by a terminal device, where the fifth indication information is used to instruct the network device to jointly train the first model and the second model.

[0322] In some embodiments, the network device 1200 further includes:

[0323] The communication unit is configured to send second configuration information to the terminal device.

[0324] In some embodiments, the processing unit 1210 is further configured to:

[0325] The first input information and the tag channel data are acquired from the terminal device.

[0326] In some embodiments, the processing unit 1210 is further configured to:

[0327] determining, according to the fourth information, whether to stop jointly training the first model and the second model;

[0328] The fourth information includes the similarity between the output information of the second model and the label channel data.

[0329] In some embodiments, the network device 1200 further includes:

[0330] A communication unit is used to send sixth indication information to the terminal device, where the sixth indication information is used to instruct to stop joint training of the first model and the second model.

[0331] In some embodiments, the network device 1200 further includes:

[0332] A communication unit is used to send the updated encoder model in the second model and the updated first model to the terminal device.

[0333] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0334] It should be understood that the network device 1200 according to the embodiment of the present application may correspond to the network device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the network device 500 are respectively for implementing the corresponding processes of the network device in the method 300 shown in Figures 7 to 8. For the sake of brevity, they will not be repeated here.

[0335] FIG12 shows a schematic block diagram of a terminal device 1300 according to an embodiment of the present application. As shown in FIG12 , the terminal device 1300 includes:

[0336] The communication unit 1310 is configured to send first input information and labeled channel data to a network device, where the first input information and the labeled channel data are used to jointly train the first model and the second model;

[0337] The first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information;

[0338] The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

[0339] In some embodiments, the second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

[0340] In some embodiments, the terminal device 1300 further includes:

[0341] a processing unit, configured to determine, based on the first information, whether to jointly train the first model and the second model;

[0342] The first information includes at least one of the following:

[0343] Channel quality information of the environment in which the terminal device is located;

[0344] Data transmission status in the recent period;

[0345] CSI feedback performance of the second model;

[0346] Mobility information of the terminal device.

[0347] In some embodiments, the communication unit 1310 is further used to: send fifth indication information to the network device, where the fifth indication information is used to instruct the network device to jointly train the first model and the second model.

[0348] In some embodiments, the communication unit 1310 is further used to: receive fourth indication information sent by the network device, where the fourth indication information is used to indicate that the network device will jointly train the first model and the second model.

[0349] In some embodiments, the fourth indication information is sent via at least one of the following signaling: downlink control information DCI, radio resource control RRC message, media access control element MAC CE.

[0350] In some embodiments, the communication unit 1310 is further configured to receive second configuration information sent by the network device.

[0351] In some embodiments, the communication unit 1310 is further used to: receive sixth indication information sent by the network device, where the sixth indication information is used to instruct to stop joint training of the first model and the second model.

[0352] In some embodiments, the communication unit 1310 is further configured to receive the encoder model in the updated second model and the updated first model sent by the network device.

[0353] Alternatively, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input / output interface of a communication chip or a system on chip. The processing unit may be one or more processors.

[0354] It should be understood that the terminal device 1300 according to the embodiment of the present application may correspond to the terminal device in the embodiment of the method of the present application, and the above-mentioned and other operations and / or functions of each unit in the terminal device 1300 are respectively for realizing the corresponding processes of the terminal device in the method 300 shown in Figures 7 to 8. For the sake of brevity, they will not be repeated here.

[0355] Figure 13 is a schematic structural diagram of a communication device 600 provided in an embodiment of the present application. The communication device 600 shown in Figure 13 includes a processor 610, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0356] Optionally, as shown in FIG13 , the communication device 600 may further include a memory 620. The processor 610 may call and execute a computer program from the memory 620 to implement the method in the embodiment of the present application.

[0357] The memory 620 may be a separate device independent of the processor 610 , or may be integrated into the processor 610 .

[0358] Optionally, as shown in FIG13 , the communication device 600 may further include a transceiver 630 , and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0359] The transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include an antenna, and the number of antennas may be one or more.

[0360] Optionally, the communication device 600 may specifically be a network device in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the network device in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0361] Optionally, the communication device 600 may specifically be a mobile terminal / terminal device in an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the mobile terminal / terminal device in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0362] Figure 14 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 700 shown in Figure 14 includes a processor 710, which can call and run a computer program from a memory to implement the method according to the embodiment of the present application.

[0363] Optionally, as shown in FIG14 , the chip 700 may further include a memory 720 , wherein the processor 710 may call and execute a computer program from the memory 720 to implement the method in the embodiment of the present application.

[0364] The memory 720 may be a separate device independent of the processor 710 , or may be integrated into the processor 710 .

[0365] Optionally, the chip 700 may further include an input interface 730. The processor 710 may control the input interface 730 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0366] Optionally, the chip 700 may further include an output interface 740. The processor 710 may control the output interface 740 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0367] Optionally, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0368] Optionally, the chip can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0369] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0370] FIG15 is a schematic block diagram of a communication system 900 provided in an embodiment of the present application. As shown in FIG15 , the communication system 900 includes a terminal device 910 and a network device 920 .

[0371] Among them, the terminal device 910 can be used to implement the corresponding functions implemented by the terminal device in the above method, and the network device 920 can be used to implement the corresponding functions implemented by the network device in the above method. For the sake of brevity, they are not repeated here.

[0372] It should be understood that the processor of the embodiments of the present application may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0373] It is understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0374] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0375] An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.

[0376] Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0377] Optionally, the computer-readable storage medium can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0378] An embodiment of the present application also provides a computer program product, including computer program instructions.

[0379] Optionally, the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.

[0380] Optionally, the computer program product can be applied to the mobile terminal / terminal device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0381] The embodiment of the present application also provides a computer program.

[0382] Optionally, the computer program can be applied to the network device in the embodiments of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not described here.

[0383] Optionally, the computer program can be applied to the mobile terminal / terminal device in the embodiments of the present application. When the computer program runs on the computer, the computer executes the corresponding processes implemented by the mobile terminal / terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0384] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0385] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0386] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0387] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0388] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0389] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0390] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: include: The terminal device jointly trains the first model and the second model according to the first input information and the label channel data; The first input information is channel data obtained by the terminal device receiving a reference signal based on first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information, and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

2. The method according to claim 1, characterized in that The second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

3. The method according to claim 1 or 2, characterized in that The method further comprises: The terminal device obtains the first model and the second model.

4. The method according to claim 3, characterized in that The first model is obtained from a network device, or the first model is predefined, or the first model is obtained from a third-party device.

5. The method according to claim 3 or 4, characterized in that The second model is obtained from a network device, or the second model is predefined, or the second model is obtained from a third-party device.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: The terminal device receives first indication information sent by a network device, where the first indication information is used to instruct the terminal device to jointly train the first model and the second model.

7. The method according to claim 6, characterized in that The first indication information is sent through at least one of the following signaling: downlink control information DCI, radio resource control RRC message, and media access control element MAC CE.

8. The method according to any one of claims 1 to 5, characterized in that The method further comprises: The terminal device determines, based on the first information, whether to perform joint training on the first model and the second model; The first information includes at least one of the following: Channel quality information of the environment in which the terminal device is located; Data transmission status in the recent period; CSI feedback performance of the second model; Mobility information of the terminal device.

9. The method according to claim 8, characterized in that The data transmission status in the recent period includes: The success rate of data packet reception in the recent period.

10. The method according to claim 8 or 9, characterized in that The CSI feedback performance of the second model includes: The similarity between the input information and the output information of the second model.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: The terminal device sends second indication information to the network device, where the second indication information is used to indicate that the terminal device will jointly train the first model and the second model.

12. The method according to claim 11, characterized in that The second indication information is sent through at least one of the following signaling: uplink control information UCI, RRC message, and physical uplink shared channel PUSCH.

13. The method according to claim 11 or 12, characterized in that The second configuration information is sent by the network device when the second indication information is received.

14. The method according to any one of claims 1 to 13, characterized in that The method further comprises: The terminal device determines, based on the second information, whether to stop jointly training the first model and the second model; The second information includes the similarity between the output information of the second model and the label channel data.

15. The method according to any one of claims 1 to 14, characterized in that The method further comprises: The terminal device sends third indication information to the network device, where the third indication information is used to instruct to stop joint training of the first model and the second model.

16. The method according to claim 15, characterized in that The third indication information is sent through at least one of the following signaling: UCI, RRC message, PUSCH.

17. The method according to any one of claims 1 to 15, characterized in that The method further comprises: The terminal device sends the updated decoder model in the second model to the network device.

18. A wireless communication method, characterized in that: include: The network device sends first configuration information and second configuration information to the terminal device, wherein the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information.

19. The method according to claim 18, characterized in that The first configuration information is used by the terminal device to receive a reference signal to obtain first input information, and the second configuration information is used by the terminal device to receive a reference signal to obtain labeled channel data, and the first input information and the labeled channel data are used to jointly train the first model and the second model; The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined based on the first output information.

20. The method according to claim 19, characterized in that The method further comprises: The network device determines, based on the third information, whether to perform joint training on the first model and the second model; The third information includes at least one of the following: Channel quality information of the environment in which the network device is located; Data transmission status in the recent period.

21. The method according to claim 19 or 20, characterized in that The method further comprises: The network device sends first indication information to the terminal device, where the first indication information is used to instruct the terminal device to jointly train the first model and the second model.

22. The method according to claim 21, characterized in that The first indication information is sent through at least one of the following signaling: downlink control information DCI, radio resource control RRC message, and media access control element MAC CE.

23. The method according to claim 19, wherein The method further comprises: The network device receives second indication information sent by the terminal device, where the second indication information is used to instruct the terminal device to jointly train the first model and the second model.

24. The method according to claim 23, wherein The second indication information is sent through at least one of the following signaling: uplink control information UCI, RRC message, and physical uplink shared channel PUSCH.

25. The method according to claim 23 or 24, characterized in that The second configuration information is sent by the network device when the second indication information is received.

26. The method according to any one of claims 19 to 25, characterized in that The method further comprises: The network device receives third indication information sent by the terminal device, where the third indication information is used to instruct to stop joint training of the first model and the second model.

27. The method according to claim 26, characterized in that The third indication information is sent through at least one of the following signaling: UCI, RRC message, PUSCH.

28. The method according to any one of claims 19 to 27, characterized in that The method further comprises: The network device receives the updated decoder model in the second model sent by the terminal device.

29. A wireless communication method, characterized in that: include: The network device jointly trains the first model and the second model based on the first input information and the label channel data; The first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

30. The method according to claim 29, wherein The second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

31. The method according to claim 29 or 30, characterized in that The method further comprises: The network device obtains the first model and the second model.

32. The method according to claim 31, characterized in that The first model is obtained from a terminal device, or the first model is predefined, or the first model is obtained from a third-party device.

33. The method according to claim 31, characterized in that The second model is obtained from the terminal device, or the second model is predefined, or the second model is obtained from a third-party device.

34. The method according to any one of claims 29 to 33, wherein: The method further comprises: The network device determines, based on the third information, whether to perform joint training on the first model and the second model; The third information includes at least one of the following: Channel quality information of the environment in which the network device is located; Data transmission status in the recent period.

35. The method according to claim 34, wherein The data transmission status in the recent period includes: The hybrid automatic repeat request (HARQ) state of the terminal device.

36. The method according to any one of claims 29 to 35, wherein: The method further comprises: The network device sends fourth indication information to the terminal device, where the fourth indication information is used to instruct the network device to jointly train the first model and the second model.

37. The method according to claim 36, wherein The fourth indication information is sent through at least one of the following signaling: downlink control information DCI, radio resource control RRC message, and media access control element MAC CE.

38. The method according to any one of claims 29 to 32, wherein: The method further comprises: The network device receives fifth indication information sent by the terminal device, where the fifth indication information is used to instruct the network device to jointly train the first model and the second model.

39. The method according to any one of claims 29 to 38, wherein The method further comprises: The network device sends second configuration information to the terminal device.

40. The method according to any one of claims 29 to 39, wherein The method further comprises: The network device obtains the first input information and the tag channel data from the terminal device.

41. The method according to any one of claims 29-40, characterized in that The method further comprises: The network device determines, based on the fourth information, whether to stop jointly training the first model and the second model; The fourth information includes the similarity between the output information of the second model and the label channel data.

42. The method according to any one of claims 29 to 41, wherein The method further comprises: The network device sends sixth indication information to the terminal device, where the sixth indication information is used to instruct to stop joint training of the first model and the second model.

43. The method according to any one of claims 29 to 42, wherein: The method further comprises: The network device sends the updated encoder model in the second model and the updated first model to the terminal device.

44. A wireless communication method, characterized in that: include: The terminal device sends first input information and label channel data to the network device, where the first input information and the label channel data are used to jointly train the first model and the second model; The first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

45. The method according to claim 44, wherein The second model includes an encoder model and a decoder model, wherein the encoder model is used to compress the second input information to obtain a target bit stream, and the decoder model is used to restore the target bit stream to obtain the target CSI.

46. ​​The method according to claim 44 or 45, characterized in that The method further comprises: The terminal device determines, based on the first information, whether to perform joint training on the first model and the second model; The first information includes at least one of the following: Channel quality information of the environment in which the terminal device is located; Data transmission status in the recent period; CSI feedback performance of the second model; Mobility information of the terminal device.

47. The method according to any one of claims 44 to 46, characterized in that The method further comprises: The terminal device sends fifth indication information to the network device, where the fifth indication information is used to instruct the network device to jointly train the first model and the second model.

48. The method according to claim 44 or 45, characterized in that The method further comprises: The terminal device receives fourth indication information sent by the network device, where the fourth indication information is used to instruct the network device to jointly train the first model and the second model.

49. The method according to claim 48, characterized in that The fourth indication information is sent through at least one of the following signaling: downlink control information DCI, radio resource control RRC message, and media access control element MAC CE.

50. The method according to any one of claims 44 to 49, wherein The method further comprises: The terminal device receives the second configuration information sent by the network device.

51. The method according to any one of claims 44 to 50, wherein: The method further comprises: The terminal device receives sixth indication information sent by the network device, where the sixth indication information is used to instruct to stop joint training of the first model and the second model.

52. The method according to any one of claims 44 to 51, wherein: The method further comprises: The terminal device receives the encoder model in the updated second model and the updated first model sent by the network device.

53. A terminal device, characterized in that: include: a processing unit, configured to jointly train the first model and the second model based on the first input information and the label channel data; The first input information is channel data obtained by the terminal device receiving a reference signal based on first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information, and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

54. A network device, characterized in that include: A communication unit, used to send first configuration information and second configuration information to a terminal device, wherein the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information.

55. A network device, characterized in that include: a processing unit, configured to jointly train the first model and the second model based on the first input information and the label channel data; The first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

56. A terminal device, characterized in that: include: a communication unit, configured to send first input information and labeled channel data to a network device, wherein the first input information and the labeled channel data are used to jointly train the first model and the second model; The first input information is channel data obtained by the terminal device receiving a reference signal based on the first configuration information, the label channel data is channel data obtained by the terminal device receiving a reference signal based on the second configuration information, the time domain resource density of the reference signal configured by the first configuration information is less than the time domain resource density of the reference signal configured by the second configuration information and / or the frequency domain resource density of the reference signal configured by the first configuration information is less than the frequency domain resource density of the reference signal configured by the second configuration information; The first model is used to perform channel estimation based on the first input information to obtain first output information, and the second model is used to compress and restore the second input information to obtain target channel state information CSI, wherein the second input information is determined according to the first output information.

57. A terminal device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to perform the method according to any one of claims 1 to 17, or the method according to any one of claims 44 to 52.

58. A network device, characterized in that include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to perform the method according to any one of claims 18 to 28, or the method according to any one of claims 29 to 43.

59. A chip, characterized in that: include: A processor for calling and running a computer program from a memory so that a device equipped with the chip performs the method as claimed in any one of claims 1 to 17, or the method as claimed in any one of claims 18 to 28, or the method as claimed in any one of claims 29 to 43, or the method as claimed in any one of claims 29 to 43.

60. A computer-readable storage medium, characterized in that Used to store a computer program, the computer program causing a computer to perform the method according to any one of claims 1 to 17, or the method according to any one of claims 18 to 28, or the method according to any one of claims 29 to 43, or the method according to any one of claims 29 to 43.

61. A computer program product, characterized in that Comprising computer program instructions which cause a computer to perform the method of any one of claims 1 to 17, or the method of any one of claims 18 to 28, or the method of any one of claims 29 to 43, or the method of any one of claims 29 to 43.

62. A computer program, characterized in that The computer program causes a computer to perform the method of any one of claims 1 to 17, or the method of any one of claims 18 to 28, or the method of any one of claims 29 to 43, or the method of any one of claims 29 to 43.

Images